This article proposed a Gated-Recurrent Learning Deep Neural Network (GRL-DNN) to predict the gate driving sequence of SiC-MOSFET in a 380 V/3A Low Voltage DC microgrid (LVDC). It is devised that the proposed intelligent fuse Active Gate Driving (AGD) requires a current limitation of 3 A to avoid fault and excess power loss. During over-current conditions in microgrid the proposed data-driven Intelligent Fuse (iFuse) acts as a circuit breaker with current limitation. The proposed GRL-DNN switching model training dataset is obtained for various operating condition in MATLAB. Training features like gate triggering, temperature, over-current magnitude, and tripping time are obtained by the proposed circuitry sequence predictor model in LTspice. By obtaining large solution space, without any delay automatic AGD can cutoff over-current in LVDC microgrid system. By comparing with conventional gate driving solid state fuse by Angelov model, the proposed iFuse integrated merits like fast reaction, accurate tripping, and high reliability to any system for improving fault protection. Online data analysis was carried to validate the outcome of the proposed iFuse AGD in hardware-in-loop simulation. The conducted real-time scaled-down experiment under over-current conditions on 380 V/3A LVDC system shows the proposed GRL-DNN based iFuse as a valuable active gate driving component for protection.

The existing photovoltaic power generation multi-source collaborative control technology cannot improve the control effect of microgrid, resulting in high peak load balancing cost of microgrid. Therefore, the photovoltaic power generation multi-source collaborative control technology based on differential evolution (DE)-gray wolf optimization (GWO) algorithm is adopted. The main components of the microgrid system, such as photovoltaic power generation equipment, hydroelectric power generation equipment, and battery pack, are modeled. With the goal of minimum peak cost and maximum transmission power, collaborative control of water, light and energy storage is carried out. The gray Wolf algorithm is used to solve the multi-objective problem of water and light storage in microgrid, and the gray Wolf algorithm is optimized by DE algorithm. Experiments show that the convergence speed of the optimized DEVOLU-Gray Wolf algorithm is obviously accelerated, and the problem of falling into the local optimal solution is completely avoided. After the application of this method, the photovoltaic, hydraulic, and battery of the microgrid run in order, ensure the smooth operation of the microgrid, and improve the economic benefit of the microgrid.

This paper proposes a novel approach for Optimal Power Flow (OPF) problems in power systems by integrating the optimal placement of Flexible Alternating Current Transmission System (FACTS) devices with a hybrid renewable energy system comprising wind and photovoltaic (PV). The objective is to optimize the placement of FACTS devices to simultaneously minimize power loss, voltage deviation and reduce gross cost. To achieve this goal, the Enhanced Multi – Strategies Sparrow Search Algorithm (EMSSA) is employed, which combines multiple optimization strategies inspired by the collaborative foraging behavior of sparrows. By considering multiple objectives, including power loss reduction, voltage deviation reduction, and gross cost minimization, the proposed methodoloty aims to identify optimal locations for installing FACTS devices such as SVC (Static Var Compensator), TCSC (Thyristor Controlled Seris Compensator), TCPS (Thyristor Controlled Phase Shifter). The results showcase the capability of the proposed methodology to achieve significant improvements in power system performance, thereby contributing to the efficient and sustainable operation of modern power grids. This research also provides valuable insights for power system operators and planners to make decisions regarding the deployment of FACTS devices and the integration of renewable energy sources.

This study focuses on optimizing wind generation plant scheduling to enhance renewable energy utilization while minimizing costs and ensuring grid stability. An advanced forecasting approach is proposed to predict wind generation plant availability for future intervals, integrating accurate demand prediction with renewable energy forecasting. Evaluation metrics like Mean Error (ME), Root Mean Square Error (RMSE), and Correlation assess the proposed solution’s performance, showing its superiority over baseline models with an RMSE of 9.39. Results highlight the effectiveness of the approach in forecasting wind generation plant availability, essential for efficient renewable energy utilization. By reducing reliance on traditional energy sources, the method contributes to cost minimization and promotes sustainability. The study underscores the potential of advanced forecasting techniques in optimizing renewable energy scheduling, offering opportunities for grid stability and reduced environmental impact. The proposed method involves training an LSTM model on preprocessed wind turbine data, integrating it with a scheduling algorithm for optimized task scheduling, and continuously learning to improve efficiency. The Optimized LSTM model outperforms other models in wind power forecasting, providing accurate predictions crucial for energy management decisions. Integration with SCADA control and maintenance scheduling further enhances operational efficiency and cost reduction in wind turbine management.

Electric vehicles (EVs) have significantly increased in recent years due to a growing awareness of the effects of polluting gases produced by combustion engines. The use of electric vehicles produces no emissions, making them a much more environmentally friendly alternative to traditional combustion engines. In addition, the price of EVs has decreased significantly in recent years, making them more affordable for consumers. The use of distributed generation (DG), an alternative source of energy for power systems, should also be considered. This study proposes a methodology for incorporating DGs and EVs into existing power systems. Power can be generated by DG directly where needed, while excess energy can be stored by EVs. Existing power systems can be made more efficient and cost-effective by combining these technologies. The methodology was applied to a 6-node IEEE system and a 33-node IEEE distribution system. It was found that DG can reduce network losses and voltage drops associated with EV penetration and that DG improves voltage drops.

Electric vehicles (EV) and hybrid plug-in EVs are receiving more and more attention due to their low fuel consumption and greenhouse gas emissions. To encourage the global adoption of EVs, on-board charger’s management scheme serving in rural locations is crucial, especially for those with erratic or nonexistent power supplies. As a novelty, this work provides the utility grid with reactive power while charging the EV. This is performed by the use of a progressive optimization approach known as the Squirrel-Wolf optimization algorithm to regulate the variables of the PI controller of the Alternative current (AC)-Direct Current (DC) converter and the DC-DC converter. The ideas of the Squirrel search optimization algorithm (SSA) and the Grey Wolf Optimization algorithm (GWO) were integrated to create the projected Squirrel-Wolf optimization algorithm. Also, the proposed method is validated over other methods in terms of error measures.

Wind is a renewable energy resource but its intermittent nature poses some issues for transmission system operators, wind farms, and the electricity market. To address these issues, wind power forecasting is crucial. In this study, the data were obtained from a turbine anemometer in the 1-year time horizon of 10 min for wind power forecasting. Models are designed with univariate long short-term memory, multivariate long short-term memory, multilayer perceptron (MLP), extreme gradient boosting (XGBOOST), convolutional neural networks (CNNs), long short-term memory, gated recurrent unit (GRU), and random forest (RF) algorithms. Outliers in the data are cleaned with the isolation forest algorithm. Hyperparameter optimization of the models, designed with machine learning algorithms for a selected month from each season (January, April, July, and November) was made with Bayesian optimization. The success of the models was measured by mean absolute error, root mean square error, and determination coefficient. Among the designed models, for January, April, and November, the multivariate long short-term memory model gave the most successful results with 0.926, 0.961, and 0.946 determination coefficient values, respectively. For July, the XGBOOST model provided the most successful result with 0.916 value of the determination coefficient

To ensure the safe and stable operation of the power system in the power market environment, a transaction model of power reserve ancillary services oriented to interruptible loads is constructed. By analyzing the benefits of interruptible users and power grid enterprises, a transaction model of interruptible load is established based on it. After obtaining the value of the minimum cost of power system to purchase interruptible load, the capacity cost, opportunity cost and standby use cost of power reserve are calculated respectively. The objective function of auxiliary power reserve service transaction model with interruptible load is established and the constraint conditions are set, and then the transaction result of auxiliary power reserve service is obtained by solving the objective function of the model. The experimental results show that the model can effectively calculate the power interruption compensation price of user interruptible load, and obtain the interruptible load transaction results according to the rapid capacity quotation, power quotation, etc. At the same time, the model has the lowest cost of reserve capacity and reserve use cost in a certain period of time, and the application effect is good.

Biomedical implants, such as implantable cardioverter heart monitors, rely on limited battery life, which necessitates costly replacements and patient discomfort. To address these challenges, a novel solar-based pacemaker model is proposed that is integrated with a fractional-order proportional integral derivative (FOPID) controller and a Hybridized Chaotic multiverse Krill Herd-based Backtracking Search Strategy (HCMKH-BS2) to enhance power generation for pacemaker operation. Our approach considers the impact of partial shading conditions on solar power. To mitigate these conditions, a FOPID controller with an HCMKH-BS2 model is developed which also addresses environmental issues through the adoption of a DC-DC converter. The gain parameters of the FOPID controller are determined using the proposed HCMKH-BS2 algorithm. The proposed technique is implemented to evaluate its performance using various measures in terms of duty cycle, convergence analysis, and power. The performance validation is performed based on the analyses of constant irradiance and changed irradiance. The proposed method achieved a fitness value of 0.01 from the convergence analysis and the duty cycle of 0.48D. These results demonstrate the superiority of our proposed technique over previous methods, highlighting its potential for enhancing the performance of solar-based cardiac pacemakers.

The current power system grapples with congestion challenges arising from technological advancements and deregulation. Conversely, renewable energy sources like wind offer an inexhaustible, cost-effective, and environmentally friendly solution, potentially alleviating congestion in the modern transmission network by reducing the need for conventional generators to reschedule. This article conducts a thorough analysis of how the penetration of wind power impacts congestion costs in conventional energy systems. To address this, a novel approach utilizing the bus sensitivity factor is introduced for precise wind turbine placement. To efficiently mitigate congestion costs, a pioneering Salp Swarm Optimization Algorithm is proposed and validated on a modified IEEE 30 Bus system, demonstrating superior performance compared to other algorithms. The findings underscore the effectiveness of the proposed algorithm and highlight wind turbines, coupled with generator rescheduling, as a potent and cost-effective solution for alleviating transmission network congestion.