首页|期刊简介|投稿指南|分类索引|刊文选读|订阅指南|证明资料|样刊邮寄查询|常见问题解答|联系我们
吴云亮,邓韦斯,姚海成,等. 基于两级结构的电网运行断面特征选择与在线生成[J]. 科学技术与工程, 2020, 20(27): 11137-11142.
WU Yun-liang,DENG Wei-si,YAO Hai-cheng,et al.Power System Operation Section Feature Selection and Online Generation Based on Two-Stage Structure[J].Science Technology and Engineering,2020,20(27):11137-11142.
基于两级结构的电网运行断面特征选择与在线生成
Power System Operation Section Feature Selection and Online Generation Based on Two-Stage Structure
投稿时间:2019-11-17  修订日期:2020-07-01
DOI:
中文关键词:  电网运行断面  在线生成  特征选择  机器学习
英文关键词:power system operation section  online generation  feature selection  machine learning
基金项目:广东省自然科学基金(编号:2018A0303130134)南方电网公司科技项目(编号:0000002019030101XT00035)
              
作者单位
吴云亮 中国南方电网电力调度控制中心
邓韦斯 中国南方电网电力调度控制中心
姚海成 中国南方电网电力调度控制中心
苏寅生 中国南方电网电力调度控制中心
周毓敏 中国南方电网电力调度控制中心
摘要点击次数: 112
全文下载次数: 58
中文摘要:
      为解决利用机器学习算法在线生成电网运行断面时所面临的特征因素“维数灾”问题,提出了一种基于两层模式的电网运行断面特征选择与在线生成方法。上层为过滤式特征选择层,采用Fisher分和信息增益两种特征选择指标对初始因素集进行筛选,重点剔除重复因素和无关因素,输出基础因素集。下层为包裹式特征选择层,利用序列后向搜索算法,进一步分析电网运行断面与运行参数之间的内在关系,生成特征因素集,同步形成基于该特征因素集的运行断面生成智能体。基于某地区电网实际数据构造的算例表明,本文方法能大幅降低特征因素“维度”,与初始因素集相比缩小90%以上,基于该特征因素集的智能体能在10秒中内在线生成运行断面,准确性评价指标达到95%,能够满足电网实时运行控制辅助决策的需要。
英文摘要:
      In order to solve the "dimensionality disaster" problem of feature factors in generating power network operation section online by machine learning algorithm, this paper proposes a two-stage structure method for power system operation section feature selection and online generation. The upper stage is a filter feature selection stage. In this stage, Fisher score and information gain are used to screen the initial factor set. The repetitive and irrelevant factors are mainly eliminated to output the basic factor set. The lower stage is an envelop feature selection stage. The sequential backward search algorithm is used to further analyze the internal relationship between the operation section and the operation parameters of the power grid, generate the feature factor set, and synchronously form the operation section generation agent based on the feature factor set. A case study based on the actual data in a certain region power grid shows that the method in this paper can greatly reduce the "dimension" of characteristic factors and reduce it by more than 90% compared with the initial factor set. The intelligent energy based on the feature factor set can generate the running section of the inner line within 10 seconds, and the accuracy evaluation index can reach more than 90%, which can meet the needs of auxiliary decision-making for real-time operation control of power grid.
查看全文  查看/发表评论  下载PDF阅读器
关闭
你是第34984784位访问者
版权所有:科学技术与工程编辑部
主管:中国科学技术协会    主办:中国技术经济学会
Tel:(010)62118920 E-mail:stae@vip.163.com
京ICP备05035734号-4
技术支持:本系统由北京勤云科技发展有限公司设计

京公网安备 11010802029091号