基本信息:
- 专利标题： 一种基于并行关联规则挖掘的配电网运行可靠性预测方法
- 专利标题（英）：Parallel association rule mining-based method for predicting running reliability of power distribution network
- 申请号：CN201610751986.5 申请日：2016-08-29
- 公开(公告)号：CN106446016A 公开(公告)日：2017-02-22
- 发明人： 胡丽娟 , 刘科研 , 刁赢龙 , 盛万兴 , 孟晓丽 , 贾东梨 , 何开元 , 叶学顺 , 董伟杰 , 唐建岗 , 李雅洁
- 申请人： 中国电力科学研究院 , 国家电网公司 , 国网北京市电力公司
- 申请人地址： 北京市海淀区清河小营东路15号
- 专利权人： 中国电力科学研究院,国家电网公司,国网北京市电力公司
- 当前专利权人： 中国电力科学研究院,国家电网公司,国网北京市电力公司
- 当前专利权人地址： 北京市海淀区清河小营东路15号
- 代理机构： 北京安博达知识产权代理有限公司
- 代理人： 徐国文
- 主分类号： G06F17/30
- IPC分类号： G06F17/30 ; G06Q10/04 ; G06Q50/06
The invention provides a parallel association rule mining-based method for predicting running reliability of a power distribution network. The method comprises the steps of 1, extracting related data from multi-source heterogeneous power distribution big data according to running reliability assessment demands; 2, mining related factors which influence the running reliability by adopting a parallel association rule mining method, and building an ''influence factor-running reliability index relevance model''; 3, obtaining a main influence factor as an input of an artificial neural network, and building an ''influence factor-running reliability index quantitative calculation model'' based on historical running conditions and running reliability parameters; and 4, taking real-time running condition data as an input of the artificial neural network, and predicting a running reliability index value in a corresponding running condition. According to the method, the main factor which influences a reliability index is accurately located, so that the input data dimensions of an assessment model are reduced, and the modeling difficulty is lowered.
IPC结构图谱:
| G | 物理 |
| --G06 | 计算；推算；计数 |
| ----G06F | 电数字数据处理 |
| ------G06F17/00 | 特别适用于特定功能的数字计算设备或数据处理设备或数据处理方法 |
| --------G06F17/30 | .信息检索；及其数据库结构 |