Application of chaotic neural network in power system load forecasting

Power system load forecasting is one of the important work of electricity production departments, the load demand is affected by many factors (such as weather, economic, and social activities, etc.) effects, and their relationship is complex, unclear, so it is difficulty to predict the load accurately. In order to improve short term load forecasting accuracy, according to this non-linear reconstruction technique based on chaos theory we constructed an improved BP algorithm based on chaotic neural network short term load forecasting model in this paper. The above model and the algorithm was applied to the short-term power load forecasting of an south area, made a good prediction.