含制氢装置的机组组合与检修低碳协同优化研究  

Low-carbon collaborative optimization for the commitment and maintenance of units considering hydrogen production equipment

作　　者：郭恒元 冯小峰 李国栋[3] 段志国 李远征[1] GUO Hengyuan;FENG Xiaofeng;LI Guodong;DUAN Zhiguo;LI Yuanzheng(School of Artificial Intelligence and Automation,Huazhong University of Science and Technology,Wuhan 430074,China;Metrology Center of Guangdong Power Grid Corporation,Guangzhou 510080,China;Electric Power Research Institute,State Grid Tianjin Electric Power Company,Tianjin 300384,China;State Grid Hebei Electric Power Company,Shijiazhuang Power Supply Company,Shijiazhuang 050004,China)

机构地区：[1]华中科技大学人工智能与自动化学院,武汉430074 [2]广东电网有限责任公司计量中心,广州510080 [3]国网天津市电力公司电力科学研究院,天津300384 [4]国网河北省电力有限公司石家庄供电分公司,石家庄050004

出　　处：《综合智慧能源》2022年第5期78-87,共10页Integrated Intelligent Energy

基　　金：国家电网公司科技项目(1400-202099523A-0-0-00)。

摘　　要：社会用电量的快速增长给电力系统带来诸多挑战,日益严重的环境问题使得电力部门迫切需要引入清洁能源以及高效的减排措施。考虑了电力需求侧存在制氢设备的情况,探讨了碳排放权交易机制下的月度机组组合与检修多目标协同优化问题。此外,结合深度强化学习理论,灵活控制多目标量子行为粒子群算法中的收缩-扩张参数,提高了算法的寻优效率。在IEEE-118节点系统下的仿真结果显示,改进算法比传统算法求解效果更优;多目标协同优化模型的节点电价稳定性目标超出单目标模型10%左右,系统可靠性目标优于单目标模型30%左右,线路安全裕度目标同样大幅优于单目标模型,充分说明了建立的多目标优化模型能寻找到兼顾多个指标的调度解,确保电力系统安全、稳定和低碳运行。The rapid growth of electricity consumption has brought challenges to power systems and environment deterioration to our society.In order to tackle the problems,it is urgent for power sector to develop clean energy and take efficient emission mitigation measures.Considering the conditions of the hydrogen production equipment on power demand side,discussion on the multi-objective collaborative optimization for the monthly commitment and maintenance of power units under the existent carbon emission trading mechanism is made.By taking the theory of deep reinforcement learning and controlling the contraction-expansion coefficient in multi-objective quantum-behaved particle swarm optimization algorithm flexibly,the optimization efficiency of the algorithm is improved.The simulation results of an IEEE 118-bus system show that the improved algorithm performs better than the traditional algorithm.The stability of the locational marginal price and the reliability of the system calculated by the multi-objective collaborative optimization model exceeds the ones by the single-objective model by about 10%and 30%,respectively,and the line security margin of the former model is significantly better than that of the latter model.These results have proven that the multi-objective optimization model can find a solution for unit scheduling which fully considers multiple objectives,and ensure the safe,stable and lowcarbon operation of the power system.

关 键 词：清洁能源 机组检修 碳排放权 节能减排 多目标优化模型 制氢装置 低碳运行 

分 类 号：TM73[电气工程—电力系统及自动化] TK01[动力工程及工程热物理]