Implementation of Support-Vector-Machine-Based Relay Coordination Scheme for Distribution System With Renewables

Vijayachandran, Vinod; Shenoy, U. Jayachandra

doi:10.1109/jestie.2020.3014875

Cited by 12 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM comes from the statistical learning theory and is based on quadratic constrained programming and kernel transformations, applied in classification and regression applications. 19,20,27,28 The SVM is initially defined as a binary classification technique derived from the optimization of the separation threshold. In a training database, each data consists of signal features (f ) in a N dimensional space and a target value, usually denoted as 1 or À1, which in this case corresponds to two faulty zones (y) as in Equation ( 4).…”

Section: Parameters Of the Classification Technique (P)mentioning

confidence: 99%

“…The LBFZLs use big‐data concepts applied in modelling engineering problems 11‐13,19 . In the proposed approach, the faulty zone location is modelled as a classification problem, where each fault is related to a faulty zone of the distribution system.…”

Section: Problem Statementsmentioning

confidence: 99%

“…The core of the proposed LBFZL is the SVM, used as a classifier. SVM comes from the statistical learning theory and is based on quadratic constrained programming and kernel transformations, applied in classification and regression applications 19,20,27,28 . The SVM is initially defined as a binary classification technique derived from the optimization of the separation threshold.…”

Section: Problem Statementsmentioning

confidence: 99%

“…The LBFZLs use big-data concepts applied in modelling engineering problems. [11][12][13]19 In the proposed approach, the faulty zone location is modelled as a classification problem, where each fault is related to a faulty zone of the distribution system. The adjustment-variables considered in this paper are defined as: the features obtained from the voltage and current signals (f ), the type of data normalization (n), the size of the representative fault database (r), the parameters of the classification technique (p) and the definition of the zone division (z).…”

Section: Problem Statementsmentioning

confidence: 99%

See 3 more Smart Citations

Adjustment strategy of a learning‐based faulty zone locator for distribution systems

Correa-Tapasco

Pérez-Londoño

Flórez

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

Fault location is a functionality of the advanced distribution automation for smart grids. This functionality is considered in this paper using a learning-based faulty zone locator (LBFZL), which requires the adequate selection of its adjustment-variables. As these variables are strongly interrelated, the strategy proposed in this paper uses an iterative approach to determine their fair values based on sampling and learning theories. The proposed strategy guides the adjustment process considering the LBFZL performance. According to the analysed tests, the results present a successful selection of the five defined adjustment-variables, due to the high performance in locating single-phase, phase-to-phase, and three-phase faulty zones, in a 34.5 kV-75 bus distribution system. As a result of the proposal application, satisfactory values for the five adjustmentvariables are obtained; and finally, the expected LBFZL performance is higher than 95% for all fault types.

show abstract

Section: Parameters Of the Classification Technique (P)mentioning

confidence: 99%

Section: Problem Statementsmentioning

confidence: 99%

Section: Problem Statementsmentioning

confidence: 99%

Section: Problem Statementsmentioning

confidence: 99%

See 2 more Smart Citations

Adjustment strategy of a learning‐based faulty zone locator for distribution systems

Correa-Tapasco

Pérez-Londoño

Flórez

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

show abstract

“…However, its performance is only explored for three‐phase‐to‐ground faults. An SVM‐based overcurrent protection scheme is proposed for distribution systems with renewable resources in [21]. However, this relies on fault current magnitude to train SVMs, which significantly reduces its operating speed.…”

Section: Introductionmentioning

confidence: 99%

Nonpilot directional protection of a microgrid

Mohammadhassani,

Mehrizi‐Sani

2023

The Journal of Engineering

View full text Add to dashboard Cite

Protection of an islanded inverter‐based microgrid is challenging because of variable and small fault current contribution of inverter‐based resources (IBR) and the absence of sequence currents. This paper proposes a fast and robust nonpilot directional protection scheme to address this challenge. This scheme relies on support vector machines (SVM) and the harmonic current injection capability of IBRs. Examining the harmonic currents measured by a relay during a fault shows that harmonic currents have similar magnitudes but different orientation under forward and reverse faults. Additionally, harmonic currents have similar orientation but different magnitudes under forward faults at different locations along the protected line. Using this, six SVMs are trained for each relay, given that there are three main types of faults (three‐phase‐to‐ground, line‐to‐line, and line‐to‐ground): three as directional elements and three as zone detection elements. A fault is detected and classified by the undervoltage element of a relay. Then, the measured harmonic currents are routed to the appropriate directionality and zone detection SVMs to facilitate proper relay coordination. The performance of the proposed method is evaluated on the CIGRE North American MV distribution benchmark system under various types of contingency scenarios using PSCAD/EMTDC software.

show abstract