A Multi-Agent NILM Architecture for Event Detection and Load Classification

André Eugenio Lazzaretti; Douglas Paulo Bertrand Renaux; Carlos Raimundo Erig Lima; Bruna Machado Mulinari; Hellen Cristina Ancelmo; Elder Oroski; Fabiana Pöttker; Robson Ribeiro Linhares; Lucas da Silva Nolasco; Lucas Tokarski Lima; Júlio Shigeaki Omori; Rodrigo Braun dos Santos

LAPSE

Living Archive for Process Systems Engineering

LAPSE:2023.26029

Published Article

LAPSE:2023.26029

A Multi-Agent NILM Architecture for Event Detection and Load Classification

André Eugenio Lazzaretti, Douglas Paulo Bertrand Renaux, Carlos Raimundo Erig Lima, Bruna Machado Mulinari, Hellen Cristina Ancelmo, Elder Oroski, Fabiana Pöttker, Robson Ribeiro Linhares, Lucas da Silva Nolasco, Lucas Tokarski Lima, Júlio Shigeaki Omori, Rodrigo Braun dos Santos

March 31, 2023

A multi-agent architecture for a Non-Intrusive Load Monitoring (NILM) solution is presented and evaluated. The underlying rationale for such an architecture is that each agent (load event detection, feature extraction, and classification) outperforms others of the same type in particular scenarios; hence, by combining the expertise of these agents, the system presents an improved performance. Known NILM algorithms, as well as new algorithms, proposed by the authors, were individually evaluated and compared. The proposed architecture considers a NILM system composed of Load Monitoring Modules (LMM) that report to a Center of Operations, required in larger facilities. For the purposed of evaluating and comparing performance, five load event detect agents, five feature extraction agents, and five classification agents were studied so that the best combinations of agents could be implemented in LMMs. To evaluate the proposed system, the COOLL and the LIT-Dataset were used. Performance improvements were detected in all scenarios, with power-ON and power-OFF detection improving up to 13%, while classification accuracy improved up to 9.4%.

Record ID

LAPSE:2023.26029

Keywords

event detection, feature extraction, load classification, NILM, NILM architecture, non-intrusive load monitoring

Subject

Process Operations

Suggested Citation

Lazzaretti AE, Renaux DPB, Lima CRE, Mulinari BM, Ancelmo HC, Oroski E, Pöttker F, Linhares RR, Nolasco LDS, Lima LT, Omori JS, Santos RBD. A Multi-Agent NILM Architecture for Event Detection and Load Classification. (2023). LAPSE:2023.26029

Author Affiliations

Lazzaretti AE: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil [ORCID]
Renaux DPB: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Lima CRE: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Mulinari BM: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Ancelmo HC: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Oroski E: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Pöttker F: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Linhares RR: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Nolasco LDS: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Lima LT: LIT—Laboratory of Innovation and Technology in Embedded Systems and Energy, Universidade Tecnológica Federal do Paraná—UTFPR, Sete de Setembro, 3165, Curitiba 80230-901, Brazil
Omori JS: COPEL—Companhia Paranaense de Energia, José Izidoro Biazetto, 158, Curitiba 82305-100, Brazil
Santos RBD: COPEL—Companhia Paranaense de Energia, José Izidoro Biazetto, 158, Curitiba 82305-100, Brazil

Journal Name

Energies

Volume

13

Issue

17

Article Number

E4396

Year

2020

Publication Date

2020-08-26