Low-Complexity Non-Intrusive Load Monitoring Using Unsupervised Learning and Generalized Appliance Models
| Autor: | Nigel Linge, Mingxu Sun, Kondwani Michael Kamoto, Qi Liu, Xiaodong Liu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Fuzzy clustering
005 Computer programming programs & data Computer science QA75 Electronic computers. Computer science Feature extraction 020206 networking & telecommunications 02 engineering and technology Centre for Algorithms Visualisation and Evolving Systems computer.software_genre 7. Clean energy Field (computer science) AI and Technologies Generalized entropy index 0202 electrical engineering electronic engineering information engineering Media Technology Home Energy Management Non-Intrusive Load Monitoring Unsupervised Learning Appliance Modeling Unsupervised learning Data mining Electrical and Electronic Engineering Hidden Markov model Energy source Software systems computer Energy (signal processing) |
| Zdroj: | IEEE Transactions on Consumer Electronics |
| ISSN: | 0098-3063 1558-4127 |
| Popis: | Awareness of electric energy usage has both societal and economic benefits, which include reduced energy bills and stress on non-renewable energy sources. In recent years, there has been a surge in interest in the field of load monitoring, also referred to as energy disaggregation, which involves methods and techniques for monitoring electric energy usage and providing appropriate feedback on usage patterns to homeowners. The use of unsupervised learning in Non-Intrusive Load Monitoring (NILM) is a key area of study, with practical solutions having wide implications for energy monitoring. In this paper, a low-complexity unsupervised NILM algorithm is presented, which is designed toward practical implementation. The algorithm is inspired by a fuzzy clustering algorithm called Entropy Index Constraints Competitive Agglomeration (EICCA), but facilitated and improved in a practical load monitoring environment to produce a set of generalized appliance models for the detection of appliance usage within a household. Experimental evaluation conducted using energy data from the Reference Energy Data Disaggregation Dataset (REDD) indicates that the algorithm has out-performance for event detection compared with recent state of the art work for unsupervised NILM when considering common NILM metrics such as Accuracy, Precision, Recall, F-measure, and Total Energy Correctly Assigned (TECA). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|