{"title":"Constraint Learning-based Optimal Power Dispatch for Active Distribution Networks with Extremely Imbalanced Data","authors":"Yonghua Song;Ge Chen;Hongcai Zhang","doi":"10.17775/CSEEJPES.2023.05970","DOIUrl":null,"url":null,"abstract":"Transition towards carbon-neutral power systems has necessitated optimization of power dispatch in active distribution networks (ADNs) to facilitate integration of distributed renewable generation. Due to unavailability of network topology and line impedance in many distribution networks, physical model-based methods may not be applicable to their operations. To tackle this challenge, some studies have proposed constraint learning, which replicates physical models by training a neural network to evaluate feasibility of a decision (i.e., whether a decision satisfies all critical constraints or not). To ensure accuracy of this trained neural network, training set should contain sufficient feasible and infeasible samples. However, since ADNs are mostly operated in a normal status, only very few historical samples are infeasible. Thus, the historical dataset is highly imbalanced, which poses a significant obstacle to neural network training. To address this issue, we propose an enhanced constraint learning method. First, it leverages constraint learning to train a neural network as surrogate of ADN's model. Then, it introduces Synthetic Minority Oversampling Technique to generate infeasible samples to mitigate imbalance of historical dataset. By incorporating historical and synthetic samples into the training set, we can significantly improve accuracy of neural network. Furthermore, we establish a trust region to constrain and thereafter enhance reliability of the solution. Simulations confirm the benefits of the proposed method in achieving desirable optimality and feasibility while maintaining low computational complexity.","PeriodicalId":10729,"journal":{"name":"CSEE Journal of Power and Energy Systems","volume":null,"pages":null},"PeriodicalIF":6.9000,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10375977","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CSEE Journal of Power and Energy Systems","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10375977/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
Abstract
Transition towards carbon-neutral power systems has necessitated optimization of power dispatch in active distribution networks (ADNs) to facilitate integration of distributed renewable generation. Due to unavailability of network topology and line impedance in many distribution networks, physical model-based methods may not be applicable to their operations. To tackle this challenge, some studies have proposed constraint learning, which replicates physical models by training a neural network to evaluate feasibility of a decision (i.e., whether a decision satisfies all critical constraints or not). To ensure accuracy of this trained neural network, training set should contain sufficient feasible and infeasible samples. However, since ADNs are mostly operated in a normal status, only very few historical samples are infeasible. Thus, the historical dataset is highly imbalanced, which poses a significant obstacle to neural network training. To address this issue, we propose an enhanced constraint learning method. First, it leverages constraint learning to train a neural network as surrogate of ADN's model. Then, it introduces Synthetic Minority Oversampling Technique to generate infeasible samples to mitigate imbalance of historical dataset. By incorporating historical and synthetic samples into the training set, we can significantly improve accuracy of neural network. Furthermore, we establish a trust region to constrain and thereafter enhance reliability of the solution. Simulations confirm the benefits of the proposed method in achieving desirable optimality and feasibility while maintaining low computational complexity.
期刊介绍:
The CSEE Journal of Power and Energy Systems (JPES) is an international bimonthly journal published by the Chinese Society for Electrical Engineering (CSEE) in collaboration with CEPRI (China Electric Power Research Institute) and IEEE (The Institute of Electrical and Electronics Engineers) Inc. Indexed by SCI, Scopus, INSPEC, CSAD (Chinese Science Abstracts Database), DOAJ, and ProQuest, it serves as a platform for reporting cutting-edge theories, methods, technologies, and applications shaping the development of power systems in energy transition. The journal offers authors an international platform to enhance the reach and impact of their contributions.