Optimal feature selection for islanding detection in distributed generation

Chandak, Sheetal; Mishra, Manohar; Nayak, Subrat Kumar; Rout, Pravat Kumar

doi:10.1049/iet-stg.2018.0021

Cited by 13 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, there exists a need to develop algorithms with negligible or null NDZ and are faster in detecting the islanding of a network. According to the IEEE 1547-2003 standard "the unintentional islanding has to be detected and DG should be disconnected within two seconds after the utility disconnection" [48,49].…”

Section: Literature Reviewmentioning

confidence: 99%

Islanding Detection Using a Micro-Synchrophasor for Distribution Systems with Distributed Generation

Subramanian¹,

Loganathan²

2020

Energies

View full text Add to dashboard Cite

Distributed Generation (DG) has changed the power generation system to small-scale instead of large-scale generation. The demanding issue with the interconnection of DG is the detection of unintended islanding in a network. Several methods proposed in the literature show drawbacks such as high non-detection zones (NDZ) and higher tripping time. In this paper, the IEEE 13 bus distribution network with DGs like wind and solar power plants is integrated at two buses. Islanding is detected by utilizing data from a micro-synchrophasor located at the distribution grid and the DG. The micro-synchrophasor-based unintended islanding detection algorithm is based on parameters such as voltage, rate of change of voltage, frequency, rate of change of frequency, voltage phase angle difference and the rate of change of the voltage phase angle difference between the utility and the islanded grid. The proposed islanding detection algorithm discriminates between islanding and non-islanding conditions and is highly efficient under zero power mismatch conditions. The proposed method has null NDZ and satisfies the IEEE 1547 standard for DG tripping time. The effectiveness of the proposed IDM was verified when there are multiple DGs in the islanded grid. Also, the proposed method does not require additional hardware as it can be incorporated in digital relays with synchrophasor functionality.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Islanding Detection Using a Micro-Synchrophasor for Distribution Systems with Distributed Generation

Subramanian¹,

Loganathan²

2020

Energies

View full text Add to dashboard Cite

show abstract

“…Mutation and cross-over are the two steps that help to generate the trial vector. Subsequently, the selection step determines the survival of better solutions for the next generation [27]. The process continues for several iterations to obtain the optimal solution.…”

Section: Binary Dementioning

confidence: 99%

Optimal performance of a self‐healing microgrid

Chandak

Rout

2020

IET Smart Grid

Self Cite

View full text Add to dashboard Cite

This study proposes a multi-objective binary differential evolution algorithm to reconfigure the system and restore the loads within the stand-alone microgrid. The approach aims to attain a restoration path having maximum power flow with the minimum number of interrupted loads and switching operations. To execute the discrete optimisation strategy, the power network has been reframed as a capacitated graph, where the edges are capacitated by the loading capacity of the feeder. The strategy implements the maximum power flow theorem, which has been enhanced using the centrality index. The major operational constraints of the microgrid have been strictly followed to maintain system stability. The proposed restoration algorithm is examined on an islanded 13-bus microgrid system with the two test scenarios of irregular power generation, and the fault instance is isolating a healthy section of a microgrid. Moreover, the efficacy of the proposed approach has been further examined on a 39-bus system, and the results are compared with the other optimisation strategies implemented for restoration.

show abstract

“…Supervised machine learning techniques are widely employed in a variety of other disciplines of research and technology [20][21][22][23][24]. The reasons behind such research trends and their preference over other technologies are their reliability, fast detection, and high accuracy [25,26]. ML-based islanding detection techniques do not require any communication medium such as that used in remote techniques, no threshold settings as applied in passive techniques, and no power quality issues found in active techniques.…”

Section: Introductionmentioning

confidence: 99%

An intelligent islanding detection of distribution networks with synchronous machine DG using ensemble learning and canonical methods

Hussain

Kim

Admasie

2021

IET Generation Trans & Dist

View full text Add to dashboard Cite

One of the crucial challenges of the distribution network is the unintentionally isolated section of electricity from the power network, called unintentional islanding. Unintentional islanding detection is severed when the local generation is equal to or closely matches the load requirement. In this paper, both ensemble learning and canonical methods are implemented for the islanding detection technique of synchronous machine-based distributed generation. The ensemble learning models for this study are random forest (RF) and Ada boost, while the canonical methods are multi-layer perceptron (MLP), decision tree (DT), and support vector machine (SVM). The training and testing parameters for this technique are the total harmonic distortion (THD) of both current and voltage signals. THD is the most important parameter of power quality monitoring under islanding scenarios. The parameter and data extraction from the test system is executed in a MAT-LAB/Simulink environment, whereas the training and testing of the presented techniques are implemented in Python. Performance indices such as accuracy, precision, recall, and F 1 score are used for evaluation, and both ensemble learning models and canonical models demonstrate good performance. Ada-boost shows the highest accuracy among all the five models with original data, while RF is robust and gives the best results with noisy data (20 and 30 dB) because of its ensemble nature. INTRODUCTIONDistributed generation (DG) integration has gained a lot of interest because of electricity market deregulation, customer requirements for reliable and high-quality power, and environmental concerns. Although DG integration has some vital benefits such as cost reduction, low transmission losses, fewer emissions, flexibility, and reliability, it also introduces challenges and hitches in the power distribution network, one of which is the islanding condition. The term "islanding" means that the operating system has all the load and generation isolated from the main utility. In a power grid, the process of islanding is partitioned into two major classes: intentional islanding and unintentional islanding. Intentional islanding is designed primarily for system repairs and operating problems, whereas unintentional islanding incidents are triggered by unex-This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Optimal feature selection for islanding detection in distributed generation

Cited by 13 publications

References 36 publications

Islanding Detection Using a Micro-Synchrophasor for Distribution Systems with Distributed Generation

Islanding Detection Using a Micro-Synchrophasor for Distribution Systems with Distributed Generation

Optimal performance of a self‐healing microgrid

An intelligent islanding detection of distribution networks with synchronous machine DG using ensemble learning and canonical methods

Contact Info

Product

Resources

About