基于智能体建模的新型电力系统下火电企业市场交易策略

doi:10.11930/j.issn.1004-9649.202303088

中国电力 ›› 2024, Vol. 57 ›› Issue (2): 212-225.DOI: 10.11930/j.issn.1004-9649.202303088

基于智能体建模的新型电力系统下火电企业市场交易策略

李超英¹(), 檀勤良¹^,²^,³()

1. 华北电力大学经济与管理学院，北京　102206
2. 北京市能源发展研究基地，北京　102206
3. 新能源电力与低碳发展研究北京市重点实验室（华北电力大学），北京　102206

收稿日期:2023-03-18 接受日期:2023-10-23 出版日期:2024-02-28 发布日期:2024-02-28
作者简介:李超英（1999—），女，硕士研究生，从事电力市场、能源经济研究，E-mail：leechying@163.com
檀勤良（1969—），男，通信作者，教授，博士生导师，从事能源经济与政策、能源环境建模与优化等研究，E-mail：tan.qinliang1@gmail.com
基金资助:
国家自然科学基金资助项目（双碳目标下发电企业低碳技术创新扩散及其产业链协同演化机制研究，72272050）。

Market Trading Strategy for Thermal Power Enterprise in New Power System Based on Agent Modeling

Chaoying LI¹(), Qinliang TAN¹^,²^,³()

1. School of Economics and Management, North China Electric Power University, Beijing 102206, China
2. Research Center for Beijing Energy Development, Beijing 102206, China
3. Beijing Key Laboratory of Renewable Electric Power and Low Carbon Development, North China Electric Power University, Beijing 102206, China

Received:2023-03-18 Accepted:2023-10-23 Online:2024-02-28 Published:2024-02-28
Supported by:
This work is supported by National Natural Science Foundation of China (Research on the Mechanism of Low-Carbon Technology Innovation Diffusion and Industrial Chain Co-evolution of Power Generation Enterprises under 30·60 Target, No.72272050).

摘要/Abstract

摘要：

高比例新能源渗透情景下火电企业竞价策略研究对保障火电企业运营和推进新型电力系统建设具有重要意义。基于智能体建模框架，建立电力现货市场仿真模型和机组自学习决策模型。其中，环境模块建立了考虑源荷双侧不确定性的风光火储多方参与的电力现货市场出清模型；智能体模块将火电机组投标决策过程刻画为部分观测马尔科夫决策过程，采用深度确定性策略梯度算法求解。以HRP-38节点系统为例进行仿真分析，明晰高比例新能源下火电企业市场交易策略。结果表明：在不考虑火电机组提供辅助服务的前提下，随着新能源渗透率的提高，仍有部分位置独特且具有成本优势的火电机组拥有竞争力；预测误差增大将使大容量火电机组投标策略趋于保守，而小容量机组投标策略相反；火电机组在各类场景下均具有隐性共谋倾向，即彼此隐藏信息时仍同时提高报价。

关键词: 电力市场, 多智能体建模, 强化学习, 报价策略, 辅助决策

Abstract:

It is of great significance to study the bidding strategy of thermal power enterprises under the scenario of high proportion of new energy penetration for guaranteeing the normal operation of thermal power enterprises and promoting the construction of new power system. Based on the multi-agent modeling framework, this paper establishes a power spot market simulation model and an unit self-learning decision model. In the environment module, a spot market clearing model with multiple participation of wind-solar-fire-storage is established considering the uncertainty of both sources and loads. The bidding decision-making process of thermal power units is described as a partially observed Markov decision-making process in the agent module and solved by improved Deep Deterministic Policy Gradient algorithm. Finally, a HRP-38 node system is simulated to clarify the market trading strategy for thermal power enterprises under a high proportion of new energy. The results show that, when the auxiliary services provided by thermal power units are not considered, with the increase of new energy penetration, some thermal power units with unique locations and cost advantages are still competitive; the increase of prediction error will make the bidding strategy of large-capacity thermal power units tend to be conservative, while the bidding strategy of small-capacity units is opposite; the thermal power units have implicit collusion tendency in all kinds of scenarios, that is, they will increase the quotation at the same time while hiding information from each other.

Key words: electricity market, multi-agent modeling, reinforcement learning, quotation strategy, auxiliary decision

李超英, 檀勤良. 基于智能体建模的新型电力系统下火电企业市场交易策略[J]. 中国电力, 2024, 57(2): 212-225.

Chaoying LI, Qinliang TAN. Market Trading Strategy for Thermal Power Enterprise in New Power System Based on Agent Modeling[J]. Electric Power, 2024, 57(2): 212-225.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202303088

https://www.electricpower.com.cn/CN/Y2024/V57/I2/212

图/表 16

参考文献 31

1	HAO S Y. A study of basic bidding strategy in clearing pricing auctions[J]. IEEE Transactions on Power Systems, 2000, 15 (3): 975- 980. DOI
2	TSAY M T, GOW H J. Congestion influence on bidding strategies in an electricity market[C]//2005 IEEE/PES Transmission & Distribution Conference & Exposition: Asia and Pacific. Dalian, China. IEEE, 2005: 1–6.
3	SINGH K, PADHY N P, SHARMA J. Influence of price responsive demand shifting bidding on congestion and LMP in pool-based day-ahead electricity markets[J]. IEEE Transactions on Power Systems, 2011, 26 (2): 886- 896. DOI
4	PRABAVATHI M, GNANADASS R. Energy bidding strategies for restructured electricity market[J]. International Journal of Electrical Power & Energy Systems, 2015, 64, 956- 966.
5	蒲勇健, 余沙, 黄毅祥. 基于独立售电公司双角色的Stackelberg博弈模型分析[J]. 中国管理科学, 2022, 30 (12): 317- 326.
	PU Yongjian, YU Sha, HUANG Yixiang, et al. A Stackelberg game model based on the dual role of independent electricity sale company[J]. Chinese Journal of Management Science, 2022, 30 (12): 317- 326.
6	李章溢, 马昕, 裴玮, 等. 含用户聚合代理的工业园区需求响应主从博弈机制与策略[J]. 中国电力, 2020, 53 (8): 40- 49.
	LI Zhangyi, MA Xin, PEI Wei, et al. Leader-follower game mechanism and strategy of industrial park demand response with user aggregator[J]. Electric Power, 2020, 53 (8): 40- 49.
7	田福银, 马骏, 王灿, 等. 基于双层主从博弈的综合能源系统多主体低碳经济运行策略[J]. 中国电力, 2022, 55 (11): 184- 193.
	TIAN Fuyin, MA Jun, WANG Can, et al. Multi-agent low-carbon and economy operation strategy of integrated energy system based on bi-level master-slave game[J]. Electric Power, 2022, 55 (11): 184- 193.
8	鲁鹏, 冯春贤, 武伟鸣, 等. 园区能源供需价量双层Stackelberg博弈模型[J]. 中国电力, 2022, 55 (6): 74- 79.
	LU Peng, FENG Chunxian, WU Weiming, et al. Two-layer Stackelberg game model for energy supply and demand in the park[J]. Electric Power, 2022, 55 (6): 74- 79.
9	崔明勇, 宣名阳, 卢志刚, 等. 基于合作博弈的多综合能源服务商运行优化策略[J]. 中国电机工程学报, 2022, 42 (10): 3548- 3564.
	CUI Mingyong, XUAN Mingyang, LU Zhigang, et al. Operation optimization strategy of multi integrated energy service companies based on cooperative game theory[J]. Proceedings of the CSEE, 2022, 42 (10): 3548- 3564.
10	武昭原, 周明, 姚尚润, 等. 基于合作博弈论的风储联合参与现货市场优化运行策略[J]. 电网技术, 2019, 43 (8): 2815- 2824. DOI
	WU Zhaoyuan, ZHOU Ming, YAO Shangrun, et al. Optimization operation strategy of wind-storage coalition in spot market based on cooperative game theory[J]. Power System Technology, 2019, 43 (8): 2815- 2824. DOI
11	EPSTEIN J M. Generative social science: studies in agent-based computational modeling[M]. Princeton, NJ: Princeton University Press, 2006.
12	RINGLER P, KELES D, FICHTNER W. Agent-based modelling and simulation of smart electricity grids and markets - a literature review[J]. Renewable and Sustainable Energy Reviews, 2016, 57, 205- 215. DOI
13	SANTOS G, PINTO T, MORAIS H, et al. Multi-agent simulation of competitive electricity markets: autonomous systems cooperation for European market modeling[J]. Energy Conversion and Management, 2015, 99, 387- 399. DOI
14	ALIABADI D E, KAYA M, ŞAHIN G. An agent-based simulation of power generation company behavior in electricity markets under different market-clearing mechanisms[J]. Energy Policy, 2017, 100, 191- 205. DOI
15	HAGHIGHAT H, SEIFI H, KIAN A R. Pay-as-bid versus marginal pricing: the role of suppliers strategic behavior[J]. International Journal of Electrical Power & Energy Systems, 2012, 42 (1): 350- 358.
16	KELES D, BUBLITZ A, ZIMMERMANN F, et al. Analysis of design options for the electricity market: the German case[J]. Applied Energy, 2016, 183, 884- 901. DOI
17	BARAZZA E, STRACHAN N. The impact of heterogeneous market players with bounded-rationality on the electricity sector low-carbon transition[J]. Energy Policy, 2020, 138, 111274. DOI
18	WANG J H, BOTTERUD A, CONZELMANN G, et al. Market power analysis in the EEX electricity market: an agent-based simulation approach[C]//2008 IEEE Power and Energy Society General Meeting-Conversion and Delivery of Electrical Energy in the 21st Century. Pittsburgh, PA. IEEE, 2008: 1–8.
19	袁唯淋, 罗俊仁, 陆丽娜, 等. 智能博弈对抗方法: 博弈论与强化学习综合视角对比分析[J]. 计算机科学, 2022, 49 (8): 191- 204. DOI
	YUAN Weilin, LUO Junren, LU Lina, et al. Methods in adversarial intelligent game: a comparative analysis from perspective of game theory and reinforcement learning[J]. Computer Science, 2022, 49 (8): 191- 204. DOI
20	PURUSHOTHAMAN K, CHANDRAKALA V. Roth-erev reinforcement learning approach for smart generator bidding towards long term electricity market operation using agent based dynamic modeling[J]. Electric Power Components and Systems, 2020, 48 (3): 256- 267. DOI
21	ESMAEILI ALIABADI D, KAYA M, SAHIN G. Competition, risk and learning in electricity markets: an agent-based simulation study[J]. Applied Energy, 2017, 195, 1000- 1011. DOI
22	孙庆凯, 王小君, 王怡, 等. 基于多智能体Nash-Q强化学习的综合能源市场交易优化决策[J]. 电力系统自动化, 2021, 45 (16): 124- 133. DOI
	SUN Qingkai, WANG Xiaojun, WANG Yi, et al. Optimal trading decision-making for integrated energy market based on multi-agent nash-Q reinforcement learning[J]. Automation of Electric Power Systems, 2021, 45 (16): 124- 133. DOI
23	LIU D N, WANG W Y, WANG L X, et al. Dynamic pricing strategy of electric vehicle aggregators based on DDPG reinforcement learning algorithm[J]. IEEE Access, 2021, 9, 21556- 21566. DOI
24	LIANG Y C, GUO C L, DING Z H, et al. Agent-based modeling in electricity market using deep deterministic policy gradient algorithm[J]. IEEE Transactions on Power Systems, 2020, 35 (6): 4180- 4192. DOI
25	周斌, 崔雪, 邹晨露, 等. 基于合作博弈的风水火联合运营研究[J]. 电测与仪表, 2019, 56 (6): 69- 75. DOI
	ZHOU Bin, CUI Xue, ZOU Chenlu, et al. Research on wind-hydro-thermal power joint operation based on cooperative game theory[J]. Electrical Measurement & Instrumentation, 2019, 56 (6): 69- 75. DOI
26	陆承宇, 江婷, 邓晖, 等. 基于合作博弈的含清洁能源发电商参与现货市场竞价策略及收益分配[J]. 电力建设, 2020, 41 (12): 150- 158.
	LU Chengyu, JIANG Ting, DENG Hui, et al. Bidding strategy and profit distribution of power generation company with clean energy in spot market based on cooperative game theory[J]. Electric Power Construction, 2020, 41 (12): 150- 158.
27	邢通. 大规模风电参与电力市场交易机制及优化模型研究[D]. 北京: 华北电力大学, 2020.
	XING Tong. The research on the transaction mechanism and optimization mode for large scale wind power participating in the power market. [D]. Beijing: North China Electric Power University, 2020.
28	袁桂丽, 贾新潮, 房方, 等. 虚拟电厂源荷双侧热电联合随机优化调度[J]. 电网技术, 2020, 44 (8): 2932- 2940. DOI
	YUAN Guili, JIA Xinchao, FANG Fang, et al. Joint stochastic optimal scheduling of heat and power considering source and load sides of virtual power plant[J]. Power System Technology, 2020, 44 (8): 2932- 2940. DOI
29	肖云鹏, 张兰, 张轩, 等. 包含独立储能的现货电能量与调频辅助服务市场出清协调机制[J]. 中国电机工程学报, 2020, 40 (S1): 167- 180. DOI
	XIAO Yunpeng, ZHANG Lan, ZHANG Xuan, et al. The coordinated market clearing mechanism for spot electric energy and regulating ancillary service incorporating independent energy storage resources[J]. Proceedings of the CSEE, 2020, 40 (S1): 167- 180. DOI
30	LILLICRAP T P, HUNT J J, PRITZEL A, et al. Continuous control with deep reinforcement learning[EB/OL]. 2015: arXiv: 1509.02971.https://arxiv.org/abs/1509.02971.pdf.
31	ZHUO Z Y, ZHANG N, YANG J W, et al. Transmission expansion planning test system for AC/DC hybrid grid with high variable renewable energy penetration[J]. IEEE Transactions on Power Systems, 2020, 35 (4): 2597- 2608. DOI

场景	场景分类	渗透率/%			预测误差/%		储能
场景	场景分类	新能源	风电	光伏	风电	光伏	储能
场景0	场景0.1	40~45	15~30	15~25	20	15	无
	场景0.2	55~60	30~35	25~30	20	15	无
	场景0.3	65~70	35~40	30~35	20	15	无
	场景0.4	80以上	40~60	30~40	20	15	无
场景1	场景1.1	40~45	15~30	15~25	8	5	无
	场景1.2	55~60	30~35	25~30	8	5	无
	场景1.3	65~70	35~40	30~35	8	5	无
	场景1.4	80以上	40~60	30~40	8	5	无
场景2	场景2.1	40~45	15~30	15~25	20	15	有
	场景2.2	55~60	30~35	25~30	20	15	有
	场景2.3	65~70	35~40	30~35	20	15	有
	场景2.4	80以上	40~60	30~40	20	15	有

场景	场景分类	渗透率/%			预测误差/%		储能
场景	场景分类	新能源	风电	光伏	风电	光伏	储能
场景0	场景0.1	40~45	15~30	15~25	20	15	无
	场景0.2	55~60	30~35	25~30	20	15	无
	场景0.3	65~70	35~40	30~35	20	15	无
	场景0.4	80以上	40~60	30~40	20	15	无
场景1	场景1.1	40~45	15~30	15~25	8	5	无
	场景1.2	55~60	30~35	25~30	8	5	无
	场景1.3	65~70	35~40	30~35	8	5	无
	场景1.4	80以上	40~60	30~40	8	5	无
场景2	场景2.1	40~45	15~30	15~25	20	15	有
	场景2.2	55~60	30~35	25~30	20	15	有
	场景2.3	65~70	35~40	30~35	20	15	有
	场景2.4	80以上	40~60	30~40	20	15	有

节点	新能源装机	火电机组装机	输电线路容量
6	6000	33000	15000
12	25000	2000	20000
15	5500	13000	27500
28	0	6000	17500

节点	新能源装机	火电机组装机	输电线路容量
6	6000	33000	15000
12	25000	2000	20000
15	5500	13000	27500
28	0	6000	17500

机组编号	所在节点	机组容量/ MW	最小技术出力/ %	启停成本/ (万元• (MW•h)^–1)	发电运行成本系数		三段非递减报价/ (元•(MW•h)^–1)
机组编号	所在节点	机组容量/ MW	最小技术出力/ %	启停成本/ (万元• (MW•h)^–1)	a	b	三段非递减报价/ (元•(MW•h)^–1)
火电0	15	2000	50	0.1080	0.142	–120.000	392	540	688
火电1	15	5500	50	0.0990	0.090	–195.380	385	551	717
火电2	15	5500	50	0.1010	0.080	–110.620	412	561	710
火电3	28	6000	40	0.1040	0.050	67.250	425	568	711
火电26	6	6000	40	0.1030	0.060	15.820	358	495	632
火电27	6	6000	40	0.0920	0.070	38.100	428	584	740
火电28	6	3000	50	0.1010	0.117	21.000	429	546	662
火电29	6	6000	40	0.0930	0.060	29.250	423	580	737
火电39	6	6000	30	0.0310	0.020	299.461	397	451	506
火电40	6	6000	30	0.0325	0.020	337.806	448	510	572
火电44	12	2000	30	0.0318	0.060	322.530	423	479	536

基于智能体建模的新型电力系统下火电企业市场交易策略

Market Trading Strategy for Thermal Power Enterprise in New Power System Based on Agent Modeling

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 31

相关文章 15

编辑推荐

Metrics

机组编号	场景0.1	场景0.2	场景0.3	场景0.4
火电0	1.13	1.13	1.09	1.06
火电1	1.50	1.15	1.10	1.00
火电2	1.50	1.07	1.11	1.27
火电3	1.50	1.06	1.07	1.07
火电26	1.50	1.00	1.00	1.00
火电27	1.50	1.01	0	0
火电28	1.50	1.00	0	0
火电29	1.50	1.02	0	0
火电39	1.00	1.00	1.00	0
火电40	1.00	0	0	0
火电44	1.21	0	0	0

机组编号	场景0.1-1	场景0.1-2	场景0.2-1	场景0.2-2	场景0.3-1	场景0.3-2	场景0.4-1	场景0.4-2
火电0	13498968	16412115	12468971	14442833	11485019	12503871	10519630	11126714
火电1	26884548	28410845	26044836	28647191	23517086	24315077	21640173	22670703
火电2	22513252	24368714	21720081	24312298	19864431	20578768	17311122	17983108
火电3	14796559	19154757	13847268	16991038	11306283	13875130	9578161	10748581
火电26	9139712	10207668	3094776	4405287	2541327	3057613	1793510	1903897
火电27	5914921	7105599	545607	3682438	0	0	0	0
火电28	3576000	4295197	269732	922590	0	0	0	0
火电29	6387290	7643048	1006129	2074372	0	0	0	0
火电39	2542630	3839581	924009	1040011	910528	978536	0	0
火电40	1098958	2227463	0	0	0	0	0	0
火电44	4023543	4398309	0	0	0	0	0	0

[1]	曾仪, 周毅, 陆继翔, 周良才, 唐宁恺, 李红. 基于多智能体安全深度强化学习的电压控制[J]. 中国电力, 2025, 58(2): 111-117.
[2]	高政南, 姜楠, 陈启鑫, 徐江, 王海利, 辛力, 徐青贵. 德国电力市场能源转型建设及启示[J]. 中国电力, 2024, 57(6): 204-214.
[3]	李汶龙, 周云, 罗祾, 陈甜甜, 冯冬涵. 计及现货交易的电能量交易全环节用电碳责任分摊[J]. 中国电力, 2024, 57(5): 99-112.
[4]	谭虎, 王小亮, 徐亭亭, 赵珂, 宿连超, 张文玉, 辛征. 风光沼储交直流混合农村微电网经济技术优化[J]. 中国电力, 2024, 57(3): 27-33.
[5]	焦昊, 殷岩岩, 吴晨, 刘建, 徐春雷, 徐贤, 孙国强. 基于安全强化学习的主动配电网有功-无功协调优化调度[J]. 中国电力, 2024, 57(3): 43-50.
[6]	郭娟娟, 沈迪, 童朴, 闫琨, 张小凡, 何昉. 中国三代核电经济评价方法与参数优化[J]. 中国电力, 2024, 57(3): 206-212, 223.
[7]	高志远, 庄卫金, 耿建, 李峰, 薛必克, 杨晓雷, 白柯鞠. 基于经济人假设的负荷侧资源市场化调节作用机理分析[J]. 中国电力, 2024, 57(3): 213-223.
[8]	仪忠凯, 侯朗博, 徐英, 吴永峰, 李志民, 吴俊飞, 冯腾, 韩柳. 市场环境下灵活性资源虚拟电厂聚合调控关键技术综述[J]. 中国电力, 2024, 57(12): 82-96.
[9]	薛松萍, 高德荃, 赵子岩, 林彧茜, 广泽晶, 张大卫. 基于业务差异化传输需求下的电力通信网路由算法[J]. 中国电力, 2024, 57(11): 183-190.
[10]	张超, 赵冬梅, 季宇, 张颖. 基于改进深度Q网络的虚拟电厂实时优化调度[J]. 中国电力, 2024, 57(1): 91-100.
[11]	吴明兴, 王宁, 王浩浩, 朱涛, 陈青, 王宣定, 杨塞特. 双轨制下电力现货市场政府授权合约分解优化模型与方法[J]. 中国电力, 2023, 56(9): 15-26.
[12]	任景, 高敏, 程松, 张小东, 刘友波. 面向新能源不确定性的西北电力电量平衡机制[J]. 中国电力, 2023, 56(9): 66-78.
[13]	彭琳钰, 刘旭, 汤玮, 刘晴, 方浩, 张光辉. 基于对抗性强化学习的配电网融合通信效率提升方法[J]. 中国电力, 2023, 56(9): 127-133.
[14]	石文喆, 李冰洁, 尤培培, 张泠. 基于深度强化学习的建筑能源系统优化策略[J]. 中国电力, 2023, 56(6): 114-122.
[15]	薛贵元, 吴垠, 诸晓骏, 谈健, 明昊. 计及用能权配额约束的发电商竞价策略双层优化方法[J]. 中国电力, 2023, 56(5): 51-61.

机组编号	场景2.1	场景2.2	场景2.3	场景2.4
火电0	14950384	13152182	10376831	9263549
火电1	29354504	25468649	20315126	18820701
火电2	24546624	21205219	17576711	14625036
火电3	17440296	15469392	11875931	9701874
火电26	10581533	5159517	2758693	2406591
火电27	7293469	3528564	0	0
火电28	4435634	1445960	0	0
火电29	7788516	2885786	0	0
火电39	2752799	738480	377546	0
火电40	1233999	0	0	0
火电44	4912170	0	0	0

机组编号	场景2.1	场景2.2	场景2.3	场景2.4
火电0	14950384	13152182	10376831	9263549
火电1	29354504	25468649	20315126	18820701
火电2	24546624	21205219	17576711	14625036
火电3	17440296	15469392	11875931	9701874
火电26	10581533	5159517	2758693	2406591
火电27	7293469	3528564	0	0
火电28	4435634	1445960	0	0
火电29	7788516	2885786	0	0
火电39	2752799	738480	377546	0
火电40	1233999	0	0	0
火电44	4912170	0	0	0

模态框（Modal）标题

基于智能体建模的新型电力系统下火电企业市场交易策略

Market Trading Strategy for Thermal Power Enterprise in New Power System Based on Agent Modeling

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 16

参考文献 31

相关文章 15

编辑推荐

Metrics