Study on Short-Term Load Forecasting of Distributed Power System Based on Wavelet Theory

Compared to the continuous growth of China's national economy and the improvement of people's living standards, the development of power systems is lagging behind and cannot meet the demand for electricity across the country. This will cause short-term blackouts, power rationing and other issues in some areas. Therefore, short-term load forecasting has become one of the most important parts of power system modernizing management. In this paper, wavelet theory is used to study the short-term load forecasting of power system. Through wavelet packet in MATLAB, the load is decomposed into three layers. The low frequency part of decomposition is programmed by continuous method and the high frequency part of the decomposition is programmed and calculated by linear regression method. The linear regression method is used to predict the historical data. After comparing the prediction results of the two methods, it is found that the prediction results after wavelet decomposition are more accurate and precise and a higher accuracy rate can be obtained. And then the load is predicted by different prediction lengths. We find that the highest accuracy is predicted by taking ten points.