Ranjan Kumar Mallick

Islanding detection is vital for maintaining the stability and safety of microgrid operations. This paper introduces an enhanced method using a Deep Convolutional Neural Network (CNN) optimized through the Grey Wolf Optimizer (GWO), combined with Markov Transition Fields (MTF) to detect islanding events with high accuracy. The GWO algorithm automatically tunes key CNN parameters, such as kernel size and number, enabling the model to efficiently learn and extract features from microgrid signals. Meanwhile, MTFs transform time-series signals into 2D representations, enriching the model with spatial-temporal context. The proposed GWO-CNN + MTF framework is trained and tested on microgrid datasets covering both islanding and non-islanding events. Experimental results confirm that the model achieves substantial accuracy and robustness even under noisy conditions. The proposed GWO-CNN model is evaluated against current state-of-the-art techniques, and results indicate its significant superiority. This research contributes to the advancement of islanding detection techniques, offering a promising solution for ensuring the reliability and resilience of microgrid systems.

This study presents an intelligent fault detection technique for wind farm-integrated power systems, contributing to the advancement of clean energy reliability and efficiency, a key focus of clean energy integration. The proposed method integrates discrete wavelet transform (DWT) with an ensemble-based bagged decision tree (BDT) classifier, optimized using the grey wolf optimization (GWO) algorithm. DWT extracts critical time-frequency features from fault signals, enabling accurate characterization under diverse operating conditions. GWO enhances BDT performance by selecting the optimal number of decision trees, improving classification accuracy while reducing computational complexity. The results demonstrate high accuracy and robust fault detection, ensuring stable wind power integration into the grid. By minimizing power losses, enhancing grid stability, and reducing system downtime, this method strengthens the sustainability of renewable energy systems, aligning with global efforts toward a cleaner and more efficient power infrastructure.

The trend of integrating different distributed generation sources into the existing grid have increased the probability of power quality disturbances to a threatening level. Eventually, detection, protection and mitigation of these disturbances are even more challenging. In this regard, the article presents an intelligent power quality disturbance classification scheme using a 2D convolutional neural network designed from a systematic and structural standpoint. A total of 8 singular, 5 complex power quality events are simulated and voltage data collection is made from a test system designed in MATLAB Simulink environment. The three-phase voltage data is converted to a single signal arrangement through a newly proposed Unique Clark’s Transformed Sequence. In addition to that, the scheme completely eliminates the worry of a signal processing stage by proposing a novel scaled matrix image created out of 2-cycle data collected at 6.4kHz sampling frequency that acts as input to the CNN architecture designed in the PYTHON environment. Further, the novelty extended to design a pseudo-real-time setup where the MATLAB environment continuously runs the test system, producing scaled matrix images. These images are saved to a shared directory, enabling a PYTHON loop for prompt event classification through the trained CNN model. The model performance is found to be 100% under ideal conditions. It has also tested under three different noise conditions of 40dB, 30dB and 20dB and obtained an overall accuracy of 98.86% with singular events. Further, the method is also verified for complex and unsymmetrical dataset and found to be equally effective. Additionally, the validation is likewise made with a trivial set of real-time simulated data using OPAL-RT 4510 setup. Finally, the proposed PQ detection scheme is compared with recently published work to express its superiority over other similar studies in terms of classification accuracy.

This study focuses on detecting Power Quality Disturbance Events (PQDE) in microgrids integrated with a Solar Energy Conversion System (SECS). The research proposes a novel signal reduction technique called Clark Transformed Modal, which reduces three-phase voltage to a single unit signal, optimizing memory utilization and reducing computational load during feature extraction. A total of 16 features are extracted from the proposed modal signal by performing multi-resolution analysis through Maximum Overlap Discrete Wavelet Transform (MODWT). Various disturbances, including sag, swell, transients, notches, and flicker, are intentionally simulated in a PV-grid tied MATLAB/Simulink model to obtain a dataset of 10800 samples. Further, the dataset is randomly divided into training-testing subsets to verify the classification ability of a novel ensemble classifier called subspace weighted k-nearest Neighbor (SWKNN). In addition to that the optimum mother wavelet (dmay) is identified to even further boost the classifier performance. The results demonstrate the superior classification capabilities of the proposed MODWT-SWKNN classifier in terms of various performance metrics like precision, recall and F1-score. It also outperformed when compared with several competitive PQ classification models based on PV-integrated systems both under ideal and noisy conditions. Additionally, the disturbance detection system is validated in an OPAL-RT real-time environment to demonstrate its efficiency in terms of detection time. The accuracy of detection is found to be 99.74% in ideal case and fall back to no more than 3% regulation i.e., 97.28% even in dense noise of 20dB with as low as 8 WKNN subspaces. Further, average detection time with 500 trails is found to be 0.0285 seconds. The efficacy of the proposed PQ detection algorithm is also tested in a large PV integrated IEEE 13-bus system.

Integrating renewable energy sources like solar power into traditional power systems poses challenges. One such challenge is the effect of renewable power plants, which use power electronics, on the grid’s stability. Specifically, these plants can impact small-signal stability by either damping or exacerbating low-frequency oscillations. This paper introduces a novel Unified Power Flow Controller (UPFC) based damping controller specifically designed for Solar Photovoltaic (PV) integrated power systems. It employs an Arithmetic Optimization Algorithm (AOA) to optimize the UPFC damping controller parameters and mitigate low-frequency oscillations in the power system. The objective function minimizes the Integral Time Absolute Error (ITAE) of speed deviations under varying loading conditions. The proposed technique is utilized simultaneously to control the modulation index of series and phase angle of shunt converters of UPFC. The MATLAB/simulation results obtained effectively from the proposed technique which is actualized and identify both detrimental and beneficial impacts of increased PV penetration for small signal stability performance. The study reveals both the small-signal stability of the system and its response to large disturbances that alter the active power balance and frequency stability. The results of the analysis demonstrated with single and multimachine environment by comparing with the other optimizations like PSO, DE, DE-PSO and GWO, the proposed one is effective for damping out the oscillations. The effectiveness of the proposed damping controller is further confirmed through real-time validation using the OPAL-RT setup.

Accurate harmonic estimation is essential for effective power quality assessment, designing appropriate harmonic filters, and ensuring the reliable operation of electrical equipment. This article proposes a novel hybrid harmonic estimation technique combining recursive least square (RLS) and arithmetic optimization algorithm (AOA) for accurate estimation of harmonics, inter-harmonics and sub-harmonics. AOA is a new meta-heuristic method based on distribution behaviour of main arithmetic operators such as addition, subtraction, multiplication and division. RLS is used for estimation of amplitude of harmonics, whereas phase is estimated by AOA. The performance of AOA–RLS is investigated in detail for estimation of power system signals using two set of test signals buried with noise. The proposed AOA–RLS is proved to be efficient for estimating both phase and amplitude parameters under different signal to noise ratio (SNR) conditions with an estimation of error of E ⁻³ . The efficacy of AOA–RLS technique is demonstrated by comparing with competitive existing techniques. The performance of AOA–RLS also verified in experimental studies.

The modern era power system is constantly undergoing constructive changes and implementations both in source and load side. Certainly, the distributed generators, unconventional/nonlinear loads, charging stations etc are mostly integrated through power electronics interfaces. As a result, frequent power quality disturbances appear in the system that is to be mitigated at the earliest. Since detection is the prerequisite for mitigation, therefore the article presents a novel intelligent power quality detection scheme to detect and classify the PQ Events. At first, the energy feature of the 5 band limited modes are calculated from variational mode decomposed voltage signals. Then the mode energy features are utilized to train a novel Hybrid Arithmetic Whale Optimized light gradient boosting machine classifier. A total of 15 different PQ events have been investigated and exceptional classification results have obtained with optimum computational complexity, both under noiseless and noisy conditions. Moreover, the accuracy of the proposed PQ classification schemes found to be towering against other related pre-published works. Finally, the ability of the proposed detection scheme is validated in real time though OPAL-RT 4510 and grid simulator hardware in loop setup.

Distributed generations (DGs) have been increasingly addressing the ongoing power deficit in the electricity market. However, a significant concern in DG‐integrated microgrids is the detection of accidental islanding. To tackle this issue, this article proposes a cost‐friendly, novel data‐driven passive islanding detection scheme named EEMD‐HOBRC, combining noise‐assisted ensemble empirical mode decomposition (EEMD) and a hybrid optimization‐based random forest classifier (HOBRFC). The detection scheme employs a diverse set of features extracted from both raw and EEMD decomposed signals. Essential features are selected using the binary grey wolf optimizer (BGWO) to reduce computational burden. To further improve classification accuracy, the parameters of the random forest classifier are optimized through a hybrid particle swarm and reformed grey wolf optimization (PSRGWO) technique with Cohen’s kappa index as the cost function. The proposed technique is rigorously validated in two different multi‐DG environments, encompassing islanding and various nonislanding events. The results demonstrate the effectiveness of the approach in terms of enhanced accuracy, detection time, and performance under both noisy and noise‐free conditions. The accuracy of detection under ideal and high noise scenarios is found to be 99.88% and 99.2%, respectively, with maximum detection time of 34.27 ms. Comparative analysis with other algorithms also supports the superiority of the proposed technique. Finally, the method is successfully applied to shrink the nondetection zone (NDZ) with minimal power mismatch, further enhancing its utility in practical applications.

Power Quality, Equipment and Personnel safety of any distributed generation (DG) system connected to utility Grid merely depends on accurate detection of Islanding and non-islanding Power quality disturbances. The main objective of the proposed research is to detect islanding events with very narrow non-detection zone (NDZ) and classification of power quality disturbances with higher accuracy using signal processing and intelligent method together. A noise robust down sampling empirical mode decomposition (DEMD) is used to extract signature of islanding and power quality (PQ) disturbance features from the collected voltage signals and multilayer perceptron neural network (MLNN) is proposed to classify islanding and non-islanding (PQ) events. The performance of the proposed (DEMD-MLNN) technique is verified with IEEE-9 bus distributed generation system dominated by solar &wind energy penetration. The simulation work is carried out in MATLAB/Simulink platform. The efficacy of the proposed DEMD-MLNN is verified by large number of numerical experimentations with and without noise and comparing with existing competitive well-known techniques.