Research on Power Load Forecasting Model Based on Hybrid AlgorithmOptimizing BP Neural Network

摘要

Short time load forecasting is essential for daily planning and operation of electric power system. It is the importantbasis for economic dispatching, scheduling and safe operation. Neural network, which has strong nonlinear fittingcapability, is widely used in the load forecasting and obtains good prediction effect in nonlinear chaotic time series forecasting.However, the neural network is easy to fall in local optimum, unable to find the global optimal solution. This paperwill integrate the traditional optimization algorithm and propose the hybrid intelligent optimization algorithm based onparticle swarm optimization algorithm and ant colony optimization algorithm (ACO-PSO) to improve the generalizationof the neural network. In the empirical analysis, we select electricity consumption in a certain area for validation. Comparedwith the traditional BP neutral network and statistical methods, the experimental results demonstrate that the performanceof the improved model with more precise results and stronger generalization ability is much better than the traditionalmethods.