Muhammad Jamshed Abbass

The complexity of voltage stability assessment in modern smart grids has increased significantly with the growing penetration of renewable energy sources and the dynamic nature of load variations. Although standard analytical methods are accurate, they are computationally expensive and unsuitable for real-time applications. This paper proposes a hybrid analytical–machine learning framework for efficient voltage stability assessment and classification. The proposed approach consists of two stages. First, a power flow analysis is performed to compute the Fast Voltage Stability Index (FVSI) and quantify the proximity of the system operating conditions to voltage instability. Then, the FVSI values are converted into binary stability labels to formulate a supervised classification problem. In the second stage, the Extreme Gradient Boosting (XGBoost) algorithm is employed to learn the relationship between system operating variables and the corresponding stability states. The performance of the proposed method is evaluated on the IEEE 30-bus system and compared with that of conventional machine learning and deep learning models, such as Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Deep Neural Networks (DNNs). The simulation results show that the XGBoost-based framework outperforms the benchmark models in terms of classification accuracy, robustness, and computational efficiency. The proposed method provides a fast, reliable, and interpretable solution for real-time voltage stability monitoring. Therefore, it is suitable for modern smart grid applications.

This study proposes three metaheuristic techniques, including differential evolution, moth-flame optimisation, and honey badger algorithm combined with a modified backward-forward sweep load flow approach to identify the optimal droop gains and reference voltage magnitudes of distributed generators (DGs) (i.e., optimal size of droop-based DGs) integrated with renewable sources to meet the electricity demands of an islanded AC microgrid. The suggested mathematical model was tested on a reconfigured 33-bus islanded microgrid under four scenarios with a time-varying load over 24 hours. The findings indicate that Case 3, which applies the honey badger (HB) algorithm to optimise droop coefficients and regulate reference voltage magnitudes within permissible limits, is the most effective in lowering power losses compared to other cases. The final results highlight the HB algorithm’s efficacy in minimising power losses while optimising the size of droop-based DGs in an islanded microgrid integrated with renewable energy sources.

Microgrids are increasingly recognized as transformative and crucial constituents within advanced smart grid systems. This study introduces a decentralized energy management approach for interconnected microgrids that leverage renewable energy sources such as wind and solar, alongside distributed energy generators and storage mechanisms. An energy coalition manager (ECM) plays a key role in facilitating each microgrid’s integration to optimize power exchanges, enhance data communication, and reduce costs. The alternate-direction multiplier method is adapted to address optimization challenges, incorporating modifications to develop a censored version that enhances communication efficacy. This refined approach involves the exchange of information among neighboring entities, evaluated against a preset threshold. Through this precise comparison, ECMs strategically reveal their local variables to ensure convergence towards an optimal solution. A detailed case study was conducted to assess the performance, efficiency, and scalability of both methodologies comprehensively.

The Photovoltaic (PV) systems depict substantially nonlinear current–voltage (I–V) characteristics that fluctuate with irradiance and temperature, enabling quick and reliable maximum power point tracking (MPPT) for optimal energy conversion. This study presents a hybrid maximum power point tracking (MPPT) technique which incorporates sliding mode control (SMC) with the perturb-and-observe (P&O) (SMP&OC) algorithm which enhances power extraction in dynamic operating situations. This technique includes a systematic control design, comprising an initial sliding surface and a continuous sliding mode control regulation, while retaining the simplicity and minimal computational expense of the P&O algorithm. The overall system is made up of a solar module, the SMP&OC MPPT controller, and a DC–DC boost converter. The efficacy of the proposed controller is assessed by simulations under rapidly fluctuating irradiance and temperature atmospheric conditions. The hybrid SMP&OC method provides swift convergence, lessened steady-state oscillations, and reliable maximum power point tracking, consequently enhancing the general efficacy of the photovoltaic system amidst external disturbances.

In this paper, a common fixed point of a countable set of nonexpansive mappings in Hilbert space. Under appropriate regulatory circumstances, the weak convergence theorems are formulated. Nonsmoothed convex minimization problems, which are expressed as the union of two suitable convex lower semicontinuous functions, are tackled by applying the proposed method. The subsequent method provides a viable answer to structured convex optimization problems that arise in many engineering and scientific settings; it is constructed within the forward-backwards splitting paradigm. Also, using an extreme learning machine model with l1-regularization, we show that it works well for machine learning classification tasks. Improving forecast accuracy through rapid iterative refinement, the proposed method deftly computes output weights by tackling the basic convex optimization problem. Its effectiveness, durability, and improved classification accuracy compared to existing methods are confirmed by numerical experiments on many benchmark datasets.

This paper presents a new image captioning system which contains facial expression recognition as a way to provide better emotional and contextual comprehension of the captions generated. A combination of affective cues and visual features is made, which enables semantically full and emotionally conscious descriptions. Experiments were carried out on two created datasets, FlickrFace11k and COCOFace15k, with standard benchmarks such as BLEU, METEOR, ROUGE-L, CIDEr, and SPICE to analyze their effectiveness. The suggested model produced better results in all metrics as compared to baselines, like Show-Attend-Tell and Up-Down, remaining consistently better on all the scores. Remarkably, it has reached gains of 2.5 points on CIDEr and 1.0 on SPICE, which means a closer correlation to the prompt captions made by people. A 5-fold cross-validation confirmed the model’s robustness, with minimal standard deviation across folds (<±0.2). Qualitative results further demonstrated its ability to capture fine-grained emotional expressions often missed by conventional models. These findings underscore the model’s potential in affective computing, assistive technologies, and human-centric AI applications. The pipeline is designed for on-prem/edge deployment with lightweight interfaces to IoT middleware (MQTT/OPC UA), enabling smart-factory integration. These characteristics align the method with Industry 4.0 sensor networks and human-centric analytics.

This paper presents a novel hybrid copy–move forgery detection method that combines the efficiency of FAST-BRIEF (for rapid keypoint detection and binary descriptors) with the robustness of SIFT (for scale- and rotation-invariant feature matching). The proposed framework employs g2NN matching for accurate feature correspondence, followed by morphological processing and LSC-SSIM superpixel segmentation for precise localization of tampered regions. The method is evaluated on 30 diverse test images from benchmark datasets comprising over 700 images, achieving a 95% F-measure with an average CPU time of 6.02 seconds. It demonstrates strong resilience to geometric transformations (rotation, scaling), photometric adjustments (contrast, brightness), additive noise, and multiple forgeries. The proposed methodology offers a 5–30% improvement in accuracy and computational speed. This approach addresses emerging challenges in deepfake detection and satellite imagery authentication, where localized manipulations threaten media integrity.

The term “image captioning” refers to the process of converting an image into text through computer vision and natural language processing algorithms. Image captioning is still considered an open-ended topic despite the fact that visual data, most of which pertains to images, is readily available in today’s world. This is despite the fact that recent developments in computer vision, such as Vision Transformers (ViT) and language models using BERT and GPT, have opened up new possibilities for the field. The purpose of this review paper is to provide an overview of the present status of the field, with a specific emphasis on the use of facial expression recognition and object detection for the purpose of image captioning, particularly in the context of fault-aware systems and Prognostics and Health Management (PHM) applications within Industry 4.0 environments. However, to the best of our knowledge, no review study has focused on the significance of facial expressions in relation to image captioning, especially in industrial settings where operator facial expressions can provide valuable insights for fault detection and system health monitoring. This is something that has been overlooked in the existing body of research on image captioning, which is the primary reason why this study was conducted. During this paper, we will talk about the most important approaches and procedures that have been utilized for this task, including fault-aware methodologies that leverage visual data for PHM in smart manufacturing contexts, and we will highlight the advantages and disadvantages of each strategy. The purpose of this review is to present a comprehensive assessment of the current state of the field and to recommend topics for future research that will lead to machine-translated captions that are more detailed and accurate, particularly for Industry 4.0 applications where visual monitoring plays a crucial role in system diagnostics and maintenance.

The assessment of voltage stability within a microgrid is essential to ensure that all buses in the system can maintain the required voltage levels. Recent research has focused on developing modern voltage stability estimation equipment rather than identifying optimal locations for integrating inverter-based resources (IBRs) within the network. This study analyzes and evaluates voltage stability in power systems with increasing levels of IBRs using modal analysis methodologies that consider active power (PV) and reactive power (QV). It examines the impact of load flow when integrating IBRs into the weakest-and strongest-load buses. Additionally, this study introduces a support vector machine (SVM) approach to assessing voltage stability in a microgrid. The results indicate that the proposed SVM approach achieved an optimal accuracy of 95.10%. Using the IEEE 14-bus scheme, the methodology demonstrated the effective and precise determination of the voltage stability category of the system. Furthermore, the analysis was conducted using the modified DES power system. The core contribution of this research lies in evaluating and identifying the locations that are the most and least favorable for integrating IBRs within the simplified DES power system network, utilizing modal analysis for both QV and solar photovoltaics (SPVs). The results of the load flow analysis suggest that integrating IBR is significantly more beneficial in the most substantial bus, as it minimally impacts other load buses assessed as the least reliable bus within the system.

Matrix converters are bi-directional power electronic devices consisting of an array of solid-state switches directly connecting a source and load without an intermediate DC link. Historically, matrix converters have seen limited industrial adoption due to the complexity of their control mechanisms. However, in recent decades, matrix converter-based systems have emerged as viable alternatives for reactive power management because of the development of reliable and straightforward commutation methods. This paper provides a comprehensive analysis of matrix converter control strategies for reactive power compensation. Initially, an overview of matrix converter technology is provided. Then, Flexible Alternating Current Transmission System (FACTS) devices, renewable energy integration systems, and electric drives adopted in the last decade for reactive power compensation are discussed. The various ways these topologies have been employed for reactive power management are investigated, and an overview of direct and indirect matrix converter topologies is given. The application of control techniques such as model predictive control, space vector modulation, direct torque control, and others for reactive power compensation is then explored and their performance compared. Finally, directions for future research are identified. The analysis shows that matrix converter technology and control mechanisms have advanced substantially, demonstrating promise for wider industrial reactive power compensation applications. The continued development of cutting-edge matrix converter topologies and increasingly sophisticated control strategies will further broaden their reactive power compensation potential.