摘要
如何从用户能耗数据中准确地挖掘出有价值的信息一直是电力行业的研究热点,而贝叶斯分类算法则是机器学习和数据挖掘研究领域中常用的数据处理方法之一。此方法具有简单、高效以及分类效果稳定的优点,而且可以建立可对数据库中给定类别的数据记录进行映射的模型以及可描述能耗数据以预测趋势的模型,从而为用户综合能耗特征识别提供有效的解决方案。但是传统的贝叶斯分类算法的分类精度较低,往往不能满足其他对于分类精度有着高要求的研究需求。基于这种情况,通过构建扩展模型,设计了基于粗糙集理论的贝叶斯分类算法,从而满足用户综合能耗特征识别中对于分类精度的需求。最后,通过直接的实验结果来验证基于粗糙集贝叶斯分类算法的综合能耗特征识别可以在很大程度上提高分类精度。
How to accurately mine valuable information from users′energy consumption data has always been a research hotspot in the power industry,and Bayesian classification algorithm is one of the commonly used data processing methods in the field of machine learning and data mining.This method has the advantages of simple,efficient and stable classification effect,and can build a model that can map the data records of a given category in the database and a model that can describe the energy consumption data to predict the trend,so as to provide an effective solution for users to identify comprehensive energy consumption characteristics.However,the traditional Bayesian classification algorithm has a low classification accuracy and is often unable to meet other research needs with high requirements for classification accuracy.Based on this situation,a Bayesian classification algorithm based on rough set theory by constructing an extended model was designed,so as to meet the requirements of classification accuracy in the user′s comprehensive energy consumption feature recognition.Through the direct experimental results to verify that the comprehensive energy consumption feature recognition based on rough set Bayesian classification algorithm can greatly improve the classification accuracy.
作者
罗婷
刘莹莹
Luo Ting;Liu Yingying(Dongguan Power Supply Bureau,Guangdong Power Grid Co.,Ltd.,Dongguan,Guangdong 523000,China)
出处
《机电工程技术》
2020年第11期151-153,共3页
Mechanical & Electrical Engineering Technology
关键词
粗糙集
贝叶斯分类算法
特征识别
分类精度
Rough set
Bayesian classification algorithm
eature identification
classification accuracy
