Operational Risk Assessment and Warning for Electricity Spot Market Based on Extension Cloud and Ensemble Learning

LIAO Jian; ZHANG Beixi; ZHANG Chenggang; CHEN Yihua; LI Yunhao; ZHANG Yao

PDF(847 KB)

Electric Power Construction ›› 0

Operational Risk Assessment and Warning for Electricity Spot Market Based on Extension Cloud and Ensemble Learning

LIAO Jian¹, ZHANG Beixi¹, ZHANG Chenggang², CHEN Yihua², LI Yunhao², ZHANG Yao¹

Author information +

History +

Abstract

[Objective] The construction of a unified national electricity market system is accelerating; however, the complexity of market mechanisms and the lack of real-time capabilities in existing methods make dynamic risk warning in spot market operations challenging. [Methods] To address this, an operational risk assessment model based on pre-clearing feature variables is proposed, utilizing a Stacking ensemble learning model for prediction. First, key feature variables with significant market impact are selected, and an improved Latin hypercube sampling method is used to generate numerous risk scenarios. Second, an operational risk evaluation index system for the spot market is established, and calculate risk indicators after the spot market is cleared. Subsequently, a cloud entropy-optimized matter-element extension cloud model is employed to balance the fuzziness and uncertainty in the transformation between quantitative and qualitative evaluations, enabling reasonable risk grading. Finally, random forest, deep neural network, and XGBoost are used as base learners for five-fold cross-validation to extract market features. Logistic regression is then employed as the meta-learner to provide early warnings for overall market risks and specific indicator risks. [Results] Simulation results based on the IEEE 24-bus system indicate that the proposed model effectively alleviates the underfitting issue for minority classes. It achieves an accuracy of 79.36% in overall risk prediction and a Top-2 accuracy of 97.01%, representing a 4%-12% improvement over traditional models. The average accuracy for single-indicator risk warnings reaches 78.95%. [Conclusions] The proposed model enables reasonable evaluation and accurate early warning of operational risks in electricity spot markets. It effectively identifies risk sources and provides reliable support for real-time risk management and decision-making.

Key words

dynamic risk early warning / stacking / matter-element extension cloud / electricity spot market / cloud entropy optimization

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LIAO Jian, ZHANG Beixi, ZHANG Chenggang, CHEN Yihua, LI Yunhao, ZHANG Yao. Operational Risk Assessment and Warning for Electricity Spot Market Based on Extension Cloud and Ensemble Learning[J]. Electric Power Construction. 0

References

[1] 发展改革委, 能源局. 国家发展改革委国家能源局关于加快建设全国统一电力市场体系的指导意见: 发改体改〔2022〕118号[A/OL]. (2022-01-18)[2024-12-05]. https://www.gov.cn/zhengce/zhengceku/2022-01/30/content_5671296.htm.
National Development and Reform Commission, National Energy Administration. Guidance on Accelerating the Construction of a National Unified Power Market System: No. 118 of the2022 Year of the Reform and Development of the State (A/OL). (2022-01-18)[2024-12-05]. https://www.gov.cn/zhengce/zhengceku/2022-01/30/content_5671296.htm.
[2] 刘丽, 叶钰童, 王宝,等. 面向省间电力现货市场的购电博弈竞价模型[J]. 浙江电力, 2024, 43(07): 111-119.
LIU Li, YE Yutong, WANG Bao, et al.A game bidding model for electricity purchasing tailored to inter-provincial electricity spot market[J]. Zhejiang Electric Power, 2024, 43(07): 111-119.
[3] 高政南, 姜楠, 陈启鑫, 等. 德国电力市场能源转型建设及启示[J]. 中国电力, 2024, 57(06): 204-214.
GAO Zhengnan, JIANG Nan, CHEN Qixin, et al.Construction Experience of German Electricity Market Adapting to Energy Transition[J]. ELECTRIC POWER, 2024, 57(06): 204-214.
[4] 黄仁辉, 张集, 张粒子, 等. 整合GARCH和VaR的电力市场价格风险预警模型[J]. 中国电机工程学报, 2009, 29(19): 85-91.
HUANG Renhui, ZHANG Ji, ZHANG Lizi, et al.Price Risk Forewarning of Electricity Market Based on GARCH and VaR Theory[J]. Proceedings of the CSEE, 2009, 29(19): 85-91.
[5] 叶海, 杨苹, 王雨. 基于改进CVaR的售电公司电力现货日前申报优化策略[J]. 电力建设, 2024, 45(5): 131-140.
YE Hai, YANG Ping, WANG Yu.Optimization Strategy for Electricity Retailer’s Day-Ahead Bidding in the Electricity Spot Market Based on Improved CVaR[J]. Electric Power Construction, 2024, 45(5): 131-140.
[6] 杜帅, 丰玉帆. 考虑系统性风险的现货市场双边报价交易机制与模型[J]. 电力需求侧管理, 2023, 25(1): 12-19.
DU Shuai, FENG Yufan.Bilateral quotation trading mechanism and model in spot market considering systemic risk[J]. Power Demand Side Management, 2023, 25(1): 12-19.
[7] 何洁, 金骆松, 赵雯, 等. 电力市场环境下考虑可再生能源保障性消纳的电价风险评估[J]. 现代电力, 2022, 39(6): 631-639.
HE Jie, JIN Luosong, ZHAO Wen, et al.Market Price Risk Analysis Under Background of Renewable Energy Assumption Guarantee[J]. Modern Electric Power, 2022, 39(6): 631-639.
[8] 高政南, 周飞航, 葛根塔娜, 等. 多维电力市场风险综合评价研究[J]. 电力需求侧管理, 2021, 23(6): 26-30.
GAO Zhengnan, ZHOU Feihang, GEGEN Tana, et al.Research on comprehensive evaluation of multi dimensional power market’s risks[J]. Power Demand Side Management, 2021, 23(6): 26-30.
[9] XIA S, ZHANG Y, YANG F, et al.Research on early warning system of provincial energy and power security based on extension cloud[C]//Eighth International Conference on Energy Materials and Electrical Engineering (ICPRE). Zhangjiajie, China: IEEE, 2023: 370-385.
[10] 魏新迟, 董佳, 时珊珊, 等. 基于云模型和随机森林的韧性城市电网风险预警模型[J]. 电力建设, 2024, 45(5): 19-28.
WEI Xinchi, DONG Jia, SHI Shanshan, et al.Enhanced Risk Warning Model for Resilient Urban Power Grid Using Cloud Model and Random Forest[J]. Electric Power Construction, 2024, 45(5): 19-28.
[11] 闫炯程, 李常刚, 刘玉田. 数据驱动的新型电力系统安全风险预警综述[J]. 电网技术: 1-12.
YAN Jiongcheng, LI Changgang, LIU Yutian.Review of Data-Driven Security Risk Early Warning Research of the New-Type Power System[J]. Power System Technology: 1-12.
[12] QIAN H, LI Y, YU X, et al.Risk Assessment and Classification to Electricity Retail Market[C]//2020 5th International Conference on Power and Renewable Energy (ICPRE). Shanghai, China: IEEE, 2020, 106-112.
[13] 陈守军. 电网运营风险度量、预警与防控优化模型研究[D]. 北京: 华北电力大学(北京), 2017.
CHEN Shoujun.The Study on the Opitmaltion Model for Power Grid Operational Risk Measurement, Early Warning and Prevention[D]. Beijing: North China Electric Power University, 2017.
[14] QI H, LIN Z, ZHENG R, et al.Construction of An Early Warning Model for Market Power Identification in the Electricity Spot Market Based on Improved BP Neural Networks[C]//2022 9th International Forum on Electrical Engineering and Automation (IFEEA). Zhuhai, China: IEEE, 2022: 1215-1220.
[15] GAO G, LO K, LU J.Risk Assessment due to Electricity Price Forecast Uncertainty in UK Electricity Market[C]// 2017 52nd International Universities Power Engineering Conference (UPEC). Heraklion, Greece: IEEE, 2017, 1-6.
[16] 邓彬. 电力市场串谋动态模拟与智能预警方法研究[D]. 保定: 华北电力大学, 2022.
Deng Bin.Research on dynamic simulation and intelligent early warning method of collusion in power market[D]. Baoding: North China Electric Power University, 2022.
[17] XU Y, ZHANG R, ZHAO J, et al.Assessing Short-Term Voltage Stability of Electric Power Systems by a Hierarchical Intelligent System[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(8): 1686-1696.
[18] 李常刚, 李华瑞, 刘玉田, 等. 计及低频减载动作的最大暂态频率偏移快速估计[J]. 电力系统自动化, 2019, 43(12): 27-35.
LI Changgang, LI Huarui, LIU Yutian, et al.Fast Estimation of Maximum Transient Frequency Deviation Considering Under-frequency Load Shedding[J]. Automation of Electric Power Systems, 2019, 43(12): 27-35.
[19] 李汶龙, 周云, 罗祾, 等. 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(05): 99-112.
LI Wenlong, ZHOU Yun, LUO Ling, et al.Carbon Allocation Throughout the Entire Process of Electric Energy Trading Considering Spot Trading[J]. ELECTRIC POWER, 2024, 57(05): 99-112.
[20] 何方波, 周庆庆, 张寓涵, 等. 考虑多类型主体的电能量与调峰辅助服务联合出清模型[J]. 电网与清洁能源, 2024, 40(07): 48-55.
HEFangbo, ZHOU Qingqing, ZHANG Yuhan, et al.TheJoint Peak Regulation-Electricity Clearing Model Considering Multiple Types of Subjects[J]. Power System and Clean Energy, 2024, 40(07): 48-55.
[21] 范玉宏, 丁珩, 张维, 等. 电力现货市场建设关键问题研究[J]. 湖北电力, 2018, 42(2): 45-50.
FAN Yuhong, DING Heng, ZHANG Wei, et al.Study on Key Issues in Power Spot Market Construction[J]. Hubei Electric Power, 2018, 42(2): 45-50.
[22] 张潮, 谢珣, 顾卫祥, 等. 考虑特高压直流输电影响的省间电力现货市场协调交易方法[J]. 浙江电力, 2024, 43(05): 83-90.
ZHANG Chao, XIE Xun, GU Weixiang, et al.A coordinated trading method for the inter-provincial electricity spot market considering the impact of UHVDC transmission systems[J]. Zhejiang Electric Power, 2024, 43(05): 83-90.
[23] 赵晋泉, 吴天娇, 林孙奔, 等. 两种第三方主体参与的现货市场出清模式比较[J]. 电力工程技术, 2023, 42(06): 241-248.
ZHAO Jinquan, WU Tianjiao, LIN Sunben, et al.Comparison of two market clearing modes for day-ahead power market incorporating third-party entity[J]. Electric Power Engineering Technology, 2023, 42(06): 241-248.
[24] 肖云鹏, 关玉衡, 张兰, 等. 集中式电力现货市场风险规避机制机分析及建设路径[J]. 电网技术, 2021, 45(10): 3981-3991.
XIAO Yunpeng, GUAN Yuheng, ZHANG Lan, et al.Analysis and Construction Path of Risk Hedging Mechanism in Centralized LMP-based Electricity Spot Market[J]. Power System Technology, 2021, 45(10): 3981-3991.
[25] 谢敬东, 刘思旺, 孙欣, 等. 考虑市场力风险防范的电力市场出清机制[J]. 电力建设, 2023, 44(4): 18-28.
XIE Jingdong, LIU Siwang, SUN Xin, et al.Electricity Market Clearing Mechanism Considering Market Power Risk Prevention[J]. Electric Power Construction, 2023, 44(4): 18-28.
[26] 赵勇, 胡斐, 黄成, 等. 电力现货市场中基于发电商竞价均衡情景的市场力缓解模型与方法[J]. 中国电机工程学报, 2024: 1-13.
Zhao Yong, Hu Fei, Huang Cheng, et al.Generators Bidding Equilibria Scenario-Based Market Power Mitigation Model and Method in Electricity Spot Market[J]. Proceedings of the CSEE, 2024: 1-13.
[27] LI X, QI Z.Impact of cascading failure based on line vulnerability index on power grids[J]. Energy Systems, 2022, 13(4): 893-918.
[28] 荆朝霞, 容语霞, 王一凡, 等. 电力市场不平衡资金综述:成因、对策与展望[J]. 电网技术, 2023, 47(09): 3586-3600.
JING Zhaoxia, RONG Yuxia, WANG Yifan, et al.Summary of Unbalanced Funds in Electricity Market: Causes, Countermeasures and Prospects[J]. Power System Technology, 2023, 47(9): 3586-3596.
[29] 王正风, 王吉文, 高卫恒, 等. 电力现货市场阻塞费用结算机制分析[J]. 浙江电力, 2024, 43(01): 57-63.
WANG Zhengfeng, WANG Jiwen, GAO Weiheng, et al.Analysis of congestion cost settlement mechanisms in electricity spot market[J]. Zhejiang Electric Power, 2024, 43(01): 57-63.
[30] 邹阳, 林锦茄, 李安娜, 等. 基于灰色关联分析和聚类云模型的变压器油纸绝缘状态评估[J]. 电力系统保护与控制, 2023, 51(21): 35-43.
ZOU Yang, LIN Jinjia, LI Anna, et al.Evaluation of transformer oil-paper insulation status based on grey relational analysis and a cluster cloud model[J]. Power System Protection and Control, 2023, 51(21): 35-43.
[31] WANG Y, YANG J, ZHOU M, et al.Evaluating the sustainability of China’s power generation industry based on a matter-element extension model[J]. Utilities Policy, 2021, 69: 101166.
[32] DONG J, WANG D, LIU D, et al.Operation Health Assessment of Power Market Based on Improved Matter-Element Extension Cloud Model[J]. Sustainability, 2019, 11(19): 5470.
[33] DONG X, YU Z, CAO W, et al.A survey on ensemble learning[J]. Frontiers of Computer Science, 2020, 14(2): 241-258.
[34] 徐继伟, 杨云. 集成学习方法:研究综述[J]. 云南大学学报(自然科学版), 2018, 40(6): 1082-1092.
XU Jiwei, YANG Yu.A survey of ensemble learning approaches[J]. Journal of Yunnan University, 2018, 40(6): 1082-1092.
[35] FERNANDEZ-DELGADO M, CERNADAS E, BARRO S, et al.Do we Need Hundreds of Classiﬁers to Solve Real World Classiﬁcation Problems?[J]. The Journal of Machine Learning Research, 2014, 15(1): 3133-3181.
[36] BAZAZEH D, SHUBAIR R.Comparative study of machine learning algorithms for breast cancer detection and diagnosis[C]//2016 5th International Conference on Electronic Devices, Systems and Applications (ICEDSA). Ras Al Khaimah, United Arab Emirates: IEEE, 2016: 1-4.
[37] SUBCOMMITTEE P. IEEE Reliability Test System[J]. IEEE Transactions on Power Apparatus and Systems, 1979, PAS-98(6): 2047-2054.
[38] GRIGG C, WONG P, ALBRECHT P, et al.The IEEE Reliability Test System-1996. A report prepared by the Reliability Test System Task Force of the Application of Probability Methods Subcommittee[J]. IEEE Transactions on Power Systems, 1999, 14(3): 1010-1020.

Funding

National Key Research and Development Program of China (No. 2022YFB2403500) and the Science and Technology Project of State Grid Corporation of China (No. SGSN0000DKJS2404539).