Literatura académica sobre el tema "Landscape-aware algorithm selection"

In optimization, algorithm selection, which is the selection of the most suitable algorithm for a specific problem, is of great importance, as algorithm performance is heavily dependent on the problem being solved. However, when using machine learning for algorithm selection, the performance of the algorithm selection model depends on the data used to train and test the model, and existing optimization benchmarks only provide a limited amount of data. To help with this problem, artificial problem generation has been shown to be a useful tool for augmenting existing benchmark problems. In this paper, we are interested in the problem of knowledge transfer between the artificially generated and existing handmade benchmark problems in the domain of continuous numerical optimization. That is, can an algorithm selection model trained purely on artificially generated problems correctly provide algorithm recommendations for existing handmade problems. We show that such a model produces low-quality results, and we also provide explanations about how the algorithm selection model works and show the differences between the problem data sets in order to explain the model’s performance.

The selection of rootstocks is one of the first and most important stages in the establishment of grape plantations under grafted conditions, which determines the productivity of rootstock-scion combinations and the further chain of design solutions: spatial placement of rows on the land plot, accompanying the production process of agronomic and agrochemical methods. Given the high importance of terroir factors for viticulture and winemaking, we were aware of the need to consider them in detail at this design stage. The aim was to create an algorithm for selecting varieties based on local terroir factors and apply it to the design of vineyards. Based on the analysis of literary sources and the agronomic experience of viticulture and winemaking specialists, we have identified key stress factors that in general, should be taken into account when selecting varieties of rootstocks. Based on the results of a comprehensive study of terroir and analytical diagnostics of soil samples taken on a land plot located in the Bakhchisaray district of the Republic of Crimea, local stress factors representing risks were clarified and prioritized neo-medially at the site of testing the landscape-adapted approach to the selection of rootstocks: carbonate condition, risk of phylloxera infestation, high content of fine fractions in granulometric composition, short-term droughts, risk of local overwatering, phosphorus deficiency. In total 20 the most common commercial varieties of rootstocks were considered for each selected soil area. The sample reduction scenario, based on the prioritization of the above stressors, reduced the number of varieties considered to three variants: 1103 Paulsen, 140 Ruggeri, and Fercal, which were scored against each other and considering the local terroir conditions of the plot, for further comparison in terms of market and logistics in making the final design decision.

The Internet of Things (IoT) represents a cutting-edge technical domain, encompassing billions of intelligent objects capable of bridging the physical and virtual worlds across various locations. IoT services are responsible for delivering essential functionalities. In this dynamic and interconnected IoT landscape, providing high-quality services is paramount to enhancing user experiences and optimizing system efficiency. Service composition techniques come into play to address user requests in IoT applications, allowing various IoT services to collaborate seamlessly. Considering the resource limitations of IoT devices, they often leverage cloud infrastructures to overcome technological constraints, benefiting from unlimited resources and capabilities. Moreover, the emergence of fog computing has gained prominence, facilitating IoT application processing in edge networks closer to IoT sensors and effectively reducing delays inherent in cloud data centers. In this context, our study proposes a cloud-/fog-based service composition for IoT, introducing a novel fuzzy-based hybrid algorithm. This algorithm ingeniously combines Ant Colony Optimization (ACO) and Artificial Bee Colony (ABC) optimization algorithms, taking into account energy consumption and Quality of Service (QoS) factors during the service selection process. By leveraging this fuzzy-based hybrid algorithm, our approach aims to revolutionize service composition in IoT environments by empowering intelligent decision-making capabilities and ensuring optimal user satisfaction. Our experimental results demonstrate the effectiveness of the proposed strategy in successfully fulfilling service composition requests by identifying suitable services. When compared to recently introduced methods, our hybrid approach yields significant benefits. On average, it reduces energy consumption by 17.11%, enhances availability and reliability by 8.27% and 4.52%, respectively, and improves the average cost by 21.56%.

AbstractRapid technological advances have made daily life easier and more convenient in recent years. As an emerging technology, the Internet of Things (IoT) facilitates interactions between physical devices. With the advent of sensors and features on everyday items, they have become intelligent entities able to perform multiple functions as services. IoT enables routine activities to become more intelligent, deeper communication, and processes more efficient. In the dynamic landscape of the IoT, effective service discovery is key to optimizing user experiences. A Quality of Service (QoS)-aware service discovery technique is proposed in this paper to address this challenge. Through whale optimization and genetic algorithms, our method aims to streamline decision-making processes in IoT service selection. The bio-inspired optimization techniques employed in our approach facilitate the discovery of services more efficiently than traditional methods. Our results demonstrate superior performance regarding reduced data access time, optimized energy utilization, and cost-effectiveness through comprehensive simulations.

Les algorithmes d'optimisation de boîte noire (BBOA) sont conçus pour des scénarios où les formulations exactes de problèmes sont inexistantes, inaccessibles, ou trop complexes pour la résolution analytique. Les BBOA sont le seul moyen de trouver une bonne solution à un tel problème. En raison de leur applicabilité générale, les BBOA présentent des comportements différents lors de l'optimisation de différents types de problèmes. Cela donne un problème de méta-optimisation consistant à choisir l'algorithme le mieux adapté à un problème particulier, appelé problème de sélection d'algorithmes (AS). La vision d'automatiser cette sélection a vite gagné du terrain dans la communauté. Un moyen important de le faire est l'AS tenant compte du paysage, où le choix de l'algorithme est basé sur la prédiction de ses performances via des représentations numériques d'instances de problèmes appelées caractéristiques. Un défi clé auquel l'AS tenant compte du paysage est confrontée est le coût de calcul de l'extraction des caractéristiques, une étape qui précède l'optimisation. Dans cette thèse, nous proposons une approche d'AS tenant compte du paysage basée sur la trajectoire de recherche qui intègre cette étape d'extraction dans celle d'optimisation. Nous montrons que les caractéristiques calculées à l'aide de la trajectoire conduisent à des prédictions robustes et fiables des performances des algorithmes, et à de puissants modèles d'AS construits dessus. Nous présentons aussi plusieurs analyses préparatoires, y compris une perspective de combinaison de 2 stratégies de régression complémentaires qui surpasse des modèles classiques de régression simple et amplifie la qualité du sélecteur
Black-box optimization algorithms (BBOAs) are conceived for settings in which exact problem formulations are non-existent, inaccessible, or too complex for an analytical solution. BBOAs are essentially the only means of finding a good solution to such problems. Due to their general applicability, BBOAs can exhibit different behaviors when optimizing different types of problems. This yields a meta-optimization problem of choosing the best suited algorithm for a particular problem, called the algorithm selection (AS) problem. By reason of inherent human bias and limited expert knowledge, the vision of automating the selection process has quickly gained traction in the community. One prominent way of doing so is via so-called landscape-aware AS, where the choice of the algorithm is based on predicting its performance by means of numerical problem instance representations called features. A key challenge that landscape-aware AS faces is the computational overhead of extracting the features, a step typically designed to precede the actual optimization. In this thesis, we propose a novel trajectory-based landscape-aware AS approach which incorporates the feature extraction step within the optimization process. We show that the features computed using the search trajectory samples lead to robust and reliable predictions of algorithm performance, and to powerful algorithm selection models built atop. We also present several preparatory analyses, including a novel perspective of combining two complementary regression strategies that outperforms any of the classical, single regression models, to amplify the quality of the final selector