基于神经网络的负荷预测仿真研究

摘要

Improving the power load forecasting accuracy is good for the safety production of the power sector, planing the power grid operation mode and overhauling the system appropriately, running and planning the system economically. In order to improve the power load forecasting accuracy, this article applied the autocorrelation conception to choose the input variables of back propagation (BP) neural network, and established the power load forecasting mode which is examined based on MATLAB. Finally, the simulation forecasts the load of a power system in one day. Simulation results indicate that this method is feasible and effective.%提高电力负荷预测精度有利于电力部门的安全生产,有利于合理安排电网运行方式和机组的检修计划,有利于系统的合理规划和经济运行.为了提高短期负荷预测的精度,把自相关函数的概念应用到反向传播( Back Propogation,BP)神经网络输入变量选择中,通过MATLAB仿真软件建立负荷预测模型.最后对某电力系统1d的负荷进行预测,仿真结果验证了该模型的可行性和有效性.