BP-GA mixed algorithms for short-term load forecasting

In this paper, a modified method (BP-GA) for short-term load forecasting is presented, which can quicken the learning speed of the network and improve the predicting precision compared with the traditional artificial neural network. The authors use GAs to train connection weights of multi-layer feedforward neural network (BP) until the learning error has tended to stability, here, the best initial weights have been found. Then they use BP method to finish short-term load forecasting process. They also consider the influence of climate for the short-term load and make it as one of the input for the BP. Simulation results show that the short-term load forecasting system based on BP-GA has high precision and real-time as well as great practical value.