Transparent AI: Explainability of deep learning based load disaggregation

被引：4
|
作者：
Murray, David [1 ]
Stankovic, Lina [1 ]
Stankovic, Vladimir [1 ]
机构：
[1] Univ Strathclyde Glasgow, Dept Elect & Elect Engn, Glasgow, Lanark, Scotland
来源：
BUILDSYS'21: PROCEEDINGS OF THE 2021 ACM INTERNATIONAL CONFERENCE ON SYSTEMS FOR ENERGY-EFFICIENT BUILT ENVIRONMENTS | 2021年
关键词：
datasets; neural networks; reliability; validation;
D O I：
10.1145/3486611.3492410
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
The paper focuses on explaining the outputs of deep-learning based non-intrusive load monitoring (NILM). Explainability of NILM networks is needed for a range of stakeholders: (i) technology developers to understand why a model is under/over predicting energy usage, missing appliances or false positives, (ii) businesses offering energy advice based on NILM as part of a broader energy home management recommender system, and (iii) end-users who need to understand the outcomes of the NILM inference.
引用
收藏
页码：268 / 271
页数：4
相关论文
共 50 条
  • [1] Toward Transparent Load Disaggregation-A Framework for Quantitative Evaluation of Explainability Using Explainable AI
    Batic, Djordje
    Stankovic, Vladimir
    Stankovic, Lina
    [J]. IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2024, 70 (01) : 4345 - 4356
  • [2] Comparative study of deep learning explainability and causal ai for fraud detection
    Parkar, Erum
    Gite, Shilpa
    Mishra, Sashikala
    Pradhan, Biswajeet
    Alamri, Abdullah
    [J]. INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS, 2024, 17 (01):
  • [3] Non-intrusive Load Disaggregation Method Based on Edge Embedded Deep Learning
    Liu Y.
    Sun Y.
    Li B.
    Huang T.
    [J]. Dianwang Jishu/Power System Technology, 2019, 43 (12): : 4329 - 4336
  • [4] Explainability and Dependability Analysis of Learning Automata based AI Hardware
    Shafik, Rishad
    Wheeldon, Adrian
    Yakovlev, Alex
    [J]. 2020 26TH IEEE INTERNATIONAL SYMPOSIUM ON ON-LINE TESTING AND ROBUST SYSTEM DESIGN (IOLTS 2020), 2020,
  • [5] Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI
    Ghosh, Promila
    Mondal, Amit Kumar
    Chatterjee, Sajib
    Masud, Mehedi
    Meshref, Hossam
    Bairagi, Anupam Kumar
    [J]. MATHEMATICS, 2023, 11 (10)
  • [6] Investigation of Deep Learning-based Techniques for Load Disaggregation, Low-Frequency Approach
    Alkhulaifi, Abdolmaged
    Aljohani, Abdulah J.
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2020, 11 (01) : 701 - 706
  • [7] Non-intrusive Load Disaggregation Based on Deep Learning and Multi-feature Fusion
    Liu, Hang
    Liu, Chunyang
    Tian, Lijun
    Zhao, Haoran
    Liu, Junwei
    [J]. 2021 3RD INTERNATIONAL CONFERENCE ON SMART POWER & INTERNET ENERGY SYSTEMS (SPIES 2021), 2021, : 210 - 215
  • [8] Non-intrusive Disaggregation of Electricity and Gas Load in Public Buildings Based on Deep Learning
    Liu H.
    Liu C.
    Zhao H.
    Tian L.
    Liu J.
    [J]. Dianwang Jishu/Power System Technology, 2023, 47 (03): : 1188 - 1195
  • [9] Non-Intrusive A/C Load Disaggregation Using Deep Learning
    Cho, Jin
    Hu, Zhen
    Sartipi, Mina
    [J]. 2018 IEEE/PES TRANSMISSION AND DISTRIBUTION CONFERENCE AND EXPOSITION (T&D), 2018,
  • [10] Explainability in deep reinforcement learning
    Heuillet, Alexandre
    Couthouis, Fabien
    Diaz-Rodriguez, Natalia
    [J]. KNOWLEDGE-BASED SYSTEMS, 2021, 214 (214)
12345