基于深度学习GRU网络的配电网理论线损计算方法

由于实际应用中对理论线损的精度要求不高,且传统计算方法所需电气参数较多,计算过程繁琐.因此,文中提出了一种基于深度学习门控循环单元(Gated Recurrent Unit,GRU)网络的配电网理论线损计算方法.为综合考虑主客观因素,将互信息理论和层次分析法相结合,进而确定所选电气参数对理论线损的影响权重;按照权重的大...

Distribution network line loss calculation methodbased on deep learning GRU network

The accuracy of theoretical line loss calculation is not high in application,in addition,and traditional method requires many electrical parameters and the process is tedious.Therefore,this paper proposes a theoretical line loss calculation method based on deep learning gated recurrent unit(GRU).Firstly,considering the subjective and objective factors,the influence weight of electrical parameters on the theoretical line loss is determined by the combination of mutual information and analytic hierarchy process.Then,different input parameter sets are constructed by the weight.Through the analysis of the calculation error,the optimal input parameters are determined,and the sample data set is formed to train the GRU network.Finally,this method is verified by taking a 10 kV distribution network as an example.The results show this method can replace the equivalent resistance method to calculate the theoretical line loss more conveniently.Compared with the traditional BP algorithm,this method proposed in this paper has better calculation performance.