市场与计划双轨制下的日内调度优化策略研究  

Research on the Intraday Scheduling Optimization Strategy under the Dual-Track System of Market and

作　　者：陈玥彤 张思远 龙高翔 胡宇 沈巍[1] 刘敦楠[1] CHEN Yuetong;ZHANG Siyuan;LONG Gaoxiang;HU Yu;SHEN Wei;LIU Dunnan(School of Economics and Management,North China Electric Power University,Beijing 102206,China;State Grid Hunan Electric Power Company Limited,Changsha 410004,Hunan,China;School of Economics and Management,Beijing Institute of Petrochemical Technology,Beijing 102617,China)

机构地区：[1]华北电力大学经济与管理学院,北京102206 [2]国网湖南省电力有限公司,湖南长沙410004 [3]北京石油化工学院经济管理学院,北京102617

出　　处：《电网与清洁能源》2025年第1期50-60,共11页Power System and Clean Energy

基　　金：国家自然科学基金项目(72171082);北京市自然科学基金项目(9244024)。

摘　　要：我国现行电力市场体系下,市场主体未能完全参与市场竞争,发电机组的日前调度计划制定由市场、计划等多方面因素影响,实时负荷波动引发的调度计划修正会带来机组的经济运行与合同偏差风险。考虑负荷预测偏差以及日前计划调整代价的影响,提出市场与计划双轨制下的日内调度优化策略。基于历史负荷数据的时序特征,构建了考虑多因素的长短期记忆(long short-term memory,LSTM)模型预测未来短期日前计划调整量;基于机组的日计划完成率和负荷率设计了日前计划调节代价函数,构建了日内多阶段优化调度模型,该模型中考虑了辅助服务市场与日前计划的衔接问题,实现了日前计划调整量的再分配;基于某省级电网运行数据对模型进行仿真验证,用McCormick方法对模型中的双线性项线性化近似,转化为混合整数线性规划模型求解。算例分析结果表明,该优化调度策略能有效修正日前计划偏差,兼顾了机组的经济性和合同执行率等目标。Under the current power market system in China,market entities have not been able to fully participate in market competition.The formulation of day-ahead dispatch plans for generating units is influenced by various factors such as the market and planning.Corrections to dispatch plans due to realtime load fluctuations can lead to risks of economic operation and contract deviations for the generating units.Considering the impact of load forecasting errors and the cost of day-ahead plan adjustments,an intraday dispatch optimization strategy under a dual-track system of market and planning is proposed.First,based on the time series characteristics of historical load data,a long short-term memory(LSTM)model that considers multiple factors is constructed to predict future short-term day-ahead plan adjustments;secondly,a day-ahead plan adjustment cost function is designed based on the unit's daily plan completion rate and load factor,and the intraday multi-stage optimization dispatch model is constructed.This model takes into account connections between the ancillary services market and the dayahead plan,achieving redistribution of the day-ahead plan adjustment amounts.Finally,the model is simulated and verified using operation data from a provincial power grid.The bilinear terms in the model are linearized and approximated using the McCormick method,transforming it into a mixedinteger linear programming model for solution.Case analysis results show that this optimization dispatch strategy can effectively correct day-ahead plan deviations while taking into account objectives such as the unit's economy and contract execution rate.

关 键 词：日内调度优化 辅助服务市场 LSTM预测 代价函数 

分 类 号：TM73[电气工程—电力系统及自动化]