电力需求侧管理2026，Vol.28Issue(3)：52-58,7.DOI:10.3969/j.issn.1009-1831.2026.03.008
基于阈值调整的负荷辨识开集识别算法
Open-set recognition algorithm for load identification based on threshold adjustment
摘要
Abstract
Load identification is one of the key technologies in power system planning,operation,and management,playing a crucial role in the efficient scheduling and stable operation of smart grids.Traditional load identification methods typically rely on the closed-set assump-tion.However,in practical applications,the presence of unknown appliances makes it difficult for algorithms based on this assumption to achieve accurate recognition.To address this issue,an open-set load identification algorithm,OpenAppliance,based on threshold adjust-ment is proposed.The proposed algorithm integrates deep learning and probabilistic models,calibrating the neural network outputs to en-hance the detection capability for unknown categories while maintaining recognition accuracy for known categories.First,load data is trans-formed into an image format suitable for deep learning,and a CNN-based load identification model is constructed.Then,the OpenAppliance algorithm is applied for post-processing to adjust classification thresholds and optimize recognition results.Finally,the method is validated on the BLUED load dataset and compared with existing load identification algorithms.Experimental results demonstrate that the OpenAppli-ance algorithm enhances the generalization ability of load identification and significantly improves the accuracy and robustness of the load identification system.关键词
负荷辨识/开集识别/深度学习/未知类识别/概率模型Key words
load identification/open-set recognition/deep learning/unknown class recognition/probabilistic model分类
管理科学引用本文复制引用
李一鸣,邓君华,李志新,程含渺,鲍进,易永仙..基于阈值调整的负荷辨识开集识别算法[J].电力需求侧管理,2026,28(3):52-58,7.基金项目
国家电网公司科技项目(5700-202418277A-1-1-ZN) （5700-202418277A-1-1-ZN）
