Power grid engineering is necessary for the distribution of power, but problem detection and categorization are made extremely difficult by their growing complexity, particularly with the incorporation of renewable energy sources. Decision trees and support vector machines are two examples of fault detection techniques that frequently fail to handle the dynamic and non-stationary character of power grid data. These techniques’ efficacy in real-time defect identification is limited because they are unable to capture the complex relationships and temporal dependencies present in time-series data. Furthermore, a lot of conventional models are unable to generalize to different kinds of problems, which results in errors and delays in fault identification. For improved fault detection and classification in power grids, this research suggests a hybrid approach that combines Temporal Fusion Transformers (TFT) with Long Short-Term Memory (LSTM) Neural networks. While the LSTM neural network is used to represent sequential data, the TFT model is particularly good at capturing complicated linkages in time-series data. By combining these two models, the suggested approach can improve grid efficiency and dependability by offering precise fault forecasts in real-time. The findings show that the suggested hybrid model works better than conventional techniques, with a fault classification accuracy of 98.66% as opposed to decision trees’ 97.42% and SE-CDAE’s 97.98% accuracy. The performance of the model demonstrates its potential for real-time implementation in contemporary power grids, guaranteeing improved fault identification and prompt reactions to avert system breakdowns.
Underground mine cable distribution systems are critical industrial local energy infrastructures, where ground faults can lead to production interruption, difficult fault searching, and safety risks. This paper proposes a ground-wire active-current based fault-location method for smart monitoring of underground mine cable distribution systems. The method uses zero-sequence voltage as the fault trigger and phase reference, and measures ground-wire currents at both ends of each monitored cable section. By extracting the active components of the head-end and tail-end ground-wire currents, a fault judgment quantity is constructed through their algebraic summation. Theoretical analysis shows that, for non-faulted cable sections, the active ground-wire current mainly behaves as through-current and is largely cancelled by the double-ended summation. In contrast, for the faulted cable section, the fault current flows from the fault point toward both ends, producing a dominant active-current summation. Simulation results under transition resistances from 0 Ω to 1000 Ω verify that the proposed method can correctly identify internal cable-section faults and distinguish terminal busbar/switchgear faults without falsely locating a healthy cable section. A distributed smart monitoring architecture integrating ground-current sensors, zero-sequence voltage measurement, RS485/LoRa communication, and master-station processing is also presented. The proposed method provides an interpretable and practical solution for online fault location, faster fault isolation, and improved reliability of underground mine local energy distribution systems.
Industrial electricity load forecasting is crucial for the stable operation of power systems and energy management. However, the complex temporal patterns and dynamic interdependencies between loads from different industries make it challenging for traditional forecasting methods to model effectively. To address this, this paper proposes a forecasting model based on an inter-industry association dynamic graph neural network that integrates periodic features. The proposed method uses the Time2Vector block to adaptively capture multiple periodic fluctuations in the load sequence, and combines this with the cointegration relationship and error correction mechanism from the Vector Error Correction Model (VECM) to quantify the association strength between industries. Each industry is represented as a node, and the association strengths define the edges and their weights. Thus, this forms a Dynamic Inter-industry Association Graph (DIAG). This graph is then integrated into a Dynamic Spatial-Temporal Aware Graph Neural Network framework. As a result, the Inter-industry Association Dynamic Graph Neural Network (IADGNN) is formed. This model captures the complex dynamic characteristics of electricity loads across different industries. Test cases based on industrial load data from one province in China show that this method significantly outperforms traditional models in terms of forecasting accuracy, providing a novel solution for addressing the complex industrial load forecasting problem.
With the high penetration of distributed energy resources (DERs), the strong uncertainty of their output and the complex interaction of network topology pose severe challenges to the real-time performance, scalability, and intelligence level of dispatching methods. This paper proposes a hierarchical distributed collaborative intelligent dispatching architecture based on deep reinforcement learning (DRL) and graph neural networks (GNNs). This architecture adopts a two-layer design of “regional agent-edge controller.” The upper-layer regional agent uses GNN to process the global power flow state and generate node marginal price signals; the lower-layer edge controllers act as independent DRL agents, making autonomous decisions based on local observations and price signals. Through a hybrid mechanism of centralized training and distributed execution, collaborative learning and plug-and-play expansion of the system are achieved. This method significantly reduces dispatch costs when dealing with uncertainty, achieving a high photovoltaic grid integration rate of up to 100%, and controlling the maximum net power deviation between day-ahead planning and real-time operation to within 0.35 MW. Even when the system is expanded to 500 DER units, the online decision-making time remains at 7.5 milliseconds, and communication overhead only slowly increases to 35.0 KB, demonstrating its significant effectiveness in improving system resilience, operational economy, and scalability.
The current trends in electric vehicle adoption in distribution networks have brought some positives into microgrid operations. EVs can reduce greenhouse gas emissions down and create a more flexible source of energy by using V2G technology; however, uncontrolled charging of these vehicles is likely to incur losses in energy, fluctuations in voltage, and reduced efficiency to the system in total. This research proposes an optimal scheduling framework for the charging/discharging of EVs understandably connected to distribution systems embedded in microgrids. Analysis and classification of forecasted EV charging will be done based on charging data obtained from Kaggle; the charging behaviors will be classified into peak/off-peak utilization and flexible/inflexible groups, wherein energy losses are minimized, and distribution system efficiency is maximized through a multi-objective optimization model with realistic operating conditions. Simulation results on the IEEE 33-bus and 69-bus test systems demonstrate that with suitable coordination of scheduling, energy loss is reduced up to 25%, voltage stability is ensured, green energy is utilized maximally, and load relief during the peak period takes place. The results from this study highlight how smart scheduling of EVs could enhance smart grid performance in the future concerning the technology, economic, and environmental aspects.
The research elaborates on a Water–Energy Recovery System (WERS) that has been developed as a sustainable manufacturing enhancer by extracting hydraulic energy from industrial wastewater networks. The study uses an extensive dataset of a Full-Scale Wastewater Treatment Plant from six important industrial areas of Iran, and the framework goes through extensive data preprocessing which consists of noise reduction, normalization, and extraction of the main indicators like Specific Energy Consumption (SEC) and Flow Power Ratio (FPR) for the evaluation of hydraulic–energy relationships. Hydraulic head estimation, power calculation, and multi-criteria ranking that considers flow stability, installation feasibility, and cost-effectiveness are the methods used to unearth the potential recovery locations. The WERS that comprises of a pump-as-turbine arrangement for hydraulic energy conversion is also backed by storage and smart control units, and the measurement of environmental and economic performance is done through a Life Cycle Assessment (LCA) integrated with Techno-Economic Assessment (TEA). Non-dominated Sorting Genetic Algorithm II (NSGA-II) is the one that performs the multi-objective optimization by maximizing the annual recovered energy and minimizing the total system cost. The outcomes show a total recoverable energy potential of 6.8 GWh from 613 Hm3 of the industrial wastewater, the Caspian region being the highest contributor (3.2 GWh). The configured WERS with optimization results in a power of 31,110.72 kW, CO2 reduction of 2.23 × 108 kg annually, and strong economic viability indicated by payback and cost–benefit metrics. These results accentuate the remarkable potential of water-based energy recovery as a large-scale solution of future low-carbon and resource-efficient industrial operations.
Microgrid energy management plays a critical role in ensuring the secure and economical operation of microgrids. To address the uncertainty of renewable energy generation, this paper proposes an MPC-guided deep reinforcement learning (DRL)–based intraday scheduling strategy for microgrids. The proposed approach integrates the advantages of model predictive control (MPC) and DRL, where the optimization results of the MPC module are provided as environmental inputs to the DRL agent, and the DRL module interacts with the real microgrid environment to generate compensation actions. This framework not only mitigates the performance degradation caused by uncertainties in model-based methods, but also reduces the search space of DRL, thereby accelerating training convergence and suppressing policy fluctuations. Comparative simulations are conducted against standalone MPC and standalone DRL controllers. The results demonstrate that the proposed strategy can significantly reduce both operational security cost and economic cost, while effectively improving the utilization of renewable energy. Therefore, it provides an innovative solution for the microgrid scheduling problem.
The transition toward decentralized energy systems has led to the development of Peer-to-Peer (P2P) energy sharing schemes, allowing prosumers to exchange surplus energy within regional networks. This paper presents an optimized energy transaction framework that improves system resilience while facilitating cost-effective energy exchange through a two-stage adaptive P2P pricing mechanism The principal objective is to develop an internal pricing structure that combines market-based initial price formation with real-time electric vehicle-aware price adjustment to support equitable energy trades, reduce dependence on centralized utilities, and enhance economic efficiency. The suggested methodology uses a mathematical optimization model that integrates supply-demand dynamics and pricing strategies. A Mixed-Integer Linear Programming (MILP) method is employed to optimize energy distribution among prosumers, while considering network limitations and variations in renewable energy. Simulation data derived from actual energy profiles are used to validate the framework across various market scenarios. Numerical results show that the P2P energy trading mechanism enhances system resilience by decreasing peak demand by 20% and reducing prosumer costs by an average of 15%. The proposed pricing strategy guarantees equitable energy distribution, reduces transaction costs, and encourages active customer engagement. The findings demonstrate that decentralized energy markets can advance sustainability while also providing modern power systems with economic advantages.
Currently, traditional monitoring methods based on physical models and SCADA static data struggle to achieve real-time insight, trend prediction, and proactive early warning of system operational states. To accurately perceive the operational situation and locate faults in distribution networks, this study introduces a distribution network operational situation perception approach grounded in graph convolutional neural network-enhanced digital twin model. This method enhances the traditional digital twin model with graph convolutional neural networks to achieve accurate positioning and fault analysis of distribution network operational situations. The research findings demonstrate that, compared to the traditional random forest algorithm, the new method improves positioning accuracy by approximately 10.5%. Meanwhile, the average positioning error of the new method is reduced by about 3.4 compared to the traditional random forest algorithm. Furthermore, using a single graph convolutional neural network results in a 7.5% decrease in positioning accuracy and a 2.1 increase in positioning error compared to the improved model proposed in this study. Stability testing shows that when the learning rate is set to 0.0003 or 0.0005, the accuracy of the model reaches 98% after 100 iterations of training. The robustness verification shows that under the interference scenario of injecting 2% false data, the accuracy, recall, F1 score, and precision of the model remain above 98%. Thus, employing the new improved model can significantly enhance the fault positioning accuracy for distribution network operational situations. This holds considerable research significance for achieving effective operational situation perception and positioning in distribution networks.
This paper presents a techno-economic optimization framework for the design and sizing of a hybrid renewable energy system (HRES) integrating photovoltaic generation, wind energy, and battery storage for isolated and weak-grid coastal communities. The proposed methodology aims to minimize the annualized life cycle cost, also referred to as the equivalent annual total cost (CAET), while explicitly incorporating system reliability through the Value of Lost Load (VOLL), a concept widely adopted in power system planning and regulatory studies. The optimization problem is formulated using an hourly energy balance over a full annual horizon of 8760 hours, allowing the explicit representation of load variability, renewable resource intermittency, and battery charge-discharge dynamics. Capital investment costs are annualized using the capital recovery factor based on established engineering economics principles, while operational costs and the economic valuation of unserved energy are jointly considered in the objective function. By embedding reliability costs directly into the cost formulation, the proposed approach modifies the mathematical structure of the optimization problem, leading to a convex cost behavior within the feasible design space. The framework is applied to a real-world case study corresponding to the coastal community of Chérrepe, Peru, using site-specific solar irradiation, wind resource, and demand data. Simulation results demonstrate that the explicit inclusion of reliability valuation significantly influences optimal system sizing, discouraging undersized configurations with excessive unmet demand as well as oversized configurations with unnecessarily high capital costs. The resulting optimal design achieves a balanced and economically consistent trade-off between investment cost and supply reliability. The results confirm that integrating reliability valuation directly into the techno-economic optimization process provides a transparent, robust, and replicable approach for the planning of hybrid renewable energy systems in isolated contexts. The proposed methodology can be readily adapted to other locations and technology combinations, offering a practical decision-support tool for distributed generation and alternative energy planning.
The increasing penetration of distributed photovoltaics (PV) into distribution grids has led to a pronounced voltage over-limit issue, posing significant challenges to grid stability and power quality. Given this context, to address voltage management, a partition-based control methodology is proposed that leverages flexibility from load-side resources. Firstly, the double-layer probability fitting is carried out for photovoltaic uncertainty. Secondly, the risk indicators are innovatively proposed, and a dynamic zoning system including risk indicators is constructed. The centralized-distributed hybrid voltage control architecture suitable for dynamic partition is constructed again. Finally, the proposed model and its performance are assessed through simulations on a modified IEEE 33-bus distribution network. The proposed algorithm effectively mitigates voltage deviations and enables flexible, efficient partition-based voltage control in modernized distribution systems.
In the scheduling of distributed multi-energy virtual power plants, this paper proposed a robust scheduling method based on Wasserstein Generative Adversarial Network with Reinforcement Learning (WGAN-RL) to address the vulnerability of scheduling strategies caused by renewable energy output fluctuations and load uncertainties. This method defined the state and action space based on physical constraints and embedded hard operating rules. Then, it designed a conditional Wasserstein GAN to generate the worst-case perturbation scenario that approximates the real distribution support boundary and covers high-risk areas, based on weather and load forecasts. On this basis, it used Proximal Policy Optimization (PPO) to train the scheduling policy in an environment with dynamically injected extreme perturbations, and improved the convergence stability by pruning probability ratios and GAE. Finally, it introduced a rolling time-domain online scheduling and a weekly fine-tuning mechanism of WGAN to achieve long-term adaptability under perturbation distribution drift. Experiments show that, in terms of economics, with a 70% renewable energy penetration rate, the average daily dispatch cost is 2680 USD ± 150 USD, and the curtailment rate is 9.6% ± 1.1%. Regarding robustness, under a perturbation of 0.7 output standard deviation, the dispatch feasibility rate remains at 90.1% ± 2.1%, and the number of strategy collapses is controlled at 9.9 ± 2.1. In terms of real-time performance, the single-step inference time is only 4.2 ms ± 0.3 ms, and the training convergence steps are only 823. This research provides a deployable, adaptive, and engineering-feasible technical path for robust dispatch of virtual power plants under high uncertainty environments.
Flue gas denitrification of boilers in large coal-fired power stations has high operating costs, and its online optimization can reduce denitrification costs and enhance the competitiveness of power generation enterprises. In addition to the operational aspects of denitrification, the logistics of denitrification agents, such as transportation, storage, and distribution, also contribute significantly to the overall cost. This study comprehensively focuses on the online modeling and optimization of denitrification cost of thermal power units, incorporating logistics costs related to denitrification agents. The paper proposes a system that integrates wireless sensor data and real-time wireless communication from thermal power plants, aiming to construct an online denitrification and logistics integrated economic optimization system. The system establishes a boiler denitrification cost prediction model using a data-driven least-squares support vector machine (LSSVM) method combined with the BP algorithm for input variable selection. An improved genetic algorithm is applied for offline optimization of the unit’s constant operating load points and construction of an offline expert database. Additionally, a logistics cost prediction sub-model is included, analyzing historical logistics data related to denitrification agents, such as transportation distances, storage durations, and vehicle utilization rates. A fuzzy association rule mining algorithm (FARM) is utilized to extract correlations between load, logistics parameters, and optimization variables, enabling real-time optimization of both denitrification and logistics costs. The results show that the BP-LSSVM modeling method effectively reduces model complexity and improves prediction accuracy, while the GA-FARM optimization method significantly reduces comprehensive denitrification and logistics costs, providing a framework for online real-time optimization in thermal power units. Least Squares Support Vector Machine (LSSVM) is a regression-based machine learning technique known for its high accuracy and good generalization ability, especially in complex nonlinear systems. In this study, LSSVM is employed to model the denitrification cost. Meanwhile, the Back Propagation (BP) algorithm is used for effective input variable selection to reduce model complexity and enhance performance.
Mega sports events pose major energy management challenges due to their scale, and varying energy requirements. This paper suggests and assesses a digital twin powered smart energy management system for minimizing energy consumption, and maximizing grid stability of such events. The approach employs real-time data collection, and multi-domain energy system modeling with sophisticated predictive analytics with load forecasting based on Long Short-Term Memory (LSTM), along with multi-objective optimization techniques. Based on the evaluation with simulated event data, the deployed system exhibited significant improvements by decreasing average energy consumption by 23.2%, and apeak demand by 28.3%, respectively. Subsequently it is also observed that the self-consumption energy rate increase to 72% compared to conventional methods. Additionally, the system was responsible for substantial operational cost savings of about 30% as well as an impressive 37.5% decrease in carbon footprints. The load forecasting model showed a Mean Absolute Percentage Error (MAPE) value of 4.8%. The findings emphasize the potential capabilities of digital twin technology toward effective, sustainable, and resilient energy management for temporary, large-scale events.
This study presents a better way to predict solar irradiance by combining the Recursive Estimation Method for Signal Decomposition with Bidirectional Long Short-Term Memory (BiLSTM) networks that are made for predictive modeling. As solar power plays a bigger and bigger role in India’s green energy strategy, it is very important to be able to accurately predict solar irradiance in order to make the best use of resources. The suggested RE-BiLSTM framework does better than standalone models like LSTM, GRU, and BiLSTM, as well as the CEEMDAN-BiLSTM model hybrid, at different times of day (15 minutes, 30 minutes, and 60 minutes) and in different seasons (summer, monsoon, autumn, and winter). RMSE, MAE, and R2 are some of the evaluation metrics that show the proposed model consistently has lower error rates and higher predictive accuracy, especially at shorter time scales. Comparative analysis shows that the forecasting errors are more than 50% lower than those of the other models, which shows how strong the method is. These results suggest that the RE-BiLSTM model is a promising way to improve solar irradiance prediction and help India adapt solar power into its energy infrastructure.
As the penetration rate of renewable energy sources such as wind and solar power continues to rise, coordinated control among multiple entities including generation, transmission, load and storage has become crucial for ensuring the economic efficiency and security of power systems. However, the uncertainty of renewable energy output, the multi-period coupling characteristics of flexible resources, and the inconsistency of benefits among entities make it challenging for traditional optimization methods to simultaneously address real-time responsiveness, robustness, and fairness. To address this, this paper proposes an intelligent control method for power generation, grid, load, and storage that integrates Proximal Policy Optimization (PPO) with cooperative game theory. First, a Markov decision model suitable for multi-source, multi-load systems is constructed. The continuous action space of flexible resources enables coordinated control of thermal power, energy storage, and adjustable loads. Subsequently, a penalty for deviation from cooperative payoffs is embedded in the reward function, ensuring that policy optimization simultaneously satisfies overall economic efficiency and inter-agent profit coordination requirements. Multi-scenario simulations on IEEE 33-node and IEEE 30-node systems demonstrate that this method achieves rapid and stable convergence, significantly reduces operational costs, smooths power fluctuations, and maintains sustainable SOC for energy storage. Compared to conventional methods, it exhibits stronger robustness and higher cooperative incentive effects under uncertain conditions.
To address the issues of high operational costs and load factors in microgrids under current renewable energy conditions, this study proposes a grid scheduling strategy based on a parrot optimization algorithm incorporating chaotic and adaptive weighting. First, a scheduling model based on power operation costs and load rates in cloud-based microgrids is constructed. Second, logistic chaos is employed during the initialization of the parameter optimization algorithm to increase population diversity, whereas an adaptive weight adjustment strategy balances global and local exploration capabilities. Finally, simulation experiments validate the algorithm’s performance. Compared with the ACO, PSO, and PO algorithms, it reduces costs and power load factors by 63.4%, 45.7%, 8.3%, and 6%, respectively, in scenarios with small numbers of users and by 37.4%, 34.4%, 23.6%, and 6%, respectively, in scenarios with large numbers of users. 23.6%, 9.51%, 9.51%, and 1.18%, respectively. This demonstrates its ability to effectively reduce operational costs and lower power load rates, indicating significant practical value.
Common-ground (CG) based transformerless multilevel inverters (MLIs) are well-suited for grid-connected photovoltaic (PV) applications, because of their ability to eliminate leakage current and high efficiency. In this paper a reduced-switch CG five-level transformerless inverter (CG-5L-TLI) is presented that uses a dc source, one diode, seven switches and two capacitors. The proposed topology inherently eliminates leakage current, offers boosting of voltage without the need for any extra boost converter, and also ensures voltage balancing of the capacitors without requiring auxiliary control circuits. To improve the quality of output waveform, a selective harmonic elimination (SHE) strategy is employed, with optimal switching angles determined using a Bayesian optimization approach for the multilevel SHE-PWM scheme. The performance and effectiveness of the suggested system are validated via detailed MATLAB/Simulink simulations. Furthermore, a reduced scale laboratory setup is built to demonstrate the practical viability and operational capability of the suggested inverter.
To address the low computational efficiency of traditional photovoltaic hosting capacity assessment methods under uncertain environments, this study proposes a rapid evaluation method based on scenario adaptation and application form optimization of the Holomorphic Embedding Method. Firstly, a node selection strategy based on the Lévy flight-improved particle swarm optimization algorithm is established. An objective model with constraint penalty functions is constructed. Candidate grid connection nodes with superior voltage regulation capability and potential for capacity enhancement are then efficiently screened. This greatly reduces the computational burden of subsequent stochastic evaluation. Secondly, Monte Carlo simulation is integrated with the optimized Holomorphic Embedding Method, combined with Latin hypercube sampling. This builds an assessment framework that considers the uncertainties of photovoltaic output and load fluctuation. The established model adopts the Holomorphic Embedding Method to solve deterministic subproblems efficiently. It then evaluates the overall adaptability and robustness of different integration schemes under various uncertain scenarios. Simulation validation on the IEEE-30 bus system demonstrates that the optimal scheme corresponds to nodes {3,19}. The maximum photovoltaic hosting capacity is 81.32 MW. This scheme obtains the minimum comprehensive flexibility score. It verifies optimal operational performance across annual stochastic scenarios. Meanwhile, the proposed method improves computational efficiency by approximately 82% compared with the conventional enumeration method. It maintains calculation accuracy. The results indicate that the application-oriented optimization of the Holomorphic Embedding Method, combined with stochastic scenario analysis and shared energy storage, can improve the photovoltaic accommodation capability and operational flexibility of distribution networks. It provides reliable theoretical and methodological support for the grid integration of high-penetration renewable energy.
This study investigates the mechanical stability of power transformers subjected to fluctuating load currents, which induce dynamic electromagnetic forces that can lead to mechanical vibrations and potentially compromise the transformer’s structural integrity. Traditional methods often overlook time-varying loads and fully coupled electromagnetic-mechanical interactions, which limits the accuracy of stability assessments in realistic operational conditions. This method introduces a novel coupled finite element framework that simultaneously models electromagnetic and mechanical interactions under fluctuating load conditions. Unlike conventional electromechanical approaches, the proposed method captures time-dependent force variations and their direct impact on structural stability, enabling more accurate and realistic transformer stability assessment. External load profiles range from 48.8% to 120% of the rated load. The electromagnetic forces are calculated using the Maxwell stress tensor method, yielding a total integrated force of 4157.24 N. The maximum magnetic flux density is found to be 1.8458 T, well below the saturation point, and the core experiences a maximum electromagnetic stress of 95.91 Pa, which is significantly lower than the material yield strength of 350 MPa, resulting in a safety factor of over 3.6 × 106. The mechanical analysis shows a maximum displacement of 0.543 μm and a total RMS vibration amplitude of 0.291 μm. The modal analysis reveals a natural frequency of 66.69 Hz, distinct from the main electromagnetic excitation frequency of 120 Hz, indicating a low risk of resonance. Overall, the results confirm that the proposed framework accurately models the electromechanical behavior of transformers under fluctuating load conditions, ensuring their mechanical stability.
