基于WOA优化Elman神经网络的线损计算研究

Research on Optimizing Line Loss Calculation of Elman Neural Network Based on Whale Algo-rithm

为准确方便地计算配电网的线损,基于配电网的实际运行数据,提出了基于鲸鱼算法优化Elman神经网络的方法来计算配电网中的线损。首先,分析影响低压台区线损的影响因素作为线损计算模型的输入;然后,建立Elman神经网络模型来完成配电网线损的计算;最后,运用鲸鱼算法来优化建立神经网络模型,从而建立WOA-Elman模型来计算配电网的线损。对所提出模型进行仿真分析,分析结果表明,采用鲸鱼算法优化的神经网络模型进行线损率计算比直接采用经验分析建立的Elman神经网络模型线损计算的性能更好,具有更好的非线性拟合能力和更高的计算精度,在进行配电网线损计算时准确率更高。

In order to calculate the line loss of the distribution network accurately and conveniently, based on the actual operating data of the distribution network, this paper proposes a method of optimizing the Elman neural network based on the whale algorithm to calculate the line loss in the distribution network.First, analyze the influencing factors that affect the line loss in the low-voltage station area as the input of the line loss calculation model;then, establish a Elman neural network model to complete the calculation of the distribution network line loss;finally, use the whale algorithm to optimize the established neural network model, Thus, a WOA-Elman model is established to calculate the line loss of the distribution network.The proposed model is simulated and analyzed.The analysis results show that the line loss rate calculation of the neural network model optimized by the whale algorithm is better than that of the Elman neural network model directly established by empirical analysis, which has better nonlinear fitting ability and higher calculation accuracy, and has higher accuracy in the calculation of distribution network line loss.