Classification of power quality events using wavelet packet transform and extreme learning machine

Abstract

A novel method of classifying Power quality (PQ) events using Wavelet Packet Transform (WPT) and Extreme Learning Machines (ELM) has been proposed. In recent times, the power quality has been a major research concern due to changing regulations, liberalized distribution market and increased use of power electronic based equipment. The first step of any remedial action requires proper identification of PQ events. One of the major challenge of this event identification is to extract significant features from the limited measurements, which can subsequently be used for the classification. Therefore, in the present study Wavelet Packet Transform (WPT) has been used to obtain several mathematical features. These features can segregate both single and simultaneous PQ event occurrences. Further to improve the classification performance, the ELM based classifier has been used. This classifier significantly reduces the training time by many-fold. The performance of the proposed approach has been compared with ANN based classifier considering over 1000 PQ signals from various PQ events. The results of the simulation demonstrate that the proposed approach can achieve over 99% classification accuracy.

Efficient feature selection of power quality events using two dimensional (2D) particle swarms

“…The overall performance of the compared algorithms is evaluated using the 'overall-score' metric (12), which considers both the cardinality, ξ, and the classification performance, J(· ), of the feature subsets obtained by the algorithm over 40 runs. As revealed by (12), a lower score indicates the consistent discovery of a subset with fewer features and lower classification error by the algorithm. As seen in Table 3-4, the overall score obtained by 2D-UPSO is the lowest amongst the compared algorithms which indicates the best overall performance.…”

“…Most of the existing PQ event identification approaches are based on this framework [6,7]. Note that the utility/efficacy of the extracted features is usually not evaluated in most of the existing PQ identification approaches [8][9][10][11][12], which often leads to the inclusion of irrelevant, redundant and noisy features.…”

Online power quality disturbance detection by support vector machine in smart meter

“…Sahani [50] composed 9 classes, including momentary interruption, sag, swell, harmonics, flicker, notch, spike, transient, and sag with harmonics. Khokhar [51] presented 6 more categories in addition to [52] which are swell with harmonics, interruption and harmonics, impulsive transient, flicker with harmonics, flicker with swell, and flicker with sag.…”

Structure Selection of Polynomial NARX Models Using Two Dimensional (2D) Particle Swarms

“…To understand the position update process, consider the velocity of an i th particle for a structure selection problem with N t = 5 as follows: Re-initialize the velocity of the particle 10 Set counti to zero 11 end 12 Update the velocity of the i th particle as per (3), (4) and (5) 13…”

“…Note that the structure selection is essentially a multiobjective problem and the aim of both information criteria, AIC and BIC, is to balance search objectives, i.e., reduction in e and cardinality of the model. The selection of in (12) is equivalent to guiding a search towards a particular region of the Pareto front. Although this gives the freedom to decision maker to guide the search as per requirement, it is quite challenging to properly tune .…”