A Multiprocessor for Transient Event Detection

The 2010 14th International Conference on Computer Supported Cooperative Work in Design

Lin

Lee

2010

ҏ Non-intrusive load monitoring (NILM) techniques are based on the analysis of load energy signatures. With characterizing associated transient energy signature, the reliability and accuracy of recognition results can be accurately understood or ascertained. In this study, the computer supported cooperative work techniques (CSCW), artificial neural networks (ANN), in combination with turn-on transient energy analysis, are used to identify loads and to improve recognition accuracy and computational speed of NILM results. The experimental results indicated that the incorporation of turn-on transient energy signature analysis into NILM revealed more information than traditional NILM methods, and the resulting recognition accuracy and computational speed were improved. In addition, in combination with computer supported cooperative work in electromagnetic transient program (EMTP) simulation, calculations of turn-on transient energy facilitated load identification that had significant effect on NILM results.

Section: Turn-on Transient Energy Algorithmsmentioning

confidence: 99%

Section: Turn-on Transient Energy Algorithmsmentioning

confidence: 99%

Load identification in nonintrusive load monitoring using steady-state and turn-on transient energy algorithms

The 2010 14th International Conference on Computer Supported Cooperative Work in Design

Lin

Lee

2010

“…The transient properties of a typical electrical load are mainly determined by the physical task that the load performs [22], [23). Transient energy may assume different forms in consumer appliances, depending on the generating mechanism [1).…”

Section: A Turn-on Transient Energy Algorithmsmentioning

confidence: 99%

“…Load classes performing different tasks are therefore distinguishable by their transient behavior [22], [23]. Since the envelopes of turn-on transient instantaneous power are closely linked to unique physical quantities, they can serve as reliable metrics for load identification.…”

Section: A Turn-on Transient Energy Algorithmsmentioning

confidence: 99%

A new measurement method for power signatures of non-intrusive demand monitoring and load identification

2011 IEEE Industry Applications Society Annual Meeting

Chen

Tsai

et al. 2011

Based upon the analysis of load signatures, this paper presents a Non-intrusive load monitoring (NILM) technique. With characterizing associated with the transient response of energy signature, a reliable and accurate recognition result can be obtained. In this study, artificial neural networks (ANN), in combination with turn-on transient energy analysis, are used to improve recognition accuracy and computational speed of NILM results. To minimize the distortion phenomenon in current measurements from the hysteresis of traditional current transformers (CTs) iron cores, coreless Hall effect current transformer is adopted to accurately detect non sinusoidal waves to improve NILM accuracy. The experimental results indicate that the incorporation of turn-on transient energy algorithm into NILM significantly improve the recognition accuracy and computational speed.

“…These appliances have no sufficient features to be identified whether the load is starting or operating, or if these features are only steady-state features or transient features. These features [4][5][6][7][8][9], when selected, have been proven to enhance the capability of a NILM system to distinguish among industrial loads or different loads with the same real power (P) and reactive power (Q) under multiple operations using the turn-on transient energy feature (U T ) and traditional steady-state power features by analyzing the physical industrial load characteristics. Figure 1 schematically illustrates the overall scheme in the NILM system.…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction of Non-intrusive Load-Monitoring System Using Genetic Algorithm in Smart Meters

2011 IEEE 8th International Conference on E-Business Engineering

Chien

Lin

et al. 2011

This paper proposes non-intrusive load-monitoring (NILM) techniques using artificial neural networks (ANN) in combination with genetic algorithm (GA) to identify load demands and improve recognition accuracy of non-intrusive load-monitoring results. The feature extraction method of genetic algorithm can improve the efficiency of load identification and computational time under multiple operations. After comparing various training algorithms and classifiers in terms of artificial neural networks due to various factors that determine whether a network is being used for pattern recognition, the back propagation artificial neural network (BP-ANN) classifier is adopted in the load identification process. Additionally, in combination with electromagnetic transients program (EMTP) simulations and measurements on site, extracting the features of power signatures can lead to accurate load identifications and is a significant feature in smart meters.