The Analysis of Influencing Factors of Power Load Forecasting by Neural Network
碩士 === 義守大學 === 電機工程學系 === 101 === Power load forecasting is an essential work for the utility company. The accurate load forecasting can not only help company to make a good scheduling of business running, but also help company to have a planning for the development of power capacity. This thesis p...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2013
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/19106055174505059490 |
| Summary: | 碩士 === 義守大學 === 電機工程學系 === 101 === Power load forecasting is an essential work for the utility company. The accurate load forecasting can not only help company to make a good scheduling of business running, but also help company to have a planning for the development of power capacity. This thesis presents a novel technique which could precisely analyze the influencing factors of power load. This technique is developed based on supervised neural network (NN) learning process. It can extract the useful information from an unknown environment. In this study, the inputs of neural network include the daily peak power load, the daily maximum temperature and the daily minimum temperature. The output of neural network is the desired forecasting peak power load. All input variables will be analyzed and calculated their influence degrees to the output variable. Besides, only the data of weekday are studied. The data of weekend and holiday are excluded in our research. The most important influencing factors of the peak load are expected to be obtained and the research result is able to improve the accuracy of power load forecasting.
|
|---|