An Empirical Research on Short Term Power Load Forecasting Based on Chaos Theory

Forecasting of power load demand is the precondition to guarantee power system security and its safe supply. According to the complexity and non-linearity of power load demand, this paper proposed a new short term power load forecasting model based on chaos theory. The proposed method makes use of chaos time series analysis to capture characteristics of complicated load behavior. First the chaotic characteristic of the load demand was verified based on Phase-space reconstitution of time series, the principal component analysis method is used for chaos identification. Then determine an optimal embedding dimension and delay time. Adding-weight one-rank local-region multi-step method is applied to a short-term power load forecasting. Comparing power load demand time series with historical date by chaos theory, the results indicated that it will be a bright merit to use chaos theory predicting power load demand and controlling power safe supply of power station.