ABSTRACT Transmission lines are crucial to the power grid. While they are continuously exposed to diverse environmental conditions, certain unpredictable conditions such as extreme wind, wildfire, and icing pose catastrophic risks to the reliability and integrity of the transmission lines. This paper presents a comprehensive thermo‐electro‐mechanical model to investigate the effect of extreme wind, wildfire, and icing on transmission lines over time in the presence of initial damage and current demand load. The developed method offers an in‐depth perspective on temperature and damage evolution within the power lines by incorporating a damage and fatigue phase field model, with thermal and electrical models. We study three scenarios deterministically to establish a basic understanding and subsequently analyze the forward uncertainty quantification (UQ), sensitivity analysis (SA), and the probability of failure using the probabilistic collocation method (PCM). The presence of initial damage significantly reduces the life span of the transmission line. In addition, the probability of failure increased substantially in the presence of unexpected conditions such as extreme wind, wildfires, and icing. This approach offers an in‐depth examination of the potential risks associated with transmission lines under adverse conditions.

Abstract Automated vehicle detection within the advanced application framework of autonomous vehicles significantly enhances road safety compared to human drivers on roads and highways. However, the intelligent identification of road vehicles in a densely populated country like Bangladesh is challenging due to irregular traffic patterns, highly diverse vehicle types, a cluttered environment, and a lack of high‐quality datasets. This study proposes a system that utilizes computer vision technology to identify road vehicles with greater speed and accuracy. First, the dataset was collected and organized in Roboflow to identify the 21 classes of Bangladeshi native vehicle images, along with two additional classes for people and animals. Subsequently, the You Only Look Once v5 (YOLOv5) model underwent training on the dataset. This process produced bounding boxes, which were then refined using the non‐maximum suppression technique. The loss function complete intersection over union is employed to obtain the accurate regression bounding box of the vehicles. The MS COCO (Microsoft Common Objects in Context) dataset weights are included in the YOLOv5 deep learning network for transfer learning. Finally, Python TensorBoard was used to evaluate and visualize the model's performance. The model was developed and validated on the Google Colab platform. A set of experimental evaluations demonstrate that the proposed method is effective and efficient in recognizing Bangladeshi vehicles. In all test road scenarios, the proposed computer vision system for road vehicle identification achieved 95.8% accuracy and 0.3 ms processing time for 200 epochs. This research could lead to intelligent transportation systems and driverless vehicles in Bangladesh.

Abstract This research introduces an innovative algorithm for the encryption and decryption of greyscale digital imaging and communications in medicine images utilizing Laplace transforms. The proposed method presents a ground breaking approach to image encryption, effectively concealing visual information and ensuring a robust, secure, and reliable encryption process. By leveraging the inherent strengths of Laplace transform, the algorithm guarantees the complete retrieval of the original image without any loss, provided the correct decryption key is used. To thoroughly evaluate the performance of the algorithm, multiple tests were conducted, including extensive statistical analyses and assessments of encryption quality. Key performance metrics were carefully measured, including correlation coefficients and entropy values, which ranged from 7.89 to 7.99. Additionally, the algorithm's effectiveness was demonstrated through peak signal‐to‐noise ratio values, which spanned from 7.597 to 9.915, indicating the degree of similarity between the original and encrypted images. Furthermore, the number of pixels change rate values, ranging from 99.519241 to 99.609375, highlighted the algorithm's ability to produce significantly different encrypted images from the original. The unified average changing intensity values, falling between 35.72345678 and 35.78233456, further underscored the algorithm's proficiency in altering pixel intensities uniformly. Overall, this research offers a significant advancement in the field of image encryption, combining theoretical robustness with practical efficiency.

Abstract Ensuring the operational reliability of substation relay protection systems through rapid defect diagnosis and state assessment is crucial for maintaining power system stability. This study introduces a new diagnostic framework that combines improved particle swarm optimization, K‐means clustering algorithms, support vector machine (SVM), and learning vector quantization neural networks to provide a comprehensive fault diagnosis and prediction model for relay protection systems. The model commences by identifying critical metrics for system state evaluation, employing an improved analytic hierarchy process to allocate weights to these indicators, and introducing variable weights theory to improve dependability of outcomes. The model enhances SVM with learning vector quantization for precise state prediction by utilizing operational data from substation relay protection systems. Improved particle swarm optimization optimizes key SVM parameters to improve accuracy. In order to effectively classify defect categories, the K‐means clustering algorithm is implemented. The model's efficacy, stability, and comprehensive applicational potential have been confirmed through experimental trials, which represent substantial progress in the field of substation fault management.

Abstract This study presents an in‐depth overview of deep neural networks (DNN) and their hybrid applications for short‐term energy forecasting (STEF). It examines DNN‐based STEF from three perspectives: basics, challenges, and prospects. The study compares recent literature using metrics like mean absolute error (MAE), mean average percentage error (MAPE), and root mean square error (RMSE). Findings indicate that combining automated data‐driven models with enhanced DNNs effectively addresses forecasting challenges. It also highlights the role of DNNs in integrating energy prosumers, renewable energy systems, microgrids, big data, and smart grids to improve STEF.

Abstract In the construction of a new power system, the identification and evaluation of power consumption status of power customers will become an important basis for them to participate in the emerging businesses such as demand response and virtual power plants. In order to ensure the power safety of important power customers, a new evaluation of power consumption status of important power customers based on the AHP (analytic hierarchy process)‐TOPSIS (technique for order preference by similarity to an ideal solution) algorithm is proposed by fully mining and applying the power big data. Firstly, a power consumption big data analysis platform based on the Hadoop architecture is built to provide a high‐performance platform support for big data analysis. Secondly, nine evaluation indexes are constructed from the three dimensions of voltage, load and synthesis, which objectively and scientifically describes the power consumption status of important power customers. Finally, the AHP‐TOPSIS algorithm is used to evaluate and analyse the voltage, load and comprehensive indicators respectively, thus, obtaining the evaluation values of three kinds of indicators. The power consumption status scores of important power customers are determined by the variable weight weighted summation. The rationality and feasibility of the method and algorithm are proved by example analysis and field verification. This method helps to promote the transformation from post fault emergency repair to warning beforehand. It has the multiple effects of ensuring safe power consumption, supporting accurate patrolling and active emergency repair serving.

Abstract High altitude platform station (HAPS) is one of the promising solutions to many of the developing and less developed countries. To a great extent, HAPS is relatively cost‐effective and can be easily moved on demand while observing the required quality of service. For tropical countries, rain attenuation is the main factor that affects HAPS performance. This study investigated HAPS performance in Tanzania under heavy rain conditions. Rain rate, rain attenuation, and carrier‐to‐noise ratio were used to quantify the system's performance. In this study, the rain rate exceeds by 0.01% of an average, was obtained using the Chebil model. Based on Tanzania Meteorological Agency data, the registered a high amount of rainfall for the five selected regions: Dar es Salaam, Kagera, Tanga, Unguja, and Pemba. By using ITU‐R model, rain attenuation for the downlink was predicted, assuming horizontal polarisation, for 31.0–31.3 GHz. Finally, the HAPS link budget was analysed with a platform altitude of 22 km at frequency of 31.0–31.3 GHz for different elevation angles. Results showed that the performance of the system was promising in the given rainfall scenarios.

Abstract This research presents a machine learning (ML)‐based model that determines the DC and RF characteristics of InGaAs sub‐channel double gate high electron mobility transistors (DG‐HEMTs) to optimize the device structure. We employ technology computer‐aided design (TCAD) simulations to analyze the DC and RF performance of InGaAs sub‐channel DG‐HEMTs, generating a range of datasets by varying the material composition, layer width, and thickness of different layers in the device structure. We then train and optimize support vector regression (SVR) models using 5‐fold cross‐validation, varying the kernel function and degree parameters, and achieve better performance with the radial basis function (RBF) kernel. The simulated results indicate that the ML model predicts physical parameters more effectively than experimental analysis, offering a compact modeling solution that requires fewer computing resources than traditional methods.

Abstract A two‐stage Class A‐AB operational transconductance amplifier with low power consumption, high slew rate, and high bandwidth is introduced for handling large capacitive loads. Unlike the conventional two‐stage operational transconductance amplifiers that use a Miller capacitor, compensation is provided by the load capacitor (CL) at the output node. The proposed two‐stage amplifier maintains a 45° phase margin (PM) over any load capacitance. This is achieved through a MOSFET‐based RC network at the output node. Dual nMOS/pMOS differential stages drive output directly, improving both SR+ and SR−. Post‐layout simulation results with a capacitive load of 100 pF (CL) demonstrate that the proposed operational transconductance amplifier has a DC gain of 60.1 dB, an excellent average slew rate of 20.3 V/µs, a gain‐bandwidth product of 10.6 MHz, an average 1% settling time of 122.2 ns and a PM of 76.6°, while consuming only 103.5 µW. Reducing the CL to 10 pF reduces the PM to 47.6°, while increasing the gain‐bandwidth and average slew rate to 82.9 MHz and 142.6 V/µs respectively.

Abstract Interior permanent magnet synchronous motors (IPMSMs) which are driven by matrix converters have many advantages, including one‐stage power conversion, high efficiency, bidirectional power transfer, near unity input power factor, and low input current harmonics. However, the virtual DC‐link voltages of matrix‐converters vary from 0.866 to and the current commutations of matrix‐converters create serious three‐phase stator harmonic currents as well. Moreover, matrix‐converter‐based IPMSM drive systems, in general, have very large external loads, which require advanced control methods. To solve these problems, two adaptive controllers, including a model reference adaptive controller and a self‐tuning controller, are investigated in this article for matrix‐converter PMSM drive systems. From the experimental results, the proposed two adaptive speed controllers provide excellent dynamic responses, which are superior to PI speed controllers, including faster transient responses, better tracking abilities, and greater robustness. As a result, this proposed matrix‐converter‐based IPMSM drive system is very suitable in industrial applications.