In this paper, an improved voltage control strategy for microgrids (MG) is proposed, using an artificial neural network (ANN)-based adaptive proportional-integral (PI) controller combined with droop control and virtual impedance techniques (VIT). The control strategy is developed to improve voltage control, power sharing and total harmonic distortion (THD) reduction in the MG systems with renewable and distributed generation (DG) sources. The VIT is used to decouple active and reactive power, reduce negative power interactions between DG’s and improve the robustness of the system under varying load and generation conditions. Simulation findings under different tests have shown significant improvements in performance and computational simulation. The rise time is reduced by 60%, the overshoot is reduced by 80%, the THD of the voltage is reduced by 75% (from 0.99 to 0.20%), and the THD of the current is reduced by 69% (from 10.73 to 3.36%) compared to the conventional PI controller technique. Furthermore, voltage and current THD values were maintained below the IEEE-519 standard limits of 5% and 8%, respectively, for the power quality enhancement. Fluctuations in voltage and frequency were also maintained at 2% tolerance and 1% tolerance, respectively, across all voltage limits, which is consistent with international norms. Power-sharing errors were reduced by 50% after conducting the robustness tests against the DC supply and load disturbances. In addition, the proposed strategy outperforms the previous control techniques presented at the state of the art in terms of adaptability, stability and, especially, the ability to reduce the THD, which validates its effectiveness for MG systems control and optimization under uncertain conditions.

Reliable segmentation of surface water is crucial for monitoring hydrological dynamics, mitigating disaster impacts, and supporting climate-resilient infrastructure development. However, traditional approaches based on spectral indices—such as the Normalized Difference Water Index (NDWI)—often suffer from poor generalization in the presence of spectral ambiguity, seasonal variations, and urban or vegetated interference. Existing deep learning architectures (DeepLabv3+, SegNet) show a trade-off between accuracy and speed, without specific adaptation to the challenges of the domain. This observation justifies the design of a hybrid architecture combining these models to achieve high semantic accuracy, environmental robustness, and computational efficiency. We propose a hybrid deep learning (DL) architecture that integrates two encoder-decoder segmentation frameworks: DeepLabv3+ with residual networks (ResNet18 and ResNet50) and SegNet with Visual Geometry Group (VGG16 and VGG19) backbones. The proposed model seamlessly combines two well-established encoding–decoding architectures, DeepLabv3+ (with ResNet) and SegNet (with VGG), by fusing their segmentation outputs at a decision level to combine the high semantic accuracy of SegNet with the computational efficiency of DeepLabv3+. This hybrid integration thus simultaneously leverages the complementary strengths of both networks to improve the overall quality of water surface segmentation while optimizing training time. This formulation briefly explains that the integration is not limited to a simple choice between models but also involves decision-level fusion or synergistic combination of results, which justifies the term hybrid or dual-stream architecture. These models are optimized for both semantic accuracy and computational efficiency, and trained using multispectral Sentinel-2 satellite imagery sourced from a publicly available Kaggle dataset featuring diverse terrain and spectral complexity. All models were implemented in MATLAB and evaluated using multiple performance metrics: overall accuracy (OA), Intersection over Union (IoU), F1 score, precision, recall, producer accuracy (PA), and user accuracy (UA). Among all configurations, SegNet with VGG16 achieved the best results, delivering An OA of 91%, IoU of 79%, and F1 score of 75%, while effectively minimizing false positives. In contrast, DeepLabv3+ with ResNet18 demonstrated exceptional computational efficiency, completing training in only 95 min with a respectable OA of 78%. These results underscore a clear trade-off between segmentation quality and training speed. Compared to baseline DL architectures and conventional NDWI-based methods, the proposed hybrid framework achieved significant gains in segmentation performance: precision improved by 2.64–22.66%, recall by 1.03–29.87%, and F1 score by 1.33–37.33%, with a 25.31–32.91% increase in IoU and up to 80% reduction in training time. Furthermore, the models proved robust under real-world environmental complexities such as cloud occlusion, seasonal transitions, and mixed urban-land–water boundaries. This research presents a scalable and high-accuracy solution for water body extraction, supporting a range of applications including flood risk assessment, environmental monitoring, and water resource planning. Future work will explore the integration of artificial neural networks (ANNs) for enhanced classification, multimodal data fusion with synthetic aperture radar (SAR) for all-weather operation, and real-time deployment using cloud-based platforms for global water surveillance.

In this paper, a Modified Genetic Algorithm (MGA) combined with ETAP (Electrical Transient Analyzer Program), is proposed to optimize the placement and sizing of Distributed Generation (DG) units while considering multiple objectives, such as improving voltage profiles, reducing line losses, and managing short-circuit levels. These factors are critical for maintaining power quality, system reliability, and overall stability. The MGA approach is validated through simulations using the IEEE 33-bus distribution system, modeled in both MATLAB and ETAP. The results show significant improvements in voltage stability, loss reduction, and short-circuit level management, enhancing energy management and operational efficiency. A comparative analysis with alternative algorithms, including the Bat Algorithm (BA), Bacterial Foraging Optimization Algorithm (BFOA), and Artificial Immune System (AIS), demonstrates that MGA achieves superior convergence speed and accuracy, making it highly effective for DG placement and power system performance optimization.

This study investigates the problems associated with the nonlinear power–voltage characteristics of photovoltaic (PV) systems, especially under partial shading conditions (PSC), which reduce energy efficiency and tracking accuracy. To overcome these limitations, two improved maximum power point tracking (MPPT) controllers based on Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) techniques are proposed. The controllers are designed with a suggested architecture that uses the power-voltage derivative (\(\:\frac{dV}{dt}\)) and the voltage time derivative (\(\:\frac{dP}{dV}\)) as input features, enabling predictive, non-iterative control. This approach eliminates the steady-state oscillations inherent in conventional perturb-and-observe (P&O) algorithms and achieves superior dynamic response under rapidly changing environmental conditions. Simulation results demonstrate significant improvements compared with the traditional P&O method. The proposed ANN and ANFIS controllers achieved average tracking efficiencies (\(\:{\eta\:}_{\text{avg}}\)) of 99.4% and 99.75%, respectively, with a response time reduction of about 55% and steady-state oscillation suppression exceeding 70%. The ANFIS controller exhibited higher stability, reducing the duty-cycle fluctuation index (\(\:{\sigma\:}_{\text{DCy}}\)) by approximately 20% compared with the ANN controller, resulting in smoother and more reliable power extraction. A comparative evaluation with recently published metaheuristic and hybrid AI-based MPPT approaches confirmed that the proposed ANFIS model achieves equal or better performance while maintaining very low computational complexity. The average execution time per control step remained below 0.2 ms, confirming the suitability of both controllers for real-time deployment on low-cost digital signal processors (DSPs). These findings demonstrate that the proposed intelligent MPPT framework provides a fast, accurate, and computationally efficient solution for improving the reliability and energy yield of PV systems operating under dynamic and partially shaded conditions.

In this paper, a bid-based dynamic economic dispatch (BBDED) problem is solved in the electricity market system under bidding strategies, including wind energy penetration using simulated annealing (SA) algorithm. The multi-objective dispatch model allows generating companies (GENCOs) and their customers to submit supply and demand bids to a market controller known as the independent system operator (ISO) and follow a bidding strategy. ISO is responsible for the market clearing and settlement to maximize the social profit and benefit for GENCOs and customers during trading periods. To study the effect and advantages of wind energy integration in the BBDED problem, the wind energy generation is computed using the forecasted wind speeds and included in the dispatch model. In this regard, the ISO's dispatch model is formulated as a bilevel nonlinear optimization problem. The higher-level is solving the market-clearing with and without wind energy, and the lower level is maximizing GENCO's social profit. The proposed SA algorithm is evaluated for optimality, convergence, robustness, and computational efficiency tested on an IEEE 30-bus test system. The simulation results are compared with those found using different algorithm-based approaches, considering various constraints like power balancing, generator limits, ramp rate limits, and transmission losses.

The multi-terminal High voltage Direct Current (HVDC) using voltage source converters (VSC) is proposed for interconnecting the renewable energy source such as offshore wind farms because it can facilitate the transnational exchange with high-cost efficiency. This paper analyses a model of three terminals VSC-HVDC system with a Voltage Margin control strategy using PSCAD/EMTDC simulation software. First, the paper begins with an overview of the development of Multi-terminal direct current system. The second part presents a review of the methodology that controls MTDC grids named Voltage Margin control. The simulation is performed to confirm the proposed Voltage margin control strategy.