| 基于FP-Growth的电力系统故障预测方法 |
| |
| 引用本文： | 潘,磊.基于FP-Growth的电力系统故障预测方法[J].教育技术导刊,2009,19(10):152-155. |
| |
| 作者姓名： | 潘 磊 |
| |
| 作者单位： | 南京工程学院 计算机工程学院，江苏 南京 211167 |
| |
| 基金项目： | 南京工程学院基础研究专项基金项目（JCYJ201825） |
| |
| 摘 要： | 为了提高电力系统中故障预测效率及便捷性，提出一种基于FP-Growth算法的电力系统故障预测方法，无需先验知识及人工标注，便可从海量历史日志数据中快速提取出故障信息模式，并基于实时日志数据对未来可能发送的系统故障进行预测。该方法首先根据电力系统不同类型的日志特征对原始数据进行预处理，然后基于FP-Growth算法挖掘日志中与故障事件相关的关联规则，并使用关联规则进行故障匹配，从而达到预测效果。算法经过真实电力系统日志数据集测试，结果表明该故障预测方法平均准确率为89.5%，平均召回率为79.8%，且执行效率较高，节省了业务人员50%以上的时间。
|
| 关 键 词： | FP-Growth 电力系统日志 关联规则 故障预测 日志挖掘 |
| 收稿时间： | 2020-07-20 |
Power System Fault Prediction Based on FP-Growth Algorithm |
| |
| PAN Lei.Power System Fault Prediction Based on FP-Growth Algorithm[J].Introduction of Educational Technology,2009,19(10):152-155. |
| |
| Authors: | PAN Lei |
| |
| Institution: | School of Computer Engineering， Nanjing Institute of Technology， Nanjing 211167， China |
| |
| Abstract: | In order to improve the efficiency and convenience of fault prediction in the power system， a power system fault prediction method based on the FP-Growth algorithm is proposed by this paper. The method can extract fault prediction rules quickly from the massive power system history logs without any prior knowledge and manual annotation， and then predict future system failures based on the real-time logs. Firstly， the original logs are preprocessed according to the characteristics of the power system logs. Then the association rules related to the failure event in the log are mined based on the FP-Growth algorithm， and the association rules are used to match the failure. The algorithm has been tested on real power system log data sets. The results show that the average accuracy of the fault prediction method in this paper is 89.5%， the average recall rate is 79.8%， and the execution efficiency is high， saving more than 50% of the time of business staff. |
| |
| Keywords: | FP-Growth power system log association rule fault prediction log mining |
|
| 点击此处可从《教育技术导刊》浏览原始摘要信息 |
| 点击此处可从《教育技术导刊》下载免费的PDF全文 |
