基于深度强化学习的多能流楼宇低碳调度方法A low-carbon scheduling method for multi-energy flow buildings based on deep reinforcement learning
胥栋,李逸超,李赟,徐刚,杜佳玮
XU Dong,LI Yichao,LI Yun,XU Gang,DU Jiawei
摘要(Abstract):
建筑减排已成为中国达到“双碳”目标的重要途径,智慧楼宇作为多能流网络耦合的综合能源主体,面临碳排放量较多、多能流网络耦合程度高、负荷用能行为动态特性明显等问题。针对这一问题,提出基于深度强化学习的多能流楼宇低碳调度方法。首先,根据智慧楼宇的实际碳排放量,建立了一种奖惩阶梯型碳排放权交易机制。其次,面向碳市场和多能流耦合网络,以最小化运行成本为目标函数,建立多能流低碳楼宇调度模型,并将该调度问题转换为马尔可夫决策过程。然后,利用Rainbow算法进行优化调度问题的求解。最后,通过仿真分析验证了优化调度模型的可行性及有效性。
Building emissions reduction has become a crucial pathway for China to achieve its 'dual-carbon' goals.As an integrated energy entity coupled with multi-energy flow networks, smart buildings face challenges such as high carbon emissions, a high degree of coupling in multi-energy flow networks, and distinct dynamic characteristics in load energy consumption behavior. In response to these challenges, a low-carbon scheduling method for multienergy flow buildings based on deep reinforcement learning(deep RL) is proposed. Firstly, a reward and punishment ladder-type carbon emissions trading mechanism is established based on the actual carbon emissions of smart buildings. Secondly, targeting the carbon market and multi-energy flow coupling networks, a low-carbon scheduling model for multi-energy flow buildings is developed, aiming to minimize operating costs as the objective function, and the scheduling is transformed into a Markov decision process(MDP). Subsequently, the Rainbow algorithm is employed to solve the optimal scheduling. Finally, the feasibility and effectiveness of the optimal scheduling model are verified through simulation analysis.
关键词(KeyWords):
“双碳”目标;多能流;低碳调度;深度强化学习
'dual-carbon' goals;multi-energy flow;low-carbon scheduling;deep RL
基金项目(Foundation): 国网上海市电力公司浦东供电公司营销项目(640921220001)
作者(Author):
胥栋,李逸超,李赟,徐刚,杜佳玮
XU Dong,LI Yichao,LI Yun,XU Gang,DU Jiawei
DOI: 10.19585/j.zjdl.202402014
参考文献(References):
- [1]周孝信,陈树勇,鲁宗相,等.能源转型中我国新一代电力系统的技术特征[J].中国电机工程学报,2018,38(7):1893-1904.ZHOU Xiaoxin,CHEN Shuyong,LU Zongxiang,et al.Technology features of the new generation power system in China[J].Proceedings of the CSEE,2018,38(7):1893-1904.
- [2]卢治霖,刘明波,尚楠,等.考虑碳排放权交易市场影响的日前电力市场两阶段出清模型[J].电力系统自动化,2022,46(10):159-170.LU Zhilin,LIU Mingbo,SHANG Nan,et al. Two-stage clearing model for day-ahead electricity market considering impact of carbon emissions trading market[J].Automation of Electric Power Systems,2022,46(10):159-170.
- [3]曹丽霞.计及多元储能的楼宇综合能源系统优化调度[D].北京:华北电力大学,2022.CAO Lixia.Optimal scheduling of building integrated energy system considering multi-energy storage[D].Beijing:North China Electric Power University,2022.
- [4]张雪纯,高广玲,张智晟,等.基于需求响应的建筑楼宇综合能源系统优化调度[J].电力需求侧管理,2019,21(4):28-34.ZHANG Xuechun,GAO Guangling,ZHANG Zhisheng,et al.Optimal scheduling of building integrated energy system based on demand response[J]. Power Demand Side Management,2019,21(4):28-34.
- [5]张宇桐.考虑楼宇不同供热模式的区域电-热综合能源系统分布式协调优化调度[D].吉林:东北电力大学,2022.ZHANG Yutong.Distributed coordinated optimal scheduling of district electric-heat integrated energy system considering different heating modes of buildings[D]. Jilin:Northeast Dianli University,2022.
- [6]余苏敏,杜洋,史一炜,等.考虑V2B智慧充电桩群的低碳楼宇优化调度[J].电力自动化设备,2021,41(9):95-101.YU Sumin,DU Yang,SHI Yiwei,et al.Optimal scheduling of low-carbon building considering V2B smart charging pile groups[J].Electric Power Automation Equipment,2021,41(9):95-101.
- [7]范宏,于伟南,柳璐,等.双碳目标下考虑电氢互补的智慧园区多楼宇协调调度[J].电力系统自动化,2022,46(21):42-51.FAN Hong,YU Weinan,LIU Lu,et al.Multi-building coordinated dispatch in smart park for carbon emission peak and carbon neutrality considering electricity and hydrogen complementary[J]. Automation of Electric Power Systems,2022,46(21):42-51.
- [8]孙国强,陈晓东,周亦洲,等.基于分布鲁棒机会约束的多类型楼宇电-碳联合分布式交易方法[J].电网技术,2023,47(8):3078-3089.SUN Guoqiang,CHEN Xiaodong,ZHOU Yizhou,et al.Electricity-carbon joint distributed trading for multi-type buildings based on distributional robust chance constraint[J].Power System Technology,2023,47(8):3078-3089.
- [9]袁桂丽,贾新潮,陈少梁,等.虚拟电厂源-荷协调多目标优化调度[J].太阳能学报,2021,42(5):105-112.YUAN Guili,JIA Xinchao,CHEN Shaoliang,et al.Multiobjective optimal dispatch considering source-load coordination for virtual power plant[J].Acta Energiae Solaris Sinica,2021,42(5):105-112.
- [10]CUI S C,WANG Y W,SHI Y,et al.A new and fair peerto-peer energy sharing framework for energy buildings[J].IEEE Transactions on Smart Grid,2020,11(5):3817-3826.
- [11]杨昭,艾欣.考虑电能共享的综合能源楼宇群分布式优化调度[J].电网技术,2020,44(10):3769-3778.YANG Zhao,AI Xin. Distributed optimal scheduling for integrated energy building clusters considering energy sharing[J].Power System Technology,2020,44(10):3769-3778.
- [12]黄炳强.强化学习方法及其应用研究[D].上海:上海交通大学,2007.HUANG Bingqiang.Research on the reinforcement learning method and its application[D]. Shanghai:Shanghai Jiao Tong University,2007.
- [13]王统.基于强化学习的智能楼宇群能量优化方法[D].北京:华北电力大学,2021.WANG Tong. A reinforcement learning-based approach for energy optimization of smart building clusters[D].Beijing:North China Electric Power University,2021.
- [14]于一潇,杨佳峻,杨明,等.基于深度强化学习的风电场储能系统预测决策一体化调度[J].电力系统自动化,2021,45(1):132-140.YU Yixiao,YANG Jiajun,YANG Ming,et al.Prediction and decision integrated scheduling of energy storage system in wind farm based on deep reinforcement learning[J].Automation of Electric Power Systems,2021,45(1):132-140.
- [15]黄刚.中国转型升级背景下的碳配额分配机制构建思路研究[J].世界环境,2019(2):50-52.HUANG Gang. Research on the construction of carbon quota allocation mechanism under the background of China’s transformation and upgrading[J].World Environment,2019(2):50-52.
- [16]田晓丽,侯忠男.浅议我国碳排放权初始配额分配机制[J].时代金融,2022(6):76-78.TIAN Xiaoli,HOU Zhongnan.On the initial quota allocation mechanism of carbon emission rights in China[J].Times Finance,2022(6):76-78.
- [17]张潇,邵鑫潇,蒋惠琴.行业碳排放权的初始配额分配:文献综述[J].资源开发与市场,2018,34(11):1520-1525.ZHANG Xiao,SHAO Xinxiao,JIANG Huiqin.Initial allocation of carbon emission rights in the industry—literature review[J]. Resource Development&Market,2018,34(11):1520-1525.
- [18]GU Y R,HUANG X L. A reactive power optimization partially observable Markov decision process with data uncertainty using multi-agent actor-attention-critic algorithm[J]. International Journal of Electrical Power&Energy Systems,2023,147:108848.
- [19]陈柏翰,冯伟,孙凯,等.冷热电联供系统多元储能及孤岛运行优化调度方法[J].电工技术学报,2019,34(15):3231-3243.CHEN Pohan,FENG Wei,SUN Kai,et al.Multi-energy storage system and islanded optimal dispatch method of CCHP[J]. Transactions Of China Electrotechnical Society,2019,34(15):3231-3243.
- [20]邱彬,宋绍鑫,王凯,等.计及需求响应和阶梯型碳交易机制的区域综合能源系统优化运行[J].电力系统及其自动化学报,2022,34(5):87-95.QIU Bin,SONG Shaoxin,WANG Kai,et al.Optimal operation of regional integrated energy system considering demand response and ladder-type carbon trading mechanism[J]. Proceedings of the CSU-EPSA,2022,34(5):87-95.