%0 Journal Article
%T 含高渗透率分布式光伏配电网的线损预测方法<br>Method for Line Loss Prediction in Distribution Networks with High Penetration of Distributed Photovoltaic Systems
%A 江楚萱
%A 杜瑞峰
%A 刘子超
%A 何阳
%A 谷丰宇
%J Smart Grid
%P 46-56
%@ 2161-8771
%D 2025
%I Hans Publishing
%R 10.12677/sg.2025.153005
%X 针对含高渗透率分布式光伏的配电网线损预测问题&#65292;提出了一种基于BI-LSTM (Bidirectional Long-Short Term Memory&#65292;即双向长短期记忆网络)的线损预测方法&#65306;构建含分布式光伏配电网模型&#65292;并以改进高斯混合模型划分源荷典型运行场景&#65292;确定最佳场景数与聚类参数后&#65292;基于双向长短期记忆网络(BI-LSTM)构建线损预测模型实现高精度预测。通过某地区10 kV配电网实例&#65292;验证该方法在多场景下的有效性&#65292;并与传统极限学习机(ELM (Extreme Learning Machine))模型比较&#65292;证明其在预测精度与稳定性上更优&#65292;为电网降损和能效管理提供依据。<br>Aiming at the line loss prediction problem in distribution networks with high penetration of distributed photovoltaics (PV), a line loss prediction method based on Bidirectional Long-Short Term Memory (BI-LSTM) is proposed. A distribution network model with distributed photovoltaics is constructed, and the typical source-load operation scenarios are divided by an improved Gaussian Mixture Model. After determining the optimal number of scenarios and clustering parameters, a line loss prediction model based on BI-LSTM is built to achieve high-precision prediction. The effectiveness of this method in multiple scenarios is verified through a 10 kV distribution network example in a certain area. Compared with the traditional Extreme Learning Machine (ELM) model, it is proven to be superior in prediction accuracy and stability, providing a basis for power grid loss reduction and energy efficiency management.
%K 分布式光伏&#65292
%K 线损预测&#65292
%K 高斯混合模型&#65292
%K BI-LSTM神经网络<br>Distributed Photovoltaics
%K Line Loss Prediction
%K Gaussian Mixture Model
%K BI-LSTM Neural Network
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=116969