基于改进鲁棒DEA模型的电力系统评价研究  

Research on Power System Evaluation Based on Improved Robust DEA Model

作　　者：唐标 程志万 李博 朱梦梦 王恩 李贵良 TANG Biao;CHENG Zhiwan;LI Bo;ZHU Mengmeng;WANG En;LI Guiliang(Yunnan Electric Power Research Institute,Kunming 650217,China;Dehong Power Supply Bureau of Yunnan Power Grid Co.,Ltd.,Mangshi Yunnan 678400,China)

机构地区：[1]云南电网有限责任公司电力科学研究院,昆明650217 [2]云南电网有限责任公司德宏供电局,云南芒市678400

出　　处：《电子器件》2020年第2期273-279,共7页Chinese Journal of Electron Devices

基　　金：国家重点研发计划“物联网与智慧城市关键技术及示范”重点专项项目(2018YFB2100100);云南电网有限责任公司科技项目(YNKJXM20180243)。

摘　　要：针对传统DEA模型在不确定环境下评价结果不稳定的缺陷,提出了一种改进的鲁棒DEA评价方法,为电网建设和投资规划提供有效的经济指导。该方法采用鲁棒模糊核主成分分析,确定电力系统评价的投入产出指标;考虑投入产出不确定性,利用不确定信息一般化思想和对偶理论构建鲁棒DEA模型。为验证模型效果,采用我国部分省级电力系统的投入产出数据,研究不确定环境下电力系统评价的稳定性,实验表明,鲁棒DEA模型会在效率最优性和求解可靠性之间权衡,当投入产出数据同时面临不确定扰动时,模型仍能保证评价的准确稳定性。In order to deal with the unstable evaluation results of traditional DEA model in uncertain environment. An improved robust DEA evaluation method is proposed to provide effective economic guidance for power grid construction and investment planning. The robust fuzzy kernel principal component analysis is used to determine the input-output index of power system evaluation. Considering the uncertainty of input and output,a robust DEA model is constructed by using the generalized idea of uncertain information and dual theory. In order to verify the effect of the model,the paper uses input-output data of some provincial power systems in China to study the stability of power system evaluation under uncertain environment. Experiments show that robust DEA model can balance efficiency optimality and solution reliability. When input-output data are faced with uncertain disturbances at the same time,the model can still ensure the accurate stability of evaluation.

关 键 词：电力系统评价 鲁棒模糊核主成分分析法 不确定信息一般化 对偶理论 鲁棒DEA模型 

分 类 号：TM715[电气工程—电力系统及自动化]