电力需求侧管理2025，Vol.27Issue(1)：88-93,6.DOI:10.3969/j.issn.1009-1831.2025.01.014
一种基于自适应RNN的居民异常用电行为智能检测方法
Intelligent detection method for abnormal electricity consumption behavior of residents based on adaptive RNN
摘要
Abstract
A novel model based on adaptive recurrent neural network(RNN)is proposed to address the issues of low efficiency and poor performance in identifying abnormal electricity consumption behavior among residents.Design a SMOTE-ENN resampling method to in-crease the classification performance of imbalanced datasets.We have established an adaptive RNN detection model,using batch normal-ized RNN as the basic learner,and combining hyperparameter optimization and buffer to dynamically adjust the BNRNN model.In the ex-perimental stage,after improved SMOTE-ENN resampling,the classification performance of the model was significantly improved.At the same time,experiments have verified that the proposed adaptive RNN model with buffering and hyperparameter optimization has the low-est MAE error,indicating that the proposed model has excellent generalization ability.The experimental results validate the practicality and excellent performance of the proposed model,which can provide some reference for the development of abnormal electricity consump-tion behavior detection.关键词
配电网/数据驱动/异常用电/循环神经网络/超参数优化Key words
Distribution network/Data driven/Abnormal electricity consumption/Recurrent neural network/Hyperparameter optimization分类
信息技术与安全科学引用本文复制引用
陈育培,朱斌..一种基于自适应RNN的居民异常用电行为智能检测方法[J].电力需求侧管理,2025,27(1):88-93,6.基金项目
中国南方电网有限责任公司科技项目(070000KK52200015(HNKJXM20200224)) （070000KK52200015(HNKJXM20200224）
