Application of Dynamic Recurrent Neural Network in Power System Short-Term Load Forecasting

Convergence speed of the traditional BP neural network is slow, and it is easy to fall into local minimum. A novel dynamic recurrent fuzzy neural network model is proposed, which is used to resolve the power system short-term load forecasting. The fuzzy inference function is realized easily by using a product operation in the network. The simulation results indicate that the proposed network can overcome the limit of back-propagation-based static network methods and accurately forecast the short-term load.