A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting
碩士 === 中原大學 === 電機工程研究所 === 86 === The thesis proposes a new self-organizing fuzzy model for the short-term forecasting of the one-day ahead hourly load demands. Due to the abilities of the fuzzy theory in resolving the problems of subjectivity, uncertainty, as well as human lin...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
1998
|
Online Access: | http://ndltd.ncl.edu.tw/handle/48401941508081054623 |
id |
ndltd-TW-086CYCU0442010 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-086CYCU04420102016-01-22T04:17:08Z http://ndltd.ncl.edu.tw/handle/48401941508081054623 A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting 自我組織式模糊系統作短期電力負載預測 Lin Chin-Shan 林金山 碩士 中原大學 電機工程研究所 86 The thesis proposes a new self-organizing fuzzy model for the short-term forecasting of the one-day ahead hourly load demands. Due to the abilities of the fuzzy theory in resolving the problems of subjectivity, uncertainty, as well as human linguistic expression and thinking manner, application of the fuzzy theory to the short-term load forecasting (STLF) can alleviate the complication of constructing the STLF model. In the thesis, the rule base for inferring the future load variation is synthesized by integrating and analyzing the relationship of the historical load to the weather variables, selecting initial membership functions of the input and the output (i.e., the load) variables of the fuzzy model, and using a simple computational algorithm. Next, evolutionary computing techniques are used to obtain the optimal membership functions and the corresponding inference rules. The mechanisms of stochastic search and natural evolution in the evolutionary computing techniques adjust the fuzzy membership functions effectively. As a result, the techniques can overcome the defects that the traditional fuzzy system cannot learn automatically from the historical load and diverse weather data. In addition, not only is the forecasting system established conveniently, but the forecasting accuracy is improved by the proposed method. The practical hourly load demands of the Taipower system and the temperature data collected from the Central Weather Bureau were employed to test the proposed fuzzy systems. In the process, the load and weather variables with higher relationship were chosen as the input variables to predict the future 24-hour load curve. The results were compared to those obtained from the back-propagation type of artificial neural network, and the existing fuzzy load forecasting method to serve as performance verification of the proposed forecasting method. Yang Hong-Tzer 楊宏澤 1998 學位論文 ; thesis 0 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 中原大學 === 電機工程研究所 === 86 === The thesis proposes a new self-organizing fuzzy model for the short-term forecasting of the one-day ahead hourly load demands. Due to the abilities of the fuzzy theory in resolving the problems of subjectivity, uncertainty, as well as human linguistic expression and thinking manner, application of the fuzzy theory to the short-term load forecasting (STLF) can alleviate the complication of constructing the STLF model. In the thesis, the rule base for inferring the future load variation is synthesized by integrating and analyzing the relationship of the historical load to the weather variables, selecting initial membership functions of the input and the output (i.e., the load) variables of the fuzzy model, and using a simple computational algorithm. Next, evolutionary computing techniques are used to obtain the optimal membership functions and the corresponding inference rules. The mechanisms of stochastic search and natural evolution in the evolutionary computing techniques adjust the fuzzy membership functions effectively. As a result, the techniques can overcome the defects that the traditional fuzzy system cannot learn automatically from the historical load and diverse weather data. In addition, not only is the forecasting system established conveniently, but the forecasting accuracy is improved by the proposed method. The practical hourly load demands of the Taipower system and the temperature data collected from the Central Weather Bureau were employed to test the proposed fuzzy systems. In the process, the load and weather variables with higher relationship were chosen as the input variables to predict the future 24-hour load curve. The results were compared to those obtained from the back-propagation type of artificial neural network, and the existing fuzzy load forecasting method to serve as performance verification of the proposed forecasting method.
|
author2 |
Yang Hong-Tzer |
author_facet |
Yang Hong-Tzer Lin Chin-Shan 林金山 |
author |
Lin Chin-Shan 林金山 |
spellingShingle |
Lin Chin-Shan 林金山 A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting |
author_sort |
Lin Chin-Shan |
title |
A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting |
title_short |
A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting |
title_full |
A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting |
title_fullStr |
A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting |
title_full_unstemmed |
A Self-Organization Fuzzy System for Short-Term Power System Load Forecasting |
title_sort |
self-organization fuzzy system for short-term power system load forecasting |
publishDate |
1998 |
url |
http://ndltd.ncl.edu.tw/handle/48401941508081054623 |
work_keys_str_mv |
AT linchinshan aselforganizationfuzzysystemforshorttermpowersystemloadforecasting AT línjīnshān aselforganizationfuzzysystemforshorttermpowersystemloadforecasting AT linchinshan zìwǒzǔzhīshìmóhúxìtǒngzuòduǎnqīdiànlìfùzàiyùcè AT línjīnshān zìwǒzǔzhīshìmóhúxìtǒngzuòduǎnqīdiànlìfùzàiyùcè AT linchinshan selforganizationfuzzysystemforshorttermpowersystemloadforecasting AT línjīnshān selforganizationfuzzysystemforshorttermpowersystemloadforecasting |
_version_ |
1718161523217530880 |