为了高精度评价电力系统运行方式合理性以及电力企业运营状况，研究基于双模调频分解的低压配电网同期线损率预测模型，利用高精度的线损率预测结果提升电网运营管理性能。采集低压配电网电能传输信号，通过双模调频分解方法利用双模调频基函数分解信号，去除无用信号；利用分层式节点识别策略在分解后的配电信号中划分低压配电网的负荷节点，获取各负荷节点的注入电流；利用支持向量机方法建立同期线损率预测模型，将所获取的注入电流输入到模型中，输出线损率预测优化结果。试验结果表明，该预测模型的预测结果与实际结果极为吻合，平均绝对误差和均方根误差均不超过0.09%，证明该模型可有效预测低压配电网同期线损率，预测精度高，可为智能配电网运营管理提供有效依据。

In order to evaluate the rationality of power system operation mode and the operation status of electric power enterprises with high accuracy, the prediction model of line loss rate of low-voltage distribution network based on dual-mode frequency modulation (FM) decomposition is studied, and the high-precision prediction result of line loss rate is used to improve the operation and management performance of power network. The power transmission signals of low-voltage distribution network are collected, and the dual-mode FM basis function is used to decompose the signals and remove useless signals by dual-mode FM decomposition method. The hierarchical node identification strategy is used to divide the load nodes of the low-voltage distribution network from the decomposed distribution signals, and the injection current of each load node is obtained. Support vector machine (SVM) method is used to establish a prediction model of line loss rate in the same period. The injection current obtained is input into the model, and the optimization result of line loss rate prediction is output. Experimental results show that the prediction results of the model are in good agreement with the actual results, and the mean absolute error and root mean square error are both lower than 0.09%, which proves that the model can effectively predict the line loss rate of low-voltage distribution network in the same period with high prediction accuracy, and can provide an effective basis for the operation and management of intelligent distribution network.