Particle Swarm Optimization based non-intrusive demand monitoring and load identification in smart meters
- 1 October 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2012 IEEE Industry Applications Society Annual Meeting
Abstract
Comparing with the traditional load monitoring system, Non-Intrusive Load Monitoring (NILM) system is simple to install and does not need individual sensor for each load. Accordingly, the NILM system can be applied for wide load monitoring and become a powerful energy management and measurement system. Though several NILM algorithms have been developed during the last two decades, the recognition accuracy and computational efficiency remain challenges. To minimize the training time and improve recognition accuracy in Artificial Neural Networks (ANNs), a Particle Swarm Optimization (PSO) is adopted in this paper to optimize parameters of training algorithm in ANN to improve NILM accuracy. Case studies are verified through the combination of Electromagnetic Transients Program (EMTP) simulations and field measurements. The results indicate that the proposed method significantly improves the recognition accuracy and computational speed under multiple operation conditions.Keywords
This publication has 16 references indexed in Scilit:
- Particle swarm optimizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Nonintrusive Load Monitoring and Diagnostics in Power SystemsIEEE Transactions on Instrumentation and Measurement, 2008
- Locating Switched Capacitor Using Wavelet Transform and Hybrid Principal Component Analysis NetworkIEEE Transactions on Power Delivery, 2007
- Neural-Network-Based Signature Recognition for Harmonic Source IdentificationIEEE Transactions on Power Delivery, 2005
- Genetic algorithm for pattern detection in NIALM systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The ANNIGMA-wrapper approach to fast feature selection for neural netsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2002
- Input feature selection for classification problemsIEEE Transactions on Neural Networks, 2002
- Nonintrusive load disaggregation computer program to estimate the energy consumption of major end uses in residential buildingsEnergy Conversion and Management, 2000
- Comparison of algorithms that select features for pattern classifiersPattern Recognition, 2000
- Using a pattern recognition approach to disaggregate the total electricity consumption in a house into the major end-usesEnergy and Buildings, 1999