论文部分内容阅读
针对电力系统负荷预测中实际的负荷数据往往具有极大的波动性,模型呈现出极大的非线性,提出一种改进粒子群优化的小波神经网络模型,将其应用于电力系统的负荷预测研究.首先,分析和介绍了小波神经网络和改进的粒子群算法的基本原理和优点;其次,将改进的PSO算法用于优化小波神经网络的参数优化;最后对改进的PSO-WNN负荷预测模型进行仿真分析.实验结果与传统PSO-WNN的实验结果进行对比,证明改进的PSO能够提高模型的运算效率和负荷预测精度.
In view of the fact that the actual load data in power system load forecast often has great volatility, the model shows great nonlinearity. A wavelet neural network model based on improved particle swarm optimization is proposed, which is applied to load forecasting of power system Firstly, the basic principles and advantages of wavelet neural network and improved particle swarm optimization are analyzed and introduced. Secondly, the improved PSO algorithm is used to optimize the parameters of wavelet neural network. Finally, the improved PSO-WNN load forecasting model The simulation results are compared with the experimental results of the traditional PSO-WNN, which shows that the improved PSO can improve the computational efficiency and load forecast accuracy of the model.