Load Disaggregation Using Microscopic Power Features and Pattern Recognition

• Published in: Energies (Basel) 2019, Vol.12 (14), p.2641
• Main Authors: de Souza, Wesley Angelino, Garcia, Fernando Deluno, Marafão, Fernando Pinhabel, da Silva, Luiz Carlos Pereira, Simões, Marcelo Godoy
• Format: Article
• Language: English
• Subjects: Accuracy; Air conditioning; Algorithms; Appliances; Artificial intelligence; Automatic meter reading; Classification; cognitive meters; Computer engineering; Computer simulation; Consumers; Datasets; Disaggregation; Efficiency; Electric appliances; Electric power generation; Electricity; Electricity consumption; Embedded systems; Energy conservation; Energy consumption; Energy efficiency; Energy management; Energy management systems; Feasibility studies; Feature recognition; Household appliances; Infrastructure; Learning algorithms; load disaggregation; Machine learning; NILM; Pattern recognition; Power plants; state machine; State machines; Ubiquitous computing; Virtual power plants; Waveforms; Wavelet transforms
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en12142641

A new generation of smart meters are called cognitive meters, which are essentially based on Artificial Intelligence (AI) and load disaggregation methods for Non-Intrusive Load Monitoring (NILM). Thus, modern NILM may recognize appliances connected to the grid during certain periods, while providing much more information than the traditional monthly consumption. Therefore, this article presents a new load disaggregation methodology with microscopic characteristics collected from current and voltage waveforms. Initially, the novel NILM algorithm—called the Power Signature Blob (PSB)—makes use of a state machine to detect when the appliance has been turned on or off. Then, machine learning is used to identify the appliance, for which attributes are extracted from the Conservative Power Theory (CPT), a contemporary power theory that enables comprehensive load modeling. Finally, considering simulation and experimental results, this paper shows that the new method is able to achieve 95% accuracy considering the applied data set.