The Prediction of Power Signal by Neural Networks

• Main Authors: CHUN JUNG CHEN, 陳俊榮
• Other Authors: Rey-Chue Hwang
• Format: Others
• Language: zh-TW
• Published: 2002
• Online Access: http://ndltd.ncl.edu.tw/handle/30559516485216235246

碩士 === 義守大學 === 電機工程學系 === 90 === The Prediction of Power Signal by Neural Networks Student: Chun-Jung Chen* Advisor: Rey-Chue Hwang** Department of Electrical Engineering I-Shou University Taiwan, R.O.C. Abstract In this study, the prediction of total load for each day by using neural network technique is investigated and developed. The data of daily total load, daily maximum temperature, daily average temperature and daily minimum temperature is studied and analyzed. Such analyzed data can be used as the input data for neural network training. Through a proper training, the network can predict the load value for next day. Compare with the real load value, we can find that the accuracy of prediction by using neural network is quite good. The structure of neural network and its learning algorithm will be clearly described in this thesis. The relationships between daily total load and weather information will also be analyzed and reported. Then, the prediction results will be discussed. The data of daily total load and its relevant weather information from year 1992 to year 1996 is studied and simulated. The first three years data is used as the input information for neural network training. The last two years data will be used as the real experimental values, i.e., for neural network testing. All of the predicted values will be computed and compared with the actual load values.