检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:孔祥玉 孙裕策 尧静涛 刘茂 崔凯 KONG Xiangyu;SUN Yuce;YAO Jingtao;LIU Mao;CUI Kai(School of Electrical and Information Engineering,Tianjin University,Tianjin 300072,China;State Grid Economic and Technological Research Institute Co.,Ltd.,Beijing 102209,China)
机构地区:[1]天津大学电气自动化与信息工程学院,天津300072 [2]国网经济技术研究院有限公司,北京102209
出 处:《供用电》2021年第10期3-11,共9页Distribution & Utilization
基 金:国家重点研发计划项目(2017YFB092900,2017YFB092902)。
摘 要:随着电力系统智能化和互动化的发展,配电网规划要素不断增加,以配电网投资效益机理分析为基础的规划投资决策模型构建越发困难。针对这一问题,提出了一种基于数据驱动的配电网规划投资决策方法。首先结合配电网规划目标及区域情况,构建规划投资指标体系。其次以与效益指标相关的各因素指标为输入,利用深度学习构建配电网投资效益模型,并通过迁移学习解决深度学习难以在小样本情况下有效应用的问题。在上述基础上,将投资效益模型替代配电网规划投资模型中的目标函数,并利用遗传算法对规划投资模型进行求解,获取规划投资方案。最后,通过算例分析验证了该方法的可行性与有效性。With the development of intelligent and interactive power system,the elements of distribution network planning are increasing,and it is more difficult to construct the investment planning decision model based on the analysis of the investment benefit mechanism of distribution network.A data-driven distribution network investment planning and decision-making method is propose proposed in the paper.Firstly,the investment planning indexes system is constructed by combining the planning target and regional situation of distribution network.Taking the benefit index as output and the factors related to the benefit index as input,the distribution network investment benefit model is established by deep learning,and we solve the problem that deep learning is difficult to be effectively applied in the case of small samples by transfer learning.On the basis of the above,the investment benefit model is used to replace the objective function in the distribution network investment planning model,and the genetic algorithm is used to solve the investment planning model to obtain the investment planning scheme.Finally,the feasibility and effectiveness of the proposed method are verified by an example analysis.
关 键 词:配电网 数据驱动 投资效益 规划决策 深度迁移学习
分 类 号:TM91[电气工程—电力电子与电力传动]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.149.250.24