Short-term load forecasting of countryside distribution network based on improved gene expression programming

Gene expression programming (GEP) was improved to overcome the shortcomings that the initial population was generated randomly. There were no standards to measure the gene, mutation rate could not be adjusted by itself and evolution result got before could not be utilized. The method that excessive multiplication, environmental factor selecting, using pheromones to measure gene, self-adaptive mutation rate and adopting mathematical model got before was proposed. The improved gene expression programming (IGEP) was applied to countryside distribution network short-term load forecasting. Firstly, the load series of the same time but different days were chosen as the training samples. Secondly, the load samples were filtered and processed generally. And finally, the short-term load was forecasted by weekday and weekend after eliminating the pseudo-data. After comparison with the results forecasted by means of genetic programming (GP) and GEP, it proves that the method of IGEP in countryside distribution network short-term load forecasting is better.