Editorial
Mining method of power consumption behavior pattern of different subject resource objects in virtual power plant based on graph neural network
@ARTICLE{10.4108/ew.12319, author={Duan Zhiguo and Jie Zhao and Xi Chen and Jiakun An and Wenyi Fan}, title={Mining method of power consumption behavior pattern of different subject resource objects in virtual power plant based on graph neural network}, journal={EAI Endorsed Transactions on Energy Web}, volume={13}, number={1}, publisher={EAI}, journal_a={EW}, year={2026}, month={6}, keywords={Consumption Behavior Pattern Mining, Graph Neural Network (GNN), Density Peak Clustering (DPC), Fuzzy C-Means (FCM), Clustering Algorithm}, doi={10.4108/ew.12319} }- Duan Zhiguo
Jie Zhao
Xi Chen
Jiakun An
Wenyi Fan
Year: 2026
Mining method of power consumption behavior pattern of different subject resource objects in virtual power plant based on graph neural network
EW
EAI
DOI: 10.4108/ew.12319
Abstract
INTRODUCTION: With the advancement of global energy internet and smart grid, massive power big data with complex temporal features is generated by widely deployed smart meters. Accurate identification of power consumption behavior patterns is essential for dispatching a virtual power plant (VPP). OBJECTIVES: This paper proposes a fine-grained mining framework that combines temporal feature extraction and a graph neural network to support VPP dispatch requirements. METHODS: Linear interpolation and same-type day mean filling are used for data cleaning and normalization. A user relationship graph is constructed via physical connection and Pearson correlation-based behavioral similarity. A GCN-based unsupervised graph autoencoder is adopted for spatio-temporal feature embedding, and an improved DPC-FCM clustering algorithm is proposed to optimize it. RESULTS: The method effectively solves the inherent defects of traditional clustering: initial center sensitivity and noise interference. CONCLUSION: This framework realizes accurate fine-grained mining of power consumption patterns, providing reliable support for VPP dispatch decision-making.
