Accelerated solution of the transmission maintenance schedule problem: a Bayesian optimization approach
2021-11-29
【论文推荐】浙江大学 梅竞成等：一种基于贝叶斯优化的输电线路检修优化加速求解方法
文章导读
为了最大限度地满足输电线路运营商的检修意愿，本研究提出了一种输电线路检修方案考虑电力系统网络安全约束和现场检修操作安全约束的检修调度模型。考虑到混合整数规划问题的计算复杂性，本文提出了一种基于机器学习的混合整数规划算法来有效地求解输电检修优化模型。该算法采用贝叶斯优化（BO）方法对分支定界过程中分支打分函数的调节因子值的大小进行优化，具有很好的应用前景。改进版本的IEEE30节点的测试算例用于试验。试验结果表明，该算法不仅能达到最优解，而且能提高系统的性能计算效率。
Accelerated solution of the transmission maintenance schedule problem: a Bayesian optimization approach
一种基于贝叶斯优化的输电线路检修优化加速求解方法
Jingcheng Mei1, Guojiang Zhang2,Donglian Qi1, Jianliang Zhang1
(1.College of Electrical Engineering, Zhejiang University, Hangzhou 310027, P.R. China 2.State grid Jiangsu Electric Power Company Limited, Nanjing, 210024, P.R. China)
一分钟语音讲解 |
Abstract
Keywords
Transmission maintenance scheduling, Mixed integer programming (MIP), Machine learning, Bayesian optimization (BO), Branch-and-bound.
Fig.1 Flowchart of the proposed algorithm
Fig.2Topology of IEEE 30-bus network
Fig.3Progress of BO of the branching score factor value
Fig.4Calculation times for different number of maintenance lines with the default and proposed methods
本文引文信息
Mei J, Zhang G, Qi D, Zhang J (2021) Accelerated solution of the transmission maintenance schedule problem: a Bayesian optimization approach, 4(5): 493-500
梅竞成，张国江，齐冬莲，张建良 (2021) 一种基于贝叶斯优化的输电线路检修优化加速求解方法. 全球能源互联网（英文），4(5): 493-500
Biographies
Jingcheng Mei
Jingcheng Mei was born in JiangSu, China, on May 3,1990. He received an M.S. degree from the College of Electrical Engineering at Wuhan University in 2014. He is currently pursuing a Ph.D. degree at the College of Electrical Engineering, Zhejiang University, Hangzhou, China. His current research interests include machine learning for combinatorial optimization and distributed optimization, with applications to energy/power systems.
Guojiang Zhang
Guojiang Zhang was a senior engineer of the State Grid Jiangsu Electric Power Company Limited. His current research interests include optimization, with applications to energy/ power and power systems.
Donglian Qi
Donglian Qi received his Ph.D. degree in control theory and control engineering from Zhejiang University, Hangzhou, China, in March 2002. Since then, she has been with the College of Electrical Engineering, Zhejiang University, where she is currently a professor. Her current research interests include the basic theory and application of cyber physical power
systems (CPPSs), digital image processing, artificial intelligence, and electric operation and maintenance robots. She is an editor for clean energy, the IET Energy Conversion and Economics, and the Journal of Robotics, Networking, and Artificial Life.
Jianliang Zhang
Jianliang Zhang received his Ph.D. degree in control theory and control engineering from Zhejiang University, Hangzhou, China, in June 2014. Since then, he has been working with the College of Electrical Engineering, Zhejiang University (ZJU). He was a visiting scholar at Hong Kong Polytechnic University (PolyU) (2016–2017). His current research interests
include distributed optimization, with applications to energy/power systems, and cyber-physical security with applications in smart grids.
编辑：王彦博
审核：王 伟
郑重声明
根据国家版权局相关规定，纸媒、网站、微博、微信公众号转载、摘编本网站作品，需包含本网站名称、二维码等关键信息，并在文首注明《全球能源互联网》原创。 个人请按本网站原文转发、分享。
