Non-Intrusive Load Monitoring Based on Feature Extraction of Change-point and XGBoost Classifier

2020 ◽  
Author(s):  
Zhuo Chen ◽  
Junxingxu Chen ◽  
Xianyong Xu ◽  
Shuangjian Peng ◽  
Jian Xiao ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Change Point ◽  
Load Monitoring

Feature Extraction for Non-intrusive Load Monitoring System

2021 ◽  
Author(s):  
Qiuzhan Zhou ◽  
Jiahui Wei ◽  
Mingyu Sun ◽  
Cong Wang ◽  
Jing Rong ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Monitoring System ◽  
Load Monitoring

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

Energies ◽  
2020 ◽  
Vol 13 (17) ◽  
pp. 4396
Author(s):  
André Eugenio Lazzaretti ◽  
Douglas Paulo Bertrand Renaux ◽  
Carlos Raimundo Erig Lima ◽  
Bruna Machado Mulinari ◽  
Hellen Cristina Ancelmo ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Event Detection ◽  
Classification Accuracy ◽  
Agent Architecture ◽  
Performance Improvements ◽  
Load Monitoring ◽  
Multi Agent ◽  
Improved Performance ◽  
New Algorithms

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%.

Helicopter flight data feature extraction or component load monitoring

1996 ◽  
Vol 33 (1) ◽  
pp. 37-45 ◽  
Author(s):  
David J. Haas ◽  
Lance Flitter ◽  
Joel Milano
Keyword(s):  
Feature Extraction ◽  
Flight Data ◽  
Helicopter Flight ◽  
Load Monitoring

scholarly journals An Embedded System for NILM Using Machine Learning

2021 ◽  
Author(s):  
Giovanni Braglia ◽  
André Eugênio Lazzaretti
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Power Consumption ◽  
Embedded System ◽  
Energy Demand ◽  
Real Life ◽  
Load Monitoring ◽  
Future Challenges ◽  
Domestic Plant

The interest in power managing systems has been growing in recent years since every industrial or domestic plant moves towards techniques to efficiently reduce energy demand and costs related to it. An attractive solution is represented by Non-Intrusive Load Monitoring (NILM) systems, whose primary purpose is to find a more appropriate way of keeping track of the power consumption caused by each of the loads that are connected to the monitored plant. A possible real-life implementation of a NILM system is addressed in this work, discussing all the fundamental blocks in its structure, including detecting events, feature extraction, and load classification, using publicly available datasets. Additionally, we provide a solution for an embedded system, able to analyze aggregated waveforms and to recognize each appliance’s contribution in it. The main algorithm, its features, drawbacks, and implementation are thus explained, showing current and future challenges for the final application.

Sign in / Sign up

Export Citation Format

Share Document