配电网馈线负荷自动预测及分布式电源接入方法研究

Research on Automatic Load Prediction and Distributed Power Supply Access Method for Distribution Network Feeders

为解决配电网馈线负荷自动预测结果精度不足的问题,研究了配电网馈线负荷自动预测和分布式电源接入方法。通过接入分布式电源、设定黑盒框架以及改进SVM回归函数构建配电网馈线负荷自动预测模型,选取预测结果评价指标输入预测变量,实现配电网馈线负荷的自动预测。模拟预测结果显示,相比于传统方法,使用优化后的模型预测的配电网馈线负荷与净负荷的均方根误差、平均绝对误差以及平均绝对误差百分比均明显减小,提高了配电网馈线负荷自动预测方法的精度,增强了配电网运行的稳定性。

In order to solve the problem of insufficient accuracy of feeder load automatic prediction results,this paper puts forward the research on feeder load automatic prediction and distributed power supply access method.Through the distributed power supply access,the black box framework was set up and the SVM regression function was improved to build the automatic load prediction model of distribution network feeders.The evaluation indexes of the predicted results were selected and the prediction variables were input to realize the automatic load prediction of distribution network feeders.Simulation results show that,using the optimized model to forecast,compared with the traditional method of load distribution feeders and net load of root mean square error,mean absolute error and mean absolute error percentage were significantly decreased,improve the accuracy of automatic distribution feeders load forecasting method,enhanced the stability of the power distribution network operation.