Search Results (86)

With the increasing penetration of electric vehicles (EVs), multi-virtual power plant (multi-VPP) systems face growing challenges in coordinating heterogeneous flexible resources, managing stochastic EV charging and discharging behaviors, and maintaining distribution network security. This paper develops an integrated collaborative scheduling strategy for multi-VPPs with EV cluster participation. In the proposed framework, EV clusters, energy storage systems, and distributed generation units are coordinated under distribution-network operational constraints. The regulation capability of EV clusters is characterized by considering state of charge (SOC) dynamics, charging/discharging power limits, arrival and departure times, vehicle availability, and user travel requirements and is further embedded into the scheduling decision space of each VPP. To coordinate operational economy and nodal voltage security, a voltage-security-aware optimization objective is formulated and transformed into a Markov game. A multi-agent deep reinforcement learning (MADRL) method is then adopted to learn coordinated scheduling policies among multiple VPP agents. Case studies show that the proposed method achieves stable convergence after approximately 3500 training episodes, with a normalized reward exceeding 0.92, and outperforms TD3, DDPG, and PPO in terms of convergence speed and training stability. The scheduling results further indicate that the proposed strategy effectively coordinates EV clusters and energy storage systems, maintains nodal voltages within safe limits, and improves the operational performance of multi-VPP systems. These results demonstrate the applicability of the proposed framework for secure and economic collaborative scheduling in distribution networks. Full article

The Dynamic Economic Dispatch (DED) problem underpins the cost-efficient and reliable operation of modern power systems, yet valve-point loading, ramp-rate coupling, and the growing share of intermittent wind, photovoltaic, and pumped-storage hydro (PSH) resources render it highly non-convex. Metaheuristic methods typically require large computational budgets and hand-crafted constraint-handling rules, whereas deep reinforcement learning agents rarely guarantee the feasibility of the schedules they produce. To address both limitations, this paper proposes a Two-Stage PPO–RLMPA framework that couples data-driven policy learning with a biomimetic metaheuristic search inspired by marine predator–prey dynamics. In the first stage, a Proximal Policy Optimization (PPO) agent is trained on a Markov Decision Process reformulation of DED in which a deterministic Safety Layer projects every raw action onto the feasible set defined by capacity, ramp-rate, and power-balance constraints, so the policy only observes physically viable transitions. In the second stage, the PPO dispatch is refined by the RLMPA module, a Marine Predators Algorithm (MPA) whose exploration–exploitation balance, Lévy-flight foraging, and Fish Aggregating Devices (FADs) attraction mechanisms emulate strategies documented in marine ecosystems; its step-size factor and FADs probability are further adapted online by a Deep Q-Network. This biomimetics-informed refinement translates predator–prey foraging intelligence into economically efficient thermal dispatch under valve-point non-convexity. Across 30 independent runs on ten- and twenty-unit benchmark systems with wind, PV, and PSH integration, the framework attains best costs of USD 368,763 and USD 737,348 on Test Systems 1 and 2, corresponding to reductions of approximately $1.1\%$ and $4.4\%$ over the CFCEP baseline, with zero post-repair constraint violations in every run. Full article

The decarbonization of railway transportation requires energy-efficient propulsion technologies capable of reducing fossil fuel dependence and improving the operational efficiency of rail systems. Hydrogen fuel cell (FC)–battery hybrid powertrains have emerged as a promising alternative for non-electrified high-speed railway lines due to their potential for energy-efficient operation and reduced environmental impact. However, the optimal sizing and coordinated operation of these hybrid energy sources remain a challenging problem because energy efficiency, component degradation, and system cost are strongly interrelated. This study proposes a degradation-aware mixed-integer linear programming (MILP) framework for the optimal sizing and energy management of a FC–battery hybrid propulsion system for high-speed trains. The optimization simultaneously determines the capacities of FC stacks, battery modules, and hydrogen storage while minimizing the overall lifecycle cost and improving system energy utilization. Battery and FC degradation models are incorporated into the optimization problem through linearized formulations to ensure realistic long-term operation. The proposed framework is evaluated using real operational data in the approximately 71 min high-speed rail corridor between Bursa and Osmaneli in Türkiye. Simulation results show that increasing battery capacity significantly reduces FC stress while enabling more efficient energy utilization through regenerative braking and power balancing. The results indicate that optimal battery sizing can notably improve system performance, reducing the total lifecycle cost from $1.12\times {10}^9$ USD to $5.65\times {10}^8$ USD, while decreasing the required number of fuel cell units from 31 to 18 and mitigating fuel cell degradation. The proposed approach provides an effective design tool for energy-efficient hydrogen-powered railway systems. Full article

CO₂ injection success hinges on the injectivity index, a major determinant of storage feasibility. This study develops a machine learning (ML)-driven framework optimized for CO₂ injectivity prediction, benchmarking its robustness and real-world applicability against an empirical correlation developed in the literature. The framework is applied to the Entrada Formation in the San Juan Basin, a laterally extensive sandstone unit with limited structural complexity across most of the basin, except for localized uplift in the Hogback region. A numerical model was calibrated to perform sensitivity analysis to identify the dominant parameters influencing injectivity. A dataset of these parameters generated through experimental design informs the development of several ML-based proxies and the best model is selected based on error metrics. These metrics include coefficient of determination (R²), mean absolute error (MAE), and mean squared error (MSE). The effective permeability-thickness product was obtained by the Peaceman’s well model, fractional flow slope, and Dykstra–Parsons coefficient were identified as the most influential parameters impacting the objective function. Train–test and blind test validation identified the Ridge model as the best, achieving an R² ≈ 0.994. The Ridge model which was used to map the Entrada Formation closely matches field-based correlations in the literature, confirming both its physical validity and the Entrada Formation’s strong injectivity potential, with slight deviations explained by the inclusion of additional parameters. This study reduces dependence on computationally intensive simulations while improving prediction accuracy. By benchmarking against established correlations, it enhances model reliability across diverse reservoir conditions. The proposed framework enables rapid, data-driven well placement and feasibility evaluations, streamlining decision-making for CO₂ storage projects. Full article

In today’s volatile digital environments, conventional data governance practices fail to adequately address the dynamic, context-sensitive, and risk-hazardous nature of data use. This paper introduces DRADG (Dynamic Risk-Adaptive Data Governance), a new paradigm that unites risk-aware decision-making with adaptive data governance mechanisms to enhance resilience, compliance, and trust in complex data environments. Drawing on the convergence of existing data governance models, best practice risk management (DAMA-DMBOK, NIST, and ISO 31000), and real-world enterprise experience, this framework provides a modular, expandable approach to dynamically aligning governance strategy with evolving contextual factors and threats in data management. The contribution is in the form of a multi-layered paradigm combining static policy with dynamic risk indicator through application of data sensitivity categorization, contextual risk scoring, and use of feedback loops to continuously adapt. The technical contribution is in the governance-risk matrix formulated, mapping data lifecycle stages (acquisition, storage, use, sharing, and archival) to corresponding risk mitigation mechanisms. This is embedded through a semi-automated rules-based engine capable of modifying governance controls based on predetermined thresholds and evolving data contexts. Validation was obtained through simulation-based training in cross-border data sharing, regulatory adherence, and cloud-based data management. Findings indicate that DRADG enhances governance responsiveness, reduces exposure to compliance risks, and provides a basis for sustainable data accountability. The research concludes by providing guidelines for implementation and avenues for future research in AI-driven governance automation and policy learning. DRADG sets a precedent for imbuing intelligence and responsiveness at the heart of data governance operations of modern-day digital enterprises. Full article

In this paper, we take the longitudinal two-stage and two-yard EMU (Electric Multiple Unit) depot as an example and discusses the optimization challenges of the first-level maintenance shunting operation plan under the background of limited maintenance capacity. A multi-objective programming is constructed, which adopts the lexicographic ordering method and aims to minimize the occupancy time of key line areas and the number of train storage times. In order to enhance the flexibility and solution efficiency of the shunting operation plan, we design an efficient three-stage strategy algorithm. Specifically, in the first stage, the genetic and mutation rules are integrated, and the fast iterative advantage of the genetic algorithm is utilized to solve the time decision variables in the optimization problem. In the second stage, the allocation of track occupancy variables is further solved. The third stage focuses on the optimized allocation of maintenance team variables to ensure the scientific scheduling of maintenance resources. Finally, a validation experiment was conducted using the maintenance tasks of 19 EMU sets as the test scenario. The results indicate that when the number of maintenance teams is set to 4, an optimal balance between maintenance efficiency and operational cost is achieved, the occupancy duration of key line zones reaches 3034 min (the theoretical optimum), the number of maintenance teams is reduced by 33.33% compared to the initial 6 teams, and the number of storage operations is optimized to 27 times. Additionally, the algorithm’s solution time remains under 50 s, demonstrating significantly improved computational efficiency. Comparative experiments with baseline algorithms show that the proposed method reduces the occupancy duration of key line zones by up to 0.49%, decreases the number of storage operations by 14 times, and advances the maximum completion time by 20 min. In summary, the proposed method provides solid theoretical support for the formulation of maintenance plans and shunting schedules in EMU depots. Particularly in complex scenarios with limited maintenance capacity, it offers innovative and robust decision-making foundations, demonstrating significant practical guidance value. Full article

State-of-charge (SoC) balancing across multiple battery energy storage systems (BESS) is a central challenge in renewable-rich mini-grids. Heterogeneous battery capacities, differing states of health, stochastic renewable generation, and variable loads create a high-dimensional uncertain control problem. Conventional droop-based SoC balancing strategies are decentralized and computationally light but fundamentally reactive and limited, whereas model predictive control (MPC) is insightful but computationally intensive and prone to modeling errors. This paper proposes a Hierarchical Predictive–Adaptive Control (HPAC) framework for SoC balancing in mini-grids using deep reinforcement learning. The framework consists of two synergistic layers operating on different time scales. A long-horizon Predictive Engine, implemented as a federated Transformer network, provides multi-horizon probabilistic forecasts of net load, enabling multiple mini-grids to collaboratively train a high-capacity model without sharing raw data. A fast-timescale Adaptive Controller, implemented as a Soft Actor-Critic (SAC) agent, uses these forecasts to make real-time charge/discharge decisions for each BESS unit. The forecasts are used both to augment the agent’s state representation and to dynamically shape a multi-objective reward function that balances SoC, economic performance, degradation-aware operation, and voltage stability. The paper formulates SoC balancing as a Markov decision process, details the SAC-based control architecture, and presents a comprehensive evaluation using a MATLAB-(R2025a)-based digital-twin simulation environment. A rigorous benchmarking study compares HPAC against fourteen representative controllers spanning rule-based, MPC, and various DRL paradigms. Sensitivity analysis on reward weight selection and ablation studies isolating the contributions of forecasting and dynamic reward shaping are conducted. Stress-test scenarios, including high-volatility net-load conditions and communication impairments, demonstrate the robustness of the approach. Results show that HPAC achieves near-minimal operating cost with essentially zero SoC variance and the lowest voltage variance among all compared controllers, while maintaining moderate energy throughput that implicitly preserves battery lifetime. Finally, the paper discusses a pathway from simulation to hardware-in-the-loop testing and a cloud-edge deployment architecture for practical, real-time deployment in real-world mini-grids. Full article

Driven by the global energy transition and carbon-neutrality goals, virtual power plants (VPPs) are expected to aggregate distributed energy resources and participate in multiple electricity markets while achieving economic efficiency and low carbon emissions. However, the strong volatility of wind and photovoltaic generation, together with the coupling between electric and thermal loads, makes real-time VPP scheduling challenging. Existing deep reinforcement learning (DRL)-based methods still suffer from limited predictive awareness and insufficient handling of physical and carbon-related constraints. To address these issues, this paper proposes an improved model, termed SAC-LAx, based on the Soft Actor–Critic (SAC) deep reinforcement learning algorithm for intelligent VPP scheduling. The model integrates an Attention–xLSTM prediction module and a Linear Programming (LP) constraint module: the former performs multi-step forecasting of loads and renewable generation to construct an extended state representation, while the latter projects raw DRL actions onto a feasible set that satisfies device operating limits, energy balance, and carbon trading constraints. These two modules work together with the SAC algorithm to form a closed perception–prediction–decision–control loop. A campus integrated-energy virtual power plant is adopted as the case study. The system consists of a gas–steam combined-cycle power plant (CCPP), battery storage, a heat pump, a thermal storage unit, wind turbines, photovoltaic arrays, and a carbon trading mechanism. Comparative simulation results show that, at the forecasting level, the Attention–xLSTM (Ax) module reduces the day-ahead electric load Mean Absolute Percentage Error (${\mathrm{M}}_{\mathrm{A}\mathrm{P}\mathrm{E}}$) from 4.51% and 5.77% obtained by classical Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to 2.88%, significantly improving prediction accuracy. At the scheduling level, the SAC-LAx model achieves an average reward of approximately 1440 and converges within around 2500 training episodes, outperforming other DRL algorithms such as Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Proximal Policy Optimization (PPO). Under the SAC-LAx framework, the daily net operating cost of the VPP is markedly reduced. With the carbon trading mechanism, the total carbon emission cost decreases by about 49% compared with the no-trading scenario, while electric–thermal power balance is maintained. These results indicate that integrating prediction enhancement and LP-based safety constraints with deep reinforcement learning provides a feasible pathway for low-carbon intelligent scheduling of VPPs. Full article

Blue hydrogen technology, generated from natural gas through carbon capture and storage (CCS) technology, is a promising solution to mitigate greenhouse gas emissions and meet the growing demand for clean energy. To improve the sustainability of blue hydrogen, it is crucial to explore alternative feedstocks, production methods, and improve the efficiency and economics of carbon capture, storage, and utilization strategies. Two established technologies for hydrogen synthesis are Steam Methane Reforming (SMR) and Autothermal Reforming (ATR). The choice between SMR and ATR depends on project specifics, including the infrastructure, energy availability, environmental goals, and economic considerations. ATR-based facilities typically generate hydrogen at a lower cost than SMR-based facilities, except in cases where electricity prices are elevated or the facility has reduced capacity. Both SMR and ATR are methods used for hydrogen production from methane, but ATR offers an advantage in minimizing CO₂ emissions per unit of hydrogen generated due to its enhanced energy efficiency and unique process characteristics. ATR provides enhanced utility and flexibility regarding energy sources due to its autothermal characteristics, potentially facilitating integration with renewable energy sources. However, SMR is easier to run but may lack flexibility compared to ATR, necessitating meticulous management. Capital expenditures for SMR and ATR hydrogen reactors are similar at the lower end of the capacity spectrum, but when plant capacity exceeds this threshold, the capital costs of SMR-based hydrogen production surpass those of ATR-based facilities. The less profitably scaled-up SMR relative to the ATR reactor contributes to the cost disparity. Additionally, individual train capacity constraints for SMR, CO₂ removal units, and PSA units increase the expenses of the SMR-based hydrogen facility significantly. Full article

Reservoir operation serves as a critical non-structural measure for real-time flood management, aimed to minimize downstream flood damage while ensuring dam safety. This study develops and evaluates a Gated Recurrent Unit (GRU)-based reservoir operation model with data integration (DI) to enhance flood management capabilities. Optimal reservoir outflows are first determined for historical flood events using the Interior Point Optimizer (IPOPT), a deterministic optimization model designed to minimize peak outflows. The optimized hydrographs are compared with observed outflows to assess the benefits of improved operational strategies. GRU models are then trained and validated using inflow hydrographs and resulting optimal reservoir storage and release data. Various input configurations are tested, incorporating DI of lagged observations and forecasted values to evaluate their influence on model accuracy. The study also examines multiple hyperparameter settings to identify the optimal configuration. The methodology is applied to the Namgang Dam in South Korea, simulating hourly operations during flood events. Results indicate that historical reservoir inflow and storage are the most influential inputs, while adding precipitation (historical or forecasted) and/or forecasted inflows does not improve model performance. The GRU model with DI successfully replicates optimized reservoir operations, demonstrating its reliability and efficiency in flood management. This framework supports timely and informed decision-making and offers a promising approach for enhancing flood risk mitigation through improved reservoir operations. Full article

The increasing penetration of renewable energy sources and the consequent rise in forecast uncertainty have underscored the need for robust operational strategies in transmission power systems. This paper introduces a risk-averse, data-driven distributionally robust optimization framework that integrates unit commitment and power flow constraints to enhance both reliability and operational security. Leveraging advanced forecasting techniques implemented via gradient boosting and enriched with cyclical and lag-based time features, the proposed methodology forecasts renewable generation and demand profiles. Uncertainty is quantified through a quantile-based analysis of forecasting residuals, which forms the basis for constructing data-driven ambiguity sets using Wasserstein balls. The framework incorporates comprehensive network constraints, power flow equations, unit commitment dynamics, and battery storage operational constraints, thereby capturing the intricacies of modern transmission systems. A worst-case net demand and renewable generation scenario is computed to further bolster the system’s risk-averse characteristics. The proposed method demonstrates the integration of data preprocessing, forecasting model training, uncertainty quantification, and robust optimization in a unified environment. Simulation results on a representative IEEE 24-bus network reveal that the proposed method effectively balances economic efficiency with risk mitigation, ensuring reliable operation under adverse conditions. This work contributes a novel, integrated approach to enhance the reliability of transmission power systems in the face of increasing uncertainty. Full article

Sparse matrix–vector multiplication (SpMV) is a fundamental kernel in high-performance computing (HPC) whose efficiency depends heavily on the storage format across central processing unit (CPU) and graphics processing unit (GPU) platforms. Conventional supervised approaches often use execution time as training labels, but our experiments on 1786 matrices reveal two issues: labels are unstable across runs due to execution-time variability, and single-label assignment overlooks cases where multiple formats perform similarly well. We propose a dynamic labeling strategy that assigns a single label when the fastest format shows clear superiority, and multiple labels when performance differences are small, thereby reducing label noise. We further extend feature analysis to multi-dimensional structural descriptors and apply clustering to refine label distributions and enhance prediction robustness. Experiments demonstrate 99.2% accuracy in hardware (CPU/GPU) selection and up to 98.95% accuracy in format prediction, with up to 10% robustness gains over traditional methods. Under cost-aware, end-to-end evaluation that accounts for feature extraction, prediction, conversion, and kernel execution, CPUs achieve speedups up to 3.15× and GPUs up to 1.94× over a CSR baseline. Cross-round evaluations confirm stability and generalization, providing a reliable path toward automated, cross-platform SpMV optimization. Full article

Air quality monitoring and forecasting have become increasingly critical in urban environments due to rising pollution levels and their impact on public health. Recent advances in Internet of Things (IoT) technology and machine learning offer promising alternatives to traditional monitoring stations, which are limited by high costs and sparse deployment. This paper presents the development of a real-time, low-cost air quality forecasting system that integrates IoT-based sensing units with predictive machine learning algorithms. The proposed system employs low-cost gas sensors and microcontroller-based hardware to monitor pollutants such as particulate matter, carbon monoxide, carbon dioxide and volatile organic compounds. A fully functional prototype device was designed and manufactured using Fused Deposition Modeling (FDM) with modular and scalable features. The data acquisition pipeline includes on-device adjustment, local smoothing, and cloud transfer for real-time storage and visualization. Advanced feature engineering and a multi-model training strategy were used to generate accurate short-term forecasts. Among the models tested, the GRU-based deep learning model yielded the highest performance, achieving $R^2$ values above 0.93 and maintaining latency below 130 ms, suitable for real-time use. The system also achieved over 91% accuracy in health-based AQI category predictions and demonstrated stable performance without sensor saturation under high-pollution conditions. This study demonstrates that combining embedded hardware, real-time analytics, and ML-driven forecasting enables robust and scalable air quality management solutions, contributing directly to sustainable development goals through enhanced environmental monitoring and public health responsiveness. Full article

Bridge Structural Health Monitoring (BSHM) is vital for assessing structural integrity and operational safety. Traditional wired systems are limited by high installation costs and complexity, while existing wireless systems still face issues with cost, synchronization, and reliability. Moreover, cloud-based methods for extreme event detection struggle to meet real-time and bandwidth constraints in edge environments. To address these challenges, this study proposes a lightweight wireless BSHM system based on edge computing, enabling local data acquisition and real-time intelligent detection of extreme events. The system consists of wireless sensor nodes for front-end acceleration data collection and an intelligent hub for data storage, visualization, and earthquake recognition. Acceleration data are converted into time–frequency images to train a MobileNetV2-based model. With model quantization and Neural Processing Unit (NPU) acceleration, efficient on-device inference is achieved. Experiments on a laboratory steel bridge verify the system’s high acquisition accuracy, precise clock synchronization, and strong anti-interference performance. Compared with inference on a general-purpose ARM CPU running the unquantized model, the quantized model deployed on the NPU achieves a 26× speedup in inference, a 35% reduction in power consumption, and less than 1% accuracy loss. This solution provides a cost-effective, reliable BSHM framework for small-to-medium-sized bridges, offering local intelligence and rapid response with strong potential for real-world applications. Full article

Power flow analysis is essential for managing power systems, helping grid operators ensure reliability and efficiency. This paper explores the use of machine learning (ML) techniques as surrogates for computationally intensive power flow calculations to evaluate the effects of distributed energy resources, such as battery energy storage systems (BESSs), on grid performance. In this paper, a case study is presented where XGBoost (eXtreme Gradient Boosting) and Artificial Neural Networks (ANNs) are trained to simulate power flows in a medium-voltage grid in Norway. The impact of BESS units on line loading, transformer loading, and bus voltages is estimated across thousands of configurations, with results compared in terms of simulation time, error metrics, and robustness. In this paper it is proven that while ML models require considerable data and training time, they offer speed-up factors of up to 45×, depending on the predicted parameter. The proposed methodology can also be used to assess the impact of other grid-connected assets, such as small-scale solar plants and electric vehicle chargers, whose presence in distribution networks continues to grow. Full article