Mining method of power consumption behavior pattern of different subject resource objects in virtual power plant based on graph neural network
DOI:
https://doi.org/10.4108/ew.12319Keywords:
Consumption Behavior Pattern Mining, Graph Neural Network (GNN), Density Peak Clustering (DPC), Fuzzy C-Means (FCM), Clustering AlgorithmAbstract
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.
Downloads
References
[1] KONG X Y, ZHENG F, E Z J, et al. Short-term load forecasting based on deep belief network[J]. Automation of Electric Power Systems, 2018, 42(5): 133-139.
[2] Tambunan H B, Barus D H, Hartono J, et al. Electrical peak load clustering analysis using K-means algorithm and silhouette coefficient[C]//2020 International Conference on Technology and Policy in Energy and Electric Power (ICT-PEP). IEEE, 2020: 258-262.
[3] Rajabi A, Eskandari M, Ghadi M J, et al. A comparative study of clustering techniques for electrical load pattern segmentation[J]. Renewable and Sustainable Energy Reviews, 2020, 120: 109628.
[4] LIU J, LUO F, LIU R J, et al. Study on application strategies of demand-side management under big data background[J]. Power Demand Side Management, 2016, 18(2): 5-10.
[5] SUN M, KONSTANTELOS I, STRBAC G. C-vine copula mixture model for clustering of residential electrical load pattern data[J]. IEEE Transactions on Power Systems, 2017, 32(3): 2382-2393.
[6] AI X, YANG Z H, HU H Y, et al. A load curve clustering method based on improved K-means algorithm for virtual power plant and its application[J]. Electric Power Construction, 2020, 41(5): 28-36.
[7] ZHAO T H, ZHANG Y, WANG J X. Identification method of load outlier based on density-based spatial clustering and outlier boundaries[J]. Automation of Electric Power Systems, 2021, 45(10): 97-105.
[8] CAI X W, YANG J S. Residents mid-term electricity demand forecasting model based on fuzzy C-means clustering[J]. Power Demand Side Management, 2016, 18(3): 23-26.
[9] Pérez-Ortega J, Roblero-Aguilar S S, Almanza-Ortega N N, et al. Hybrid fuzzy C-means clustering algorithm oriented to big data realms[J]. Axioms, 2022, 11(8): 377.
[10] XU W Y. Research and analysis of customer demand response based on artificial intelligence[J]. Power Demand Side Management, 2019, 21(3): 17-20, 31.
[11] WANG X, LIU Z, ZHANG H, et al. A review on virtual power plant concept, application and challenges[C]//2019 IEEE Innovative Smart Grid Technologies-Asia (ISGT Asia). 2019: 4328-4333.
[12] LI Z Y, WU J Y, WU W L, et al. Power customers load profile clustering using the SOM neural network[J]. Automation of Electric Power Systems, 2008(15): 66-70, 78.
[13] NAUGHTON J, WANG H, CANTONI M, et al. Co-optimizing virtual power plant services under uncertainty: A robust scheduling and receding horizon dispatch approach[J]. IEEE Transactions on Power Systems, 2021, 36(5): 3960-3972.
[14] E. Mokaramian, H. Shayeghi, F. Sedaghati, A. Safari, H.H. Alhelou, An optimal energy hub management integrating EVs and RBS based on three-stage model considering various uncertainties, IEEE Access 10 (2022) 17349–17365.
[15] Wu Z, Lin X, Lin Z, et al. Interpretable graph convolutional network for multi-view semi-supervised learning[J]. IEEE Transactions on Multimedia, 2023, 25: 8593-8606.
[16] Sierla S, Pourakbari-Kasmaei M, Vyatkin V. A taxonomy of machine learning applications for virtual power plants and home/building energy management systems[J]. Automation in Construction, 2022, 136: 104174.
[17] Ikotun A M, Ezugwu A E, Abualigah L, et al. K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data[J]. Information Sciences, 2023, 622: 178-210.
[18] Hashemi S E, Gholian-Jouybari F, Hajiaghaei-Keshteli M. A fuzzy C-means algorithm for optimizing data clustering[J]. Expert Systems with Applications, 2023, 227: 120377.
[19] Zhu J, Ma X, Martínez L, et al. A probabilistic linguistic three-way decision method with regret theory via fuzzy c-means clustering algorithm[J]. IEEE Transactions on Fuzzy Systems, 2023, 31(8): 2821-2835.
[20] Ezugwu A E, Ikotun A M, Oyelade O O, et al. A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects[J]. Engineering Applications of Artificial Intelligence, 2022, 110: 104743.
[21] Wang L, Pan Q, Wang S. Data-driven predictions of shield attitudes using Bayesian machine learning[J]. Computers and Geotechnics, 2024, 166: 106002.
[22] Mat S R T, Ab Razak M F, Kahar M N M, et al. A Bayesian probability model for Android malware detection[J]. ICT Express, 2022, 8(3): 424-431.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Duan Zhiguo, Zhao Jie, Chen Xi, An Jiakun, Wenyi Fan
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
