{"title":"MAMBA2NILM: a non-intrusive load monitoring approach combined the SENet attention mechanism and Mamba2","authors":"Chunning Na, Yudi Zhou, Feng Li, Huan Pan","doi":"10.1016/j.epsr.2025.111805","DOIUrl":null,"url":null,"abstract":"<div><div>Non-Intrusive Load Monitoring (NILM) aims to disaggregate smart meter measurement into individual appliance-level power consumption. Existing Transformer-based models in NILM often fail to capture local signal features, resulting in suboptimal decomposition performance and excessive training times. To address these challenges, we propose Mamba2NILM, a hybrid framework integrating the Squeeze and Excitation networks (SENet) and Mamba2 into a Transformer architecture. This design synergistically balances local feature extraction and global context modeling, while reducing computational complexity. Additionally, the embedded SE module emphasizes indirect enhancement of periodic features and dynamic screening of multi-scale features. Experimental evaluations, including quantitative metrics and visual analysis, confirm that Mamba2NILM achieves superior efficiency and effectiveness, outperforming state-of-the-art baselines.</div></div>","PeriodicalId":50547,"journal":{"name":"Electric Power Systems Research","volume":"247 ","pages":"Article 111805"},"PeriodicalIF":3.3000,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electric Power Systems Research","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378779625003967","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
Non-Intrusive Load Monitoring (NILM) aims to disaggregate smart meter measurement into individual appliance-level power consumption. Existing Transformer-based models in NILM often fail to capture local signal features, resulting in suboptimal decomposition performance and excessive training times. To address these challenges, we propose Mamba2NILM, a hybrid framework integrating the Squeeze and Excitation networks (SENet) and Mamba2 into a Transformer architecture. This design synergistically balances local feature extraction and global context modeling, while reducing computational complexity. Additionally, the embedded SE module emphasizes indirect enhancement of periodic features and dynamic screening of multi-scale features. Experimental evaluations, including quantitative metrics and visual analysis, confirm that Mamba2NILM achieves superior efficiency and effectiveness, outperforming state-of-the-art baselines.
期刊介绍:
Electric Power Systems Research is an international medium for the publication of original papers concerned with the generation, transmission, distribution and utilization of electrical energy. The journal aims at presenting important results of work in this field, whether in the form of applied research, development of new procedures or components, orginal application of existing knowledge or new designapproaches. The scope of Electric Power Systems Research is broad, encompassing all aspects of electric power systems. The following list of topics is not intended to be exhaustive, but rather to indicate topics that fall within the journal purview.
• Generation techniques ranging from advances in conventional electromechanical methods, through nuclear power generation, to renewable energy generation.
• Transmission, spanning the broad area from UHV (ac and dc) to network operation and protection, line routing and design.
• Substation work: equipment design, protection and control systems.
• Distribution techniques, equipment development, and smart grids.
• The utilization area from energy efficiency to distributed load levelling techniques.
• Systems studies including control techniques, planning, optimization methods, stability, security assessment and insulation coordination.