The conventional PV array configurations fail to eliminate the ill effects of partial shading (PS) thereby resulting in mismatch losses. PV array reconfiguration is considered as the most competent solution for shading-related issues. However, many reconfiguration techniques reported in the literature fail to disperse the shade effectively, not compatible with large-scale arrays, and are not generalized for all array sizes. To overcome these limitations, a highly efficient generalized Henon Map technique which is extensively used in the image encryption process is proposed in this paper to reconfigure the PV array. The proposed technique is extensively analyzed for 9 × 9, 8 × 8, 4 × 4, 3 × 5 and 4 × 3 PV arrays under distinct shading patterns with seven parameters. The obtained results are compared with conventional Series-Parallel, Total-Cross-Tied, and very recently reported Odd-Even, Odd-Even-Prime, Chaotic Baker’s Map, Magic square, and Diagonal-TCT reconfiguration techniques. Besides, an experimental prototype model is developed and tested under artificially shading conditions to validate the competence of the proposed configuration. From the comprehensive analysis, it is noted that the proposed technique offers consistently superior performance with the least percentage mismatch and maximum power enhancement of 24.17%, 25.65%, and 47.81% for various shading cases of 9 × 9, 8 × 8, and 4 × 4 PV arrays, respectively. Further, a qualitative comparative assessment of the proposed technique with other state-of-art techniques is presented.

The partial shading phenomenon significantly limits the PV array output. To maximize the output power during shading, various reconfiguration techniques have been reported in the literature. However, many of these techniques are not scalable, ineffective, and inconsistent in uniform shade dispersion. Therefore, two highly efficient Arnold’s Cat Map and Henon Map-based chaotic approaches which are widely used in image encryption are employed to effectively disperse the shade by reconfiguring the modules without disturbing the electrical circuitry. The proposed approaches are evaluated in a MATLAB environment for symmetrical 8 × 8 PV array and unsymmetrical 5 × 7 PV array under different groups of progressive shading like left-to-right, triangular, top-to-bottom, and diagonal shading conditions. The efficacy of the proposed approaches is compared with conventional Series-Parallel, Total-Cross-Tied, existing Chaotic Baker-Map, Odd-Even, and Odd-Even-Prime-based reconfiguration techniques and extensively analyzed using different performance indices. A laboratory experimental setup of a 4 × 4 PV array reconfiguration system is developed and examined under distinct progressive shading cases. From the quantitative results obtained, it is noted that the proposed approaches offer consistently superior and reliable performance compared to existing state-of-art configurations under shading reinforcing their effectiveness.

This paper presents a highly efficient image encryption-based Arnold's cat map (ACM) technique to reconfigure the photovoltaic (PV) array to enhance the output and mitigate the mismatch losses due to partial shading (PS). The proposed ACM technique concentrates on alleviating the power loss by effectively dispersing the shade over the entire PV array without modifying its electrical circuitry. The proposed reconfiguration technique is investigated and analyzed with conventional series–parallel and total-cross-tied configurations along with the recently reported chaotic Baker's map, odd–even, odd–even–prime pattern-based configurations. The proposed technique is examined for symmetrical 6 × 6 PV array and unsymmetrical 6 × 9 PV array under distinct nonuniform and uniform PS cases. To confirm the potency and superior performance of the proposed technique, the system has been extensively examined with nine performance parameters such as global maximum power, mismatch power, power loss, efficiency, fill factor, array yield, capacity factor, performance ratio, and the number of maximum power peaks. An experimental setup of a 4 × 4 array reconfiguration system prototype is developed and tested in a real-time environment to validate the effectiveness of the proposed technique over the existing ones. From the comprehensive investigation, it is regarded that the proposed technique offers consistently superior performance with the least percentage mismatch losses and maximum power enhancement of 48.8%, 31.03%, and 27.5% for various shading cases of 6 × 6 and 6 × 9 PV arrays.

Solar PV arrays are susceptible to various faults, such as hotspots, cracks, and Potential Induced Degradation, which can impair efficiency and longevity. Traditional fault detection methods are time-intensive and limited in accuracy, especially for large-scale installations. This paper proposes an Adaptive Attention Pyramid Network (AAPN) for accurate and efficient fault detection in PV modules. AAPN integrates depthwise separable convolutions, squeeze-and-excitation blocks, and adaptive attention mechanisms to achieve high accuracy in identifying fault types across different classification complexities. Extensive experimentation on a comprehensive dataset of infrared PV images, organized into 12 fault classes, demonstrated AAPNs high classification accuracy of up to 96% in binary and 92% in 12-class classification scenarios. The proposed model is tested using an infrared solar module dataset for 2-class, 8- class, 11-class, and 12-class fault categories. Its effectiveness is compared with 69 existing deep-learning models for various fault classes. An ablation study was conducted to evaluate the impact of different architectural components, such as depthwise separable convolutions and squeeze-and-excitation blocks, on the models performance, showing an optimal trade-off between accuracy and computational efficiency. The proposed architecture model is very lightweight, utilizing only 0.8 million parameters. Its effective balance between high accuracies and low parameter utilization makes it highly suitable for deployment on drone-based edge devices, facilitating on-site real-time PV fault monitoring, maintenance, and detection. Additionally, the model has been successfully implemented on the Google Coral Edge TPU, achieving 40.2 ms inference time per image, confirming its efficiency and suitability for real-time applications in resource-constrained environments.

The output power and terminal voltage of the fixed speed induction generator fluctuate in the partial load region where the wind speed is below the rated vale, resulting in fluctuations in the grid frequency and voltage. In this paper, a novel pitch angle control strategy has developed by introducing an exponential moving average (EMA) concept from which the controller reference power (signal) can be set for below-rated wind speeds. Therefore, the employed pitch angle controller together with static synchronous compensator (STATCOM), named the unified voltage and pitch angle controller (UVPC), addresses the objective of smoothing the output power and terminal voltage regulation of a wind generator, subjected to below-rated wind speed variations. Moreover, an interval type-2 fuzzy logic technique has incorporated in the pitch angle controller design, since it is more efficient in handling the uncertainties in membership functions and rules than its traditional fuzzy logic counterparts. Simulation results clearly show that the proposed UVPC effectively smoothens out the generator output power and also regulates the terminal voltage at its constant magnitude.