Abstract:

It is easy for a BP neural network (BPNN) to be trapped into a local minimum point for the time series forecasting problem. To improve the forecasting accuracy, we design a hybrid algorithm which combines the selfadaptive differential evolution algorithm (SDE) with the BPNN. We adopt the SDE algorithm to search for global initial weights and thresholds of the BPNN. These values are then employed to further search for the optimal weights and thresholds. The performance of the proposed SDE algorithm is  verified through benchmark functions and a wellknown real data set is used to verify the effectiveness of the hybrid algorithm. Compared with general neural network, ARIMA and other hybrid models,experimental results indicate that the proposed algorithm can be an effective way to improve forecasting accuracy.

Key words: time series forecasting;BP neural network;differential evolution algorithm