基于数据驱动核极限学习机的风光容量配置方案研究  

Research on wind solar capacity configuration scheme based on data driven kernel extreme learning machine

作　　者：涂菁菁 赵鹏 邹伟东[2] TU Jingjing;ZHAO Peng;ZOU Weidong(China Energy Engineering Group Investment Co.,Ltd.,Beijing 100122,China;School of Automation,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]中国能源建设集团投资有限公司,北京100122 [2]北京理工大学自动化学院,北京100081

出　　处：《电气应用》2024年第10期32-38,共7页Electrotechnical Application

基　　金：国家自然科学基金青年基金资助项目(61906015)。

摘　　要：风光发电的大量接入,将引起配电网规划与运行特征的根本性改变,因而研究配电网中风光发电的选址定容问题具有重要意义。先利用数据驱动构建基于核极限学习机的容量选择模型;再以总投资成本和网络损耗最小为目标函数,以电压稳定性为评价指标对容量配置结果进行评估;最后采用IEEE 33节点系统作为算例进行仿真,将结果分别与支持向量机、粒子群和遗传算法进行比较。结果表明该容量配置方案能够起到节约成本、降低网络损耗及提高网络电压水平的作用,并能够为新能源接入配电网的投资方案提供一定的参考。The extensive integration of wind and solar power generation will fundamentally change the planning and operational characteristics of the distribution network,therefore,studying the site selection and capacity determination of wind and solar power generation in the distribution network is of great significance.Firstly,a capacity selection model based on kernel extreme learning machine is constructed using data-driven approach;Then,the capacity allocation results are evaluated with the objective function of minimizing total investment cost and network loss,and voltage stability as the evaluation index;Finally,the IEEE 33 node system was used as an example for simulation,and the results were compared with support vector machine,particle swarm optimization,and genetic algorithm.The results show that the capacity configuration scheme obtained through this method can achieve cost savings,reduce network losses,improve network voltage stability,and provide certain reference for investment scheme of new energy access to distribution networks.

关 键 词：配电网 数据驱动 核极限学习机 有功损耗 电压稳定 

分 类 号：TM73[电气工程—电力系统及自动化] TP18[自动化与计算机技术—控制理论与控制工程]