基于强化学习的微电网能源调度策略及优化

doi:10.13190/j.jbupt.2019-040

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (1): 28-34.doi: 10.13190/j.jbupt.2019-040

基于强化学习的微电网能源调度策略及优化

刘金华¹, 柯钟鸣^1,2, 周文辉¹

1. 电子科技大学中山学院, 中山 528402;
2. 电子科技大学自动化工程学院, 成都 611731

收稿日期:2019-03-18 出版日期:2020-02-28 发布日期:2020-03-27
作者简介:刘金华(1982-),女,副教授,E-mail:29565575@qq.com.
基金资助:
国家自然科学基金项目（61773126）

Reinforcement Learning Based Energy Dispatch Strategy and Control Optimization of Microgrid

LIU Jin-hua¹, KE Zhong-ming^1,2, ZHOU Wen-hui¹

1. Zhongshan Institute, University of Electronic Science and Technology of China, Zhongshan 528402, China;
2. School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China

Received:2019-03-18 Online:2020-02-28 Published:2020-03-27
Supported by:

摘要/Abstract

摘要： 针对微电网中能源调度的经济效益、充电效率优化、系统负荷波动以及碳排放问题，提出将强化学习运用到微电网调度中，通过建立一个完整的微电网模型，使强化学习在不断迭代过程中得到最优策略，同时达到经济效益趋向最大化、充电功率相对稳定、系统负荷波动减少、碳排放量达到最小化这4个联合优化目标.仿真结果表明，采用的控制策略既能很好地实现经济效益最大化收敛、碳排放量最小化收敛，同时又能使得充电功率相对稳定，微电网的负荷也能减少，极大地提高了系统的稳定性.

关键词: 微电网, 经济效益, 系统优化, 碳排放, 强化学习

Abstract: Aiming at the economic benefit problem, charging efficiency optimization problem, system load fluctuation problem and carbon emissions problem of energy scheduling in microgrid, application of reinforcement learning to energy scheduling in microgrid is presented. By establishing a complete microgrid model and using reinforcement learning to obtain the optimal strategy in the continuous iterative process, economic benefits tended to be maximized, charging power is relatively stable, load fluctuation of the system is reduced, and carbon emissions is tended minimized. These four joint optimization objectives are reached. Simulations show that the control strategy used in this system can not only maximize the convergence of economic benefits and minimize carbon emissions, but also make the charging power relatively stable, and reduce the load of microgrid. The stability of this system will be improved greatly.

Key words: microgrid, economic benefits, system optimization, carbon emissions, reinforcement learning

中图分类号:

TP273

刘金华, 柯钟鸣, 周文辉. 基于强化学习的微电网能源调度策略及优化[J]. 北京邮电大学学报, 2020, 43(1): 28-34.

LIU Jin-hua, KE Zhong-ming, ZHOU Wen-hui. Reinforcement Learning Based Energy Dispatch Strategy and Control Optimization of Microgrid[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(1): 28-34.

参考文献

[1] 郑漳华, 艾芊. 微电网的研究现状及在我国的应用前景[J]. 电网技术, 2008, 32(16):27-31. Zheng Zhanghua, Ai Qian. Research status and application prospect of micro power grid in China[J]. Power Grid Technology, 2008, 32(16):27-31.
[2] 王成山, 李鹏. 分布式发电、微网与智能配电网的发展与挑战[J]. 电力系统自动化, 2010, 34(2):10-14. Wang Chengshan, Li Peng. Development and challenges of distributed generation, micro grid and intelligent distribution network[J]. Power System Automation, 2010, 34(2):10-14.
[3] 鞠平, 周孝信, 陈维江, 等. "智能电网+"研究综述[J]. 电力自动化设备, 2018, 38(5):2-11. Ju Ping, Zhou Xiaoxin, Chen Weijiang, et al. Research review of "smart grid +"[J]. Electric Power Automation Equipment, 2018, 38(5):2-11.
[4] 张素香. 智能小区的商业智能[J]. 北京邮电大学学报, 2012, 35(5):94-97. Zhang Suxiang. Business intelligence of intelligent community[J]. Journal of Beijing University of Posts and Telecommunications, 2012, 35(5):94-97.
[5] Thomas Strasser, Filip Andrén, Johannes Kathan, et al. A review of architectures and concepts for intelligence in future electric energy systems[J]. IEEE Transactions on Industrial Electronics, 2015, 62(4):2424-2438.
[6] Roberts B. Capturing grid power[J]. IEEE Power and Energy Magazine, 2009, 7(4):32-41.
[7] 徐丰. 微电网建模及其控制策略研究[D]. 南京:南京理工大学, 2013.
[8] 周围, 韩礼冬, 李钢, 等. 基于PSCAD/EMTDC的微电网永磁直驱风力发电系统建模与仿真研究[J]. 电气技术, 2016, 17(2):52-57. Zhou Wei, Han Lidong, Li Gang, et al. Modeling and simulation of PSCAD/EMTDC based micro grid permanent magnet direct drive wind power generation system[J]. Electrical Technology, 2016, 17(2):52-57.
[9] 刘国静, 韩学山, 王尚, 等. 基于强化学习方法的风储合作决策[J]. 电网技术, 2016, 40(9):2729-2736. Liu Guojing, Han Xueshan, Wang Shang, et al. Wind storage cooperative decision-making based on reinforcement learning[J]. Power Grid Technology, 2016, 40(9):2729-2736.
[10] 钟伟锋. 智能电网中V2G系统能量管理及应用研究[D]. 广东:广东工业大学, 2016.
[11] 周文辉, 钟伟锋, 吴杰, 等. 面向智能电网负荷调节的自适应储能系统控制[J]. 北京邮电大学学报, 2017, 40(1):32-35. Zhou Wenhui, Zhong Weifeng, Wu Jie, et al. Adaptive energy storage system control for smart grid load regulation[J]. Journal of Beijing University of Posts and Telecommunications, 2017, 40(1):32-35.
[12] Wei C, Zhang Z, Qiao W, et al. An adaptive network-based reinforcement learning method for MPPT control of PMSG wind energy conversion systems[J]. IEEE Transactions on Power Electronics, 2016, 31(11):7837-7848.
[13] Etemad S, Mozayani N. Using reinforcement learning to make smart energy storage sources in microgrid[C]//2015 30th International Power System Conference (PSC). Tehran:[s. n.], 2015:345-350.
[14] Wu Jingda, He Hongwen, Peng Jiankun, et al. Continuous reinforcement Jingda learning of energy management with deep Q network for a power split hybrid electric bus[J]. Applied Energy, 2018, 222(15):799-811.

[1]	刘阳, 滕颖蕾, 牛涛, 郅佳琳. 基于深度强化学习的滤波器剪枝方案[J]. 北京邮电大学学报, 2023, 46(3): 31-36.
[2]	谭炜骞, 吴斌伟, 汪硕. 确定性网络跨域传输架构与DRL流量调度算法[J]. 北京邮电大学学报, 2023, 46(3): 37-42.
[3]	杨华, 耿烜, 孔宁. 一种采用dueling-DDQN算法的无线网络MAC协议[J]. 北京邮电大学学报, 2023, 46(3): 25-30.
[4]	公雨魏翼飞. 一种集成学习辅助DDPG的资源优化算法[J]. 北京邮电大学学报, 2023, 46(2): 29-36.
[5]	孙国玮许方敏朱瑾瑜张恒升赵成林. 算力网络中的确定性调度与路由联合智能优化方案[J]. 北京邮电大学学报, 2023, 46(2): 9-14.
[6]	郭兴康孙君. 基于交替方向乘子法与深度强化学习算法的资源分配[J]. 北京邮电大学学报, 2022, 45(6): 126-130.
[7]	郭令奇褚智贤廖建新王敬宇陆璐. 意图驱动的自智网络资源按需服务[J]. 北京邮电大学学报, 2022, 45(6): 85-91.
[8]	陈峻磊刘凯俊董辰周虹媛. 一种基于无线网络场景的自适应比特率算法模型[J]. 北京邮电大学学报, 2022, 45(5): 115-120.
[9]	郅佳琳, 王楠, 满毅, 滕颖蕾. 面向硬件感知的边缘计算卸载和资源分配[J]. 北京邮电大学学报, 2022, 45(2): 22-28.
[10]	杜梅, 周军华, 李敦桥, 陈士钊, 魏翼飞. MEC计算卸载与资源分配联合智能优化方案[J]. 北京邮电大学学报, 2022, 45(2): 65-71.
[11]	杨灿, 罗涛, 刘颖, 李泽旭, 徐永庆. 面向QoS需求的分簇自组织网络路由算法[J]. 北京邮电大学学报, 2022, 45(1): 1-6.
[12]	黄浩, 胡智群, 王鲁晗, 路兆铭, 温向明. 基于Sumtree DDPG的智能交通信号控制算法[J]. 北京邮电大学学报, 2021, 44(1): 97-103.
[13]	管婉青, 张海君, 路兆铭. 基于DRL的6G多租户网络切片智能资源分配算法[J]. 北京邮电大学学报, 2020, 43(6): 132-139.
[14]	马庆刘, 喻鹏, 吴佳慧, 熊翱, 颜拥. 基于深度强化学习的综合能源业务通道优化机制[J]. 北京邮电大学学报, 2020, 43(2): 87-93.
[15]	程超, 滕俊杰, 赵艳领, 宋梅. 一种基于多智能体强化学习的流量分配算法[J]. 北京邮电大学学报, 2019, 42(6): 43-48,57.

基于强化学习的微电网能源调度策略及优化

Reinforcement Learning Based Energy Dispatch Strategy and Control Optimization of Microgrid

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价