Dissertations / Theses on the topic 'Energy consumption – Ontario – Forecasting'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 43 dissertations / theses for your research on the topic 'Energy consumption – Ontario – Forecasting.'
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.
Bae, Kyungcho. "Energy consumption forecasting: Econometric model vs state space model." Diss., The University of Arizona, 1994. http://hdl.handle.net/10150/187010.
Full textHe, Miaofen 1976. "Assessing the economic feasibility of a carbon tax on energy inputs in Ontario's pulp and paper industry : an econometric analysis." Thesis, McGill University, 2001. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=31232.
Full textDodds, Gordon Ivan. "Modelling and forecasting electricity demand using aggregate and disaggregate data." Thesis, Queen's University Belfast, 1988. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.306073.
Full textMcCafferty, Peter. "Forecasting electricity demand in the industrial sector based on disaggregate data." Thesis, Queen's University Belfast, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.385049.
Full textCheng, Yuanzhi. "Forecasting by learning methods: The gross domestic product, total energy consumption and petroleum consumption of the United States." Diss., The University of Arizona, 1994. http://hdl.handle.net/10150/186631.
Full textMuendej, Krisanee. "Predictions of monthly energy consumption and annual patterns of energy usage for convenience stores by using multiple and nonlinear regression models." Texas A&M University, 2004. http://hdl.handle.net/1969.1/1221.
Full textHadjipaschalis, Constantinos. "An investigation of artificial neural networks applied to monthly electricity peak demand and energy forecasting." Thesis, Imperial College London, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.286627.
Full textMangisa, Siphumlile. "Statistical analysis of electricity demand profiles." Thesis, Nelson Mandela Metropolitan University, 2013. http://hdl.handle.net/10948/d1011548.
Full textSakva, Denys. "Evaluation of errors in national energy forecasts /." Link to online version, 2005. https://ritdml.rit.edu/dspace/handle/1850/1166.
Full textTrujillo, Iliana Cardenes. "Quantifying the energy consumption of the water use cycle." Thesis, University of Oxford, 2017. https://ora.ox.ac.uk/objects/uuid:df481801-cce1-4824-986c-612f4673b8eb.
Full textNedzingahe, Livhuwani. "Forecasting models for operational and tactical requirements in electricity consumption: The case of the Ferrochrome Sector in South Africa." Thesis, University of Limpopo (Medunsa Campus ), 2010. http://hdl.handle.net/10386/1150.
Full textForecasting electricity consumption is a challenge for most power utilities. In South Africa the anxiety posed by electricity supply disruption is a cause for concern in sustainable energy planning. Accurate forecasting of future electricity consumption has been identified as an essential input to this planning process. Forecasting electricity consumption has been widely researched and several methodologies suggested. However, various methods that have been proposed by a number of researchers are dependent on environment and market factors related to the scope of work under study making portability a challenge. The aim of this study is to investigate models to forecast short term electricity consumption for operational use and medium term electricity consumption for tactical use in the Ferrochrome sector in South Africa. An Autoregressive Moving Average method is suggested as an appropriate tool for operational planning. The Holt-Winter Linear seasonal smoothing method is suggested for tactical planning. Keywords: Forecasting, electricity consumption, operational planning, tactical planning, ARIMA, Holt-Winter Linear seasonal smoothing, Ferrochrome sector
Leung, Chun Kai. "Sectoral consumption of oil in China, 1990-2006." HKBU Institutional Repository, 2009. http://repository.hkbu.edu.hk/etd_ra/1078.
Full textSi, Yau-li, and 史有理. "Forecasts of electricity demand and their implication for energy developments in Hong Kong." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1990. http://hub.hku.hk/bib/B31976384.
Full textSILVA, FELIPE LEITE COELHO DA. "BAYESIAN STOCHASTIC EXTENSION OF DETERMINISTIC BOTTOM-UP APPROACH FOR THE LONG TERM FORECASTING OF ENERGY CONSUMPTION." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2017. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=33006@1.
Full textCOORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR
PROGRAMA DE EXCELENCIA ACADEMICA
O comportamento do consumo de energia elétrica do setor industrial tem sido amplamente investigado ao longo dos últimos anos, devido a sua importância econômica, social e ambiental. Mais especificamente, o consumo de eletricidade dos subsetores da indústria brasileira exerce grande importância para o sistema energético brasileiro. Neste contexto, as projeções de longo prazo do seu consumo de energia elétrica para um país ou uma região são informações de grande relevância na tomada de decisão de órgãos e entidades que atuam no setor energético. A abordagem bottom-up determinística tem sido utilizada para obter a previsão de longo prazo em diversas áreas de pesquisa. Neste trabalho, propõe-se uma metodologia que combina a abordagem bottom-up com os modelos lineares hierárquicos para a previsão de longo prazo considerando os cenários de eficiência energética. Além disso, foi utilizada a inferência bayesiana para a estimação dos parâmetros do modelo, permitindo a incorporação de incerteza nessas previsões. Os resultados utilizando os dados de consumo de eletricidade de subsetores da indústria brasileira mostraram que a metodologia proposta consegue capturar a tajetória do consumo de eletricidade, em particular, dos subsetores de papel e celulose, e de metais não-ferrosos e outros de metalurgia. Por exemplo, os intervalos de credibilidade de 95 por cento construídos a partir do modelo estocástico contemplam os valores reais observados nos anos de 2015 e 2016.
The electricity consumption behaviour in the Brazilian industry has been extensively investigated over the past years due to its economic, social and environmental importance. Specifically, the electricity consumption of the subsectors of Brazilian industry have great importance for the Brazilian energy system. In this context, the long-term projections of energy consumption of a country or region are highly relevant information to decision-making of organs and entities operating in the energy sector. The deterministic bottom-up approach has been used for the long-term forecast in several areas of research. In this paper, we propose a methodology that combines the bottom-up approach with hierarchical linear models for long-term forecasting considering energy efficiency scenarios. In addition, Bayesian inference was used to estimate the parameters of the model, allowing the uncertainty incorporation in these forecasts. The results using the electricity consumption data from subsectors of the Brazilian industry showed that the proposed methodology is able to capture the trajectory of their electricity consumption, in particular of the pulp and paper, and of non-ferrous metals and other metallurgical subsectors. For example, the 95 percent credibility intervals constructed from the stochastic model contemplate the actual values observed in the years 2015 and 2016.
CARON, MATHIEU. "Long-term forecasting model for future electricity consumption in French non-interconnected territories." Thesis, KTH, Skolan för industriell teknik och management (ITM), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-299457.
Full textI samband med utfasningen av fossila källor för elproduktion i franska icke-sammankopplade territorier är kunskapen om framtida elbehov, särskilt årlig förbrukning och topplast på lång sikt, avgörande för att utforma ny infrastruktur för förnybar energi. Hittills är dessa territorier, främst öar som ligger i Stilla havet och Indiska oceanen, beroende av anläggningar med fossila bränslen. Energipolitiken planerar att på bred front utveckla förnybar energi för att gå mot en koldioxidsnål elmix till 2028. Denna avhandling fokuserar på den långsiktiga prognosen för elbehov per timme. En metod är utvecklad för att utforma och välja en modell som kan passa korrekt historisk data och för att förutsäga framtida efterfrågan inom dessa specifika områden. Historiska data analyseras först genom en klusteranalys för att identifiera trender och mönster, baserat på en k-means klusteralgoritm. Specifika kalenderinmatningar utformas sedan för att beakta dessa första observationer. Externa inmatningar, såsom väderdata, ekonomiska och demografiska variabler, ingår också. Prognosalgoritmer väljs utifrån litteraturen och de testas och jämförs på olika inmatade dataset. Dessa inmatade dataset, förutom den nämnda kalenderdatan och externa variabler, innehåller olika antal fördröjda värden, från noll till tre. Kombinationen av modell och inmatat dataset som ger de mest exakta resultaten på testdvärdena väljs för att förutsäga framtida elbehov. Införandet av fördröjda värden leder till betydande förbättringar i exakthet. Även om gradientförstärkande regression har de lägsta felen kan den inte upptäcka toppar av elbehov korrekt. Tvärtom, visar artificiella neurala nätverk (ANN) en stor förmåga att passa historiska data och visar en god noggrannhet på testuppsättningen, liksom för förutsägelse av toppefterfrågan. En generaliserad tillsatsmodell, en relativt ny modell inom energiprognosfältet, ger lovande resultat eftersom dess prestanda ligger nära den för ANN och representerar en intressant modell för framtida forskning. Baserat på de framtida värdena på indata, prognostiserades elbehovet 2028 i Réunion med ANN. Elbehovet förväntas nå mer än 2,3 GWh och toppbehovet cirka 485 MW. Detta motsvarar en tillväxt på 12,7% respektive 14,6% jämfört med 2019 års nivåer.
Wöstmann, Corinna. "Energy Consumption - Forecasting for Linköping and Helsingborg : A Comparison of SARIMA Modelling and Double Seasonal Holt-Winters Exponential Smoothing." Thesis, Linnéuniversitetet, Institutionen för matematik (MA), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-28318.
Full textBuzatoiu, Roxana. "Long Term Forecasting of Industrial Electricity Consumption Data With GRU, LSTM and Multiple Linear Regression." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-289632.
Full textNoggranna långsiktiga energiprognosprognoser för industriella enheter är av intresse för distributionsföretag eftersom det potentiellt kan bidra till att minska deras churn och erbjuda stöd i beslutsfattandet vid säkring. Detta avhandlingsarbete presenterar olika metoder för att prognostisera energiförbrukningen för industriella enheter under en lång tids förutsägelsehorisont på 1 år. I synnerhet inkluderar det experiment med två varianter av de återkommande neurala nätverken, nämligen GRU och LSTM. Deras prestanda jämförs med traditionella metoder, nämligen MLR och SARIMA. Vidare fokuserar undersökningen på att skräddarsy modellen för återkommande neurala nätverk för att förbättra prestanda. Experimenten fokuserar på effekterna av olika modellarkitekturer. För det andra fokuserar den på att testa effekten av tidsrelaterat funktionsval som en extra ingång till RNN -nätverk. Specifikt undersökte den hur traditionella metoder som Exploratory Data Analysis, Autocorrelation och Partial Autocorrelation Funtions Plots kan bidra till prestanda för RNN -modellen. Det aktuella arbetet visar genom en empirisk studie av tre industriella datamängder att GRU -arkitektur är en kraftfull metod för den långsiktiga prognosuppgiften som överträffar ac LSTM på vissa scenarier. Jämfört med MLR -modellen uppnådde RNN en minskning av RMSE mellan 5 % upp till 10 %. De viktigaste resultaten inkluderar: (i) GRU -arkitekturen överträffar LSTM på datauppsättningar för industriell energiförbrukning jämfört med ett lägre antal dolda enheter. GRU överträffar också LSTM på vissa datauppsättningar, oavsett antalet valenheter; (ii) RNN -varianter ger bättre noggrannhet än statistiska modeller eller regressionsmodeller; (iii) att använda ACF och PACF som verktyg för upptäckt i funktionsvalsprocessen är otydligt och ineffektivt när man siktar på en allmän modell; (iv) att använda deterministiska funktioner (t.ex. årets dag, månadsdagen) har begränsade effekter på att förbättra djupinlärningsmodellens prestanda.
Волощук, Андрій Володимирович, and Andrii Volodymyrovych Voloshchuk. "Методи і засоби автоматизованого збору та прогнозування середньострокового енергоспоживання на рівні області." Master's thesis, Тернопільський національний технічний університет імені Івана Пулюя, 2021. http://elartu.tntu.edu.ua/handle/lib/36537.
Full textIn the master's thesis the methods and means of automated collection and forecasting of medium-term energy consumption at the regional level are investigated. An analysis of current trends in the design of computer systems in the field of energy management and found that appropriate and effective technologies for their design is the use of IoT devices as end devices and control devices in the relevant communication networks. The architecture of the intelligent electricity consumption meter was substantiated and designed, which made it possible to provide optimization and forecasting of energy consumption and rational operation of connected devices. Models of energy consumption forecasting based on autoregression, exponential smoothing and neural networks were studied, and their software was implemented using the Python programming language, which made it possible to obtain accurate forecast results with an error of 3% -4%.
ПЕРЕЛІК ОСНОВНИХ УМОВНИХ ПОЗНАЧЕНЬ, СИМВОЛІВ І СКОРОЧЕНЬ ...8 ВСТУП ... 9 РОЗДІЛ 1 АНАЛІЗ СУЧАСНИХ СИСТЕМ ЗБОРУ ТА ПРОГНОЗУВАННЯ ЕНЕРГОСПОЖИВАННЯ ...13 1.1. Аналіз особливостей споживачів електричної енергії ...13 1.2. Аналіз виробництва і споживання електроенергії в Україні ...17 1.3. Аналіз сучасних трендів при проектуванні комп’ютерних систем управління енергетичними ресурсами ...20 1.4. Аналіз підходів до прогнозування енергоспоживання ...22 РОЗДІЛ 2 МАТЕМАТИЧНЕ ТА АПАРАТНЕ ЗАБЕЗПЕЧЕННЯ СИСТЕМИ ОБЛІКУ ТА ПРОГНОЗУВАННЯ СПОЖИВАННЯ ЕЛЕКТРИЧНОЇ ЕНЕРГІЇ ...31 2.1. Проектування інтелектуальної системи обліку електричної енергії ...31 2.2. Обґрунтування моделей прогнозування середньострокового енергоспоживання на рівні області ...41 2.2.1. Моделі авторегресії ...41 2.2.2. Підхід експоненційного згладжування при прогнозуванні споживання електроенергії ...49 2.2.3. Методи машинного навчання ...52 РОЗДІЛ 3 АПРОБАЦІЯ СИСТЕМИ ОБЛІКУ ЕЛЕКТРИЧНОЇ ЕНЕРГІЇ ТА ПРОГРАМНА ІМПЛЕМЕНТАЦІЯ МОДЕЛЕЙ ПРОГНОЗУВАННЯ ЕЛЕКТРОСПОЖИВАННЯ ...56 3.1. Архітектура і результати обліку електричної енергії у системі середньострокового прогнозування споживання електроенергії ...56 3.2. Аналіз даних для прогнозування споживання електроенергії ...61 3.3. Дослідження та аналіз характеристик часового ряду енергоспоживання на рівні області ... 64 3.4. Побудова моделей прогнозування енергоспоживання на рівні області та порівняння результатів моделювання ...707 3.4.1. Моделі на основі експоненційного згладжування ...71 3.4.2. Моделі на основі нейронних мереж ...77 РОЗДІЛ 4 ОХОРОНА ПРАЦІ ТА БЕЗПЕКА В НАДЗВИЧАЙНИХ СИТУАЦІЯХ ...81 4.1. Охорона праці ...81 4.2. Вплив стихійних лих, аварій (катастроф) та їх наслідки ...83 ВИСНОВКИ ...88 СПИСОК ВИКОРИСТАНИХ ДЖЕРЕЛ ...90 Додаток А Тези конференцій ...93
Katayama, Munechika. "Dynamic analysis in productivity, oil shock, and recession." Diss., Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2008. http://wwwlib.umi.com/cr/ucsd/fullcit?p3315857.
Full textTitle from first page of PDF file (viewed September 3, 2008). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 98-104).
Oliveira, Silvia Fernanda. "Predicting the growth of industrial production: an analysis from the demand for electric energy in the state of Ceara." Universidade Federal do CearÃ, 2011. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=7387.
Full textA tempestividade com a qual os agentes econÃmicos tomam suas decisÃes estimula o desenvolvimento de ferramentas que permitam antecipar as mudanÃas nos agregados econÃmicos. Deste modo, o estudo realiza uma anÃlise e previsÃo da produÃÃo industrial cearense a partir do consumo de energia elÃtrica mensurado pela COELCE. Modelos Vetoriais Auto-regressivos (VAR) sÃo estimados e cenÃrios sÃo construÃdos para o perÃodo 2011-2012. As estimativas se mostraram robustas com um elevado poder de explicaÃÃo do modelo e as simulaÃÃes indicaram um crescimento de 3,9% da produÃÃo industrial cearense atà 2012 com base no valor verificado em 2010, jà desconsiderando as influÃncias sazonais.
Moura, Fernando Alves de. "Previsão do consumo de energia elétrica por setores através do modelo SARMAX." Universidade de São Paulo, 2011. http://www.teses.usp.br/teses/disponiveis/12/12139/tde-15122011-180812/.
Full textThe prediction of electricity consumption in Brazil is very important to the industry regulators. A number of methodologies have been used for the projection of this consumption. Noteworthy are the regression models with data in panel, co-integration and distributed lag models, time series structural models and Box & Jenkins time series models among others. In this work we intend to estimate a forecasting model of the Brazilian commercial, industrial and residential consumption of energy by means of SARMAX models. In these models the power consumption can be estimated by a multiple linear regression considering various macro-economic variables as explanatory variables. The residues of this model are explained by a Box & Jenkins model. In this study it is carried out a bibliographic research on factors that influence energy consumption and proxy variables are risen to predict the consumption in Brazil. The consumption of electricity is estimated for the commercial, industrial and residential sectors. It is used a monthly data base over the period between January 2003 and September 2010 for the construction of each of the three prediction models mentioned. It is used a validation sample from October 2010 to February 2011. It is carried out the assessment of the estimated models in terms of compliance with the theoretical premises and the performance on measures of accuracy MAPE, RMSE and adjusted determinant coefficient. The estimated models for the energy consumption of commercial, industrial and residential sectors obtain a MAPE of 2.05%, 1.09% and 1.27%; a RMSE of 144.13, 185.54 and 158.40; and a adjusted determinant coefficient of 95.91%, 93.98% and 96.03% respectively. All estimated models satisfy the assumptions of normality, absence of serial autocorrelation and absence of conditioned heteroscedasticity of the residues. The results confirmed the viability of the usage of the macroeconomic variables tested to estimate the energy consumption by sector and the viability of the methodology for the prediction of these series in the selected data sample.
Giacometto, Torres Francisco Javier. "Adaptive load consumption modelling on the user side: contributions to load forecasting modelling based on supervised mixture of experts and genetic programming." Doctoral thesis, Universitat Politècnica de Catalunya, 2017. http://hdl.handle.net/10803/457631.
Full textEste trabajo de investigación propone tres aportaciones principales en el campo de la previsión de consumos: la mejora en la exactitud de la predicción, la mejora en la adaptabilidad del modelo ante diferentes escenarios de consumo y la automatización en la ejecución de los algoritmos de modelado y predicción. La mejora de precisión que ha sido introducida en la estrategia de modelado propuesta ha sido obtenida tras la implementación de algoritmos de aprendizaje supervisados pertenecientes a las siguientes familias de técnicas: aprendizaje de máquinas, inteligencia computacional, redes evolutivas, sistemas expertos y técnicas de regresión. Otras las medidas implementadas para aumentar la calidad de la predicción han sido: la minimización del error de pronóstico a través de la extracción de información basada en análisis multi-variable, la combinación de modelos expertos especializados en atributos específicos del perfil de consumo, el uso de técnicas de pre procesamiento para aumentar la precisión a través de la limpieza de variables, y por último implementación de la algoritmos de clasificación no supervisados para obtener los atributos y las clases características del consumo. La mejora en la adaptación del algoritmo de modelado se ha conseguido mediante la implementación de tres componentes al interior de la estrategia de combinación de modelos expertos. El primer componente corresponde a la implementación de técnicas de muestreo sobre cada conjunto de datos agrupados por clase; esto asegura la replicación de la distribución de probabilidad global en múltiples y estadísticamente independientes subconjuntos de entrenamiento. Estos sub conjuntos son usados para entrenar los modelos expertos que consecuentemente pasaran a formar los modelos base de la estructura jerárquica que combina los modelos expertos. El segundo componente corresponde a técnicas de análisis multi-resolución. A través de la descomposición de variables endógenas en sus componentes tiempo-frecuencia, se abstraen e implementan conocimientos importantes sobre la forma de la estructura jerárquica que adoptaran los modelos expertos. El tercero componente corresponde a los algoritmos de modelado que generan una topología interior auto organizada, que proporciona de modelo experto base completamente personalizado al perfil de consumo analizado. La mejora en la automatización se alcanza mediante la combinación de procedimientos automáticos para minimizar la interacción de un usuario experto en el procedimiento de predicción. Los resultados experimentales obtenidos, a partir de la aplicación de las estrategias de predicción de consumos propuestas, han demostrado la idoneidad de las técnicas y metodologías implementadas; sobre todo en el caso de la novedosa estrategia para la combinación de modelos expertos.
Drevna, Michael J. "An application of Box-Jenkins transfer functions to natural gas demand forecasting." Ohio : Ohio University, 1985. http://www.ohiolink.edu/etd/view.cgi?ohiou1183999594.
Full textBrégère, Margaux. "Stochastic bandit algorithms for demand side management Simulating Tariff Impact in Electrical Energy Consumption Profiles with Conditional Variational Autoencoders Online Hierarchical Forecasting for Power Consumption Data Target Tracking for Contextual Bandits : Application to Demand Side Management." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASM022.
Full textAs electricity is hard to store, the balance between production and consumption must be strictly maintained. With the integration of intermittent renewable energies into the production mix, the management of the balance becomes complex. At the same time, the deployment of smart meters suggests demand response. More precisely, sending signals - such as changes in the price of electricity - would encourage users to modulate their consumption according to the production of electricity. The algorithms used to choose these signals have to learn consumer reactions and, in the same time, to optimize them (exploration-exploration trade-off). Our approach is based on bandit theory and formalizes this sequential learning problem. We propose a first algorithm to control the electrical demand of a homogeneous population of consumers and offer T⅔ upper bound on its regret. Experiments on a real data set in which price incentives were offered illustrate these theoretical results. As a “full information” dataset is required to test bandit algorithms, a consumption data generator based on variational autoencoders is built. In order to drop the assumption of the population homogeneity, we propose an approach to cluster households according to their consumption profile. These different works are finally combined to propose and test a bandit algorithm for personalized demand side management
Söderberg, Max Joel, and Axel Meurling. "Feature selection in short-term load forecasting." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259692.
Full textI denna rapport undersöks korrelation och betydelsen av olika attribut för att förutspå energiförbrukning 24 timmar framåt. Attributen härstammar från tre kategorier: väder, tid och tidigare energiförbrukning. Korrelationerna tas fram genom att utföra Pearson Correlation och Mutual Information. Detta resulterade i att de högst korrelerade attributen var de som representerar tidigare energiförbrukning, följt av temperatur och månad. Två identiska attributmängder erhölls genom att ranka attributen över korrelation. Tre attributmängder skapades manuellt. Den första mängden innehåll sju attribut som representerade tidigare energiförbrukning, en för varje dag, sju dagar innan datumet för prognosen av energiförbrukning. Den andra mängden bestod av väderoch tidsattribut. Den tredje mängden bestod av alla attribut från den första och andra mängden. Dessa mängder jämfördes sedan med hjälp av olika maskininlärningsmodeller. Resultaten visade att mängden med alla attribut och den med tidigare energiförbrukning gav bäst resultat för samtliga modeller.
Maréchal, Kevin. "The economics of climate change and the change of climate in economics: the implications for climate policy of adopting an evolutionary perspective." Doctoral thesis, Universite Libre de Bruxelles, 2009. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/210278.
Full textClimate change is today often seen as one of the most challenging issue that our civilisation will have to face during the 21st century. This is especially so now that the most recent scientific data have led to the conclusion that the globally averaged net effect of human activities since 1750 has been one of warming (IPCC 2007, p. 5) and that continued greenhouse gas emissions at or above current rates would cause further warming (IPCC, 2007 p. 13). This unequivocal link between climate change and anthropogenic activities requires an urgent, world-wide shift towards a low carbon economy (STERN 2006 p. iv) and coordinated policies and measures to manage this transition.
The climate issue is undoubtedly a typical policy question and as such, is considered amenable to economic scrutiny. Indeed, in today’s world economics is inevitable when it comes to arbitrages in the field of policy making. From the very beginning of international talks on climate change, up until the most recent discussions on a post-Kyoto international framework, economic arguments have turned out to be crucial elements of the analysis that shapes policy responses to the climate threat. This can be illustrated by the prominent role that economics has played in the different analyses produced by the Intergovernmental Panel on Climate Change (IPCC) to assess the impact of climate change on society.
The starting point and the core idea of this PhD research is the long-held observation that the threat of climate change calls for a change of climate in economics. Borrowing from the jargon used in climate policy, adaptation measures could also usefully target the academic discipline of economics. Given that inherent characteristics of the climate problem (e.g. complexity, irreversibility, deep uncertainty, etc.) challenge core economic assumptions, mainstream economic theory does not appear as appropriately equipped to deal with this crucial issue. This makes that new assumptions and analyses are needed in economics in order to comprehend and respond to the problem of climate change.
In parallel (and without environmental considerations being specifically the driving force to it), the mainstream model in economics has also long been (and still is) strongly criticised and disputed by numerous scholars - both from within and outside the field of economics. For the sake of functionality, these criticisms - whether they relate to theoretical inconsistencies or are empirically-based - can be subsumed as all challenging part of the Cartesian/Newtonian legacy of economics. This legacy can be shown to have led to a model imprinted with what could be called “mechanistic reductionism”. The mechanistic side refers to the Homo oeconomicus construct while reductionism refers to the quest for micro-foundations materialised with the representative agent hypothesis. These two hypotheses constitute, together with the conjecture of perfect markets, the building blocks of the framework of general equilibrium economics.
Even though it is functional for the purpose of this work to present them separately, the flaws of economics in dealing with the specificities of the climate issue are not considered independent from the fundamental objections made to the theoretical framework of mainstream economics. The former only make the latter seem more pregnant while the current failure of traditional climate policies informed by mainstream economics render the need for complementary approaches more urgent.
2. Overview of the approach and its main insights for climate policy
Starting from this observation, the main objective of this PhD is thus to assess the implications for climate policy that arise from adopting an alternative analytical economic framework. The stance is that the coupling of insights from the framework of evolutionary economics with the perspective of ecological economics provides a promising way forward both theoretically as well as on a more applied basis with respect to a better comprehension of the socioeconomic aspects related to the climate problem. As claimed in van den Bergh (2007, p. 521), ecological economics and evolutionary economics “share many characteristics and can be combined in a fruitful way" - which renders the coupling approach both legitimate and promising.
The choice of an evolutionary line of thought initially stems from its core characteristic: given its focus on innovation and system change it provides a useful approach to start with for assessing and managing the needed transition towards a low carbon economy. Besides, its shift of focus towards a better understanding of economic dynamics together with its departure from the perfect rationality hypothesis renders evolutionary economics a suitable theoretical complement for designing environmental policies.
The notions of path-dependence and lock-in can be seen as the core elements from this PhD research. They arise from adopting a framework which is founded on a different view of individual rationality and that allows for richer and more complex causalities to be accounted for. In a quest for surmounting the above-mentioned problem of reductionism, our framework builds on the idea of ‘multi-level selection’. This means that our analytical framework should be able to accommodate not only for upward but also for downward causation, without giving analytical priority to any level over the other. One crucial implication of such a framework is that the notion of circularity becomes the core dynamic, highlighting the importance of historicity, feedbacks and emergent properties.
More precisely, the added value of the perspective adopted in this PhD research is that it highlights the role played by inertia and path-dependence. Obviously, it is essential to have a good understanding of the underlying causes of that inertia prior to devising on how to enforce a change. Providing a clear picture of the socio-economic processes at play in shaping socio-technical systems is thus a necessary first step in order to usefully complement policy-making in the field of energy and climate change. In providing an analytical basis for this important diagnosis to be performed, the use of the evolutionary framework sheds a new light on the transition towards low-carbon socio-technical systems. The objective is to suggest strategies that could prove efficient in triggering the needed transition such as it has been the case in past “lock-in” stories.
Most notably, the evolutionary framework allows us to depict the presence of two sources of inertia (i.e at the levels of individuals through “habits” and at the level of socio-technical systems) that mutually reinforce each other in a path-dependent manner. Within the broad perspective on path dependence and lock-in, this PhD research has first sketched the implications for climate policy of applying the concept of ‘technological lock-in’ in a systemic perspective. We then investigated in more details the notion of habits. This is important as the ‘behavioural’ part of the lock-in process, although explicitly acknowledged in the pioneer work of Paul David (David, 1985, p. 336), has been neglected in most of subsequent analyses. Throughout this study, the notion of habits has been studied at both the theoretical and applied level of analysis as well as from an empirical perspective.
As shown in the first chapters of the PhD, the advantage of our approach is that it can incorporate theories that so far have been presented opposite, partial and incomplete perspectives. For instance, it is shown that our evolutionary approach not only is able to provide explanation to some of the puzzling questions in economics (e.g. the problem of strong reciprocity displayed by individual in anonymous one-shot situations) but also is very helpful in bringing a complementary explanation with respect to the famous debate on the ‘no-regret’ emission reduction potential which agitates the experts of climate policy.
An emission reduction potential is said to be "no regret" when the costs of implementing a measure are more than offset by the benefits it generates such as, for instance, reduced energy bills. In explaining why individuals do not spontaneously implement those highly profitable energy-efficient investments ,it appears that most prior analyses have neglected the importance of non-economic obstacle. They are often referred to as “barriers” and partly relate to the ‘bounded rationality’ of economic agent. As developed in the different chapters of this PhD research, the framework of evolutionary economics is very useful in that it is able to provide a two-fold account (i.e. relying on both individual and socio-technical sources of inertia) of this limited rationality that prevent individuals to act as purely optimising agents.
Bearing this context in mind, the concept of habits, as defined and developed in this study, is essential in analysing the determinants of energy consumption. Indeed, this concept sheds an insightful light on the puzzling question of why energy consumption keeps rising even though there is an evident increase of awareness and concern about energy-related environmental issues such as climate change. Indeed, if we subscribe to the idea that energy-consuming behaviours are often guided by habits and that deeply ingrained habits can become “counter-intentional”, it then follows that people may often display “locked-in” practices in their daily energy consumption behaviour. This hypothesis has been assessed in our empirical analysis whose results show how the presence of strong energy-consuming habitual practices can reduce the effectiveness of economic incentives such as energy subsidies. One additional delicate factor that appears crucial for our purpose is that habits are not fully conscious forms of behaviours. This makes that individuals do not really see habits as a problem given that it is viewed as easily changed.
In sum, based on our evolutionary account of the situation, it follows that, to be more efficient, climate policies would have to both shift the incumbent carbon-based socio-technical systems (for it to shape decisions towards a reduction of greenhouse gas emissions) and also deconstruct habits that this same socio-technical has forged with time (as increased environmental awareness and intentions formulated accordingly are not sufficient in the presence of strong habits).
Accordingly, decision-makers should design measures (e.g. commitment strategies, niche management, etc.) that, as explained in this research, specifically target those change-resisting factors and their key features. This is essential as these factors tend to reduce the efficiency of traditional instruments. Micro-level interventions are thus needed as much as macro-level ones. For instance, it is often the case that external improvements of energy efficiency do not lead to lower energy consumption due to the rebound effect arising from unchanged energy-consuming habits. Bearing this in mind and building on the insights from the evolutionary approach, policy-makers should go beyond the mere subsidisation of technologies. They should instead create conditions enabling the use of the multi-layered, cumulative and self-reinforcing character of economic change highlighted by evolutionary analyses. This means supporting both social and physical technologies with the aim of influencing the selection environment so that only the low-carbon technologies and practices will survive.
Mentioned references:
David, P. A. (1985), Clio and the economics of QWERTY, American Economic Review 75/2: 332–337.
IPCC, 2007, ‘Climate Change 2007: The Physical Science Basis’, Contribution of Working Group I to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change [Solomon, S. D. Qin, M. Manning, Z. Chen, M. Marquis, K.B. Averyt, M. Tignor and H.L. Miller (eds.)]. Cambridge University Press, Cambridge, United Kingdom and New York, NY, USA, 996 pp.
Stern, N. 2006, ‘Stern Review: The economics of Climate Change’, Report to the UK Prime Minister and Chancellor, London, 575 p. (www.sternreview.org.uk)
van den Bergh, J.C.J.M. 2007, ‘Evolutionary thinking in environmental economics’, Journal of Evolutionary Economics 17(5): 521-549.
Doctorat en Sciences économiques et de gestion
info:eu-repo/semantics/nonPublished
Flor, Ambrosi Mario Alberto. "Método para descubrir patrones espacio-temporales de comportamiento de usuarios eléctricos utilizando herramientas de aprendizaje automático." Doctoral thesis, Universitat de Girona, 2021. http://hdl.handle.net/10803/673421.
Full textquesta investigació presenta un enfocament nou per definir zones geogràfiques amb perfils típics de consum elèctric a partir dels registres de mesuradors intel·ligents, utilitzant mètodes d'aprenentatge automàtic i anàlisi espacial. Les empreses d'electricitat han de garantir la qualitat i fiabilitat del servei elèctric. Per aconseguir aquest objectiu, les empreses de distribució d'electricitat requereixen conèixer en detall i amb una periodicitat adequada els perfils de consum dels seus clients. Els moderns dispositius de telemesura, com els mesuradors intel·ligents, obren la porta a una immensa quantitat de dades i nous anàlisis, a causa de la major freqüència i precisió de la informació del consumidor, però els mètodes convencionals no poden abordar els voluminosos i ràpids conjunts de dades que generen aquests dispositius. L'objectiu d'aquesta investigació és utilitzar tècniques d'aprenentatge automàtic combinades amb l'anàlisi espacial per generar perfils de càrrega més eficients i precisos a les zones d'estudi. L'estudi analitza una voluminosa base de dades amb mesuraments de 4 anys recollits per 1000 mesuradors intel·ligents georeferenciats a la ciutat de Guayaquil a l’Equador. A l'estudi s'implementa una metodologia d'aprenentatge no supervisat per agrupar i classificar les sèries temporals de mesures d'energia, utilitzant la tècnica de deformació dinàmica de temps per descobrir perfils de càrrega típics d'acord amb el seu consum característic setmanal. A continuació, es va realitzar una anàlisi espai temporal restringit per definir zones geogràfiques amb comportament constant i predictible
Programa de Doctorat en Tecnologia
Mendes, Hugo Miguel Nogueira. "Energy consumption forecasting: a proposed framework." Master's thesis, 2020. http://hdl.handle.net/10071/22280.
Full textCom o desenvolvimento de países subdesenvolvidos e a digitalização das sociedades, é esperado que o consumo de energia continue a apresentar um crescimento elevado nas próximas décadas. Existindo ainda um grande foco em fontes fósseis para a geração de energia, a implementação de políticas energéticas são cruciais para a mudança gradual para energias renováveis e consequente redução de emissões de CO2. Edifícios são atualmente o sector que mais energia consomem. De forma a contribuir para uma melhor eficiência no consumo de energia foi proposta uma framework, a aplicar em edifícios ou apartamentos, para possibilitar aos utilizadores ter um conhecimento do seu consumo de energia bem como a previsão desse mesmo consumo. Diferentes técnicas de análise de dados para séries temporais foram utilizadas para proporcionar informação ao utilizador sobre o seu consumo de energia bem como a validação de caraterísticas importantes dos dados, nomeadamente a verificação da estacionariedade e a existência da sazonalidade, que terão impacto no modelo de previsão. Para a definição dos modelos preditivos, foi feita uma revisão de literatura sobre modelos utilizados atualmente para previsão do consumo de energia e testados três modelos para os dois tipos de dados, univariados e multivariados. Para os dados univariados os modelos testados foram SARIMA, Holt-Winters e LSTM e para os dados multivariados SARIMA com variáveis exógenas, Support Vector Regression e LSTM. Após a primeira execução de cada modelo, foi feita uma otimização dos modelos para concluir na melhoria dos resultados previstos e na robustez dos modelos para posterior aplicação na framework.
Talmo, Dan. "Energy use and forecasting in Wisconsin manufacturing industries." 1987. http://catalog.hathitrust.org/api/volumes/oclc/16319156.html.
Full textLin, Po-Heng, and 林柏亨. "Forecasting Energy Consumption using Vector Autoregression and Genetic Planning." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/22425591254582313690.
Full text國立交通大學
工業工程與管理系所
101
After three oil crises, the international energy situation is now characterized by volatility, rising energy prices, and heightened societal attention to issues related to energy. Accurate predict is a nation's annual energy consumption would enable help government to develop a policy of energy resources. Most studies constructed energy consumption prediction models for using univariate time series model. However, univariate time series model does not consider other variables such as some economic indice. When energy consumption are affected significently by other variables, the result of univariate time series model will be inaccurate. Because the energy consumption is tied up with the economic growth, this study will focus on predict energy consumption using the economic Indicators. This study utilizes economic indicators, such as population and total exportd and their lag effects as input data, and the energy consumption data as the output variable to build a Vector Autoregression model for predicting energy consumption. In addition, genetic Programming is employed to build a residual prediction model to enhance the forecasting accuracy. Finally, a hybrid energy consumption prediction model is developed by combining the Vetor Autoregression model and residual prediction model. The energy consumption data in Taiwan from 1979~2010 are utilized to demonstrate the effectiveness of the proposed method.
Chuang, Chao-Bin, and 莊朝斌. "Constructing an Energy Consumption Model using Rolling Gray Forecasting Method." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/12562865610821030510.
Full text國立交通大學
工業工程與管理學系
99
Since the Oil crisis in 1973, energy has been an important source of economic development. Therefore, many countries are concerned with energy-related issues and energy consumption becomes an important economic index. However, it is generally difficult to accurately predict energy consumption. Although there are studies relating to energy consumption forecasting based on social-economic indicators such as gross domestic product, population and import–export figures, those studies have certain deficiencies and disadvantages, such as regression models and artificial neural network (ANN)-based models. For example, their predictive accuracy is low when the sample is small. Grey model (GM) only needs at least four data points to construct a reliable and acceptable prediction model, thus GM is appropriate to be utilized to predict future energy consumption. However, GM also has some drawbacks. This study proposed an improve grey model, using a rolling grey model combining a residual modification model to construct an energy consumption forecasting model to enhance the prediction accuracy of GM. A Taiwanese energy consumption dataset is utilized to demonstrate the effectiveness and feasibility of the proposed method.
Lee, Yi-Shian, and 李宜憲. "Using Grey Theory and Genetic Programming to Construct Forecasting Models-Case Study of Forecasting Energy Consumption." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/40678566385164095054.
Full text國立交通大學
工業工程與管理學系
99
The issue of energy consumption has become increasingly important due to its impact on the economies of nations. Forecasting energy consumption by conventional statistical methods usually requires assumptions such as normality, independence or large data sets. However, data collected on energy consumption are often very few and do not meet the statistical assumptions. The grey forecasting model, based on grey theory, can be constructed for at least four observations and it does not require any statistical assumptions. Thus, it is suitable to use a grey forecasting model to forecast the energy consumption. In some cases, however, the grey forecasting model may obtain large forecasting errors. To overcome this problem, this dissertation proposes three improved grey forecasting models, which combines grey theory and genetic programming. Finally, two energy consumption data sets from 1990 to 2007 of China and US are used to demonstrate the effectiveness of the proposed forecasting models. The proposed models are also compared with the existing forecasting models of energy consumption. The empirical results indicated that the proposed models can enhance both of the accuracy and the precision of forecasting the energy consumption data.
Hung, I.-Hsien, and 洪亦賢. "Using Grey Markov and Genetic Programming to Construct Energy Consumption Forecasting Models." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/47300001556696705283.
Full text國立交通大學
工業工程與管理系所
103
The rapid growth of technology and population drives the human needs for energy. It influences widely on many national issues, including economic development, environmental protection, etc. However, because of energy resources are not inexhaustible, so the forecasting and management of energy consumption have become an increasingly important issue now and future. The conventional statistical methods are typically utilized to construct the prediction model, but the data collected on energy consumption are often very few, non-linear or do not meet the statistical assumptions, such as normality, homogeneity and independence, resulting poor prediction accuracy of forecasting models. Some studies have proposed GM(1,1) and residual modification GM(1,1) models to predict the energy consumption. The advantages of these GM(1,1) models can be constructed for at least four observations and they do not require any statistical assumptions. However, the energy consumption is influenced by random fluctuations of various factors, such as: economic development, technological breakthroughs, changes in national policy, and GM(1,1) is a smooth function of exponential curve, which has poor prediction accuracy when the data is random. Therefore, the objective of this study is to combined GM(1,1), Markov chains and genetic programming to establish the improved prediction models on energy consumption data. Finally, the energy consumption data set from 1990 to 2005 of US was utilized to demonstrate the effectiveness of the proposed energy consumption forecasting model.
Ravichandran, S., A. Vijayalakshmi, K. S. Swarup, Haile S. Rajamani, and Prashant Pillai. "Short term energy forecasting techniques for virtual power plants." 2016. http://hdl.handle.net/10454/11101.
Full textThe advent of smart meter technology has enabled periodic monitoring of consumer energy consumption. Hence, short term energy forecasting is gaining more importance than conventional load forecasting. An Accurate forecasting of energy consumption is indispensable for the proper functioning of a virtual power plant (VPP). This paper focuses on short term energy forecasting in a VPP. The factors that influence energy forecasting in a VPP are identified and an artificial neural network based energy forecasting model is built. The model is tested on Sydney/ New South Wales (NSW) electricity grid. It considers the historical weather data and holidays in Sydney/ NSW and forecasts the energy consumption pattern with sufficient accuracy.
曾子豪. "Analyzing and Forecasting CO2 Emission, Energy Consumption, and Real GDP in the Top New Renewable Energy Countries." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/79gz9p.
Full text國立交通大學
管理科學系所
106
This study explores the causality among energy (Fossil Fuel and new renewable energy), environment (CO2 emission) and economic (real GDP), which is based on three countries without record of use of nuclear energy and with highest share of renewable energy in the world in 1980 to 2016.As the economic rapidly develop, the use and demand of energy annually grows up. But it also causes the damage and pollution to the environment. For the sustainable development of the environment, each government of countries starts to set new energy policy. In this study, it found that the renewable energy couldn’t completely substitute the fossil fuel in the short term because of the economic growth, but each countries make the change of the use of energy in the long term. If it decrease the use of fossil fuel, it can not only reduce the pollution of environment but also reduce the dependence on imported fossil fuel. Moreover, we also make the forecast of our data by using the XGBoost, one of famous machine learning algorithm. The performance of model prediction is well. If we can successfully build the model, the result can serve as a reference for future policy development and suggestion.
Huang, Chian-Shan, and 黃千珊. "A comparison of seasonal time series models for forecasting the energy consumption in Taiwan." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/26773247449379626795.
Full text淡江大學
數學學系碩士班
96
Recently, the energy price keeps increasing.Both the demand and the consumption are on the rise.Due to these scenarios,this essay will try to predict the energy consumption in Taiwan,hoping to get a better grasp of the future trend.We will use the following four models for prediction,and they are Seasonal Autoregressive Integrated Moving Average Models(SARIMA),Regression Models with Time Series Errors (RMTSE),Back-propagation Network(BPN),and hybrid SARIMA and BPN(SARIMABP).The findings discovered that,at that time series of graph the sequence shook obviously uses BPN to be able to obtain a better forecast,otherwise,the graph shook steadily, used SARIMA to be able to obtain a better forecast,and adopt the mixing model to be able to improve the forecast error.
Greyling, Jean. "Mine energy budget forecasting : the value of statistical models in predicting consumption profiles for management systems / Jean Greyling." Thesis, 2014. http://hdl.handle.net/10394/12240.
Full textMBA, North-West University, Potchefstroom Campus, 2014
Deline, Mary Elizabeth. "Keeping Up With the Joneses: Electricity Consumption, Publicity and Social Network Influence in Milton, Ontario." Thesis, 2010. http://hdl.handle.net/10012/5219.
Full textSánchez-Lugo, Ahira M. "An index to measure the influences of climate on residential natural gas demand." Thesis, 2007. http://hdl.handle.net/10125/20709.
Full textVan, Rooyen Gerhardus Christiaan. "Spesifieke verbruik van steenkool in die Suid-Afrikaanse energie-ekonomie met spesiale verwysing na die invloed van hoër steenkoolpryse." Thesis, 2014. http://hdl.handle.net/10210/12080.
Full textCoal is today providing more than seventy-five percent of South Africa's energy requirements and will, to a large extent, remain so in the future. It is thus important to evaluate the adequacy of the country's available coal resources against expected future demand. The main objective of this study, which was done under the supervision of Prof. D. J. Kotze, was therefore to analyse the specific consumption of coal in the various consumption sectors in order to establish historical trends. The specific comsumption of coal is defined as the amount of coal used to produce a unit of final product. The factors attributing to these observed trends were determined and their future role evaluated in order to establish whether it was possible to extrapolate historical trends into the future. By means of curve fitting to the observed data and extrapolation it was possible to obtain future values of specific coal consumption for each of the sectors. These values, together with the production output forecasts for the various sectors were then used to calculate the total coal requirements for three reference years, namely, 1990, 1995 and 2000. The role of coal prices in explaining trends in specific coal consumption of various sectors was also analised separately. Information to conduct the study was obtained mainly from the various coal producers' associations as well as from individual producers and other organizations such as Escom, Sasol and Iscor, the Department of Hineral and Energy Affairs and the Hinerals Bureau. In some instances private firms and producers' associations were also consulted as well as a wide variety of literature on the subject. The principal finding of the study was that coal was substituted or was still being substituted by electricity in most final applications because of the convenience of use. Coal, however, still plays and probably will continue to play an important role in future in basic industries such as the metallurgical industry. Coal prices have not up to now played a very important role in the overall specific consumption of coal which can probably be attributed to the relatively low prices of coal on the inland market. It was also found that it was not desirable to do away with the present system of price control entirely as a certain measure of control was still necessary to safeguard the usuage of coal in certain applications for which there were no other substitutes. It was further concluded that South Africa does not have the vast quantities of coal commonly thought and that measures have to be taken in order to ensure that the country's coal resources are conserved and that optimum use is made of available resources.
Moroke, N. D. "An application of Box-Jenkins transfer function analysis to consumption-income relationship in South Africa / N.D. Moroke." Thesis, 2005. http://hdl.handle.net/10394/11344.
Full textThesis (M. Com. (Statistics) North-West University, Mafikeng Campus, 2005
Arienti, João Henrique Leal. "Time series forecasting applied to an energy management system ‐ A comparison between Deep Learning Models and other Machine Learning Models." Master's thesis, 2020. http://hdl.handle.net/10362/108172.
Full textA large amount of energy used by the world comes from buildings’ energy consumption. HVAC (Heat, Ventilation, and Air Conditioning) systems are the biggest offenders when it comes to buildings’ energy consumption. It is important to provide environmental comfort in buildings but indoor wellbeing is directly related to an increase in energy consumption. This dilemma creates a huge opportunity for a solution that balances occupant comfort and energy consumption. Within this context, the Ambiosensing project was launched to develop a complete energy management system that differentiates itself from other existing commercial solutions by being an inexpensive and intelligent system. The Ambiosensing project focused on the topic of Time Series Forecasting to achieve the goal of creating predictive models to help the energy management system to anticipate indoor environmental scenarios. A good approach for Time Series Forecasting problems is to apply Machine Learning, more specifically Deep Learning. This work project intends to investigate and develop Deep Learning and other Machine Learning models that can deal with multivariate Time Series Forecasting, to assess how well can a Deep Learning approach perform on a Time Series Forecasting problem, especially, LSTM (Long Short-Term Memory) Recurrent Neural Networks (RNN) and to establish a comparison between Deep Learning and other Machine Learning models like Linear Regression, Decision Trees, Random Forest, Gradient Boosting Machines and others within this context.
Alani, Adeshina Yahaha. "Short-term multiple forecasting of electric energy loads with weather profiles for sustainable demand planning in smart grids for smart homes." Diss., 2018. http://hdl.handle.net/10500/25216.
Full textSchool of Computing
M. Sc. (Computer Science)