Application of soft computing techniques to forecast monthly electricity demand

---

Hsiao-Fan Wang

National Tsing Hua University, Taiwan

: J Comput Eng Inf Technol

Abstract

---

Electricity demand forecasting is an important tool for energy generation enterprise to develop electricity supply system. The purpose of this study is to develop monthly electricity forecasting model in order to predict electricity demand for energy management. Since the influence of the weather factors such as temperature and humidity are diluted in an overall value that represents the total monthly electricity demand, therefore the forecasting model uses only historical electricity consumption data as an integrated factor to obtain future prediction. This study presents an approach to monthly electricity demand time series forecasting model, including two series of the fluctuation and trend series. The trend series describe the trend of the electricity demand series and the fluctuation series describe the periodic fluctuation that imbedded in the trend. Then an integrated genetic algorithm and neural network model are trained for forecasting the trend series. Since the fluctuation series presents an oscillatory behavior, we apply Fourier series to fit the fluctuations series. Validation is made by using electricity demand data in United States to evaluate the proposed model and compare that with model solved by using neural network only.

Biography

---

Email: hsiaofanwang@gmail.com