基于多场景置信间隙决策的风光储联合鲁棒规划  

Joint Robust Planning of Wind-Photovoltaic-Energy Storage System Based on Multi-scenario Confidence Gap Decision

作　　者：彭春华 熊志盛 张艺 孙惠娟 PENG Chunhua;XIONG Zhisheng;ZHANG Yi;SUN Huijuan(School of Electrical and Automation Engineering,East China Jiaotong University,Nanchang 330013,China)

机构地区：[1]华东交通大学电气与自动化工程学院,江西省南昌市330013

出　　处：《电力系统自动化》2022年第16期178-187,共10页Automation of Electric Power Systems

基　　金：国家自然科学基金资助项目(52167009);江西省主要学科学术和技术带头人项目(20204BCJL22038);江西省研究生创新专项资金资助项目(YC2020-S325)。

摘　　要：为实现具有鲁棒性的风光储联合规划以应对可再生能源出力不确定性带来的负面影响,提出基于鲁棒驱动的多场景置信间隙决策理论(MCGDT);以风光消纳率最大化和总投资成本最小化为优化目标,构建了基于MCGDT的风光储联合鲁棒规划模型;基于不确定性理论将模型中复杂的机会约束进行等效确定性转换,设计了一种新颖的交叉熵-雷达扫描微分进化算法高效求解模型。MCGDT不仅能弥补常规鲁棒优化和信息间隙决策理论未能计及鲁棒准确性以及随机因素多态性的不足,还能解决随机规划中典型场景不具有区间遍历性的问题,可实现更为合理而准确的不确定性规划。所提理论与方法的有效性和优越性通过算例分析得到了验证。In order to achieve the joint planning with robustness of wind-photovoltaic-energy storage system(ESS)to deal with the negative impact of the uncertainties of renewable energy output,a robust-driven multi-scenario confidence gap decision theory(MCGDT)is proposed.Considering the optimization objectives of maximizing the wind/photovoltaic power consumption rate and minimizing the total investment cost,a wind-photovoltaic-ESS joint robust planning model based on MCGDT is established.Furthermore,the complex chance constraints are transformed into the equivalent determinate constraints according to the uncertainty theory,and a novel cross entropy-radar scanning differential evolution(CE-RSDE)algorithm is proposed to solve the model efficiently.MCGDT can not only make up for the inadequacy of conventional robust optimization and information gap decision theory(IGDT)that fails to measure the robustness accuracy and embody the polymorphism of randomness,but also solve the problem of non-interval ergodicity of typical scenarios in stochastic programming.Therefore,a more reasonable and accurate uncertainty planning can be realized.The validity and superiority of the proposed theory and method are verified by case study.

关 键 词：风光储联合规划 多场景置信间隙决策 鲁棒优化 雷达扫描机制 交叉熵微分进化 

分 类 号：TM61[电气工程—电力系统及自动化] TM715