Electric power systems are huge real time energy distribution networks where accurate short term load forecasting (STLF) plays an essential role. This thesis is an effort to comprehensively investigate new and advanced neural network (NN) architectures to perform STLF. Two hybrid and two 3-layered NN architectures are introduced. Each network is individually tested to generate weekday and weekend forecasts using data from three jurisdictions of Canada. Overall findings suggest that 3-layered cascaded NN have outperformed almost all others for weekday forecasts. For weekend forecasts 3-layered feed forward NN produced most accurate results. Recurrent and hybrid networks performed well during peak hours but due to occurrence of constant high error spikes were not able to achieve high accuracy.

The accuracy of load forecast has a significant impact for power companies on executing the plan of power development, reducing operating costs and providing reliable power to the client. Short-term load forecasting is to forecast load demand for the duration of one hour or less. This study presents a new approach to process load forecasting. A Support Vector Machine (SVM) was used for the initial load estimation. Particle Swarm Optimization (PSO) was then adopted to search for optimal parameters for the SVM. In doing the load forecast, training data is the most important factor to affect the calculation time. Using more data for model training should provide a better forecast results, but it needs more computing time and is less efficient. Applications of data mining can provide means to reduce the data requirement and the computing time. The proposed Modified Support Vector Machines approach can be proved to provide a more accurate load forecasting.

Traditional forecasting approaches forecast the total system load directly without considering the individual consumer's load. With the introduction of the smart grid, lots of renewable energy resources such as wind and solar are added to the system from consumer side fluctuates the system load and makes forecasting more complex. Thus, it is necessary to forecast individual consumers load. Here, a framework is presented in which individual customer loads is forecasted rather than the system load. At first, a hierarchical cluster analysis is performed to classify daily load patterns into different groups for all the individuals. Then an association analysis is performed to determine critical influential factors that affect the load curve for given day. The next step is the application of a decision tree to establish classification rules between the different groups of the load curve and the critical influential factors. Then, appropriate forecasting models are chosen for different load patterns and the individual load is forecasted. Finally, the forecasted total system load is obtained through an aggregation of an individual load forecasting results. The relative error of forecasting the system load using this framework is compared with the relative errors using SVM regression and this framework had better accuracy. This framework is also used for forecasting the power output of the renewable generation. Also, the results of the day ahead forecast of system load and renewable generation is used for economic power scheduling for the microgrid and peak shaving for the utilities.

No description available.

Short-term load forecasting (STLF) deals with forecasting of hourly system demand with a lead time ranging from one hour to 168 hours. The basic objective of the STLF is to provide for economic, reliable and secure operation of the power system. This dissertation establishes a new approach to artificial neural network (ANN) based STLF. It first decomposes the prediction problem into representation and function approximation problems. The representation problem is solved using phase-space embedding which identifies time delay variables from load time series that are used in forecasting. The concept is inherently different from the methods used so far because it does not use correlated variables for forecasting. Temperature variables are included as well using identified embedding parameters. Function approximation problem is approached using ANN ensemble and active selection of a training set. Training set is selected based on predicted weather parameters for a prediction horizon. Selection is done applying the k-nearest neighbors technique in a temperature-based vector space. A novel approach of pilot set simulation is used to determine the number of hidden units for every forecast period. Ensemble consists of two ANNs which are trained and cross validated on complementary training sets. Final prediction is obtained by a simple average of two trained ANNs. The described technique is used for predicting one week’s load in four selected months in summer peaking and winter peaking US utilities. Mean absolute percent errors (MAPEs) for 24-hour lead time predictions are slightly greater than 2% for all months. For 120-hour lead time (weekday) predictions, MAPEs are around 2.3%. MAPEs for 48- hour lead time (weekend) predictions are around 2.5%. Maximal errors for these cases are around 7%. Predictions for one-hour lead time are slightly higher than 1% for all months, with maximal errors not exceeding 4.99%. Peak load MAPEs are 2.3% for both utilities. Maximal peak-load errors do not exceed 6%. The technique shows very good performance faced with sudden and large changes in weather. For changes in temperature larger than 20° F for two consecutive days, forecasting error is smaller than 3.58%. / Ph. D.

[pt] O objetivo principal desta dissertação é desenvolver um método de previsão de carga elétrica de curto prazo (previsão horária), através de um sistema híbrido (Redes Neurais e Lógica Fuzzy) utilizando temperaturas máximas e mínimas como variáveis explicativas. Como primeiro passo, foram definidos os perfis homogêneos das curvas de carga diárias através de um classificador utilizando os Mapas Auto Organizáveis (Self-Organizing Maps- SOM). Um previsor será adicionado ao esquema de previsão através da Lógica Fuzzy que associará as variáveis climáticas aos perfis criados pela SOM produzindo as previsões. O modelo foi aplicado em dados de duas concessionárias de energia elétrica do Brasil usando dados horários coletados durante dois anos. / [en] This dissertation presents a short-term load forecasting procedure mixing a classifier scheme and a predictive scheme. The classifier is implemented through an artificial neural network using a non-supervised learning procedure (SOM). Concerning the predictive scheme, a fuzzy logic procedure uses climatic variables and their prediction to choose the appropriate profiles created by SOM and then combines them to produce the desired forecast. The model is applied to two utilities in Brazil using hourly observations collected during two calendar years and the results obtained, in terms of mean absolute percentage error (MAPE) through the period analyzed, are presented.

Submitted by Geandra Rodrigues (geandrar@gmail.com) on 2018-10-24T12:50:06Z No. of bitstreams: 1 taisdemedeirospedreira.pdf: 1862768 bytes, checksum: 0c6ee31fd9be772b5b609051a207f61f (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2018-11-23T12:17:19Z (GMT) No. of bitstreams: 1 taisdemedeirospedreira.pdf: 1862768 bytes, checksum: 0c6ee31fd9be772b5b609051a207f61f (MD5) / Made available in DSpace on 2018-11-23T12:17:19Z (GMT). No. of bitstreams: 1 taisdemedeirospedreira.pdf: 1862768 bytes, checksum: 0c6ee31fd9be772b5b609051a207f61f (MD5) Previous issue date: 2018-09-05 / As previsões a curto prazo da carga elétrica (de algumas horas até alguns dias à frente) são essenciais para o planejamento, controle e operação dos sistemas de energia, tanto por por razões técnicas quanto financeiras. Como não é possível estocar grandes quantidades, torna-se indispensável um maneira eficaz de programar a produção da energia para que ela atenda a demanda. Por conta disso, uma grande literatura desenvolveu-se sobre o assunto. Devido à complexidade das séries de carga e à dependência não-linear destas carga em relação a diversas variáveis exógenas, os sistemas de previsão mais frequentemente propostos em trabalhos recentes são aqueles baseados em algoritmos complexos de inteligência computacional. No entanto, métodos lineares simples ainda são muito comumente usados, por si sós ou em combinação com técnicas não-lineares. Um desses métodos é o de Holt-Winters-Taylor, que é uma adaptação do conhecido método de amortecimento exponencial de Holt-Winters para que múltiplas sazonalidades possam ser modelados concomitantemente. Este trabalho implementa três variantes deste método HWT e analisa seus desempenhos em duas séries de dados reais de carga. Verificou-se que uma combinação linear dessas variantes nitidamente supera o método HWT original e fornece previsões precisas, com um baixo custo computacional. / Short-term load forecasts (forecasts for horizons ranging from a few hours to a few days ahead) are essential for the planning, controling and operation of energy systems, both for technical and financial reasons. Since it is not feasible to store energy in large quantities, an efficient way to forecast energy demand becomes indispensable. Because of this, a large literature has developed on the subject. Due to the complexity of load series and the nonlinear relationship of the load with exogenous variables, the most frequently proposed forecasting systems in recent papers are those based on complex algorithms of computational intelligence. However, simple linear methods are still very frequently used, either alone or in combination with non-linear techniques. One of these methods is Holt-Winters-Taylor (HWT), which is an adaptation of the well-known Holt-Winters exponential smoothing method, modified so that multiple seasonalities can be modeled at the same time. In this paper, we implement three variants of this HWT method and analyze their performances over two sets of actual load data. We found that a linear combination of these variants clearly outperforms the original HWT method, and provides accurate forecasts at a low computational cost.

L'effacement des consommations électriques a été identifié comme l'une des solutions pour pallier les problèmes liés aux pics de consommation électrique, à l’intermittence des énergies renouvelables et à la congestion des réseaux. Ces travaux de recherche s’intéressent à l’intégration de la consommation industrielle en tant que ressources effaçables à court terme dans le contexte de la réserve rapide du mécanisme d’ajustement français. Parmi les différents secteurs, le secteur industriel présente un intérêt particulier en raison de l’importance de sa consommation. Afin d'intégrer ce type de consommation dans l’équilibre offre-demande, il est nécessaire de prévoir le comportement de ces consommations à court terme ainsi que d’évaluer la fiabilité de ces prévisions. Ainsi, différentes méthodes de prévision à très court-terme adaptées aux données et au contexte ont été déployées sur différents consommations disponibles à deux niveaux d’agrégation différents : site et usage industriel. Des indicateurs de performance adaptés aux contraintes opérationnelles, appelés "taux de fiabilité", sont proposés et calculés pour évaluer la performance des méthodes de prévision. Ce taux de fiabilité est estimé pour différentes heures de la journée pour les différents sites et usages industriels étudiés. Les taux de fiabilité estimés permettent d'évaluer le risque pour une consommation spécifique (au niveau du site ou au niveau de chaque usage industriel) de ne pas respecter des contraintes opérationnelles imposées à chaque instant de simulation. / Demand response has been identified as one of the solutions to overcome the problems associated with peaks in electricity consumption, intermittency of renewable energy and network congestion. This thesis focuses on the integration of industrial electricity consumptions as short-term demand response resources in the context of a supply-demand balancing mechanism in France. Among the various sectors, industrial electricity consumptions are of particular interest because of their orders of magnitude. In order to integrate these consumptions to the supply-demand balance, it is necessary forecast their behavior in the short term and to evaluate the reliability of these forecasts. Thus, different short-term load forecasting methods adapted to the data and to the operational context are implemented on different sets of industrial consumptions data at two different consumption levels: the industrial site and the end-point equipment consumption. Performance indicators adapted to operational constraints, called "trust factors" are proposed and calculated to evaluate the performance of the forecasting methods. These trust factors are estimated for different hours of the day for all the different studied industrial sites and workshops. The estimated trust are used to assess the risks for a specific consumption to not to respect the operational constraints at a moment a forecast is simulated. Demand response is considered to become one of the elements to be implemented in order to achieve a successful energy transition through a more flexible power system.

The aim of this study is to develop novel forecasting methodologies. The applications of our proposed models lie in two different areas: macroeconomics and energy. Though we consider two very different applications, the common underlying theme of this thesis is to develop novel methodologies that are not only accurate, but are also parsimonious. For macroeconomic time series, we focus on generating forecasts for the US Gross National Product (GNP). The contribution of our study on macroeconomic forecasting lies in proposing a novel nonlinear and nonparametric method, called weighted random analogue prediction (WRAP) method. The out-of-sample forecasting ability of WRAP is evaluated by employing a range of different performance scores, which measure its accuracy in generating both point and density forecasts. We show that WRAP outperforms some of the most commonly used models for forecasting the GNP time series. For energy, we focus on two different applications: (1) Generating accurate short-term forecasts for the total electricity demand (load) for Great Britain. (2) Modelling Irish electricity smart meter data (consumption) for both residential consumers and small and medium-sized enterprises (SMEs), using methods based on kernel density (KD) and conditional kernel density (CKD) estimation. To model load, we propose methods based on a commonly used statistical dimension reduction technique, called singular value decomposition (SVD). Specifically, we propose two novel methods, namely, discount weighted (DW) intraday and DW intraweek SVD-based exponential smoothing methods. We show that the proposed methods are competitive with some of the most commonly used models for load forecasting, and also lead to a substantial reduction in the dimension of the model. The load time series exhibits a prominent intraday, intraweek and intrayear seasonality. However, most existing studies accommodate the ‘double seasonality’ while modelling short-term load, focussing only on the intraday and intraweek seasonal effects. The methods considered in this study accommodate the ‘triple seasonality’ in load, by capturing not only intraday and intraweek seasonal cycles, but also intrayear seasonality. For modelling load, we also propose a novel rule-based approach, with emphasis on special days. The load observed on special days, e.g. public holidays, is substantially lower compared to load observed on normal working days. Special day effects have often been ignored during the modelling process, which leads to large forecast errors on special days, and also on normal working days that lie in the vicinity of special days. The contribution of this study lies in adapting some of the most commonly used seasonal methods to model load for both normal and special days in a coherent and unified framework, using a rule-based approach. We show that the post-sample error across special days for the rule-based methods are less than half, compared to their original counterparts that ignore special day effects. For modelling electricity smart meter data, we investigate a range of different methods based on KD and CKD estimation. Over the coming decade, electricity smart meters are scheduled to replace the conventional electronic meters, in both US and Europe. Future estimates of consumption can help the consumer identify and reduce excess consumption, while such estimates can help the supplier devise innovative tariff strategies. To the best of our knowledge, there are no existing studies which focus on generating density forecasts of electricity consumption from smart meter data. In this study, we evaluate the density, quantile and point forecast accuracy of different methods across one thousand consumption time series, recorded from both residential consumers and SMEs. We show that the KD and CKD methods accommodate the seasonality in consumption, and correctly distinguish weekdays from weekends. For each application, our comprehensive empirical comparison of the existing and proposed methods was undertaken using multiple performance scores. The results show strong potential for the models proposed in this thesis.

Submitted by Geandra Rodrigues (geandrar@gmail.com) on 2018-01-17T11:13:15Z No. of bitstreams: 1 samuelbelinidefilippo.pdf: 2610291 bytes, checksum: 6c4f48d00a0649b56977f6c8a7ada4e0 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2018-01-22T16:33:53Z (GMT) No. of bitstreams: 1 samuelbelinidefilippo.pdf: 2610291 bytes, checksum: 6c4f48d00a0649b56977f6c8a7ada4e0 (MD5) / Made available in DSpace on 2018-01-22T16:33:53Z (GMT). No. of bitstreams: 1 samuelbelinidefilippo.pdf: 2610291 bytes, checksum: 6c4f48d00a0649b56977f6c8a7ada4e0 (MD5) Previous issue date: 2017-09-20 / Todo a produção, transmissão e distribuição de energia elétrica ocorre concomitantemente com o consumo da energia. Isso é necessário porque ainda não existe hoje uma maneira viável de se estocar energia em grandes quantidades. Dessa forma, a energia gerada precisa ser consumida quase que instantaneamente. Isso faz com que as previsões de demanda sejam fundamentais para uma boa gestão dos sistemas de energia. Esse trabalho focaliza métodos de previsão de demanda a curto prazo, até um dia à frente. Nos métodos mais simples, as previsões são feitas por modelos lineares que utilizam dados históricos da demanda de energia. Contudo, modelos baseados em inteligência computacional têm sido estudados para este fim, por explorarem a relação não-linear entre a demanda de energia e as variáveis climáticas. Em geral, estes modelos conseguem melhores previsões do que os métodos lineares. Seus resultados, porém, são instáveis e sensíveis a erros de medição, gerando erros de previsão discrepantes, que podem ter graves consequências para o processo de produção. Neste estudo, empregamos redes neurais artificiais e algoritmos genéticos para modelar dados históricos de carga e de clima, e combinamos estes modelos com métodos lineares tradicionais. O objetivo é conseguir previsões que não apenas sejam mais acuradas em termos médios, mas que também menos sensíveis aos erros de medição. / The production, transmission and distribution of electric energy occurs concomitantly with its consumption. This is necessary because there is yet no feasible way to store energy in large quantities. Therefore, the energy generated must be consumed almost instantaneously. This makes forecasting essential for the proper management of energy systems. This thesis focuses on short-term demand forecasting methods up to one day ahead. In simpler methods, the forecasts are made by linear models, which use of historical data on energy demand. However, computer intelligence-based models have been studied for this end, exploring the nonlinear relationship between energy demand and climatic variables. In general, these models achieve better forecasts than linear methods. Their results, however, are unstable and sensitive to measurement errors, leading to outliers in forecasting errors, which can have serious consequences for the production process. In this thesis, we use artificial neural networks and genetic algorithms for modelling historical load and climate data, and combined these models with traditional linear methods. The aim is to achieve forecasts that are not only more accurate in mean terms, but also less sensitive to measurement errors.