摘要
智能电表低频采样非侵入式负荷分解任务中存在负荷启停事件稀疏、样本类别分布失衡的问题,少数类及边界样本匮乏易导致模型在负荷开启与过渡阶段出现漏检、误判,而现有过采样方法在合成样本数量精确控制、近邻筛选及边界界定上存在不足,随机插值策略还容易引入重复或跨类混叠样本。为解决上述问题,本文提出了结合K-means聚类与Borderline-SMOTE的改进算法(KB-SMOTE):先提取少数类边界样本并聚类分簇,再以簇心引导簇内插值生成新样本,减少冗余并增强边界可分性。模型层面,针对传统时序网络对关键瞬态与局部特征捕捉不足的问题,设计了基于卷积块注意力模块改进混合注意力机制的Bi-LSTM负荷分解模型,通过通道与空间注意力协同实现特征自适应重加权,强化负荷运行相关关键信息。UK-DALE数据集仿真实验表明:相较于DAE、Seq2point及基础Bi-LSTM等基线模型,本文方法在多项评价指标上性能更优,验证了其在不平衡负荷数据场景的有效性。
In smart-meter based non-intrusive load disaggregation with low-frequency sampling,load switching events are sparse and the class distribution is imbalanced.The shortage of minority-class and boundary samples tends to cause missed detections and misclassifications during load ON states and transition stages.Existing oversampling methods still have limitations in precisely controlling the number of synthesized samples,selecting nearest neighbors,and defining boundary samples,and random interpolation strategies may further introduce redundant samples or cross-class mixed samples.To address these issues,this paper proposes an improved algorithm that combines K-means clustering with Borderline-SMOTE(KB-SMOTE):minority boundary samples are first extracted and clustered,and then centroid-guided within-cluster interpolation is performed to generate new samples,thereby reducing redundancy and enhancing boundary separability.At the model level,to overcome the limited capability of conventional sequence networks in capturing key transient and local features,a Bi-LSTM based load disaggregation model embedded with a convolutional block attention module is designed.By jointly leveraging channel and spatial attention,the model adaptively reweights features and strengthens key information relevant to load operating states.Experiments on the UK-DALE dataset show that,compared with baseline models including DAE,Seq2point,and the basic Bi-LSTM,the proposed method achieves better performance on multiple evaluation metrics,validating its effectiveness in imbalanced-load scenarios.
作者
周求湛
李新萌
沈皓庆子
武慧南
李媛媛
荣静
胡春华
刘萍萍
ZHOU Qiu-zhan;LI Xin-meng;SHEN Hao-qing-zi;WU Hui-nan;LI Yuan-yuan;RONG Jing;HU Chun-hua;LIU Ping-ping(College of Communication Engineering,Jilin University,Changchun 130012,China;Jinhua Power Supply Company Metering Center,State Grid Zhejiang Electric Power Company,Jinhua 321000,China;Yantai Dongfang Wisdom Electric Co.,Ltd.,Yantai 264003,China;College of Computer Science and Technology,Jilin University,Changchun 130012,China)
出处
《吉林大学学报(工学版)》
北大核心
2026年第1期239-246,共8页
Journal of Jilin University:Engineering and Technology Edition
基金
中央引导地方科技发展资金项目(YDZX2023075).
