Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/6006
Title: | Short-Term Load Demand Modelling and Forecasting |
Authors: | Abu-El-Magd, Mohamed A. |
Advisor: | Sinha, Naresh K. |
Department: | Electrical and Computer Engineering |
Keywords: | Electrical and Computer Engineering;Electrical and Computer Engineering |
Publication Date: | 1983 |
Abstract: | <p>The major effort in this thesis has been directed towards the problem of short-term load demand forecasting. Special attention has been given to on-line load forecasting of several loading nodes simultaneously. A critical review of the state of the art in short-term load forecasting methods is presented. A new approach has been used to classify these methods according to the modelling approaches used for representing the load demand.</p> <p>Two multivariable, autoregressive and state space, models simultaneously have been proposed. The order of the autoregressive model is obtained without fitting coefficients to different models. Based on multivariable state space representation an efficient and completely automatic algorithm for on-line load forecasting is proposed. It has been shown that by utilizing the innovations representation an ordinary recursive least-square algorithm can be used to give unbiased estimates of the model parameters. The proposed algorithms obtain good forecasts even in case of loss of observations from one or more nodes.</p> <p>To obtain load forecasts for one-weak-ahead, the total load is divided into three components: nominal, weather sensitive, and stochastic. A special approach has been proposed to identify the weather-sensitive load component. Also, a study has been carried out to identify those weather variables which have a significant effect on the load demand.</p> <p>Actual load data from Ontario Hydro has been used to test the proposed methods.</p> |
URI: | http://hdl.handle.net/11375/6006 |
Identifier: | opendissertations/1343 2355 1291077 |
Appears in Collections: | Open Access Dissertations and Theses |
Files in This Item:
File | Size | Format | |
---|---|---|---|
fulltext.pdf | 2.83 MB | Adobe PDF | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.