信息–物理–社会融合的智慧能源调度机器人及其知识自动化:框架、技术与挑战
|
摘要
着眼于能源5.0前瞻性基础理论,重点研究基于信息–物理–社会融合系统(cyber-physical-social systems,CPSS)的智慧能源调度机器人(robot of energy control,Robo EC)群体及其知识自动化的关键理论方法。包括:构建面向下一代能源电力系统的平行CPSS理想框架及工程可行性框架体系;提出基于数据驱动及自校正引导方法的新型高精度镜像计算实验方法,实现镜像系统对真实物理系统的趋优引导;研究面向未来能源电力系统集中/分散调度模式下的知识自动化流程和平行机器学习方法,实现Robo EC群体的知识自我探索和群体智慧水平的自动提升;探讨平行系统与真实系统的交互协调收敛数学机理及实现CPSS大闭环的系统化设计方法,获得能源、信息、社会三者的深度融合方法和系统化工程设计方法。在后续研究过程中,不断完善基于平行CPSS架构的Robo EC研究平台,并提出可最终尝试将Robo EC投入到小规模实际工程进行运行测试。最后,分析了其面临的挑战,为中国在"能源4.0"到"能源5.0"的技术发展之路上先行一步提供借鉴和思考。
This paper attempts on systematically developing the key theories of Energy 5.0 based on smart energy robot dispatcher Robo EC, in which the Robo ECs based on cyber-physical-social systems(CPSS) and its knowledge automation technologies are thoroughly investigated. First, the ideal framework and engineering feasible framework systems of parallel CPSS facing to next generation of energy and electric power systems(EEPS) are constructed. In addition, novel high-precision mirrored computational experiment approaches are proposed based on data-driven and self-correction mechanisms, thus an optimal approximation from mirrored system to the real physical system can be achieved. Moreover, knowledge automation and parallel machine learning are comprehensively studied for centralized/decentralized dispatch of future EEPS, which can effectively achieve a knowledge self-exploration for Robo ECs as well as significantly enhance their swarm intelligence. Besides, the convergence property between the coordinated parallel system and real system is discussed in depth, together with design of global closed-loop CPSS, so that a highly incorporated and systematic engineering design of energy, information and society can be realized. Lastly, a small-scale experiment project is proposed for testing the engineering feasibility of theoretical results with ambitious aims of China to make the substantial scientific progress from Energy 4.0 to Energy 5.0.
This paper attempts on systematically developing the key theories of Energy 5.0 based on smart energy robot dispatcher Robo EC, in which the Robo ECs based on cyber-physical-social systems(CPSS) and its knowledge automation technologies are thoroughly investigated. First, the ideal framework and engineering feasible framework systems of parallel CPSS facing to next generation of energy and electric power systems(EEPS) are constructed. In addition, novel high-precision mirrored computational experiment approaches are proposed based on data-driven and self-correction mechanisms, thus an optimal approximation from mirrored system to the real physical system can be achieved. Moreover, knowledge automation and parallel machine learning are comprehensively studied for centralized/decentralized dispatch of future EEPS, which can effectively achieve a knowledge self-exploration for Robo ECs as well as significantly enhance their swarm intelligence. Besides, the convergence property between the coordinated parallel system and real system is discussed in depth, together with design of global closed-loop CPSS, so that a highly incorporated and systematic engineering design of energy, information and society can be realized. Lastly, a small-scale experiment project is proposed for testing the engineering feasibility of theoretical results with ambitious aims of China to make the substantial scientific progress from Energy 4.0 to Energy 5.0.
引文
[1]邓建玲,王飞跃,陈耀斌,等.从工业4.0到能源5.0:智能能源系统的概念、内涵及体系框架[J].自动化学报,2015,41(12):2003-2016.Deng Jianling,Wang Feiyue,Chen Yaowu,et al.From industries 4.0 to energy 5.0:Concept and framework of intelligent energy systems[J].Acta Automatica Sinica,2015,41(12):2003-2016(in Chinese).
[2]管晓宏,赵千川,贾庆山,等.信息物理融合能源系统[M].北京:科学出版社,2015.
[3]王飞跃.软件定义的系统与知识自动化:从牛顿到默顿的平行升华[J].自动化学报,2016,41(1):1-7.Wang Feiyue.Software-based systems and knowledge automation:a parallel paradigm shift from Newton to Merton[J].Acta Automatica Sinica,2016,41(1):1-7(in Chinese).
[4]Wang F Y.The emergence of intelligent enterprises:From CPS to CPSS[J].IEEE Intelligent Systems,2010,25(4):85-88.
[5]杨胜春,汤必强,姚建国,等.基于态势感知的电网自动智能调度架构及关键技术[J].电网技术,2014,38(1):33-39.Yang Shengchun,Tang Bijia,Yao Jianguo,et al.Architecture and key technologies for situational awareness based automatic intelligent dispatching of power grid[J].Power System Technology,2014,38(1):33-39(in Chinese).
[6]Dy-Liacco T E.Enhancing power system security control[J].Computer Applications in Power IEEE,1997,10(3):38-41.
[7]卢强,戚晓耀,何光宇.智能电网与智能广域机器人[J].中国电机工程学报,2011,31(10):1-5.Lu Qiang,Qi Xiaoyao,He Guangyu,et al.Smart grid and smart wide area robot[J].Proceedings of the CSEE,2011,31(10):1-5(in Chinese).
[8]钱学森,于景元,戴汝为.一个科学的新领域:开放的复杂巨系统及其方法论[J].自然杂志,1990,13(1):3-10.Qian Xuesen,Yu Jingyuan,Dai Ruwei.A new field of science:An open and complex giant system and its methodology[J].Chinese Journal of Nature,1990,13(1):3-10(in Chinese).
[9]郑南宁.人工智能面临的挑战[J].自动化学报,2016,42(5):641-642.Zheng Nanning.The challenges of artificial intelligence[J].Acta Automatica Sinica,2016,42(5):641-642(in Chinese).
[10]Mnih V,Kavukcuoglu K,Silver D,et al.Human-level control through deep reinforcement learning[J].Nature,2015,518(7540):529-533.
[11]Silver D,Huang A,Maddison C,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529(7587):484-489.
[12]李力,林懿伦,曹东璞,等.平行学习--机器学习的一个新型理论框架[J].自动化学报,2017,43(1):1-8.Li Li,Lin Yilun,Cao Dongpu,et al.Parallel learninga new framework for machine learning[J].Acta Automatica Sinica,2017,43(1):1-8(in Chinese).
[13]Wiering M,van Otterlo M.Reinforcement learning:State-of-the-art[M].Berlin Heidelberg:Springer,2012.
[14]Yu T,Zhou B,Chan K W,et al.Stochastic optimal relaxed automatic generation control in non-markov environment based on multi-step Q(λ)learning[J].IEEE Transactions on Power Systems,2011,26(3):1272-1282.
[15]Tang Y,He H,Wen J,et al.Power system stability control for a wind farm based on adaptive dynamic programming[J].IEEE Transactions on Smart Grid,2015,6(1):166-177.
[16]杨佩,蔡皓,裘洪彬,等.面向能源互联网的大数据关键技术研究[J].电力信息与通信技术,2016,14(4):9-12.Yang Pei,Cai Hao,Qiu Hongbin,et al.Research on key technologies of big data for energy interconnection[J].Electric Power Information and Communication Technology,2016,14(4):9-12(in Chinese).
[17]Bevrani H,Hiyama T.Intelligent automatic generation control[M].Florida:CRC Press,2011.
[18]O'Brien T,Steven A P.PJM Advanced Control Center-a service oriented architecture[C].In:2008 IEEE Power and Energy Society General Meeting-Conversion and Delivery of Electrical Energy in the 21st Century,20-24July 2008,Pittsburgh,PA,USA:1-2.
[19]王伟亮,王丹,贾宏杰,等.能源互联网背景下的典型区域综合能源系统稳态分析研究综述[J].中国电机工程学报,2016,36(12):3292-3304.Wang Weiliang,Wang Dan,Jia Hongjie,et al.Review of steady-state analysis of typical regional integrated energy system under the background of energy Internet[J].Proceedings of the CSEE,2016,36(12):3292-3304(in Chinese).
[20]孙秋野,滕菲,张化光,等.能源互联网动态协调优化控制体系构建[J].中国电机工程学报,2015,35(14):3667-3677.Sun Qiuye,Teng Fei,Zhang Huaguang,et al.Construction of dynamic coordinated optimization control system for energy Internet[J].Proceedings of the CSEE,2015,35(14):3667-3677(in Chinese).
[21]孙宏斌,潘昭光,郭庆来.多能流能量管理研究:挑战与展望[J].电力系统自动化,2016,40(15):1-7.Sun Hongbin,Pan Zhaoguang,Guo Qinglai.Energy management for multi-energy flow:Challenges and prospects[J].Automation of Electric Power Systems,2016,40(15):1-7(in Chinese).
[22]王飞跃,刘德荣,熊刚,等.复杂系统的平行控制理论及应用[J].复杂系统与复杂性科学,2012,9(3):1-12.Wang Feiyue,Liu Derong,Xiong Gang,et al.Parallel control theory of complex systems and applications[J].Complex Systems and Complexity Science,2012,9(3):1-12(in Chinese).
[23]张孝顺,李清,余涛,等.基于协同一致性迁移Q学习算法的虚拟发电部落AGC功率动态分配[J].中国电机工程学报,2017,37(5):1455-1466.Zhang Xiaoshun,Li Qing,Yu Tao,et al.Collaborative consensus transfer-Q learning based dynamic generation dispatch of automatic generation control with virtual generation tribe[J].Proceedings of the CSEE,2017,37(5):1455-1466(in Chinese).
[24]梅生伟,刘峰,魏韡.工程博弈论基础及电力系统应用[M].北京:科学出版社,2016.
[25]徐俊明.图论及其应用(第三版)[M].合肥:中国科学技术大学出版社,2008.
[26]张东霞,邱才明,王晓蓉,等.全球能源互联网中的大数据应用研究[J].电力信息与通信技术,2016,14(3):20-24.Zhang Dong-xia,Qiu Cai-ming,Wang Xiao-rong,et al.Research on big data application in global energy interconnection[J].Electric Power Information and Communication Technology,2016,14(3):20-24.
[27]陈冲,吴越.基于能源互联和“互联网+”理念的智慧园区2.0的研究[J].电力信息与通信技术,2016,14(4):22-26.Chen Chong,Wu Yue.Study on smart park 2.0 based on the concept of energy interconnection and“internet+”[J].Electric Power Information and Communication Technology,2016,14(4):22-26(in Chinese).
[2]管晓宏,赵千川,贾庆山,等.信息物理融合能源系统[M].北京:科学出版社,2015.
[3]王飞跃.软件定义的系统与知识自动化:从牛顿到默顿的平行升华[J].自动化学报,2016,41(1):1-7.Wang Feiyue.Software-based systems and knowledge automation:a parallel paradigm shift from Newton to Merton[J].Acta Automatica Sinica,2016,41(1):1-7(in Chinese).
[4]Wang F Y.The emergence of intelligent enterprises:From CPS to CPSS[J].IEEE Intelligent Systems,2010,25(4):85-88.
[5]杨胜春,汤必强,姚建国,等.基于态势感知的电网自动智能调度架构及关键技术[J].电网技术,2014,38(1):33-39.Yang Shengchun,Tang Bijia,Yao Jianguo,et al.Architecture and key technologies for situational awareness based automatic intelligent dispatching of power grid[J].Power System Technology,2014,38(1):33-39(in Chinese).
[6]Dy-Liacco T E.Enhancing power system security control[J].Computer Applications in Power IEEE,1997,10(3):38-41.
[7]卢强,戚晓耀,何光宇.智能电网与智能广域机器人[J].中国电机工程学报,2011,31(10):1-5.Lu Qiang,Qi Xiaoyao,He Guangyu,et al.Smart grid and smart wide area robot[J].Proceedings of the CSEE,2011,31(10):1-5(in Chinese).
[8]钱学森,于景元,戴汝为.一个科学的新领域:开放的复杂巨系统及其方法论[J].自然杂志,1990,13(1):3-10.Qian Xuesen,Yu Jingyuan,Dai Ruwei.A new field of science:An open and complex giant system and its methodology[J].Chinese Journal of Nature,1990,13(1):3-10(in Chinese).
[9]郑南宁.人工智能面临的挑战[J].自动化学报,2016,42(5):641-642.Zheng Nanning.The challenges of artificial intelligence[J].Acta Automatica Sinica,2016,42(5):641-642(in Chinese).
[10]Mnih V,Kavukcuoglu K,Silver D,et al.Human-level control through deep reinforcement learning[J].Nature,2015,518(7540):529-533.
[11]Silver D,Huang A,Maddison C,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529(7587):484-489.
[12]李力,林懿伦,曹东璞,等.平行学习--机器学习的一个新型理论框架[J].自动化学报,2017,43(1):1-8.Li Li,Lin Yilun,Cao Dongpu,et al.Parallel learninga new framework for machine learning[J].Acta Automatica Sinica,2017,43(1):1-8(in Chinese).
[13]Wiering M,van Otterlo M.Reinforcement learning:State-of-the-art[M].Berlin Heidelberg:Springer,2012.
[14]Yu T,Zhou B,Chan K W,et al.Stochastic optimal relaxed automatic generation control in non-markov environment based on multi-step Q(λ)learning[J].IEEE Transactions on Power Systems,2011,26(3):1272-1282.
[15]Tang Y,He H,Wen J,et al.Power system stability control for a wind farm based on adaptive dynamic programming[J].IEEE Transactions on Smart Grid,2015,6(1):166-177.
[16]杨佩,蔡皓,裘洪彬,等.面向能源互联网的大数据关键技术研究[J].电力信息与通信技术,2016,14(4):9-12.Yang Pei,Cai Hao,Qiu Hongbin,et al.Research on key technologies of big data for energy interconnection[J].Electric Power Information and Communication Technology,2016,14(4):9-12(in Chinese).
[17]Bevrani H,Hiyama T.Intelligent automatic generation control[M].Florida:CRC Press,2011.
[18]O'Brien T,Steven A P.PJM Advanced Control Center-a service oriented architecture[C].In:2008 IEEE Power and Energy Society General Meeting-Conversion and Delivery of Electrical Energy in the 21st Century,20-24July 2008,Pittsburgh,PA,USA:1-2.
[19]王伟亮,王丹,贾宏杰,等.能源互联网背景下的典型区域综合能源系统稳态分析研究综述[J].中国电机工程学报,2016,36(12):3292-3304.Wang Weiliang,Wang Dan,Jia Hongjie,et al.Review of steady-state analysis of typical regional integrated energy system under the background of energy Internet[J].Proceedings of the CSEE,2016,36(12):3292-3304(in Chinese).
[20]孙秋野,滕菲,张化光,等.能源互联网动态协调优化控制体系构建[J].中国电机工程学报,2015,35(14):3667-3677.Sun Qiuye,Teng Fei,Zhang Huaguang,et al.Construction of dynamic coordinated optimization control system for energy Internet[J].Proceedings of the CSEE,2015,35(14):3667-3677(in Chinese).
[21]孙宏斌,潘昭光,郭庆来.多能流能量管理研究:挑战与展望[J].电力系统自动化,2016,40(15):1-7.Sun Hongbin,Pan Zhaoguang,Guo Qinglai.Energy management for multi-energy flow:Challenges and prospects[J].Automation of Electric Power Systems,2016,40(15):1-7(in Chinese).
[22]王飞跃,刘德荣,熊刚,等.复杂系统的平行控制理论及应用[J].复杂系统与复杂性科学,2012,9(3):1-12.Wang Feiyue,Liu Derong,Xiong Gang,et al.Parallel control theory of complex systems and applications[J].Complex Systems and Complexity Science,2012,9(3):1-12(in Chinese).
[23]张孝顺,李清,余涛,等.基于协同一致性迁移Q学习算法的虚拟发电部落AGC功率动态分配[J].中国电机工程学报,2017,37(5):1455-1466.Zhang Xiaoshun,Li Qing,Yu Tao,et al.Collaborative consensus transfer-Q learning based dynamic generation dispatch of automatic generation control with virtual generation tribe[J].Proceedings of the CSEE,2017,37(5):1455-1466(in Chinese).
[24]梅生伟,刘峰,魏韡.工程博弈论基础及电力系统应用[M].北京:科学出版社,2016.
[25]徐俊明.图论及其应用(第三版)[M].合肥:中国科学技术大学出版社,2008.
[26]张东霞,邱才明,王晓蓉,等.全球能源互联网中的大数据应用研究[J].电力信息与通信技术,2016,14(3):20-24.Zhang Dong-xia,Qiu Cai-ming,Wang Xiao-rong,et al.Research on big data application in global energy interconnection[J].Electric Power Information and Communication Technology,2016,14(3):20-24.
[27]陈冲,吴越.基于能源互联和“互联网+”理念的智慧园区2.0的研究[J].电力信息与通信技术,2016,14(4):22-26.Chen Chong,Wu Yue.Study on smart park 2.0 based on the concept of energy interconnection and“internet+”[J].Electric Power Information and Communication Technology,2016,14(4):22-26(in Chinese).