To see the other types of publications on this topic, follow the link: Load balancing.
Dissertations / Theses on the topic 'Load balancing'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Load balancing.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Burrows, Richard B. P. "Dynamic load balancing." Thesis, University of Oxford, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.363886.
Full text
2
Nagel, Lars. "Randomised load balancing." Thesis, Durham University, 2011. http://etheses.dur.ac.uk/3207/.
Full textAbstract:
Due to the increased use of parallel processing in networks and multi-core architectures, it is important to have load balancing strategies that are highly efficient and adaptable to specific requirements. Randomised protocols in particular are useful in situations in which it is costly to gather and update information about the load distribution (e.g. in networks). For the mathematical analysis randomised load balancing schemes are modelled by balls-into-bins games, where balls represent tasks and bins computers. If m balls are allocated to n bins and every ball chooses one bin at random, the gap between maximum and average load is known to grow with the number of balls m. Surprisingly, this is not the case in the multiple-choice process in which each ball chooses d > 1 bins and allocates itself to the least loaded. Berenbrink et al. proved that then the gap remains ln ln(n) / ln(d). This thesis analyses generalisations and variations of the multiple-choice process. For a scenario in which batches of balls are allocated in parallel, it is shown that the gap between maximum and average load is still independent of m. Furthermore, we look into a process in which only predetermined subsets of bins can be chosen by a ball. Assuming that the number and composition of the subsets can change with every ball, we examine under which circumstances the maximum load is one. Finally, we consider a generalisation of the basic process allowing the bins to have different capacities. Adapting the probabilities of the bins, it is shown how the load can be balanced over the bins according to their capacities.
3
Clifton, Christopher W. "Dynamic load balancing." Thesis, Massachusetts Institute of Technology, 1986. http://hdl.handle.net/1721.1/81504.
Full textAbstract:
Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1986.MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING
Bibliography: leaves 72-74.
by Christopher W. Clifton.
M.S.
4
Friedetzky, Thomas. "Randomised dynamic load balancing." [S.l. : s.n.], 2002. http://deposit.ddb.de/cgi-bin/dokserv?idn=96937979X.
Full text
5
Wang, Chunpu. "Distributed random load balancing." Thesis, University of British Columbia, 2017. http://hdl.handle.net/2429/61801.
Full textAbstract:
Low latency is highly desirable for cloud services spanning thousands of servers. With the rapid development of cloud market, the size of server farms grows fast. Hence, stringent timing requirements are needed for task scheduling in a large-scale server farm. Conventionally, the Join-the-Shortest-Queue (JSQ) algorithm, which directs an arriving task to the least loaded server, is adopted in scheduling. Despite its excellent delay performance, JSQ is throughput-limited, and thus doesn't scale well with the number of servers. There are two distributed algorithms proposed as "approximations" of the idealized JSQ. The first one is the Power-of-d-choices (Pod) algorithm, which selects d servers at random and routes a task to the least loaded server of the d servers. Despite its scalability, Pod suffers from long tail response times. The second one is the distributed Join-the-Idle-Queue (JIQ), which take advantages idle servers for task scheduling.
In this thesis, we are interested in exploring Pod and JIQ further. First, a hybrid scheduling strategy called Pod-Helper is proposed. It consists of a Pod scheduler and a throughput-limited helper. Hybrid scheduling takes the best of both worlds, enjoying scalability and low tail response times. In particular, hybrid scheduling has bounded maximum queue size in the large-system regime, which is in sharp contrast to the Pod scheduling whose maximum queue size is unbounded. Second, we conduct an in-depth analysis for distributed Join-the-Idle-Queue (JIQ), a promising new approximation of an idealized task-scheduling algorithm. In particular, we derive semi-closed form expressions for the delay performance of distributed JIQ. Third, we propose a new variant of distributed JIQ that offers clear advantages over alternative algorithms for large systems.Applied Science, Faculty of
Engineering, School of (Okanagan)
Graduate
6
Montag, David. "Load balancing of IP telephony." Thesis, Linköping University, Department of Computer and Information Science, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-16066.
Full textAbstract:
In today's world, more and more phone calls are made over IP. This results in an increasing demand for scalable IP telephony equipment.
Ingate Systems AB produces firewalls specialized in handling IP telephony. They have an inherent limit in the number of concurrent phone calls that they can handle. This can be a bottleneck at high loads. There is a load balancing solution available in the platform, but it has a number of drawbacks, such as media latency and client capability requirements, limiting its usage.
Many companies provide load balancing solutions for SIP. However, it appears few handle all the problematic scenarios that the Ingate firewall does. This master's thesis aims to add load balancing functionality to the Ingate firewall, so that it can handle all types of clients.
By splitting the firewall into two completely separate layers - a SIP layer and a firewall layer - the concept of a virtual machine emerges. A machine is no longer restricted to its physical SIP and firewall layers. Instead, virtual machines are used to process calls. They still have SIP and firewall layers, but the layers can reside on different physical machines.
This thesis demonstrates the operation of an innovative load balancing implementation. The implementation was evaluated, and using four machines the test setup performed 50% better than the original Ingate platform, while still retaining all functionality -- something that was not possible with the original platform. This surpassed both the company's and my own expectations.
7
Mohammad, Malik Adeel, and Saeed Muhammad Sheharyar. "Load Balancing in Microwave Networks." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-121698.
Full textAbstract:
Microwave links are very commonly used in carrier networks especially towards the access side. They not only ease deployment of a network but are also very cost effective. However, they bring along a multitude of challenges which are characteristic of the wireless technology. Microwave links are fickle. Being exposed to varying weather conditions, they experience bandwidth fluctuations. This is true especially in the case of links operating at higher frequencies. The unpredictable nature of microwave links makes it quite challenging to plan capacity in a network beforehand. Radio links employ adaptive modulation. They operate on a range on modulation schemes each of which offers different throughput and bit error rates. When operating at a low bit rate modulation scheme, a situation may arise where the microwave link is not able to support the entire traffic incident from the backbone network. As a result, the microwave link will suffer from congestion and packets arriving at the microwave link will eventually be dropped. The switching nodes that precede the microwave link along a communication path are unaware of the microwave link conditions and, therefore, continue to transmit traffic at a high rate. Large carrier networks cannot afford to have performance inconsistencies like data loss and increased latency. Service degradation, even for a very short duration, can have dire consequences in terms of customer dissatisfaction and revenue loss. The goal of this thesis is to use MPLS-TP Linear Protection to load balance traffic across alternative paths in a network where links use adaptive modulation. Rerouted traffic must take other paths so that the congested microwave link is completely avoided. The idea is augmented by the use of a radio condition signaling mechanism between the packet switching node and the microwave node that precede a microwave link. The microwave node sends radio condition control messages to the preceding packet switching node to rate limit traffic and avoid congestion at the microwave link. The result of this thesis work is a system prototype that achieves the stated goal. Evaluation of the prototype is carried out through graphical results, generated by a traffic generator, that advocate the correctness, performance and robustness of the system.
8
Macharia, Geoffrey Muragori. "Cellular load distribution : dynamic load balancing in scalable multicomputers." Thesis, University of York, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.276343.
Full text
9
Do, Manh Duc. "Green Cloud - Load Balancing, Load Consolidation using VM Migration." TopSCHOLAR®, 2017. https://digitalcommons.wku.edu/theses/2059.
Full textAbstract:
Recently, cloud computing is a new trend emerging in computer technology with a massive demand from the clients. To meet all requirements, a lot of cloud data centers have been constructed since 2008 when Amazon published their cloud service. The rapidly growing data center leads to the consumption of a tremendous amount of energy even cloud computing has better improved in the performance and energy consumption, but cloud data centers still absorb an immense amount of energy. To raise company’s income annually, the cloud providers start considering green cloud concepts which gives an idea about how to optimize CPU’s usage while guaranteeing the quality of service. Many cloud providers are paying more attention to both load balancing and load consolidation which are two significant components of a cloud data center.
Load balancing is taken into account as a vital part of managing income demand, improving the cloud system’s performance. Live virtual machine migration is a technique to perform the dynamic load balancing algorithm. To optimize the cloud data center, three issues are considered: First, how does the cloud cluster distribute the virtual machine (VM) requests from clients to all physical machine (PM) when each computer has a different capacity. Second, what is the solution to make CPU’s usage of all PMs to be nearly equal? Third, how to handle two extreme scenarios: rapidly rising CPU’s usage of a PM due to sudden massive workload requiring VM migration immediately and resources expansion to respond to substantial cloud cluster through VM requests. In this chapter, we provide an approach to work with those issues in the implementation and results. The results indicated that the performance of the cloud cluster was improved significantly.
Load consolidation is the reverse process of load balancing which aims to provide sufficient cloud servers to handle the client requests. Based on the advance of live VM migration, cloud data center can consolidate itself without interrupting the cloud service, and superfluous PMs are turned to save mode to reduce the energy consumption. This chapter provides a solution to approach load consolidation including implementation and simulation of cloud servers.
10
Garcia, Gasulla Marta. "Dynamic load balancing for hybrid applications." Doctoral thesis, Universitat Politècnica de Catalunya, 2017. http://hdl.handle.net/10803/406040.
Full textAbstract:
It is well known that load imbalance is a major source of efficiency loss in HPC (High Performance Computing) environments. The load imbalance problem has very different sources, from static ones related to the data distribution to very dynamic ones, for example, the noise of the system.
In this thesis, we present DLB: Dynamic Load Balancing library. DLB is a framework to improve the efficient use of the computational resources of a computational node. With DLB we offer a dynamic solution to load imbalance problems. DLB is applied at runtime and does not need previous information to solve load imbalance problems, for this reason, it can deal with load imbalances coming from any source.
The DLB framework includes a novel load balancing algorithm: LeWI (Lend When Idle). The main idea of LeWI is to use the computational resources assigned to a process or thread when it is idle, to speed up another process running on the same node that it is still doing computation. We will see how this idea although being quite simple it is powerful and flexible to obtain an efficient use of resources close to the ideal one.En aquesta tesi presentem DLB (Dynamic Load Balancing), una llibreria que ajuda a fer un us eficient dels recursos d'un node de càlcul. Dins de DLB hem implementat un algoritme de balanceig original: LeWI (Lend When Idle). LeWI està basat en la idea que quan un procés MPI està esperant en una crida MPI bloquejant els recursos de càlcul que té assignats no estan ocupats. Per tant, aquests recursos els poden fer servir altres processos que s'estiguin executant al mateix node per acabar el seu càlcul més ràpid. DLB intercepta les crides MPI i canvia el nombre de threads OpenMP com calgui. Quan un procés arriba a una crida MPI bloquejant cedirà les seves CPUs a un altre procés que s'estigui executant al mateix node. Quan el primer procés MPI acabi la crida MPI bloquejant recuperarà les seves CPUs. Hem implementat LeWI a DLB i avaluat el seu rendiment, amb aquesta avaluació hem vist que DLB i LeWI poden millorar el rendiment d'aplicacions híbrides. LeWI pot balancejar aplicacions amb patrons regulars o irregular de desbalanceig sense modificar l'aplicació. Hem observat que la mal·leabilitat del model de programació i de l'aplicació pot afectar el rendiment que s'obté amb l'algoritme de balanceig. Tot i que OpenMP és mal·leable té una limitació, el nombre de threads només es pot canviar fora d'una regió paral·lela. El model de programació OmpSs és més mal·leable, ja que el nombre de threads es pot canviar en qualsevol punt. L'avaluació ens va demostrar que la mal·leabilitat del model de programació que es fa servir te un impacte substancial en el rendiment que obté l'algoritme de balanceig. Per defecte els diferents processos MPI es distribueixen de manera consecutiva entre els nodes de càlcul, però hem observat que en les aplicacions científiques la tendència és que els processos més carregats siguin consecutius. Per aquest motiu fer una distribució cíclica (Round Robin) dels processos MPI entre els nodes permet a l'algoritme de balanceig obtenir un millor rendiment. També hem observat que lligar els threads a CPUs o no fer-ho afecta al rendiment de les aplicacions i en especial quan es fa servir l'algoritme de balanceig. Per a permetre que LeWI pugui gestionar CPUs concretes hem modificat la llibreria perquè utilitzi mascares de CPUs. Amb l'avaluació hem vist que lligar els threads a CPUs té un impacte important en el rendiment que s'obté. Però també que l'impacte depèn de la mida del node (nombre de CPUs per node) i l'estructura de la memòria. Hem integrat DLB amb un runtime parallel, Nanos++. Aquesta integració ens ha mostrat el potencial d'aquest tipus de col·laboracions entre runtimes. Ens ha permès identificar els punts clau de coordinació necessaris i ens ha demostrat que DLB està preparat per a ser integrat amb altres runtimes paralels. L'avaluació ha mostrat el potencial d'aquest tipus d'integracions i col·laboracions. Finalment, hem fet una avaluació exhaustiva de l'entorn i l'algoritme amb una aplicació en producció: Alya. Hem vist que podem reduir fins a un 40% el temps d'execució per a situacions amb un alt desbalanceig. I en el cas de situacions sense desbalanceig l'ús de DLB no penalitza el rendiment de l'aplicació. També hem vist que el rendiment de la paral·lelització OpenMP de l'aplicació té un alt impacte en el rendiment de DLB i LeWI. Hem pogut provar que DLB i LeWI estan llestos per a ser utilitzats en execucions reals. I en executar proves d'escalabilitat fins a 16.000 cores hem vist que no només LeWI pot escalar fins a milers de cores sinó que l'algoritme de balanceig que només s'aplica dins del node de càlcul pot millorar el rendiment d'execucions en milers de nodes de càlcul.
11
Pham, Vinh. "Performing Gateway Load Balancing in MANETs." Doctoral thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for telematikk, 2012. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-15131.
Full textAbstract:
During the last decades, the advances in Information Technology have formed the basis for increased interest and research activity in the field of ad hoc wireless multihop networks or simply ad hoc networks. This emerging technology enables internetworking between wireless nodes that are deployed in an ad hoc and temporary manner. All nodes in an ad hoc network take the role as both hosts in an end-to-end communication session, or as routers to collaboratively relay data traffic in a multihop fashion on behalf of other nodes. Furthermore, ad hoc networks are highly dynamic in nature, i.e. nodes can join or leave the network at any time, and additionally, the nodes have also the flexibility to move around while being in the network. The fact that ad hoc networks can be rapidly deployed with minimal prior planning, cost, and without the need of any pre-existing infrastructure makes this technology very attractive and suitable in a number of applications, including emergency and rescue operations, and military operations. Although ad hoc networks represent a promising technology that offers a broad range of potential useful applications, this technology is still in an immature phase. There are yet many issues and challenges that need to be resolved, which mainly arise from the inherent unreliability of wireless communication, the dynamic nature of these networks, the limited availability in resources with respect to bandwidth, processing capacity, battery power, and from the possibly large scale of these networks. These challenges require that the networking protocols at all layers in the network stack, that in many cases were originally designed for wired networks, must be modified or optimized, in order to adapt to the characteristic of the wireless environment. The focus of this thesis has been devoted to the investigation of two specific issues within the field of ad hoc networking, i.e. node mobility and load balancing. The aim is to provide solutions in order to improve the overall performance in ad hoc networks. Node mobility is one of the most important features in ad hoc networks, however, it is also the reason for frequent link breaks and the constant change in the topology. An ongoing data transmission that is interrupted by a link break, must be rerouted to alternative paths in order to circumvent the broken link. However, this process of rerouting traffic takes a certain amount of time, which is referred to as the rerouting time. Minimizing the rerouting time is essential in order to reduce packet loss and improve network performance. In this thesis we investigate the factors that affect the rerouting time in proactive routing protocols and propose solutions for minimizing it. Load balancing refers to the process of distributing traffic load more evenly in the network in order to minimize congestion and to optimize the usage of network resources. Performing load balancing in ad hoc networks is generally very challenging due to the inherently interfering nature of the wireless medium. In this thesis we therefore investigate the feasibility and the potential benefits of performing load balancing in ad hoc networks. We consider two scenarios, i.e. load balancing for intradomain and interdomain traffic. Intradomain traffic is traffic between nodes inside an ad hoc network. Performing load balancing on intradomain traffic can be done in two ways. The first is referred to as multipath load balancing where a traffic flow between a source and destination pair is distributed over multiple alternative disjoint/semi-disjoint paths. The aim is to maximize throughput and reduce the risk for packet loss. However, a number of previous work has investigated and reported that this type of load balancing can only provide a rather limited improvement in performance due to the interference between the paths [1] [2]. Due to this reason, multipath load balancing is therefore not considered in this thesis. Instead we focus on the second way which is referred to as transit routing. Transit routing is about routing part of the local traffic over a backbone network in order to relief the traffic load in the ad hoc network. The assumption behind this concept is a network architecture similar to a Wireless Mesh Network (WMN), where a high capacity backbone network is an integrated part of the Mobile Ad hoc Network (MANET). This backbone network is commonly used to provide Internet-connectivity services, but can also be exploited to alleviate the traffic load in the MANET. In addition, for certain source and destination pairs, performing transit routing can considerably increase the throughput compared to if the traffic is routed within the ad hoc network. Interdomain traffic refers to traffic between a node inside the ad hoc network and a remote node outside of the ad hoc network. Load balancing for interdomain traffic considers the potential of distributing interdomain traffic among multiple gateways in order to avoid congestion at the gateways and maximize the capacity for interdomain traffic. This type of load balancing is commonly referred to as gateway load balancing in the literature. Furthermore, interdomain can either be inbound or outbound traffic. The work in this thesis mainly focuses on performing load balancing for outbound traffic. However, we believe that the results in our work are also applicable to inbound traffic as well. The main contributions in this thesis are the investigation and the proposals of different solutions for intradomain and interdomain load balancing.
12
Liang, Zhengang. "Transparent Web caching with load balancing." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2001. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/MQ59383.pdf.
Full text
13
Glazer, D. W. (David William). "Load balancing parallel discrete event simulations." Thesis, McGill University, 1992. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=39384.
Full textAbstract:
This thesis presents several load balancing algorithms for parallel discrete event simulations executed under both optimistic and conservative mechanisms. The algorithms rest upon recent developments in active process migration, which permits the use of dynamic strategies. Dynamic load balancing allow for re-adjustments when resource requirements vary during simulation. It is also useful when initial resource predictions are unknown or incorrect.A simulated multi-processor environment (PARALLEX) was developed in order to evaluate the algorithms. Results indicate that substantial performance gains may be realized with these algorithms.
This thesis also presents a scheme which allows the Time of Next Event algorithm (GROS89) to be employed as a complete deadlock prevention mechanism in shared memory environments. Comparisons are made to Chandy & Misra null message schemes.
14
Nuttall, Mark Patrick. "Cluster load balancing using process migration." Thesis, Imperial College London, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.267613.
Full text
15
Maselino, Prince. "Load balancing for parallel 3D visualisation." Thesis, University of Westminster, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.442101.
Full text
16
Predari, Maria. "Load balancing for parallel coupled simulations." Thesis, Bordeaux, 2016. http://www.theses.fr/2016BORD0369/document.
Full textAbstract:
Dans le contexte du calcul scientique, l'équilibrage de la charge est un problème crucial qui conditionne la performance des simulations numériques parallèles. L'objectif est de répartir la charge de travail entre un nombre de processeurs donné, afin de minimiser le temps global d'exécution. Une stratégie populaire pour résoudre ce problème consiste à modéliser la simulation à l'aide d'un graphe et à appliquer des algorithmes de partitionnement. En outre, les simulations numériques tendent à se complexifier, notamment en mixant plusieurs codes représentant des physiques différentes ou des échelles différentes. On parle alors de couplage de codes multi-physiques ou multi-échelles. Dans ce contexte, le problème de l'équilibrage de charge devient également plus difficile, car il ne s'agit plus d'équilibrer chacun des codes séparément, mais l'ensemble de ces codes pris dans leur globalité. Dans ce travail, on propose de resoudre ce problème en utilisant le modèle de partitionnement à sommets fixes qui pourrait représenter efficacement les contraintes supplémentaires imposées par les codes couplés (co-partitionnement). Nous avons donc développé un algorithme direct de partitionnement de graphe qui gère des sommets fixes. L'algorithme a été implémenté dans le partitionneur Scotch et une série d'expériences ont été menées sur la collection des graphes DIMACS. Ensuite nous avons proposé trois algorithmes de co-partitionnement qui respectent les contraintes issues des codes couplés respectifs. Nous avons egalement validé nos algorithmes par une étude expérimentale en comparant nos méthodes aux strategies actuelles sur des cas artificiels ainsi que sur des codes réels couplésLoad balancing is an important step conditioning the performance of parallel applications. The goal is to distribute roughly equal amounts of computational load across a number of processors, while minimising interprocessor communication. A common approach to model the problem is based on graph structures and graph partitioning algorithms. Moreover, new challenges involve the simulation of more complex physical phenomena, where different parts of the computational domain exhibit different physical behavior. Such simulations follow the paradigm of multi-physics or multi-scale modeling approaches. Combining such different models in massively parallel computations is still a challenge to reach high performance. Additionally, traditional load balancing algorithms are often inadequate, and more sophisticated solutions should be explored. In this thesis, we propose new graph partitioning algorithms that balance the load of such simulations, refered to as co-partitioning. We formulate this problem with the use of graph partitioning with initially fixed vertices which we believe represents efficiently the additional constraints of coupled simulations. We have therefore developed a direct algorithm for graph partitioning that manages successfully problems with fixed vertices. The algorithm is implemented inside Scotch partitioner and a series of experiments were carried out on the DIMACS graph collection. Moreover we proposed three copartitioning algorithms that respect the constraints of the respective coupled codes. We finally validated our algorithms by an experimental study comparing our methods with current strategies on artificial cases and on real-life coupled simulations
17
Cronk, David. "Dynamic load balancing via thread migration." W&M ScholarWorks, 1999. https://scholarworks.wm.edu/etd/1539623961.
Full textAbstract:
Light-weight threads are becoming increasingly useful for parallel processing. This is particularly true for threads running in a distributed memory environment. Light-weight threads can be used to support latency hiding techniques, communication and computation overlap, and functional parallelism. Additionally, dynamic migration of light-weight threads supports both data locality and load balancing. Designing a thread migration mechanism presents some very unique and interesting challenges. One such challenge is maintaining communication between mobile threads. A potentially more difficult challenge involves maintaining the correctness of pointers within mobile threads. Since traditional pointers have no concept of address space, moving threads from processor to processor has a strong impact on the use of pointers. Options for dealing with pointers include restricting their use, adding a layer of software to support pointers referencing non-local data, and binding data to threads such that referenced data is always local to the thread. This dissertation presents the design and implementation of Chant, an efficient light-weight threads package which runs in a distributed memory environment. Chant was designed and implemented as a runtime system using MPI like and Pthreads like calls. Chant supports point-to-point message passing between threads executing in distributed address spaces. We focus on the use of Chant as a framework to support dynamic load balancing based on thread migration. We explore many of the issues which arise when designing and implementing a thread migration mechanism, as well as the issues which arise when considering the use of thread migration as a means for performing dynamic load balancing. This load balancing framework uses both system state information, including communication history, and user input. One of the basic functionalities of this load balancing framework is the ability of the user to customize the load balancing to fit particular classes of problems. This dissertation provides implementation details as well as discussion and justification of design choices. We go on to show that the overhead associated with our approach is within an acceptable range, and that significant performance gains can be achieved through the use of thread migration as a means of performing dynamic load balancing.
18
Elsässer, Robert. "Spectral methods for efficient load balancing strategies." [S.l.] : [s.n.], 2002. http://deposit.ddb.de/cgi-bin/dokserv?idn=965647145.
Full text
19
Ronoh, Kennedy, and Awoke Mengistie. "Load Balancing in Heterogeneous LTE-A Networks." Thesis, Linköpings universitet, Kommunikations- och transportsystem, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-81208.
Full textAbstract:
LTE-A is the latest cellular network technology. One feature of LTE-A is the use ofheterogeneous networks (HetNets) which consist of macro-cells and low power nodes(LPNs). One of the objectives of heterogeneous networks is to increase capacity especially inhotspot areas where there is high density of users. Due to their low transmit power, very fewusers associate with LPNs and this will result in load imbalance between LPNs and macrocells.Load balancing is therefore key issue in HetNets so as to maximize cell splitting gainsand ensure even user experiences. Cell range extension (CRE) is a technique that can be usedto achieve load balancing in HetNets. Under CRE, an offset is added to LPNs during cellselection so as to expand the range of LPNs and offload more users from macro-cells toLPNs. CRE usually involves the use of uniform offsets. The use of uniform offsets results insome degree of load balancing in a HetNet which is not optimal. This arises because differentLPNs require different offsets due to varying conditions such as user distribution andpropagation environment in different hotspots. The use of cell-specific offsets is necessary forimproving the level of load balancing in HetNets. In this thesis a heuristic load balancingalgorithm that is used to assign cell-specific offsets to LPNs is designed. The algorithm makesuse of a range optimization framework which applies the concept of cell load coupling. Ourresults show that the use of the cell-specific offsets results in not only a high degree of loadbalancing as measured by Jain’s fairness index but also more even user experiences in termsof throughput.
20
Piccinini, Federico. "Dynamic load balancing based on latency prediction." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-143333.
Full textAbstract:
Spotify is a music streaming service that offers access to a vast music catalogue; it counts more than 24 million active users in 28 different countries. Spotify's backend is made up by a constellation of independent loosely-coupled services; each service consists of a set of replicas, running on a set of servers in multiple data centers: each request to a service needs to be routed to an appropriate replica. Balancing the load across replicas is crucial to exploit available resources in the best possible way, and to provide optimal performances to clients. The main aim of this project is exploring the possibility of developing a load balancing algorithm that exploits request-reply latencies as its only load index. There are two reasons why latency is an appealing load index: in the first place it has a significant impact on the experience of Spotify users; in the second place, identifying a good load index in a distributed system presents significant challenges due to phenomena that might arise from the interaction of the different system components such as multi-bottlenecks. The use of latency as load index is even more attractive under this light, because it allows for a simple black box model where it is not necessary to model resource usage patterns and bottlenecks of every single service individually: modeling each system would be an impractical task, due both to the number of services and to the speed at which these services evolve. In this work, we justify the choice of request-reply latency as a load indicator, by presenting empirical evidence that it correlates well with known reliable load index obtained through a white box approach. In order to assess the correlation between latency and a known load index obtained through a white box approach, we present measurements from the production environment and from an ad-hoc test environment. We present the design of a novel load balancing algorithm based on a modified ' accrual failure detector that exploits request-reply latency as an indirect measure of the load on individual backends; we analyze the algorithm in detail, providing an overview of potential pitfalls and caveats; we also provide an empirical evaluation of our algorithm, compare its performances to a pure round-robin scheduling discipline and discuss which parameters can be tuned and how they affect the overall behavior of the load balancer.
21
El-Khatib, Khalil M. "Dynamic load balancing for clustered time warp." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape16/PQDD_0003/MQ29686.pdf.
Full text
22
Skagos, P. Takis. "Load balancing in a heterogeneous, distributed environment." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/mq39153.pdf.
Full text
23
El-Khatib, Khalil M. "Dynamic load balancing for clustered time warp." Thesis, McGill University, 1996. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=27311.
Full textAbstract:
In this thesis, we consider the problem of dynamic load balancing for parallel discrete event simulation. We focus on the optimistic synchronization protocol, Time Warp.A distributed load balancing algorithm was developed, which makes use of the active process migration in Clustered Time Warp. Clustered Time Warp is a hybrid synchronization protocol; it uses an optimistic approach between the clusters and a sequential approach within the clusters. As opposed to the centralized algorithm developed by H. Avril for Clustered Time Warp, the presented load balancing algorithm is a distributed token-passing one.
We present two metrics for measuring the load: processor utilization and processor advance simulation rate. Different models were simulated and tested: VLSI models and queuing network models (pipeline and distributed networks). Results show that improving the performance of the system depends a great deal on the nature of the simulated model.
For the VLSI model, we also examined the effect of the dynamic load balancing algorithm on the total number of processed messages per unit time. Performance results show that dynamically balancing the load, the throughput of the simulation was improved by more than 100%.
24
Chow, Ka-po, and 周嘉寶. "Load-balancing in distributed multi-agent computing." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2000. http://hub.hku.hk/bib/B3122426X.
Full text
25
張立新 and Lap-sun Cheung. "Load balancing in distributed object computing systems." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2001. http://hub.hku.hk/bib/B31224179.
Full text
26
Muniz, Francisco Junqueira. "Parallel load-balancing on message passing architectures." Thesis, University of Southampton, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.239888.
Full text
27
Fellheimer, Eric Todd. "Dynamic load-balancing of StreamIt cluster computations." Thesis, Massachusetts Institute of Technology, 2006. http://hdl.handle.net/1721.1/36763.
Full textAbstract:
Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2006.Includes bibliographical references (p. 145-147).
This thesis discusses the design and implementation of a dynamic load-balancing mechanism for computationally distributed programs running on a cluster written in the StreamIt programming language. StreamIt is useful for streaming data applications such as MPEG codecs. The structure of the language carries a lot of static information, such as data rates and computational hierarchy, and therefore lends itself well to parallelization. This work details a simulator for StreamIt cluster computations used to measure metrics such as throughput. Built on top of this simulation is an agent-based market used for load balancing the computation at StreamIt check-points to adapt to exogenously changing loads on the nodes of the cluster. The market models the structure of the computation as a supply chain. Our experiments study the throughput produced by the market compared to other policies, as well as qualitative features such as stability.
by Eric Todd Fellheimer.
M.Eng.
28
Butt, Wajeeh U. N. "Load balancing strategies for distributed computer systems." Thesis, Loughborough University, 1993. https://dspace.lboro.ac.uk/2134/14162.
Full textAbstract:
The study investigates various load balancing strategies to improve the performance of distributed computer systems. A static task allocation and a number of dynamic load balancing algorithms are proposed, and their performances evaluated through simulations. First, in the case of static load balancing, the precedence constrained scheduling heuristic is defined to effectively allocate the task systems with high communication to computation ratios onto a given set of processors. Second, the dynamic load balancing algorithms are studied using a queueing theoretic model. For each algorithm, a different load index has been used to estimate the host loads. These estimates are utilized in simple task placement heuristics to determine the probabilities for transferring tasks between every two hosts in the system. The probabilities determined in this way are used to perform dynamic load balancing in a distributed computer system. Later, these probabilities are adjusted to include the effects of inter-host communication costs. Finally, network partitioning strategies are proposed to reduce the communication overhead of load balancing algorithms in a large distributed system environment. Several host-grouping strategies are suggested to improve the performance of load balancing algorithms. This is achieved by limiting the exchange of load information messages within smaller groups of hosts while restricting the transfer of tasks to long distance remote hosts which involve high communication costs. Effectiveness of the above-mentioned algorithms is evaluated by simulations. The model developed in this study for such simulations can be used in both static and dynamic load balancing environments.
29
Mäkeläinen, M. (Marko). "Algorithms for opportunistic load balancing cognitive engine." Master's thesis, University of Oulu, 2013. http://urn.fi/URN:NBN:fi:oulu-201303011071.
Full textAbstract:
Due to the increasing use of more and more powerful smart devices demands on the scarce radio spectrum are becoming more intense. One way to cope with increasing demands on radio spectrum is to apply innovative and flexible authorization schemes like spectrum sharing. Under the spectrum sharing paradigm, multiple users and/or systems are authorized to utilize the same spectrum band in a defined sharing agreement. A technology that is generally recommended for the implementation of spectrum sharing is called cognitive radio (CR). In this thesis, we design and implement a cognitive engine (CE) that intelligently and dynamically allocates spectrum resources to users. We first consider a scenario where a network has an exclusive access to a spectrum band and the CE accepts or rejects the arrival user requests based on an algorithm that takes into account a user’s priority and its bandwidth demand. We then consider a spectrum sharing scenario where along with the exclusive utilization to its own spectrum band a network also can opportunistically utilize another network’s spectrum band. For this scenario, we design and implement a CE that performs two main tasks: 1) Accepts or rejects arrival user requests based on a priority based algorithm; and 2) it intelligently load balances the user traffic between the two available network resources, while taking into account the primary user activity in the shared spectrum band. We provide a load balancing algorithm and evaluate its performance under different primary and secondary user traffic scenarios. We show that the proposed load balancing algorithm increases average throughput of the network and it also reduces the average number of users rejected by the networkYhä tehokkaampien älykkäiden langattomien päätelaitteiden nopea lisääntyminen johtaa niukan radiospektrin yhä kiihtyvään käyttöön. Eräs menetelmä radiospektrin lisääntyvän kysynnän tyydyttämiseen on hyödyntää innovatiivista ja joustavaa resurssin käytönjakoa kuten spektrin jakamista. Spektrinjakamismalli mahdollistaa useiden käyttäjien ja/tai järjestelmien yhtäaikaisen käytön samalla taajuuskaistalla hyödyntämällä sovittua käytäntöä resurssien jakamisesta. Radiospektrin jakaminen on tänä päivänä yleisesti suositeltu toteuttamaan hyödyntämällä kognitiivista radioteknologiaa. Tässä työssä suunnittellaan ja toteutetaan kognitiivinen päätöksentekokone, joka jakaa radiospektriresursseja käyttäjille älykkäästi ja dynaamisesti. Kognitiivista päätöksentekokonetta radioresurssien jakamisessa hyödynnetään kahdessa skenaariossa. Ensimmäisessä skenaariossa radioverkolla on yksinomainen pääsy taajuuskaistalle, jonka käyttöä kognitiivinen päätöksentekokone säätelee joko hyväksymällä tai hylkäämällä verkkoon liittyviä käyttäjiä. Kognitiivinen päätöksentekokoneen päätökset perustuu algoritmiin, joka ottaa huomioon käyttäjien määritetyn tärkeyden ja käyttäjän vaatiman kaistanleveyden. Seuraavassa skenaariossa radioverkko voi oman yksinomaisen taajuuskaistan lisäksi hyödyntää opportunisesti toisen radioverkon taajuuskaistaa silloin, kun siellä ei ole liikennettä. Tätä skenaariota varten suunnitteltiin kognitiivinen päätöksentekokone, jolla on kaksi päätehtävää: 1) hyväksyä tai hylätä verkkoon liittyviä käyttäjiä edellämainitun tärkeysperusteisen algoritmin avulla; ja 2) jakaa käyttäjien liikennettä kahden tarjolla olevan verkon välillä samalla ottaen huomioon opportunistisen resurssin pääkäyttäjien liikenteen jaetulla taajuuskaistalla. Tässä työssä esitellään toteutettu kuormantasausalgoritmi, jonka suorituskykyä tarkastellaan erilaisissa pääkäyttäjien ja toissijaisien käyttäjien liikenneskenaarioissa. Simulaatiotulokset osoittavat, että esitellyn kuormanjakoalgoritmin hyödyntäminen kognitiivisessa päätöksentekokoneessa parantaa verkon keskimääräistä siirtonopeutta, sekä vähentää keskimääräistä käyttäjien hylkäysastetta verkossa. Algoritmimme parantaa opportunistisen taajuuskaistan käyttöastetta. Algoritmimme ottaa myös huomioon käyttäjille asetetut prioriteetit ja parantaa korkeampi prioriteettisten käyttäjien asemaa verkossa. Tämä tulee ilmi muun muassa korkeampi prioriteettisten käyttäjien pienemmässä hylkäysasteessa
30
Iyer, Sundar. "Load balancing and parallelism for the internet /." May be available electronically:, 2008. http://proquest.umi.com/login?COPT=REJTPTU1MTUmSU5UPTAmVkVSPTI=&clientId=12498.
Full text
31
Chow, Ka-po. "Load-balancing in distributed multi-agent computing /." Hong Kong : University of Hong Kong, 2000. http://sunzi.lib.hku.hk:8888/cgi-bin/hkuto%5Ftoc%5Fpdf?B2295644x.
Full text
32
Cheung, Lap-sun. "Load balancing in distributed object computing systems." Hong Kong : University of Hong Kong, 2001. http://sunzi.lib.hku.hk/hkuto/record.jsp?B2329428.
Full text
33
Kumar, Rahul. "Load Balancing Parallel Explicit State Model Checking." Diss., CLICK HERE for online access, 2004. http://contentdm.lib.byu.edu/ETD/image/etd455.pdf.
Full text
34
Wallace, Brian T. "Automated system for load-balancing EBGP peers." [Gainesville, Fla.] : University of Florida, 2004. http://purl.fcla.edu/fcla/etd/UFE0008800.
Full text
35
Adams, Daniel Alan. "Optimal Load Balancing in a Beowulf Cluster." Link to electronic thesis, 2005. http://www.wpi.edu/Pubs/ETD/Available/etd-050205-135758/.
Full text
36
Lu, Kai. "Decentralized load balancing in heterogeneous computational grids." Thesis, The University of Sydney, 2007. http://hdl.handle.net/2123/9382.
Full textAbstract:
With the rapid development of high-speed wide-area networks and powerful yet low-cost computational resources, grid computing has emerged as an attractive computing paradigm. The space limitations of conventional distributed systems can thus be overcome, to fully exploit the resources of under-utilised computing resources in every region around the world for distributed jobs. Workload and resource management are key grid services at the service level of grid software infrastructure, where issues of load balancing represent a common concern for most grid infrastructure developers. Although these are established research areas in parallel and distributed computing, grid computing environments present a number of new challenges, including large-scale computing resources, heterogeneous computing power, the autonomy of organisations hosting the resources, uneven job-arrival pattern among grid sites, considerable job transfer costs, and considerable communication overhead involved in capturing the load information of sites. This dissertation focuses on designing solutions for load balancing in computational grids that can cater for the unique characteristics of grid computing environments. To explore the solution space, we conducted a survey for load balancing solutions, which enabled discussion and comparison of existing approaches, and the delimiting and exploration of the apportion of solution space. A system model was developed to study the load-balancing problems in computational grid environments. In particular, we developed three decentralised algorithms for job dispatching and load balancing—using only partial information: the desirability-aware load balancing algorithm (DA), the performance-driven desirability-aware load-balancing algorithm (P-DA), and the performance-driven region-based load-balancing algorithm (P-RB). All three are scalable, dynamic, decentralised and sender-initiated. We conducted extensive simulation studies to analyse the performance of our load-balancing algorithms. Simulation results showed that the algorithms significantly outperform preexisting decentralised algorithms that are relevant to this research.
37
Cosenza, Biagio. "Efficient distributed load balancing for parallel algorithms." Doctoral thesis, Universita degli studi di Salerno, 2011. http://hdl.handle.net/10556/205.
Full textAbstract:
2009 - 2010With the advent of massive parallel processing technology, exploiting the power offered by hundreds, or even thousands of processors is all but a trivial task. Computing by using multi-processor, multi-core or many-core adds a number of additional challenges related to the cooperation and communication of multiple processing units. The uneven distribution of data among the various processors, i.e. the load imbalance, represents one of the major problems in data parallel applications. Without good load distribution strategies, we cannot reach good speedup, thus good efficiency. Load balancing strategies can be classified in several ways, according to the methods used to balance workload. For instance, dynamic load balancing algorithms make scheduling decisions during the execution and commonly results in better performance compared to static approaches, where task assignment is done before the execution. Even more important is the difference between centralized and distributed load balancing approaches. In fact, despite that centralized algorithms have a wider vision of the computation, hence may exploit smarter balancing techniques, they expose global synchronization and communication bottlenecks involving the master node. This definitely does not assure scalability with the number of processors. This dissertation studies the impact of different load balancing strategies. In particular, one of the key observations driving our work is that distributed algorithms work better than centralized ones in the context of load balancing for multi-processors (alike for multi-cores and many-cores as well). We first show a centralized approach for load balancing, then we propose several distributed approaches for problems having different parallelization, workload distribution and communication pattern. We try to efficiently combine several approaches to improve performance, in particular using predictive metrics to obtain a per task compute-time estimation, using adaptive subdivision, improving dynamic load balancing and addressing distributed balancing schemas. The main challenge tackled on this thesis has been to combine all these approaches together in new and efficient load balancing schemas. We assess the proposed balancing techniques, starting from centralized approaches to distributed ones, in distinctive real case scenarios: Mesh-like computation, Parallel Ray Tracing, and Agent-based Simulations. Moreover, we test our algorithms with parallel hardware such has cluster of workstations, multi-core processors and exploiting SIMD vectorial instruction set. Finally, we conclude the thesis with several remarks, about the impact of distributed techniques, the effect of the communication pattern and workload distribution, the use of cost estimation for adaptive partitioning, the trade-off fast versus accuracy in prediction-based approaches, the effectiveness of work stealing combined with sorting, and a non-trivial way to exploit hybrid CPUGPU computations. [edited by author]
IX n.s.
38
Igbe, Damian. "Dynamic load balancing of parallel road traffic simulation." Thesis, University of Westminster, 2010. https://westminsterresearch.westminster.ac.uk/item/90644/dynamic-load-balancing-of-parallel-road-traffic-simulation.
Full textAbstract:
The objective of this research was to investigate, develop and evaluate dynamic load-balancing strategies for parallel execution of microscopic road traffic simulations. Urban road traffic simulation presents irregular, and dynamically varying distributed computational load for a parallel processor system. The dynamic nature of road traffic simulation systems lead to uneven load distribution during simulation, even for a system that starts off with even load distributions. Load balancing is a potential way of achieving improved performance by reallocating work from highly loaded processors to lightly loaded processors leading to a reduction in the overall computational time. In dynamic load balancing, workloads are adjusted continually or periodically throughout the computation. In this thesis load balancing strategies were evaluated and some load balancing policies developed. A load index and a profitability determination algorithms were developed. These were used to enhance two load balancing algorithms. One of the algorithms exhibits local communications and distributed load evaluation between the neighbour partitions (diffusion algorithm) and the other algorithm exhibits both local and global communications while the decision making is centralized (MaS algorithm). The enhanced algorithms were implemented and synthesized with a research parallel traffic simulation. The performance of the research parallel traffic simulator, optimized with the two modified dynamic load balancing strategies were studied.
39
Korzeniowski, Miroslaw. "Dynamic load balancing in peer-to-peer networks." [S.l.] : [s.n.], 2006. http://deposit.ddb.de/cgi-bin/dokserv?idn=983620296.
Full text
40
Ljungkvist, Karl. "Autonomic Dynamic Load Balancing of Parallel SAMR Applications." Thesis, Uppsala universitet, Avdelningen för teknisk databehandling, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-155517.
Full textAbstract:
When solving partial differential equations using finite difference methods on structured meshes, adaptive refinement can be used to increase the accuracy of the solution in an efficient manner. When implementing solvers using structured adaptive mesh refinement for modern parallel computer systems, an important task is the partitioning of the grid hierarchy over the available processors. The Meta-partitioner is an autonomic framework which can dynamically select between a large number of grid-partitioning algorithms at run time. In this thesis we investigate which modifications that are necessary in order to connect the Meta-partitioner to the existing SAMR-framework Chombo, and begin the process of performing this connection. We conclude that although significant changes to both Chombo and the Meta-partitioner are necessary, a connection definitely seams feasible. We estimate that that the major work of the connection has been done, and that with the experience gained from this project, the continuation is straightforward. We also connect a patch-based partitioning algorithm to Chombo and evaluate it for the first time as part of a real SAMR-based simulation. The results are promising and we conclude that it is a viable candidate for inclusion in the Meta-partitioner.
41
Schlimbach, Frank. "Optimising subdomain aspect ratios for parallel load balancing." Thesis, University of Greenwich, 2000. http://gala.gre.ac.uk/6293/.
Full textAbstract:
In parallel adaptive Finite Element simulations the work load 011the individual processors can change frequently. To (re)distribute the load evenly over the processors a load balancing heuristic is needed. Common strategies try to minimise subdomain dependencies by minimising the number of cut edges in the partition. For many solvers this is the most influential factor. However for example, for certain preconditioned Conjugate Gradient solvers this cutsize can play only a minor role, but their convergence can be highly dependent on the subdomain shapes. Degenerated subdomain shapes can cause them to need significantly more iterations to converge. Common heuristics often fail to address these requirements. In this thesis a new strategy is introduced which directly addresses the problem of generating and conserving reasonably good subdomain shapes while balancing the load in a dynamically changing Finite Element Simulation. A new definition of Aspect Ratio is presented which assesses subdomain shapes. The common methodology of using adjacency information to select the best elements to be migrated is not considered since it is not necessarily related to the subdomain shapes. Instead, geometric data is used to formulate several cost functions to rate elements in terms of their suitability to be migrated. The well known diffusive and Generalised Dimension Exchange methods which calculate the necessary load flow are enhanced by weighting the subdomain edges in order to influence their impact on the resulting partition positively. The results of comprehensive tests are presented and demonstrate that the proposed methods are competitive with state-of-the-art load balancing tools.
42
Cai, Haiying. "Dynamic load balancing on the EARTH-SP system." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk2/tape16/PQDD_0006/MQ29667.pdf.
Full text
43
Khanna, Varun. "Intelligent load balancing in mobile ad hoc networks." Thesis, Wichita State University, 2010. http://hdl.handle.net/10057/3729.
Full textAbstract:
On demand ad hoc routing protocols such as AODV and DSR do not look for new routes unless there is a change in the network topology. In scenarios where same intermediate node is used for longer time, this behavior may cause the traffic concentration on few intermediate nodes resulting in large latency and depletion of battery power at the nodes. To overcome this problem, a load balancing algorithm is proposed in this thesis. Each node forwards its residual energy information to all its neighbor nodes using reserved fields in the hello packets. Each node calculates a desirability metric, for each of its neighbor, based on the neighbor‟s energy information and the available bandwidth towards it. The choice of a particular route depends upon the desirability metric of the next hop. The proposed scheme is independent of the underlying routing protocol however the routing protocol should be able to save multiple routes to a destination and be able to put and retrieve the energy information to and from the hello messages.Thesis (M.S.)--Wichita State University, College of Engineering, Dept. of Electrical Engineering and Computer Science.
44
Cai, Haïying. "Dynamic load balancing on the earth-SP system." Thesis, McGill University, 1997. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=27292.
Full textAbstract:
The rapid progress of computer systems based on fine-grain multithreaded program execution models introduce both unique opportunities and challenges in the design and application of dynamic load balancing algorithms. This thesis presents a study of dynamic load balancing under the EARTH muitithreaded model.In this study, we have implemented a number of load balancing algorithms on the EARTH-SP testbed--a realization of EARTH model on the IBM-SP2 system. Our study has been carried out on both benchmark programs and a set of stress tests. The major results of this thesis include: (A) Demonstration that a load balancing algorithm is likely to be robust if it has the following features: (1) initiating load balancing requests by both the satiated and the hungry nodes; (2) making use of certain history information to guide balancing decisions. (B) Several specific observations and conclusions: (1) The performances of the load balancers vary under different computation models. This difference between load balancers becomes substantial under certain class of computation such as SPMD model. (2) When the parallelism grain size is small, the performance difference between load balancing algorithms becomes significant. This indicates the importance of searching good load balancers for efficient exploitation of fine-grain parallelism. (3) Some architecture parameters such as polling interval have a considerable impact on the effect of dynamic load balancing. (4) A load balancer with shorter communication path is likely to be scalable. (C) Suggestions for a number of aspects which should be considered in the exploitation of the design space for load balancing algorithms and their evaluations.
45
Du, Lin. "Intelligent geographic load balancing for mobile cellular networks." Thesis, Queen Mary, University of London, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.414466.
Full text
46
須成忠 and Cheng-zhong Xu. "Iterative methods for dynamic load balancing in multicomputers." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1993. http://hub.hku.hk/bib/B31233302.
Full text
47
Liu, Zhenhua. "Greening Geographical Load Balancing." Thesis, 2011. https://thesis.library.caltech.edu/6442/2/ZhenhuaLiu_MS_Thesis.pdf.
Full textAbstract:
Energy expenditure has become a significant fraction of data center operating costs. Recently, "geographical load balancing" has been suggested to reduce energy cost by exploiting the electricity price differences across regions. However, this reduction of cost can paradoxically increase total energy use. This work explores whether the geographical diversity of internet-scale systems can additionally be used to provide environmental gains.
We first focus on geographical load balancing, which is modeled as a convex optimization problem. We derive two distributed algorithms for achieving optimal geographical load balancing and characterize the optimal solutions.
Then we continue to use the framework and algorithms to investigate whether geographical load balancing can encourage use of "green" renewable energy and reduce use of "brown" fossil fuel energy. Here we consider two approaches, namely, dynamic pricing and local renewables.
For the dynamic pricing case, our numeric results show that if electricity is dynamically priced in proportion to the instantaneous fraction of the total energy that is brown, then geographical load balancing provides significant reductions in brown energy use. However, the benefits depend strongly on the degree to which systems accept dynamic energy pricing and the form of pricing used.
For the local renewable case, we perform a trace-based study to evaluate three issues related to achieving this goal: the impact of geographical load balancing, the role of storage, and the optimal mix of renewables. Our results highlight that geographical load balancing can significantly reduce the required capacity of renewable energy by using the energy more efficiently with "follow the renewables" routing. Further, our results show that small-scale storage can be useful, especially in combination with geographical load balancing, and that an optimal mix of renewables includes significantly more wind than photovoltaic solar.
48
DEEPTI. "LOAD BALANCING IN CLOUD COMPUTING." Thesis, 2014. http://dspace.dtu.ac.in:8080/jspui/handle/repository/15432.
Full textAbstract:
The advent of cloud computing in recent years has sparked an interest from different
organizations, institutions and users to take advantage of services and applications. Because
of serving a very attractive package of services, cloud technology has grasped a huge
attention from academia, IT industry and government organizations. Cloud computing
promises scalability and on-demand availability of resources. As the number of users on the
internet goes on increasing, it becomes difficult to handle the millions of user requests on it.
Many a times it happens during the peak-hours that the traffic on the network increases
abruptly. In such situations it is commonly observed that the system performance degrades.
Though having many good features such issues restrict a user to use the services. Users may
not find it that much reliable.
Therefore, one of the important issues which need a major consideration of the researchers is
load balancing in cloud computing systems. A number of load balancing algorithm are
proposed by various researchers, to solve this problem. Two kinds of load balancing
algorithms are there one is static and other is dynamic. A cloud computing system is
supposed to handle the request dynamically rather than doing it by a static approach which is
supposed to be the less efficient approach. Also there are number of parameters like resource
utilization, throughput, scalability, flexibility, response time, which are used to validate any
load balancing algorithm. Any load balancing developer is supposed to maintain a good of
trade-off between these parameters.
In this thesis a new approach for load balancing in cloud computing is proposed. This
algorithm aims at distributing the equal load on each server in the cloud network. This also
improves the resource utilization. With the proposed approach a situation in which only few
resources are loaded heavily while others are just sitting idle will never arise. The proposed
algorithm is also compared with the existing load balancing techniques.
49
Tung-Wei, Yang. "Dynamic Load Balancing for Multiple Processors." 2005. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0001-1307200518393900.
Full text
50
Singh, Sarabjot active 21st century. "Load balancing in heterogeneous cellular networks." Thesis, 2014. http://hdl.handle.net/2152/28387.
Full textAbstract:
Pushing wireless data traffic onto small cells is important for alleviating congestion in the over-loaded macrocellular network. However, the ultimate potential of such load balancing and its effect on overall system performance is not well understood. With the ongoing deployment of multiple classes of access points (APs) with each class differing in transmit power, employed frequency band, and backhaul capacity, the network is evolving into a complex and “organic” heterogeneous network or HetNet. Resorting to system-level simulations for design insights is increasingly prohibitive with such growing network complexity. The goal of this dissertation is to develop realistic yet tractable frameworks to model and analyze load balancing dynamics while incorporating the heterogeneous nature of these networks. First, this dissertation introduces and analyzes a class of user-AP association strategies, called stationary association, and the resulting association cells for HetNets modeled as stationary point processes. A “Feller-paradox”-like relationship is established between the area of the association cell containing the origin and that of a typical association cell. This chapter also provides a foundation for subsequent chapters, as association strategies directly dictate the load distribution across the network. Second, this dissertation proposes a baseline model to characterize downlink rate and signal-to-interference-plus-noise-ratio (SINR) in an M-band K-tier HetNet with a general weighted path loss based association. Each class of APs is modeled as an independent Poisson point process (PPP) and may differ in deployment density, transmit power, bandwidth (resource), and path loss exponent. It is shown that the optimum fraction of traffic offloaded to maximize SINR coverage is not in general the same as the one that maximizes rate coverage. One of the main outcomes is demonstrating the aggressive of- floading required for out-of-band small cells (like WiFi) as compared to those for in-band (like picocells). To achieve aggressive load balancing, the offloaded users often have much lower downlink SINR than they would on the macrocell, particularly in co-channel small cells. This SINR degradation can be partially alleviated through interference avoidance, for example time or frequency resource partitioning, whereby the macrocell turns off in some fraction of such resources. As the third contribution, this dissertation proposes a tractable framework to analyze joint load balancing and resource partitioning in co-channel HetNets. Fourth, this dissertation investigates the impact of uplink load balancing. Power control and spatial interference correlation complicate the mathixematical analysis for the uplink as compared to the downlink. A novel generative model is proposed to characterize the uplink rate distribution as a function of the association and power control parameters, and used to show the optimal amount of channel inversion increases with the path loss variance in the network. In contrast to the downlink, minimum path loss association is shown to be optimal for uplink rate coverage. Fifth, this dissertation develops a model for characterizing rate distribution in self-backhauled millimeter wave (mmWave) cellular networks and thus generalizes the earlier multi-band offloading framework to the co-existence of current ultra high frequency (UHF) HetNets and mmWave networks. MmWave cellular systems will require high gain directional antennas and dense AP deployments. The analysis shows that in sharp contrast to the interferencelimited nature of UHF cellular networks, mmWave networks are usually noiselimited. As a desirable side effect, high gain antennas yield interference isolation, providing an opportunity to incorporate self-backhauling. For load balancing, the large bandwidth at mmWave makes offloading users, with reliable mmWave links, optimal for rate.text