考虑碳排放的综合能源系统抗差参数辨识  

Robust Parameter Identification for Integrated Energy System Considering Carbon Emissions

作　　者：陈洪银 王松岑 贾晓强 李德智 刘铠诚 钟鸣 芋耀贤 金璐 郭毅 CHEN Hongyin;WANG Songcen;JIA Xiaoqiang;LI Dezhi;LIU Kaicheng;ZHONG Ming;YU Yaoxian;JIN Lu;GUO Yi(State Key Laboratory of Power Grid Safety,Haidian District,Beijing 100192,China;China Electric Power Research Institute Co.,Ltd.,Haidian District,Beijing 100192,China)

机构地区：[1]电网安全全国重点实验室,北京市海淀区100192 [2]中国电力科学研究院有限公司,北京市海淀区100192

出　　处：《电力信息与通信技术》2023年第11期30-38,共9页Electric Power Information and Communication Technology

基　　金：国家电网有限公司总部科技项目资助“面向碳中和的综合能源系统结构演化机理与稳态模型研究”(5100-202155316A-0-0-00)。

摘　　要：近年来随着综合能源系统研究的深入,对能源设备建模的完整性和准确性提出了更高要求。针对传统研究中尚未考虑设备碳排放参数以及现有参数辨识方法的不足,文章提出一种考虑碳排放的综合能源系统抗差参数辨识方法。首先,建立了考虑碳排放强度的常见能源设备模型;其次,针对获取的系统历史运行数据,利用BP神经网络对其中的缺失值进行拟合填充,获取高可信的有效数据;最后,采用基于投票法的参数辨识方法对设备进行参数辨识,并通过旧数据遗忘与更新对设备参数进行动态辨识,通过算例对比分析了所提方法相较于现有方法的优势,说明了所提方法的必要性和有效性。As the study of the integrated energy system(IES)progresses,higher requirements are placed on the completeness and accuracy of energy equipment modelling.In response to the shortcomings of traditional research that has not yet considered carbon emission parameters of equipment and existing parameter identification methods,a robust parameter identification method was proposed to identify the parameters of IES considering carbon emission.Firstly,a model of common energy equipment considering carbon emission intensity was developed.Secondly,for the obtained IES historical operation data,BP neural network was used to fit the missing values to obtain the valid data with high confidence.Then,a voting-based parameter identification method is adopted to identify the equipment parameters,and the equipment parameters are dynamically identified by forgetting and updating the old data.The advantages of the proposed method over the existing methods are compared and the necessity and effectiveness of the proposed method are proved.

关 键 词：参数辨识 碳排放强度 投票法 综合能源系统 BP神经网络 

分 类 号：TM73[电气工程—电力系统及自动化]