Performance Evaluation of New and Advanced Neural Networks for Short Term Load Forecasting PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Performance Evaluation of New and Advanced Neural Networks for Short Term Load Forecasting PDF full book. Access full book title Performance Evaluation of New and Advanced Neural Networks for Short Term Load Forecasting by Syed Talha Mehmood. Download full books in PDF and EPUB format.
Author: Syed Talha Mehmood
Publisher:
ISBN:
Category :
Languages : en
Pages : 408
Get Book Here
Book Description
ABSTRACT: 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.
Author: Syed Talha Mehmood
Publisher:
ISBN:
Category :
Languages : en
Pages : 408
Get Book Here
Book Description
ABSTRACT: 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.
Author: Filippo Maria Bianchi
Publisher: Springer
ISBN: 3319703382
Category : Computers
Languages : en
Pages : 74
Get Book Here
Book Description
The key component in forecasting demand and consumption of resources in a supply network is an accurate prediction of real-valued time series. Indeed, both service interruptions and resource waste can be reduced with the implementation of an effective forecasting system. Significant research has thus been devoted to the design and development of methodologies for short term load forecasting over the past decades. A class of mathematical models, called Recurrent Neural Networks, are nowadays gaining renewed interest among researchers and they are replacing many practical implementations of the forecasting systems, previously based on static methods. Despite the undeniable expressive power of these architectures, their recurrent nature complicates their understanding and poses challenges in the training procedures. Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet. This work performs a comparative study on the problem of Short-Term Load Forecast, by using different classes of state-of-the-art Recurrent Neural Networks. The authors test the reviewed models first on controlled synthetic tasks and then on different real datasets, covering important practical cases of study. The text also provides a general overview of the most important architectures and defines guidelines for configuring the recurrent networks to predict real-valued time series.
Author: Pradeepta Kumar Sarangi
Publisher:
ISBN:
Category :
Languages : en
Pages : 0
Get Book Here
Book Description
Short Term Load Forecasting (STLF) is an essential and integral component for energy management and distribution corporations. Accurate load forecasting not only increases the efficiency of a distribution system, but also saves money. STLF is essential in taking quick decisions for a short period such as, for the next few hours or next day or a week. It helps to prevent load shedding and evaluations of various sophisticated financial products on energy pricing. It is important to consider that the forecasting is neither too optimistic nor too conservative because optimistic forecasting creates generation of surplus energy, causing loss of money and resources. Similarly, conservative forecasting will lead to shortage of energy requirement and hence will be a cause for power blackout. This paper examines and analyzes the use of Artificial Neural Network (ANN) as forecasting tools for predicting the future electric load demand and the impact of different numbers of neurons in the hidden layer in a three layered ANN architecture.
Author: Wei-Chiang Hong
Publisher: MDPI
ISBN: 3038975826
Category :
Languages : en
Pages : 445
Get Book Here
Book Description
This book is a printed edition of the Special Issue "Short-Term Load Forecasting by Artificial Intelligent Technologies" that was published in Energies
Author: Antonio Gabaldón
Publisher: MDPI
ISBN: 303943442X
Category : Technology & Engineering
Languages : en
Pages : 324
Get Book Here
Book Description
Short-term load forecasting (STLF) plays a key role in the formulation of economic, reliable, and secure operating strategies (planning, scheduling, maintenance, and control processes, among others) for a power system and will be significant in the future. However, there is still much to do in these research areas. The deployment of enabling technologies (e.g., smart meters) has made high-granularity data available for many customer segments and to approach many issues, for instance, to make forecasting tasks feasible at several demand aggregation levels. The first challenge is the improvement of STLF models and their performance at new aggregation levels. Moreover, the mix of renewables in the power system, and the necessity to include more flexibility through demand response initiatives have introduced greater uncertainties, which means new challenges for STLF in a more dynamic power system in the 2030–50 horizon. Many techniques have been proposed and applied for STLF, including traditional statistical models and AI techniques. Besides, distribution planning needs, as well as grid modernization, have initiated the development of hierarchical load forecasting. Analogously, the need to face new sources of uncertainty in the power system is giving more importance to probabilistic load forecasting. This Special Issue deals with both fundamental research and practical application research on STLF methodologies to face the challenges of a more distributed and customer-centered power system.
Author: Behnam Farsi
Publisher:
ISBN:
Category :
Languages : en
Pages : 0
Get Book Here
Book Description
Since electricity plays a crucial role in industrial infrastructures of countries, power companies are trying to monitor and control infrastructures to improve energy management, scheduling and develop efficiency plans. Smart Grids are an example of critical infrastructure which can lead to huge advantages such as providing higher resilience and reducing maintenance cost. Due to the nonlinear nature of electric load data there are high levels of uncertainties in predicting future load. Accurate forecasting is a critical task for stable and efficient energy supply, where load and supply are matched. However, this non-linear nature of loads presents significant challenges for forecasting. Many studies have been carried out on different algorithms for electricity load forecasting including; Deep Neural Networks, Regression-based methods, ARIMA and seasonal ARIMA (SARIMA) which among the most popular ones. This thesis discusses various algorithms analyze their performance for short-term load forecasting. In addition, a new hybrid deep learning model which combines long short-term memory (LSTM) and a convolutional neural network (CNN) has been proposed to carry out load forecasting without using any exogenous variables. The difference between our proposed model and previously hybrid CNN-LSTM models is that in those models, CNN is usually used to extract features while our proposed model focuses on the existing connection between LSTM and CNN. This methodology helps to increase the model's accuracy since the trend analysis and feature extraction process are accomplished, respectively, and they have no effect on each other during these processes. Two real-world data sets, namely "hourly load consumption of Malaysia" as well as "daily power electric consumption of Germany", are used to test and compare the presented models. To evaluate the performance of the tested models, root mean squared error (RMSE), mean absolute percentage error (MAPE) and R-squared were used. The results show that deep neural networks models are good candidates for being used as short-term prediction tools. Moreover, the proposed model improved the accuracy from 83.17\% for LSTM to 91.18\% for the German data. Likewise, the proposed model's accuracy in Malaysian case is 98.23\% which is an excellent result in load forecasting. In total, this thesis is divided into two parts, first part tries to find the best technique for short-term load forecasting, and then in second part the performance of the best technique is discussed. Since the proposed model has the best performance in the first part, this model is challenged to predict the load data of next day, next two days and next 10 days of Malaysian data set as well as next 7 days, next 10 days and next 30 days of German data set. The results show that the proposed model also has performed well where the accuracy of 10 days ahead of Malaysian data is 94.16\% and 30 days ahead of German data is 82.19\%. Since both German and Malaysian data sets are highly aggregated data, a data set from a research building in France is used to challenge the proposed model's performance. The average accuracy from the French experiment is almost 77\% which is reasonable for such a complex data without using any auxiliary variables. However, as Malaysian data and French data includes hourly weather data, the performance of the model after adding weather is evaluated to compare them before using weather data. Results show that weather data can have a positive influence on the model. These results show the strength of the proposed model and how much it is stable in front of some challenging tasks such as forecasting in different time horizons using two different data sets and working with complex data.
Author:
Publisher:
ISBN:
Category :
Languages : pt-BR
Pages :
Get Book Here
Book Description
A previsão de perfis de carga elétrica (i.e., das séries de cargas a cada hora de um dia) tem sido freqüentemente tentada por meio de modelos baseados em redes neurais. Os resultados conseguidos por estes modelos, contudo, ainda não são considerados inteiramente convincentes. Há duas razões para ceticismo: em primeiro lugar, os modelos sugeridos geralmente se baseiam em redes que parecem ser complexas demais em relação aos dados que pretendem modelar (isto é, estes modelos parecem estar superparametrizados); em segundo lugar, estes modelos geralmente não são bem validados, pois os artigos que os propõem não comparam o desempenho das redes ao de modelos de referência. Nesta tese, examinamos estes dois pontos por meio de revisões críticas da literatura e de simulações, a fim de verificar se é realmente viável a aplicação de redes neurais à previsão de perfis de carga. Nas simulações, construímos modelos bastante complexos de redes e verificamos empiricamente sua validade, pela comparação de seu desempenho preditivo fora da amostra de treino ao desempenho de vários outros modelos de previsão. Os resultados mostram que as redes, mesmo quando muito complexas, conseguem previsões de perfis mais acuradas do que os modelos tradicionais, o que sugere que elas poderão trazer uma grande contribuição para a solução do problema de previsão de cargas.
Author:
Publisher:
ISBN:
Category :
Languages : pt-BR
Pages :
Get Book Here
Book Description
Esta dissertação investiga a utilização de Redes Neurais Artificiais (RNAs) na área de previsão de carga elétrica. Nesta investigação foram utilizados dados reais de energia relativos ao sistema elétrico brasileiro. O trabalho consiste de quatro partes principais: um estudo sobre o problema de previsão de carga no contexto de sistemas elétricos de potência; o estudo e a modelagem das RNAs para previsão de carga; o desenvolvimento do ambiente de simulação; e o estudo de casos. O estudo sobre o problema de previsão de carga envolveu uma investigação sobre a importância da previsão de demanda de energia na área de sistemas elétricos de potência. Enfatizou-se a classificação dos diversos tipos de previsão de acordo com o seu horizonte, curto e longo prazo, bem como a análise das variáveis mais relevantes para a modelagem da carga elétrica. O estudo também consistiu da análise de vários projetos na área de previsão de carga, apresentando as metodologias mais utilizadas. O estudo e a modelagem de RNAs na previsão de carga envolveu um extenso estudo bibliográfico de diversas metodologias. Foram estudadas as arquiteturas e os algoritmos de aprendizado mais empregados. Constatou-se uma predominância da utilização do algoritmo de retropropagação (Backpropagation) nas aplicações de previsão de carga elétrica horária para curto prazo. A partir desse estudo, e utilizando o algoritmo de retropropagação, foram propostas diversas arquiteturas de RNAs de acordo com o tipo de previsão desejada. O desenvolvimento do ambiente de simulação foi implementado em linguagem C em estações de trabalho SUN. O pacote computacional engloba basicamente 3 módulos: um módulo de pré-processamento da série de carga para preparar os dados de entrada; um módulo de treinamento da Rede Neural para o aprendizado do comportamento da série; e um módulo de execução da Rede Neural para a previsão dos valores futuros da série. A construção de uma interface amigável para a execução do sistema de previsão, bem como a obtenção de um sistema portátil foram as metas principais para o desenvolvimento do simulador. O estudo de casos consistiu de um conjunto de implementações com o objetivo de testar o desempenho de um sistema de previsão baseado em Redes Neurais para dois horizontes distintos: previsão horária e previsão mensal. No primeiro caso, foram utilizados dados de energia da CEMIG (Estado de Minas Gerais) e LIGHT (Estado do Rio de Janeiro). No segundo caso, foram utilizados dados de energia de 32 companhias do setor elétrico brasileiro. Destaca-se que a previsão mensal faz parte de um projeto de interesse da ELETROBRÁS, contratado pelo CEPEL. Para ambos os casos, investigou-se a influência do horizonte de previsão e da época do ano no desempenho do sistema de previsão. Além disso, foram estudadas as variações do desempenho das Redes Neurais de acordo com a empresa de energia elétrica utilizada. A avaliação do desempenho foi feita através da análise das seguintes estatísticas de erro: MAPE (Mean Absolute Percentage Error), RMSE (Root Mean Square Error) e U de Theil. O desempenho das RNAs foi comparado com o de outras técnicas de previsão, como os métodos de Holt-Winters e Box & Jenkins, obtendo-se resultados, em muitos casos, superiores.
Author: Wei-Chiang Hong
Publisher: MDPI
ISBN: 3038972908
Category : Electronic books
Languages : en
Pages : 251
Get Book Here
Book Description
This book is a printed edition of the Special Issue "Hybrid Advanced Techniques for Forecasting in Energy Sector" that was published in Energies
Author: Christopher M. Bishop
Publisher: Oxford University Press
ISBN: 0198538642
Category : Computers
Languages : en
Pages : 501
Get Book Here
Book Description
Statistical pattern recognition; Probability density estimation; Single-layer networks; The multi-layer perceptron; Radial basis functions; Error functions; Parameter optimization algorithms; Pre-processing and feature extraction; Learning and generalization; Bayesian techniques; Appendix; References; Index.
