您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2020, Vol. 50 ›› Issue (4): 90-97.doi: 10.6040/j.issn.1672-3961.0.2019.341

• 电气工程 • 上一篇    

基于学习理论的含光储联合系统的输电网双层规划

孙东磊1,赵龙1,秦敬涛2*,韩学山2,杨明2,王明强2   

  1. 1. 国网山东省电力公司经济技术研究院, 山东 济南 250021;2. 电网智能化调度与控制教育部重点实验室(山东大学), 山东 济南 250061
  • 发布日期:2020-08-13
  • 作者简介:孙东磊(1988— ),男,山东济宁人,博士,高级工程师,主要研究方向为电力系统规划. E-mail:sdusdlei@sina.com. *通信作者简介:秦敬涛(1995— ),男,山东青州人,硕士研究生,主要研究方向为深度强化学习算法在可再生能源消纳中的应用. E-mail:201814272@mail.sdu.edu.cn
  • 基金资助:
    国网山东省电力公司科技资助项目

Bi-level planning of transmission network with solar-storage combination system based on learning theory

SUN Donglei1, ZHAO Long1, QIN Jingtao2*, HAN Xueshan2, YANG Ming2, WANG Mingqiang2   

  1. 1. Economic &
    Technology Research Institute, State Grid Shandong Electric Power Company, Jinan 250021, Shandong, China;
    2. Key Laboratory of Power System Intelligent Dispatch and Control of Ministry of Education(Shandong Uniersity), Jinan 250061, Shandong, China
  • Published:2020-08-13

PDF (PC)

234

摘要： 针对传统输电网规划中对光伏出力不确定性处理中存在的问题,提出一种基于学习理论的含光储联合系统的输电网双层规划模型。下层基于学习理论对光储联合系统进行优化,目标为光伏电站长期运行收益最大与计划功率不确定性最小。将下层优化求解得到的光储联合系统计划功率代入上层的输电网规划模型,以线路投资成本、运行成本和弃光成本最小为目标进行规划。最后用改进的IEEE118节点算例验证了光储联合系统可以减小计划功率的不确定性,提高规划结果的可信度。本研究建立的Q学习控制器具有良好的在线学习能力,通过大量数据的学习后能对光储联合系统的计划出力进行有效的指导。

关键词: 学习理论, Q学习算法, 输电网规划, 光储联合系统, 不确定性

Abstract: In order to address the solar power output uncertainty in transmission network planning, a bi-level planning model of transmission network was proposed in which the solar-storage combination system was modeled by learning theory. In the lower level, the scheduled power of solar-storage combination system submitted to the large power system was optimized by maximizing the long-term profit of the solar-storage combination system and minimizing the uncertainty of the planned power. Substituting the planned power of the solar-storage combination system obtained by the lower layer optimization into the upper transmission network planning model, then we minimized the transmission line investment cost, power system operating cost, and solar-shedding cost. The modified IEEE-118 bus system experimental results verified that the solar-storage combination system could reduce the uncertainty of the planned power and enhanced the credibility of planning result. The Q-learning controller established in this paper had good online learning ability and could effectively guide the planned output of the solar-storage combination system after learning a large amount of data.

Key words: learning theory, Q learning algorithm, planning of transmission network, solar-storage combination system, uncertainty

中图分类号: 

  • TM71
[1] 宋新甫, 戴拥民, 赵志强, 等.全球能源互联电网发展的规划技术框架及研究方向[J].电工技术,2018(9):7-10. SONG Xinfu, DAI Yongmin, ZHAO Zhiqiang, et al. Planning technical framework and research direction of global energy interconnected power grid development[J]. Electric Engineering, 2018(9): 7-10.
[2] 管霖, 陈旭, 吕耀棠, 等. 适用于电网规划的光伏发电概率模型及其应用[J]. 电力自动化设备, 2017, 37(11):1-7. GUAN Lin, CHEN Xu, LYU Yaotang, et al. Probability model of PV generation for power system planning and its application[J]. Electric Power Automatic Equipment, 2017, 37(11): 1-7.
[3] GOMES P V, SARAIVA J T. Transmission system planning considering solar distributed generation penetration[C] //European Energy Market. Dresden, Germany: IEEE, 2017.
[4] 唐一铭, 袁越, 张新松,等. 基于最大投资回报率的风光联合并网情况下输电网规划[J]. 水电能源科学, 2013, 31(10):221-224. TANG Yiming, YUAN Yue, ZHANG Xinsong, et al. Tranmission network planning containing grid-connected wind-PV hybrid system based on maximum return rate of investment[J]. Water Resources and Power, 2013, 31(10): 221-224.
[5] 史智萍, 王智敏, 吴玮坪, 等. 基于态势感知的电网消纳可再生能源发电评估与扩展规划方法[J]. 电网技术, 2017,41(7):2180-2186. SHI Zhiping, WANG Zhimin, WU Weiping, et al. Evaluation of renewable energy intergration capability and network expansion planning based on situation awareness theory[J]. Power System Technology, 2017, 41(7): 2180-2186.
[6] 徐少华,李建林.光储微网系统并网/孤岛运行控制策略[J].中国电机工程学报,2013,33(34):25-33. XU Shaohua, LI Jianlin.Grid-connected/Island operation control strategy for photovoltaic/battery micro-grid[J]. Proceedings of the CSEE, 2013, 33(34):25-33.
[7] 高志强,孟良,梁宾,等. 光储联合发电系统控制策略[J]. 储能科学与技术, 2013, 2(3): 300-306. GAO Zhiqiang, MENG Liang, LIANG Bin, et al. Control strategies for a photovoltaic-energy storage hybrid system[J]. Enengy Storage Science and Technology, 2013, 2(3): 300-306.
[8] 孔令国,蔡国伟,杨德友,等.光储联合并网发电系统建模与协调控制[J].电网技术,2013,37(2):312-318. KONG Lingguo, CAI Guowei, YANG Deyou, et al. Modeling and coordinated control of grid-connected PV generation system with energy storage devices[J].Power System Technology, 2013, 37(2):312-318.
[9] ALAM M J E, MUTTAQI K M, SUTANTO D. Mitigation of rooftop solar PV impacts and evening peak support by managing available capacity of distributed energy storage systems[J]. IEEE Transactions on Power Systems, 2013, 28(4):3874-3884.
[10] 吴小刚,刘宗歧,田立亭,等.独立光伏系统光储容量优化配置方法[J].电网技术,2014,38(5):1271-1276. WU Xiaogang, LIU Zongqi, TIAN Liting, et al. Optimized capacity configuration of photovoltaic generation and energy storage device for stand-alone photovoltaic generation system[J]. Power System Technology, 2014, 38(5):1271-1276.
[11] 翟世涛,刘泽槐,杨家豪,等. 考虑多时段并网点电压控制的光储容量匹配与优化运行[J]. 电网技术, 2017, 41(6): 1855-1865. ZHAI Shitao, LIU Zehuai, YANG Jiahao, et al. Capactity matching and optimal operation of photovoltaic-storage systems based on multi-period PCC voltage control[J]. Power System Technology, 2017, 41(6): 1855-1865.
[12] 余涛,胡细兵,刘靖. 基于多步回溯Q(λ)学习算法的多目标最优潮流计算[J]. 华南理工大学学报(自然科学版), 2010, 38(10): 139-145. YU Tao, HU Xibing, LIU Jing. Multi-objective optimal power flow calculation based on multi-step Q(λ)learning algorithm[J]. Journal of South China University of Technology(Natural Science Edition), 2010, 38(10): 139-145.
[13] 李红梅,严正. 具有先验知识的Q学习算法在AGC中的应用[J]. 电力系统自动化, 2008, 32(23): 36-40. LI Hongmei, YAN Zheng. Application of Q-learning approach with prior knowledge to non-linear AGC system[J]. Automation of Electric Power System, 2008, 32(23): 36-40.
[14] 马豫超,蒋传文,侯志俭,等. 基于自加强学习算法的发电商报价策略研究[J]. 中国电机工程学报, 2006,26(17): 12-17. MA Yuchao, JIANG Chuanwen, HOU Zhijian, et al. Strategic bidding of the electricity producers based on the reinforcement learning[J]. Proceedings of the CSEE, 2006, 26(17):12-17.
[15] 高瞻,宋依群. 基于Q学习算法的发电商报价策略模型[J]. 华东电力, 2008, 36(4): 20-22. GAO Zhan, SONG Yiqun. Power supplier bidding strategies based on Q-learning algorithm[J]. East China Electric Power, 2008, 36(4): 20-22.
[16] 王尚. 实现风电场自律的调控与配置策略研究[D]. 济南:山东大学,2015. WANG Shang. Studies on regulation and storage allocation strategies of wind farm self-discipline[D]. Jinan: Shandong University, 2015.
[17] 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. Optimal decision-making in the cooperation of wind power and energy storage based on reinforcement learning algorithm[J]. Power System Technology, 2016, 40(9): 2729-2736.
[18] 余涛,王宇名,刘前进. 互联电网CPS调节指令动态最优分配Q学习算法[J]. 中国电机工程学报, 2010, 20(7): 62-69. YU Tao, WANG Yuming, LIU Qianjin. Q-learning-based dynamic optimal allocation algorithm for CPS order of interconnected power grids[J]. Proceedings of the CSEE, 2010, 20(7): 62-69.
[1] 崔恒斌,周瑾,董继勇,金超武. V-Gap度量磁悬浮推力轴承系统H∞控制器设计[J]. 山东大学学报(工学版), 2018, 48(2): 86-93.
[2] 褚晓东,唐茂森,高旭,刘伟生,贾善杰,李笋. 基于集中式信息系统的主动配电网鲁棒优化调度[J]. 山东大学学报(工学版), 2017, 47(6): 20-25.
[3] 何东之,张吉沣,赵鹏飞. 不确定性传播算法的MapReduce并行化实现[J]. 山东大学学报 (工学版), 2015, 45(5): 22-28.
[4] 张慧慧, 夏建伟. 不确定随机多时滞系统鲁棒随机稳定性分析[J]. 山东大学学报(工学版), 2015, 45(1): 54-63.
[5] 赵文忠 史军. 复功率注入空间的电力系统概率安全性指标研究[J]. 山东大学学报(工学版), 2009, 39(6): 135-138.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发