Convolutional Neural Network‐Based Intelligent Protection Strategy for Microgrids

Bukhari, Syed Basit Ali; Kim, Chul‐Hwan; Mehmood, Khawaja Khalid; Haider, Raza; Zaman, Muhammad Saeed Uz

doi:10.1049/iet-gtd.2018.7049

Cited by 40 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [28], the support vector machine (SVM) classifier detected the existence of a fault in the microgrid. The strategies presented in [29] and [30] used a convolutional neural network to protect the microgrids. KF was used for microgrids protection in ref.…”

Section: Introductionmentioning

confidence: 99%

A Kalman Filter-Based Protection Strategy for Microgrids

et al. 2022

Self Cite

View full text Add to dashboard Cite

Recently, the concept of microgrids has emerged in the world due to the integration of distributed energy resources (DERs) at the distribution end. The design of a reliable protection strategy is one of the top-most challenges associated with microgrids. This is because of the transition of microgrids between grid-tied and autonomous modes of operation. This paper presents a state-of-the-art microgrid protection scheme based on the Kalman filter (KF). The proposed scheme uses the one-end current signal of a distribution line for the detection and classification of faults. Firstly, the KF is applied to each phase of a three-phase current signal individually to generate residuals and total harmonic distortion (THDs). Next, the variations in the residuals and THDs of each phase are compared with pre-specified threshold values to detect the faulty events in the microgrid. As each phase is processed through KF individually, therefore, the proposed scheme is inherently phase segregated. Afterward, the KF is applied to extract the third harmonic component from the three-phase current and voltage signals. Then, the KF-based reactive power (KFBRP) is obtained from the extracted third harmonic components. Finally, the directional properties of the threephase KFBRP are used to locate the faulty section in the microgrids. Extensive simulations in MATLAB/ Simulink software are performed for the grid-tied as well as the autonomous modes of operation under radial and meshed topologies. The results show that the proposed scheme is highly robust in all testing scenarios without any false tripping and blinding issues.

show abstract

Section: Introductionmentioning

confidence: 99%

A Kalman Filter-Based Protection Strategy for Microgrids

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence algorithms are also used in microgrid fault detection. Syed Basit Ali Bukhari [10] use convolution neural network to process three-phase current, but the amount of data processed is large. Using fault characteristics such as short-circuit current to find short-circuit fault is the mainstream method at present.…”

Section: Introductionmentioning

confidence: 99%

Design and Simulation of Selective Short Circuit Protection System in AC Microgrid with Grid-connected Mode

Chen

Liu

Chen

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The fast detection and accurate location on short-circuit faults has always been the research direction of AC microgrid fault protection. A short-circuit fault protection system for grid-connected AC microgrid is designed based on dsPIC33FJ32GP204 in this paper, which realizes the fast detection and regional location. The short-circuit fault simulation model is built on PSCAD, and all kinds of fault waveforms generated by simulation are imported into Proteus. The designed protection system is used to transform the wavelet energy spectrum of all kinds of fault waveforms generated by simulation, and then output the corresponding control signal to circuit breakers. Simulation results show that the control system can quickly perceive and accurately locate the microgrid short-circuit fault area and realize the output of selective protection signal.

show abstract

“…Their study has not considered noise samples. Bukhari et al (2020) have proposed a convolutional neural network-based intelligent fault protection scheme using current signals. The efficiency of their proposed method has been proved in terms of security and dependability.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic weighted voting model using multiple machine learning methods for fault detection and classification

Ülker

Küçüker

2022

COMPEL

View full text Add to dashboard Cite

Purpose The individual machine learning methods used for fault detection and classification have accuracy performance at a certain level. A combined learning model composed of different base classifiers rather than an individual machine learning model is introduced to ensure diversity. In this way, this study aims to improve the generalization capability of fault detection and classification scheme. Design/methodology/approach This study presents a probabilistic weighted voting model (PWVM) with multiple learning models for fault detection and classification. The working principle of this study’s proposed model relies on weight selection and per-class possibilities corresponding to predictions of base classifiers. Moreover, it can improve the power of the prediction model and cope with imbalanced class distribution through validation metrics and F-score. Findings The performance of the proposed PWVM was better than the performance of the individual machine learning methods. Besides, the proposed voting model’s performance was compared with different voting mechanisms involving weighted and unweighted voting models. It can be seen from the results that the presented model is superior to voting mechanisms. The performance results revealed PWVM has a powerful predictive model even in noisy conditions. This study determines the optimal model from among voting models with the prioritization method on data sets partitioned different ratios. The obtained results with statistical analysis verified the validity of the proposed model. Besides, the comparative results from different benchmark data sets verified the effectiveness and robustness of this study’s proposed model. Originality/value The contribution of this study is that PWVM is an ensemble model with outstanding generalization capability. To the best of the authors’ knowledge, no study has been performed using a PWVM composed of multiple classifiers to detect no-faulted/faulted cases and classify faulted phases.

show abstract

Convolutional Neural Network‐Based Intelligent Protection Strategy for Microgrids

Cited by 40 publications

References 30 publications

A Kalman Filter-Based Protection Strategy for Microgrids

A Kalman Filter-Based Protection Strategy for Microgrids

Design and Simulation of Selective Short Circuit Protection System in AC Microgrid with Grid-connected Mode

Probabilistic weighted voting model using multiple machine learning methods for fault detection and classification

Contact Info

Product

Resources

About