电力信息与通信技术2026，Vol.24Issue(4)：91-97,7.DOI:10.16543/j.2095-641x.electric.power.ict.2026.04.12
基于知识蒸馏与不确定性估计的分布式异常检测
Distributed Anomaly Detection Based on Knowledge Distillation and Uncertainty Estimation
摘要
Abstract
A distributed anomaly detection scheme based on knowledge distillation and uncertainty estimation is proposed to meet the real-time and accurate requirements of power Internet of Things systems.The scheme first constructs a high-precision teacher model of anomaly detection based on the multi-scale spatiotemporal residual network and Gate Recurrent Unit,enhancing spatiotemporal data features'deep representation and generalization ability.Then,utilizing knowledge distillation techniques to generate lightweight and efficient student models to meet the requirements of distributed deployment.Finally,utilizing uncertainty estimation to optimize the anomaly detection results of distributed nodes further enhances the detection performance of the model.The experimental results show that the anomaly detection accuracy of the proposed system can reach 95%,the time efficiency of model training is improved by about 60%,and with better generalizability.关键词
知识蒸馏/不确定性估计/分布式异常检测/电力物联网Key words
knowledge distillation/uncertainty estimation/distributed anomaly detection/power Internet of Things分类
信息技术与安全科学引用本文复制引用
沙倚天,刘少君,李天一,陈鹏,李雪菲,金倩倩..基于知识蒸馏与不确定性估计的分布式异常检测[J].电力信息与通信技术,2026,24(4):91-97,7.基金项目
国网江苏省电力有限公司科技项目"基于深度学习的内生免疫持续增强技术研究"(J2023110). （J2023110）
