Electric Power Load Forecasting Based on Fractional PID Model

Load forecasting is one of the important work of the power system management. Increased load forecasting skills, conducive to saving coal and oil, and reduce cost of power generation, will help improve economic and social benefits of power system. In order to improve the accuracy of load forecasting, we designed a fractional order PID neural network model. Adjust parameters through using BP neural network, you can achieve a five-dimensional variable predictive model of self-learning. Fractional PID controller digitizes regulate synaptic weights of the network by BP algorithm adjustment of the neural network output as the parameter of fractional order PID controller. The simulation concluded that the accuracy of fractional PID neural network model is higher than the traditional neural network forecasting model. To improve the accuracy of load forecasting provides a reference program.