C. Li and L. Zhang (PRC)
Data mining, wavelet analysis, chaos theory, electricity price time series, Lyapunov exponent
A new short-term electricity price forecasting method based on chaos theory and data mining was proposed. A sketch of chaos theory and data mining was given firstly. Data preprocessing was an import part of data mining, concerning the characteristics of electricity price time sequence, Haar wavelet was used to do data compression. After processing, the effect of “price nail” on forecasting electricity price was reduced. The largest Lyapunov exponent was larger than zero from small data sets, it verified the electricity price still met chaotic behavior. Based on this, chaos time series to forecast short-term electricity price could be used. At last, the example analysis about American California electricity market showed that the forecasting method increased the precision of electricity forecasting more effectively and steadily.
Important Links:
Go Back
