Global projects are mobilizing technologies to fight power generation curtailment and smooth demand by exploiting excess energy via transactive energy management and control. Sharing and transferring energy between microgrids helps manufacturers and businesses create energy autonomously. The transition to Multi-Vector Multi-Agent Energy Systems (MMV-ES) demands a paradigm shift from traditional centralized control to decentralized, market-based coordination. Transactive Energy Management (TEM) has emerged as a key enabler in this context, supporting local flexibility, peer-to-peer (P2P) trading, and integrated energy vectors across distributed assets. This review systematically decomposes and classifies the existing state of TEM from several perspectives: the market topology, the interaction of the agent, game-theoretic models and the real deployment challenges. Moreover, two game-theory formulations (cooperative and non-cooperative) were given special attention and a detailed comparison between Shapley value and Nucleolus was provided as approaches for fair cost allocation. To enhance the adaptability of the market and the overall efficiency of the system, we introduce the Transactive Energy Reformulation Model (TE-RM), a hybrid model combining AI-powered congestion pricing with coalition formation and fairness-based incentives. The comparative tables in this paper summarize TEM and TE-RM's strengths and weaknesses and compare it to the centralized and conventional DSM methodologies. Lastly, key research gaps including scalability, regulatory fit, and AI model interpretability are reviewed, and future directions are proposed for the integration of future advanced technologies (e.g., reinforcement learning, blockchain, IoT) to enable stable, fair and interoperable energy markets.

Plant diseases are a major problem for farmers around the world, reducing crop yields. The absence of expertise makes plant disease detection difficult and complicated. Plant disease detection is made easier by deep learning algorithms; however, they are computationally demanding and need huge training datasets. This research work proposes a novel Conv-7 DCNN model with modified ParNet attention layer to classify plant leaves into distinct categories with improved accuracy. Because of its architecture, the proposed network can identify leaf diseases with more accuracy by extracting the wider range of features from the images. The proposed Conv-7 DCNN model classifies the leaf diseases of three plants such as tomato, potato, and pepper-bell into fifteen categories. The CNN model is trained using publicly accessible Kaggle dataset, utilising image augmentation techniques. It is evident from the simulation results that the proposed model outperforms several pre-trained, and other trending deep learning models. Proposed model achieves 99.18% classification accuracy with an average precision of 99.17% and area under the curve (AUC) of 1, making this model highly effective in leaf diseases detection. Additionally, Conv-7 DCNN achieved high FPS of 112.49, low inference time of 18.34 s, and low GFLOPS of 13.98, making it suitable for real-time applications in smart agriculture systems.

The incipient faults classification of transformers is crucial for preventing failures and ensuring reliable operation. This paper presents a machine learning (ML) model designed for transformer fault identification, integrating modified artificial data with a novel 4GM graphical algorithm. The study trains the KNN model on a 4GM-based dataset of 1022 transformers specifically for fault identification. The model’s performance is validated using the IEC TC 10 database, demonstrating effective accuracy in fault classification. Additionally, a modified Artificial Data Generation (ADG) technique is introduced to enhance the dataset, addressing data imbalances and improving model robustness. Initial integration of the ADG technique led to reduced accuracy, necessitating further adjustments. Through iterative modifications, the combination of the 4GM algorithm and the enhanced ADG technique resulted in improved accuracy and robustness. This research will help many researchers in this fields for further improvement of ML performance when data imbalance, low database problem occurred.

Nowadays, metaheuristic algorithms are used as an essential tool for solving complex optimization problems, and the majority of them are motivated by the collective intelligence of living things in the natural world. An innovative metaheuristic algorithm called African Vulture Optimizer (AVO) is presented in this study. The African Vulture Optimization Algorithm (AVOA) was created based on the orienting and feeding habits of African vultures. The social behavior of African vultures in the wild serves as an inspiration for it. AVOA maintains the ideal ratio of exploration to exploitation and provides powerful stochastic operators for addressing optimization problems. Though several publications have been written about these methods, little attention has been paid to fully summarizing the AVO algorithm. This effort aims to document current information on the AVO algorithm to assist researchers working in this field. Moreover, to address the ORPD challenges of the IEEE 30-bus power systems, we have employed the AVO algorithm and evaluated its effectiveness. The AVO algorithm has been shown to generate higher-quality solutions in a reasonable time by comparing ORPD results with alternative techniques disclosed in the most recent literature. For example, the AVOA algorithm applied to the IEEE 30-bus system improved voltage deviation approximately 93.19

Plant infestations have become a global threat in vertical farming, substantially impacting crop yields. Accurate diagnosis of these diseases is often hindered by the lack of specialized knowledge. Deep learning algorithms offer promising solutions for plant disease detection but are computationally intensive and require extensive training data. This research work introduces a novel FusionNet-OptiMLP deep learning model to categorize the hydroponics-grown lettuce plant's leave diseases with improved accuracy. By integrating DenseNet121, ResNet50V2, and a custom Convolutional Neural Network proposed model extracts a wider range of features from infected leaves, enhancing classification performance. The extracted features are fused and employed to optimize a Multilayer Perceptron classifier using the Walrus Optimization Algorithm The optimized MLP classifier achieves remarkable metrics, including an accuracy of 99.42 %, precision of 99.43 %, F1-score of 99.43 %, recall of 99.44 %, and Matthews Correlation Coefficient of 0.9913. The FusionNet-OptiMLP model, trained on a hydroponics lettuce leaf dataset, outperforms pre-trained models like DenseNet-121, ResNet-50V2, VGG-19, InceptionV3, and Xception in both accuracy and complexity. The proposed model demonstrates a swift response, with training and test times of 94.66 and 0.07, respectively. Statistical tests, including one-way ANOVA followed by Tukey HSD and Friedman ranking, validate the remarkable performance of the proposed model.

The asymmetrical scenery of renewable sources (RESs) has raised renewable insecurity. As a result, it is dominant to introduce energy storage systems (ESSs) along with DRP to lighten the instability of uncertain RESs. The combination of FACTs such as static synchronous compensator (STATCOM) and Compressed air energy storage (CAES) both provide impending advantages for the power system including better system stability, improved voltage profile, and lower network obstruction. Other schemes are being deployed to increase control of power flows and optimize energy storage capacity. Furthermore, the need for DRP and CAES synchronized with STATCOM devices to ensure minimizes operational cost and system security makes the SCUC problem more demanding to solve due to the increasing problem size. In this perspective, the paper proposes a problem on stochastic SCUC with STATCOM devices, DRP, CAES and renewable sources. The modeling of the STATCOM devices within the power system in AC network is more intricate and finding a best possible location is discussed. The reduced problem size mitigates the burden arising from the combinatorial nature of the difficulty. The speed-up and optimality of the decomposed method are proven on the IEEE- 30 bus systems.

Interpreting incipient faults in mineral oil transformers using dissolved gas analysis (DGA) involves understanding the complex interrelationships in the evolution of various gases caused by different incipient faults. The Duval Triangle 1 method is commonly used to interpret DGA results due to its wide acceptance, however, it still does not address the severity level of discharge and thermal (DT) incipient fault. The paper focusses on understanding the relative concentration of different gases during DT and assign a severity level with fault-space refinement by combining trusted graphical and synthetic data generation (SDG) techniques. DTs occur sparsely and require an SDG approach due to lack of real-world data related to different severity levels of DT faults. Integration of SDG techniques and analysis of key gas concentrations, such as methane and ethylene, critical fault thresholds are identified, with methane concentrations exceeding 43% indicating severe faults like T3 and D2, while ethylene concentrations below 29% suggest low-to-medium thermal faults. 1113, 2166873, 13989, 396593, and 1899995 data instances were identified for fault categories D1, D2, T1, T2, and T3 faults respectively. Based upon rigorous analysis and training, the DT fault regions are segregated into different severity levels. This research offers a novel DT fault categorization which helps in condition monitoring of transformers.

Abstract The depletion of fossil fuels and the rising demand for electricity are driving the global shift toward renewable energy sources (RES). The primary goal of incorporating RES into the conventional smart grid is to establish a more ecological and eco-friendly energy system. However, due to their lower system inertia, RESs struggle to effectively respond to fluctuations in load demand. This study investigates how a Dual Loop LADRC-FOPIDN-(1 + TD) controller can improve frequency regulation in a multi-area deregulated electricity system while taking RES’s intermittent nature into account. By integrating LADRC with a cascade controller, the proposed approach delivers improved transient performance over selected benchmark controllers (LADRC, FOPIDN, FOPIDN-(1 + TD)) under the tested scenarios. Furthermore, an enhanced Quasi Opposition Arithmetic Optimization Algorithm (QOAOA) is employed to optimize controller parameters for improved efficiency. Simulation results highlight its strong adaptability to specific uncertainties modeled in this study, such as RES intermittency, load fluctuations, and delay effects, ensuring grid stability. Moreover, this study addresses the use of electric vehicles (EVs) to regulate frequencies in a hybrid power system under the conditions of real-time load demand variations. Plug-in Electric Vehicles (PEVs) are incorporated in every system region as a measure to reduce undesirable transient components on load frequency and power sharing. PEVs absorb unnecessary electrical energy and give it back to the grid when needed, which offers useful grid support, particularly within RES-dominated networks. The proposed controller is tested on a better IEEE-39 bus system with real-time load variation and variability of RES, through data provided by BSES Rajdhani Power Limited (BRPL), Delhi. Lastly, OPAL-RT hardware is used to run a real-time simulation environment, which targets the integration of real hardware with a virtual test environment, to test the effectiveness and the robustness of the controller. Finally, the MATLAB simulation results are compared with OPAL-RT hardware results.

Electric power is crucial for driving the progress of any nation, because of the accumulative demand for power production worldwide. In this regard, conventional energy sources (CES) are depleting and emitting greenhouse gases into the environment. Therefore, renewable energy sources (RES) are the best option for meeting the required clean power generation. This paper introduces a novel neural network (NN)-based MPPT technique for optimizing the power generation of wind turbine (WT) framework management under variable environmental conditions. The proposed framework effectively captures the complex relationship between WS, turbine parameters, and power output, enabling specific tracking of the MPP. The proposed approach is simulated in MATLAB/Simulink and performs better than conventional specified MPPT algorithms. This results in enhanced energy extraction and improved system efficiency of the WT module.

An electric vehicle (EV) represents a mode of transportation which is propelled by the utilization of one or more electric motors. Both electric vehicles (EVs) and microgrids rely on the use of an energy storage system for their functioning. The device can operate autonomously using a battery, which may be recharged through the utilization of a solar photovoltaic (PV) panel. In this context, EVs powered by Renewable Energy Sources (RES) have many advantages over traditional vehicles based on Internal Combustion Engines (ICE). The nonlinear features exhibited by solar PV panels are produced by using environmental changes. Therefore, the development of the Maximum Power Point Tracking (MPPT) approach is proposed to find the stable maximum power from solar PV panels. This method is recommended to optimize the effectiveness of solar PV systems by maximizing the utilization of available solar radiation (SR). This article poses an investigation of the optimized fuzzy logic controller (FLC) approach for solar output power management in EV battery charging systems. The proposed work is established as a charging station in order to charge the battery banks, which improves the effectiveness of EV charging. The simulation of a novel system has been conducted in various working environments, and the resulting data has been thoroughly analyzed. PV frameworks produced output responses of voltage, current and power are 26.15 V, 7.702 A and 201.4 W respectively in steady-state conditions using novel FLC MPPT and produced output responses of voltage, current and power are 23.95 V, 7.663 A, and 183.5 W, respectively using conventional P&O MPPT. The proposed PV frameworks using novel FLC MPPT are greater than the conventional P&O MPPT by 9.8 %. Further research can be developed in favour of electronic power-based regulators using novel AI-based hybrid MPPT controllers, which effectively control the battery charging system for EVs.

The Fine aggregates are widely used in concrete and mortar. Use of fine aggregates in the concretes results in mining of riverbeds for aggregates. Excessive mining on the river bed causes environmental hazards and has the potential to change the hydrology of the region. It results in changing the natural drainage area of any watershed. It results in excessive cutting of riverbanks and also results in floods, landslides and river bank erosion. Further there is lot of generation of demolition waste as a result of development. Dumping of demolition waste in landfill is another environmental hazard which is again a cause of concern. Use of recycled aggregates as a replacement for river sand aggregate can solve the problem of mining and also of waste disposal. This paper compares the various properties of concrete made from fine aggregates from river sand and from demolition waste. There is reduction in workability and compressive strength due to increased porosity and non-uniform size of fine aggregate. The fineness modulus of recycled aggregate is higher than fineness modulus of river sand aggregate. All the power requirement for the test were met by generating power by 5 KW solar smart generation capacity. It uses hybrid inverter which directly supplies generated electricity during day time. The inverter uses r-MPPT technology which monitors output and can take power from panels, battery or grid and achieves optimization.

The growing adoption of wind turbines to generate electricity raises the need for more accurate WSP to understand the instability of WS and mitigate the negative effect caused by the random nature of WS in achieving optimal electricity production. This paper used the Machine Learning model (Random Forest Regression) to examine the effect of Empirical Mode Decomposition (EMD) application in feature extraction for WSP. The obtained datasets for this work were from a credible open-access website collected on tropical cities (Khota Bahru, KLIA Sepang, Kuantan, Muadzam Shah, and Pulau Langkawi) meteorological stations in Malaysia as case studies. The dataset underwent preparation before duplicating the dataset into a reference and extraction dataset, then applied Empirical Mode Decomposition (EMD) on the extraction dataset for all five case studies to decompose each feature of the extraction datasets respectively into five Intrinsic Mode Functions (IMFs) then, reconstructed the IMFs into separate columns as new variables and used the IMFs extracted datasets and the reference datasets for predictions. The model prediction accuracy and performance for both datasets were obtained and compared. After comparison, the EMD-extracted dataset predictions produced higher accuracy and lower errors than the actual dataset prediction for Khota Bahru, KLIA Sepang, Kuantan, Muadzam Shah and most effectively for Pulau Langkawi. In conclusion, Empirical Mode Decomposition (EMD) application improved the accuracy and model performance.

This paper represents the use of portable battery bank for battery powered electrical vehicles. Environmental consciousness and energy concerns have fuelled the development of sustainable transportation solutions. Electric vehicles (EVs) are becoming increasingly popular as a viable substitute for traditional transportation due to their environmental friendliness, effectiveness, and practicality. Additional power bank has converted a very appropriate substitute to batteries in EV since of their noteworthy energy concentration and hasty charge/discharge eras. EV are gaining popularity worldwide as a greener substitute to old-style gasoline-powered vehicles. As the request for EVs remains increasing, nearby a growing need to address the challenges associated with charging infrastructure. Many EV owners face the inconvenience of limited charging stations, especially in remote areas or during long journeys. This is where portable power chargers for EVs come in, offering a practical solution for on-the-go charging. These portable chargers, also known as mobile EV chargers, allow EV owners to charge their vehicles anytime and anywhere, providing a level of flexibility and convenience that traditional charging stations cannot always offer. In this report, we will explore the motivation behind researching portable power chargers for EVs and delve into their potential to revolutionize the EV charging landscape.

With increased demand for generative AI and LLM-based digital services across society, data centers are shifting towards GPU-centric servers with higher power consumption and cooling requirements. Operators utilize power profiles at the server’s AC-input boundary for planning and control. When these profiles are interpretable at the component-level, the drivers of peaks, ramps, and sustained plateaus can be attributed to specific components. However, component-level power profiles are rarely available outside controlled testbeds; in operational facilities, these profiles are restricted to authorized teams and fragmented into non-synchronized logs. Existing datasets and simulators rarely provide an end-to-end power profiling approach that links workload scenarios to component activity, component power, and server AC-input power. This study presents a multi-level approach that generates component-activity profiles using a semi-Markov process (Level-1), maps activity to component-level power using lightweight analytical models (Level-2), and generates AC-input power profiles (Level-3). The approach outputs 6-hour profiles at 1-min cadence for component activity, component power, and AC-input power. A guard-and-repair quality-control policy with six physics guards (D1–D6) enforces physical plausibility and accepts 98.79 % (9879 of 10000) profiles. Generated profiles for publicly available workloads (Llama/ResNet variants) are validated against published DGX H100 AC-input traces, and report 3.7–5.95 % mean absolute percentage error and sub-kW RMSE. The performance of the proposed framework is analyzed under varying inlet temperatures, capping policies, and power modes, along with comparative evaluation against existing simulators. The approach is useful for researchers and practitioners designing, evaluating, and benchmarking power-aware planning and control methods at the AC-input boundary.

Quadratic boost converter (QBC) is crucial in immediate technologies, including renewable energy, electric vehicles (EV), DC microgrids and EV charging stations, where efficient and dependable power conversion is essential. This article introduces a high-gain, high-efficiency QBC operating with soft-switching capabilities explicitly tailored for renewable energy sources that can be used in charging stations for EVs. The design achieves high voltage gain (VGN) by incorporating a coupled inductor (CIN) with a restricted duty cycle, which minimizes the need for extreme duty cycle adjustments that often impact efficiency and cause component stress. The leakage inductances of the CIN’s enable zero voltage switching (ZVS) for the power switches at turn-on and ZVS turn-on and zero current switching (ZCS) turn-off for the diodes. This approach mitigates the switches’ losses and enhances the efficiency. Furthermore, an active clamp circuit is employed, allowing the converter to operate with reduced voltage stress across semiconductor components, thus improving their durability and reliability. The converter operated in continuous conduction mode (CCM) is extensively analysed to assess its performance across various operating conditions. This converter compares VGN, efficiency, and stress on components with several recent QBCs for a comprehensive performance assessment. The converter’s 250 W hardware prototype has also been built and tested, demonstrating its practical suitability and effectiveness for high-demand renewable energy applications. Experimental findings affirm the converter’s high efficiency and reliable performance in real-world situation.

Effective Battery Management Systems (BMS) are crucial for the safe operation, longevity, and optimal performance of batteries in renewable energy and electric vehicle applications. However, accurate real-time estimation of the State of Charge (SOC) and timely fault detection remain challenging due to the nonlinear behaviour of batteries and varying environmental conditions. Conventional methods often suffer from limited accuracy and slow fault diagnosis, which can lead to reduced battery life and system reliability. This paper proposes a hybrid Battery Management System (BMS) approach that combines convolutional neural networks (CNN) with the extended Kalman filter (EKF) to enhance SOC estimation and facilitate early fault detection. The CNN component learns complex non-linear battery dynamics and identifies anomalies from historical data, while the EKF dynamically refines SOC estimates under changing load and temperature conditions. The proposed method is implemented and validated using MATLAB / Simulink simulations, demonstrating enhanced accuracy and faster response compared to traditional approaches. Future work will focus on experimental validation of the proposed framework using real lithium-ion cells and hardware-in-the-loop setups to bridge the simulation-to-reality gap and assess real-time feasibility on embedded BMS platforms.

Deep learning is efficiently used for photovoltaic power generation forecasting to handle the intermittent nature of solar energy. However, big data are required for training deep networks which are not available for newly installed plants. Therefore, in this study, a novel strategy is proposed to train a deep learning model using a transfer learning technique to cop up with the unavailability of enough training datasets. A new 400 kWp solar power plant installed in the Himalayan region is considered as a case study to evaluate the proposed model. The proposed approach utilizes solar radiation data to train a deep neural network and then fine-tune the model using the power generation data from the plant. The network architecture is optimized using grey wolf optimizer to find the best suitable model for the data. The evaluation results show that the same model can achieve higher performance in generation forecasting with percentage error improved by 2% and R-value increased by 7.7% after applying transfer learning. Moreover, SHapley Additive exPlanation and Partial Dependence Plots are used to interpret the model behavior and showed that the model is mostly dependent on the previous generation values (up to 4 days) followed by the temperature and solar radiation.

The correct and precise forecast of solar radiation is very important for enhancing the efficacy and use of solar energy systems. This research project deals with the same and advancements of machine learning structures Transformer designs in forecasting solar radiation using environmental data gotten from a trusted dataset. Both full-feature and featureselected criteria using Random Forest importance are studied to compute the effects of dimensions of reduction on forecast precision. The structures are studied using many regression numbers: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Bias Error (MBE), and Coefficient of Determination $\left(\mathbf{R}^{2}\right)$. The results of the experiment show that the Transformer model without feature selection is more precise and trusted over feature selection, getting the lowest RMSE and highest $\mathbf{R}^{\mathbf{2}}$, showing good prediction trustworthiness. The research throws light on the potential of deep learning and ensemble approaches for accurate predictions of solar radiation, and the effects of feature selection on structural efficacy. This study throws light on valuable insights for research and practices aiming at enhancing renewable energy resource assessment through data-driven structures of forecasting.

The increasing integration of renewable energy systems such as photovoltaic (PV) arrays and wind turbines demands highly efficient and reliable power conversion for motor drive applications. Boost-Luo converters, known for their high voltage gain and improved efficiency, are commonly used in such systems. However, power electronic components and motor drives are susceptible to faults due to thermal, electrical, and mechanical stress, leading to unplanned downtimes and maintenance challenges. This paper presents a comprehensive AI-based predictive maintenance framework for Boost-Luo converter-fed motor drive systems operating in renewable energy environments. The proposed system leverages Deep Neural Networks (DNN) for fault classification and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for Remaining Useful Life (RUL) prediction. Multisensor data including voltage, current, temperature, and vibration are processed through feature extraction and dimensionality reduction techniques. Additionally, a Grey Wolf Optimization (GWO) algorithm is employed to optimally tune the PI controller for voltage regulation and harmonic distortion minimization. Simulation results validate the system's ability to perform early fault detection, precise RUL estimation, and enhanced converter control, leading to improved system reliability and efficiency.