Research on Optimization of Distribution Network Connection Mode Based on Graph Neural Network and Genetic Algorithm
DOI:
https://doi.org/10.13052/dgaej2156-3306.3964Keywords:
Distribution network, connection mode, graph neural network, genetic algorithm, model parameter optimizationAbstract
With the deep integration of electric power and information technology systems, the distribution system shows the trend of increasingly complex structures and increasing external risk factors. This leads to more diversified types of faults in the distribution network, so it is crucial to optimize its topology. In this paper, we first compare the main connection modes of high-voltage and medium-voltage distribution networks in China, and combine them with the specific needs of Shaanxi Power Grid to propose a differentiated flexible network model and its scope of application. Using Graph Neural Network and Genetic Algorithm, an innovative optimization method of distribution network connection is proposed to support the typical network structure of the new distribution network. Analysis of examples shows that the proposed algorithm can improve the original network’s network loss and voltage deviation by 32.8% and 37.3%, respectively, and the improvement effect is better than that of the traditional genetic algorithm. At the same time, considering the different stages of distribution network development and the uncertainties that may be faced, this paper also explores the flexible transition scheme of each typical network structure to ensure a smooth transition to a more efficient, green and intelligent distribution network model without affecting the reliability of the existing power supply.
Downloads
References
Mahdi Sedghi, Ali Ahmadian, Masoud Aliakbar-Golkar. (2016). Assessment of optimization algorithms capability in distribution network planning: Review, comparison and modification techniques. Renewable and Sustainable Energy Reviews, 66, 415–434,
Xin Du, Jiali Huo, Lin Chen, Mingchang Wang, Zhaoshun Wu, Chengliang Zhang. (2023). Application of Intelligent Optimization Algorithms in the Distribution Network Planning and Evaluation Models. Procedia Computer Science, 228, 1205–1214,
Akihiko Yokoyama. (2022). Toward Deregulated, Smart and Resilient Power Systems with Massive Integration of Renewable Energy in Japan. IEEJ Transactions on Electrical and Electronic Engineering, 17, 1242–1254.
Liu Xiang jun, MA Shuang, Xu Gang. (2012). Formation of Typical Connection Mode for Distribution Network by Elementary Connection Model. Power System Technology, 36, 59–63.
Qin, X. (2013). Analysis of Different Connection Modes in MV Distribution Systems. Lecture Notes in Electrical Engineering, 206, 107–114.
Y. Jian, S. Lin, Y. Anxin, S. Ruoxuan. (2019). Research on a Typical Connection Mode of Flexible DC Distribution Applied to High Reliability Area. 2019 IEEE Innovative Smart Grid Technologies, 38, 2732–2737.
Zhang Chi, Cheng Haozhong, Xi Xun. (2006). A Study of Distribution Network Feeding Modes Selection Based on Analytic Hierarchy Process and Fuzzy Comprehensive Evaluation. Power System Technology, 30, 67–71.
Pan Feng, Zhang Yujun, Zhou Min. (2009). A Comprehensive Evaluation Hierarchy for MV Distribution Network based on Connection Modes. Power System Protection and Control, 37, 19–21.
He Yongxiu, Wang Wei, Yang Weihong. (2009). Assessment of Connection Mode in Distribution Network Based on Blind Number Theory. Transactions of China Electrotechnical Society, 24, 139–144.
Wang Chengshan, Wang Saiyi, Ge Shaoyun. (2002). Economy and Reliability Analysis of Different Connection Modes in MV Distribution Systems. Automation of Electric Power Systems, 26, 34–39.
Minh Y Nguyen, Yong Tae Yoon. (2014). A Comparison of Microgrid Topologies Considering Both Market Operations and Reliability. Electric Power Components and Systems, 42, 585–594.
Wu Han, Lin Han, Chen Bin, Wu Han, WenBu Ying. (2012). The Selection Algorithm for Connection Modes of Medium Voltage Power Distribution Network Based on FAHP-GRA. Physics Procedia, 24, 345–353.
Wu Z, Pan S, Chen F. (2020). A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32, 4–24.
Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, Maosong Sun. (2020). Graph neural networks: A review of methods and applications. AI Open, 1, 57–81.
Yaniv, A., Kumar, P., and Beck, Y. (2023). Towards adoption of GNNs for power flow applications in distribution systems. Electric Power Systems Research, 216, 109005.
Christian Nauck, Michael Lindner, Konstantin Schürholt, Frank Hellmann. (2023). Toward dynamic stability assessment of power grid topologies using graph neural networks. Chaos, 33, 103103.
W. Liao, D. Yang, Q. Liu, Y. Jia, C. Wang, Z. Yang. (2024). Data-Driven Reactive Power Optimization of Distribution Networks via Graph Attention Networks. Journal of Modern Power Systems and Clean Energy, 12, 874–885.
Ali, Z. M., Diaaeldin, I. M., El-Rafei, A., Hasanien, H. M., Abdel Aleem, S. H. E., and Abdelaziz, A. Y. (2021). A novel distributed generation planning algorithm via graphically-based network reconfiguration and soft open points placement using Archimedes optimization algorithm. Ain Shams Engineering Journal, 12, 1923–1941.
M. Baran, F. Wu. (1989). Network reconfiguration in distribution systems for loss reduction and load balancing. IEEE Transactions on Power Delivery, 4, 1401–1407.
T. Han, D. J. Hill. (2023). Learning-Based Topology Optimization of Power Networks. IEEE Transactions on Power Systems, 38, 1366–1378.
Elkazaz, M. H., Hoballah, A. A., Azmy, A. M. (2016). Operation optimization of distributed generation using artificial intelligent techniques. Ain Shams Engineering Journal, 7, 855–866.
Bakry, O. M., Alhabeeb, A., Ahmed, M., Alkhalaf, S., Senjyu, T., Mandal, P., and Dardeer, M. (2022). Improvement of distribution networks performance using renewable energy sources based hybrid optimization techniques. Ain Shams Engineering Journal, 13, 101786.
Xiaoyu Sun, Jinsong Liu, Xin Sun, Jin-miao Hu. (2016). Optimization of Distribution Network with Distributed Generation Based on an Improved Genetic Algorithm. International Journal of Grid and Distributed Computing, 9, 105–116.
Jo Seungchan, Oh Jae-Young, Lee Jaeho, Oh Seokhwa, Moon Hee Seung, Zhang Chen, Gadh Rajit, Yoon Yong Tae. (2023). Hybrid Genetic Algorithm With k-Nearest Neighbors for Radial Distribution Network Reconfiguration. IEEE Transactions on Smart Grid, 15, 2614–2624.
Morad Abdelaziz. (2017). Distribution network reconfiguration using a genetic algorithm with varying population size. Electric Power Systems Research, 142, 9–11.
Defferrard M, Bresson X, Vandergheynst P. (2016). Convolutional neural networks on graphs with fast localized spectral filtering[J]. Advances in neural information processing systems, 29, 3844–3852.
K. Chen, J. Hu, Y. Zhang, Z. Yu and J. He. (2019). Fault location in power distribution systems via deep graph convolutional networks. IEEE Journal on Selected Areas in Communications, 38, 119–131.
Li G Q, Cai C X. (2017). Estimation parameters of hydrocracking model with NSGA-ii (Non-dominated Sorting Genetic Algorithm) by using discrete kinetic lumping model. Fuel, 200, 333–344.
Nyathi, T., Pillay, N. (2018). Comparison of a genetic algorithm to grammatical evolution for automated design of genetic programming classification algorithms. Expert Syst. Appl., 104, 213–234.
Federico R, Corrado P, Luca M. (2017). Optimization algorithms for computational systems biology. Frontiers in Applied Mathematics and Statistics, 3, 1–12.
