改进粒子群—BP神经网络模型的短期电力负荷预测

为了准确、快速、高效地预测电网短期负荷，提出了改进的粒子群算法(MPSO)，并与BP算法相结合，形成改进的粒子群—BP(MPSO-BP)神经网络算法，用此算法训练神经网络，实现了神经网络参数优化，得到了基于MPSO-BP算法的神经网络模型。综合考虑气象、天气、日期类型等影响负荷的因素，进行电网短期负荷预测。算例分析表明，与传统BP神经网络法和PSO-BP神经网络方法相比，该方法改善了BP神经网络的泛化能力，预测精度高，收敛速度快，对电力系统短期负荷具有良好的预测能力。

Short-term load forecast based on modified particle swarm optimizer and back propagation neural network model

Aiming at improving the power short-term forecast accuracy and speed, the Modified Particle Swarm Optimizer (MPSO) algorithm was presented. The forecast model was set up by combining with the Back Propagation (BP) neural network to form Modified Particle Swarm Optimizer and Back Propagation (MPSO-BP) neural network algorithm, and then the neural network was trained by using the MPSO-BP algorithm. It can automatically determine the parameters of the neural network from the sample data. The power short-term forecast model based on the MPSO-BP neural network was formed with considering weather, date and other factors. The experimental results show that the MPSO-BP algorithm improves the BP neural network generalization capacity, and the convergence of method is faster and forecast accuracy is more accurate than that of the traditional BP neural network. Therefore, the model can be used to forecast the short-term load of the power system.