The increasing demand for renewable energy sources necessitates advanced methods to ensure grid stability and operational efficiency. Smart grids present a viable solution by enabling the seamless integration of renewable energy systems, such as solar photovoltaic (PV) and other sources. However, the performance and reliability of such systems are critically dependent on the performance and functionality of power inverters (e.g., solar PV inverters). This paper proposes the application of several decision tree algorithms, which are traditional decision tree (TDT), iterative dichotomizer tree (IDT), C4.5 algorithm, and CART algorithm, for fault prediction and diagnostics in solar PV inverters. The training and prediction phases of the decision tree models employ both key inverter specifications, such as nominal operating ranges, abnormal readings, and fault conditions, alongside critical operational parameters, including voltage, current, temperature, conversion efficiency, power factor (PF), and total harmonic distortion (THD). Also, a cost-benefit analysis is made to consider the cost-effectiveness of predictive maintenance of solar PV inverters with the presence of significant economic benefits. A substantial cost advantage is shown, where 12,000 $/year in losses is saved with an investment of merely 4000 $/year in support of a predictive maintenance model with a first year ROI of 200%. Overall, the results of all decision tree models, implemented in MATLAB, confirm that both TDT algorithm and CART algorithm attain a high classification accuracy of about 95% with TDT possessing the shortest fault prediction time of about 50 ms. Markedly, the CART algorithm proves effective when it comes to dealing with an up to 90% missing values. Additionally, the analysis demonstrates a direct proportional relationship between voltage, current, temperature, and conversion efficiency, while revealing an inverse relationship between conversion efficiency and THD. The proposed algorithms for fault prediction hold significant potential for enhancing the reliability of solar PV systems integrated within smart grid frameworks.

The integration of intermittent renewable energy into smart grids introduces critical vulnerabilities in security, transparency, and real-time resilience. This paper presents a novel blockchain-secured 6G Smart grid framework that synergistically integrates sixth generation (6G) ultra-reliable low-latency communication (URLLC), distributed ledger technology, and ensemble machine learning to establish a secure, scalable, and intelligent energy ecosystem. The proposed architecture leverages adaptive 6G network slicing to support differentiated services-including peer-to-peer energy trading, grid control, and cybersecurity monitoring-while ensuring sub-30 ms latency and robust connectivity. A permission blockchain layer provides decentralized trust, immutability, and automated transaction validation via formally verified smart contracts. An ensemble learning model combining XGBoost, Random Forest, and LightGBM enables real-time multi-dimensional anomaly detection across energy, network, and transaction layers. The framework is evaluated using a synthetically generated dataset of 5000 hourly records encompassing energy generation, consumption, 6G network performance, and blockchain transactions. Experimental results demonstrate a blockchain transaction success rate of 95.16% and sustained network latency below 30 ms across all slices, even under cyberattack conditions. Reported using class-based anomaly-detection metrics, the model achieves a Recall of 0.93 and F1-score of 0.97 for the anomaly class, and a Recall of 1.00 and F1-score of 0.99 for the normal class, with an overall accuracy of 0.98. The proposed system provides a foundational architecture for resilient, autonomous, and secure renewable energy management in next generation decentralized smart grids.

Abstract Tall cell grids have been proposed as an efficient approach to accelerate large‐scale liquid simulation. In this framework, regions near the liquid surface are discretized with regular grids, while regions farther away are represented by elongated rectangular cells. The regular grid region close to the surface is referred to as the optical layer. In previous work, the thickness of this optical layer was uniformly fixed across the entire liquid domain. In this paper, we propose a novel tall cell grid structure in which the thickness of the optical layer is dynamically adjusted according to the motion of the liquid. This adaptive strategy reduces the number of grid cells required in the projection step without compromising visual quality, thereby accelerating the overall simulation. Furthermore, we introduce a two‐way coupling scheme between rigid bodies and liquids in regions where the optical layer remains thin. Our algorithm is simple and can be easily integrated into existing tall cell grid frameworks.

This study proposed an intelligent classification and content recognition framework for enterprise financial archives based on a multimodal deep-learning architecture. The model integrated image, audio-video, and text modalities, using DenseNet—a 3D densely connected convolutional neural network with openSMILE software features—and a bidirectional-encoder-representations-from-transformers encoder. An attention-guided bidirectional gated-recurrent-unit fusion module modeled intramodal and intermodal dependencies, and a grid-structured classification head preserved spatial and temporal consistency. A class-aware readout with additive-margin softmax strengthened category separation and improved interpretability. Experiments on a dataset of 38,420 multimodal financial records showed that the proposed framework achieved an accuracy of 95.8%, an F1-score of 95.3%, and an area under the curve of 0.981, surpassing unimodal and transformer-based baselines. The results indicated that the multimodal attention–gated-recurrent-unit grid framework effectively captured cross-modal semantics and localized features, offering an efficient approach for financial document analysis and audit automation.

The global transition towards sustainable and resilient energy systems has emphasized the need for efficient utilization of renewable energy sources (RESs) and rapid electrification of transportation. However, smart grids must address the intermittency of solar and wind power while accommodating the growing demand from electric vehicles (EVs). Hence, in this paper, a data-driven energy management system (EMS) is proposed that combines multivariable forecasting, generation scheduling, and EV charging coordination in a dual-level decentralized framework to increase the efficiency, reliability, and scalability of modern power grids. First, short-term forecasts of solar irradiance, wind speed, and load demand are addressed via five machine learning models ranging from nonlinear to ensemble models. Accordingly, a unified CatBoost-based platform for forecasting these three variables is selected because of its better performance and accuracy. These forecasts are subsequently utilized in a mixed-integer linear programming (MILP) framework for optimal generation scheduling in the considered network, fulfilling load demand at reduced electricity and emission costs while maintaining grid stability. Finally, a priority-based scheme is proposed for charging/discharging coordination of the aggregated EVs, minimizing demand variability while fulfilling vehicles’ charging needs and maintaining their batteries’ lifetime. The superiority of the proposed method lies in integrating a multivariable forecasting pipeline, linear MILP generation scheduling, and battery-health-aware V2G coordination in a unified decoupled framework, unlike many recent frontier works that treat these capabilities independently. Simulation results, under different scenarios, confirm that the proposed intelligent EMS can significantly reduce operational fluctuations, satisfy load and EV demands, optimize RES utilization, and support system cost-effectiveness, sustainability, and resilience.

Discrete Global Grid Systems (DGGS), as a next-generation framework for the digital Earth, inevitably suffer from geometric non-uniformity, which impacts the accuracy of data representation and analysis. Existing quality assessments, predominantly based on Goodchild's criteria, are inadequate for diamond-based grids, particularly in evaluating angular and distance uniformity. This paper addresses this gap by proposing a comprehensive evaluation framework for spherical diamond grids. We extend the Goodchild criteria by incorporating metrics for angular and distance uniformity, creating an integrated five-dimensional system (shape, topology, size, distance, and angle). Using this framework, we systematically compare three typical diamond DGGS derived from the cube, octahedron, and icosahedron. Our results demonstrate that the icosahedron-based grid exhibits optimal uniformity across all five dimensions. Critically, we reveal that the octahedron-based grid, despite having more initial faces, suffers from severe angular distortion in the across-face boundary regions, rendering its uniformity inferior to that of the cube-based grid. We further validate our framework by constructing a Spherical Residual Network for Diamond Grids (SResNet-DG) for a classification task. Our experimental results demonstrate a strong positive correlation between grid uniformity and the SResNet-DG's performance, substantiating the effectiveness and practical relevance of our proposed geometric evaluation system.

Modern power systems no longer fail only because of line or generator outages; they also drift into insecure states when the SCADA/EMS links slow down or when the operator cannot react at the required pace. To study this joint effect, we build an AI-supported stochastic resilience framework that treats the communication layer and the human layer as first-class, time-varying elements of the grid. Communication delay and packet–drop behaviour are captured through a multi-level Markov description, while operator performance is estimated through a small cognitive–reliability block that changes with workload and stress. On top of these two sources of uncertainty, a reinforcement-learning controller updates the stabilizing actions so that the system can return to acceptable voltage and frequency bands after faults. Tests on the IEEE 39-bus and 118-bus systems show three tangible gains: damping improves by about 91%, the probability of a blackout event falls by around 42%, and the composite resilience index rises from 0.74 to 0.91 against conventional stochastic assessments. Taken together, the results suggest that resilience estimates become more faithful only when human variability and communication degradation are evaluated in the same loop, which makes the approach suitable for cognitively aware, self-healing grid operation.

Dynamic renewable energy integration for EV charging via model-based reinforcement learning

The global clean energy transition is essential for limiting the global temperature rise to 1.5 °C and achieving net-zero greenhouse gas (GHG) emissions by 2050. This review synthesizes evidence from peer-reviewed studies, policy reports and industry benchmarks, addressing the three interrelated pillars of the clean energy transition: clean energy technologies, critical material scarcity, and operational challenges. This study highlights that although clean energy technologies, particularly solar photovoltaics and wind power, have achieved cost parity with fossil fuels, their widespread deployment is still hindered by technical, material, and system-level challenges. The demand for critical minerals, essential for renewable energy technologies, is growing faster than mining supply chains can respond, exacerbated by high geographical concentration, price volatility, and low recycling rates. Furthermore, lifecycle and operational challenges, including premature asset retirement and grid integration issues, continue to hinder progress. To address these challenges, this review identifies four priority research areas: reducing material intensity through low-scarcity technologies, improving recycling and reuse systems for critical materials, optimizing smart grid frameworks, and promoting coordinated policy frameworks for fair cost allocation and mineral supply chain governance. This review offers a unified analytical framework to inform technology selection, infrastructure investment, and policy design, contributing to a resource-secure, sustainable clean energy transition.

Land use transformation directly affects the stability and sustainability of regional ecosystems. Clarification of the trade-off/synergy dynamics among ecosystem services (ESs) provides a theoretical foundation to understand the transition of ES interactions from trade-offs to synergies, thereby facilitating the achievement in ecological sustainability in the ecoregion. This study, taking Jiangxi Province, China, as an example, utilized the InVEST model, Theil–Sen estimator, Mann–Kendall test, bivariate spatial autocorrelation, ecosystem service bundles (ESBs), and Random Forest (RF) models to conduct such an ecosystem-focused integrated analysis. According to land use changes from 1980 to 2020, the time-series spatiotemporal patterns of water yield (WY), soil conservation (SC), habitat quality (HQ), and carbon storage (CS) were analyzed. Differences in ES trade-off/synergy relationships and their underlying motivating factors were examined using a 3 km spatial grid framework. Compared with previous studies that mainly focused on typical subregions and of which driver analyses often remained at the individual ES level, this study introduced an explainable RF-SHAP framework based on the cooperative game theory at the grid scale, to quantitatively characterize the relative contributions of every motivating factor to ES trade-off/synergy relationships. The results indicate that from 1980 to 2020, forests and croplands constituted the predominant land use types, taking up 88% of the studied area. Throughout this period, forests, croplands, and grasslands decreased markedly, while built-up areas expanded notably, with a rise of 2876.65 km2. Over the same time span, WY increased on average by 0.50% whereas SC, HQ, and CS declined by 0.50%, 0.98%, and 1.30%, respectively. Overall, these ESs demonstrated a geographical distribution characterized by low levels in SC, HQ and CS in the central area and high levels towards the provincial boundary. At the grid scale, the four ESs demonstrated predominantly a synergistic relationship while WY&HQ and WY&SC pairs were characterized by trade-offs. The constraint effect analysis revealed U-shaped relationships for SC&HQ, WY&HQ, and WY&SC, and inverted U-shaped relationships for SC&CS and HQ&CS, with clear threshold effects among these ES pairs. Based on self-organizing maps, the study area is partitioned into six ESBs, and the trade-off/synergy linkages of ESs are affected by the interplay of natural and societal forces. Elevation, slope, and rainfall emerge as the primary driving variables accompanied by population density and proximity to urban centers. These results are anticipated to offer reference to governments for their sustainable management in environmental resources to achieve United Nations Sustainable Development Goal (SDG) 15 (Life on Land: Protect, restore and promote sustainable use of terrestrial ecosystems). The methods used in this paper provide a replicable framework for exploring ES interactions and driving mechanisms in other ecologically sensitive regions in the world.

Rising global electricity demand and the expansion of distribution networks require a critical assessment of component-level greenhouse gas contributions. Distribution transformers, although indispensable, have significant life-cycle carbon impacts due to the use of materials, manufacturing, and in-service losses. This study conducts a life-cycle assessment of a single-phase, 75 kVA oil-immersed distribution transformer manufactured in Newfoundland, one of the provinces with the cleanest, hydro-dominated grids in Canada, and evaluates it over a 40-year lifespan. Using a cradle-to-use boundary, the analysis quantifies embodied emissions from raw material extraction, manufacturing, and transportation, alongside operational emissions derived from empirically measured no-load and load losses. All the data are collected directly during the manufacturing process, ensuring high analytical fidelity. The energy efficiency of the transformer is analyzed in MATLAB version R2023b using measured no-load and load losses to generate efficiency, load characteristics under various operating conditions. Under varying load factor scenarios and based on Newfoundland’s 2025 grid intensity of 18 g CO2e/kWh, the lifetime operational emissions are estimated to range from 0.19 t CO2e under no-load operation to 4.4 t CO2e under full-load conditions. A linear regression-based decarbonization model using Microsoft Excel projects grid intensity to reach net-zero around 2037, two years beyond the provincial target, indicating that post-2037 transformer losses will remain energetically relevant but carbon-neutral. Sensitivity analysis reveals that temporary overloading can substantially elevate lifetime emissions, emphasizing the value of smart-grid-enabled load management and optimal transformer sizing. Comparative assessment with fossil fuel-intensive provinces across Canada demonstrates the dominant influence of grid generation mix on life-cycle emissions. Additionally, refurbishment scenarios indicate up to 50% reduction in cradle-to-gate emissions through material reuse and oil reclamation. The findings establish a scalable framework for integrating grid decarbonization trajectories, life-cycle carbon modelling, and circular-economy strategies into sustainable distribution network planning and transformer asset management.

Energy efficient unified computing framework for smart grids with AI-driven communication, supercomputing, and energy perception orchestration

• Seasonally adaptive PV–BESS dispatch framework for high EV penetration grids. • CNN–BiLSTM model achieves >92 % accuracy in short-term PV forecasting. • GA optimizes multi-objective PV-EV-BESS scheduling. • Reduces feeder losses by 63.55 % and Voltage Unbalance Factor by 55 %. • Enhances PV utilization, power quality, and grid resilience under stress. The rapid proliferation of photovoltaic (PV) systems and electric vehicles (EVs) poses significant challenges for distribution networks, including voltage unbalance, high feeder losses, and deteriorating power quality, further complicated by seasonal variability in solar output and demand. This paper proposes a seasonally adaptive PV–battery energy storage system (BESS) dispatch strategy that integrates short-term PV forecasting with multi-objective optimization. The primary novelty of this work lies in the tight integration of a seasonally adaptive, forecasting-driven dispatch strategy that synergistically combines a hybrid CNN-BiLSTM model for high-accuracy PV prediction with a Genetic Algorithm for multi-objective optimization in unbalanced distribution grids. A hybrid CNN–BiLSTM model, trained on distinct seasonal datasets (summer and winter) from NASA irradiance data, enables accurate real-time PV prediction, achieving an RMSE of 13.99 kWh, MAE of 12.94 kWh, and MAPE of 7.45 %, corresponding to a forecasting accuracy of 92.55 %. Meanwhile, a genetic algorithm (GA) optimizes coordinated PV–BESS scheduling under diverse seasonal scenarios. The approach is validated on a modified IEEE 13-bus system, demonstrating robustness across a wide range of EV penetration levels (40–70 %) and both summer and winter conditions, and showing reductions of up to 55 % in Voltage Unbalance Factor (VUF) and 63.55 % in feeder losses, alongside enhanced PV utilization. Compared to uncoordinated dispatch, the proposed framework delivers superior power quality, higher grid resilience, and practical scalability. The framework is designed for real-world application, with the forecasting model providing high-frequency predictions and the GA-based optimization operating on a computationally feasible hourly rolling horizon, making it suitable for deployment in larger distribution networks. These findings highlight the potential of forecast-driven, seasonally aware coordinated dispatch as a practical pathway toward reliable and sustainable smart grid operation.

The increasing integration of distributed energy resources (DERs) and renewable energy poses significant challenges to the operational efficiency, stability, and adaptability of modern power systems. Traditional distribution grid frameworks, design ed for unidirectional energy flow and deterministic load profiles, are inadequate under the high variability and uncertainty of DER outputs and renewable generation. This paper proposes a novel optimization framework for the distribution grid based on a Double Deep Q-Network (DDQN) architecture, which leverages a Markov decision process (MDP), prioritized experience replay, and actor-critic design to dynamically optimize grid topology in real time. The proposed approach introduces a multi-objective reward function to balance power loss minimization, renewable energy integration, and voltage stability. Extensive simulations conducted on IEEE 33- and 123-bus test systems demonstrate that the DDQN-based framework achieves a 12.3% reduction in power losses, surpasses traditional mixed integer linear programming (MILP) and baseline deep Q-network (DQN) methods, and maintains robust voltage stability even under extreme scenarios such as sudden load surges and sharp drops in photovoltaic output. The results validate the scalability, adaptability, and computational efficiency of the framework, highlighting its potential for practical deployment in next-generation smart distribution grids facing high renewable penetration and stochastic operating conditions.

A real-time reconstructed grid method for soft tissue cutting and haptic.

Abstract The article introduces the plasma evolution of dielectric barrier discharge driven by the pulsed waveforms. The model is established under the Afivo adaptive grid framework and PIC-MCC simulation method. Through introducing the heavy particle reaction process, such as ion drift motion, photoemission, the accumulation and mapping of surface charges, and twobody radiative recombination process, the details of the plasma forming process and distribution is discussed. . The study yielded the evolution of electron and ion distributions under a time-varying electric field, corresponding alterations in potential and electric field induced by charged particle motion, are obtained under the first pulse of dielectric barrier discharge (DBD) structure at 2 kPa argon. The simulation results reveal the inceptive discharge evolution at the rising edge of pulse, the discharge extinction occurred near the upper dielectric layer is induced by the reverse electric field formed by the surface charge accumulation at the pulse duration period, and the second plasma packets in the entire cavity is obtained at the falling edge of the pulse. Meanwhile, the time resolved plasma discharge intensity distribution is obtained by ICCD, and the comparison and explanation of the result is discussed with the proposed simulation model. The key factor of formation of plasma sheath at different time period and the verification of simulation result is discussed. The proposed model is of great significance for exploring the evolution of plasma dynamics and the evolution of long pulse width discharges by analyzing the evolution process of discharge points during the first pulse, which is non steady state.

Implicit Neural Video Representation (INVR) has emerged as a novel approach for video representation and compression, using learnable grids and neural networks. Existing methods focus on developing new grid structures efficient for latent representation and neural network architectures with large representation capability, lacking the study on their roles in video representation. In this paper, the difference between INVR based on neural network and INVR based on grid is first investigated from the perspective of video information composition to specify their own advantages, i.e., neural network for general structure while grid for specific detail. Accordingly, an INVR based on mixed neural network and residual grid framework is proposed, where the neural network is used to represent the regular and structured information and the residual grid is used to represent the remaining irregular information in a video. A Coupled WarpRNN-based multi-scale motion representation and compensation module is specifically designed to explicitly represent the regular and structured information, thus terming our method as CWRNN-INVR. For the irregular information, a mixed residual grid is learned where the irregular appearance and motion information are represented together. The mixed residual grid can be combined with the coupled WarpRNN in a way that allows for network reuse. Experiments show that our method achieves the best reconstruction results compared with the existing methods, with an average PSNR of 33.73 dB on the UVG dataset under the 3M model and outperforms existing INVR methods in other downstream tasks. The code can be found at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/yiyang-sdu/CWRNN-INVR.git</uri>.

Global efforts to reduce carbon emissions and promote sustainable development have made solar energy integration into contemporary power systems more and more popular. For grid operators and energy planners, however, the intrinsically erratic and weather-dependent character of solar radiation poses a serious problem. Optimizing photovoltaic (PV) power generation, maintaining grid stability, lowering reserve capacity, and enhancing energy management techniques in smart grid frameworks all depend on accurate short-term solar radiation forecasting. For the purpose of short-term solar radiation forecasting using meteorological parameters, this study provides a thorough comparative analysis of several Artificial Intelligence (AI)-based models. These models, which include K-Nearest Neighbors (KNN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), and Long Short-Term Memory (LSTM) networks, are a combination of both conventional machine learning algorithms and cutting-edge deep learning techniques. A wealth of historical meteorological inputs, including temperature, relative humidity, wind speed, and cloud cover—all of which are important factors in determining the variability of solar irradiance—were used to train these models. To guarantee data quality, extensive preprocessing methods were used, such as temporal alignment, normalization, and handling of missing values. To improve the predictive power of the models, temporal feature engineering was also used to capture seasonal and diurnal variations in solar radiation. To ensure a fair comparison, every AI model was trained and evaluated using the same experimental setup. Standard error metrics, such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2), were used to assess the model's performance. These metrics shed light on each model's forecasts' dependability and accuracy. The LSTM model consistently outperformed all other models across a variety of forecast horizons and environmental conditions, according to the comparative study's findings, even though more conventional machine learning models like Random Forest and XGBoost did fairly well. The non-linear and time-dependent nature of solar radiation was better modeled by LSTM networks, which are specifically made to capture temporal dependencies in sequential data. The model generated extremely accurate forecasts by skillfully utilizing the temporal structure present in the meteorological data. This emphasizes how crucial it is to apply deep learning architectures to time series forecasting issues in the energy sector. The results of this study highlight how important sophisticated AI models—in particular, deep learning methods like LSTM—are to improving the forecasting accuracy of solar radiation forecasting systems. These developments have the potential to greatly improve the planning and operation of smart grids that integrate renewable energy sources. By comparing the advantages and disadvantages of well-known AI models, the study also establishes a standard for further research in solar energy forecasting. Ultimately, by offering dependable instruments for incorporating renewable energy sources into the electrical grid, this work advances the larger goal of moving toward cleaner energy systems.

The global energy sector is undergoing a profound restructuring, compelled by a triad of pressures: escalating power demand worldwide, the critical imperative to mitigate greenhouse gas emissions, and the strategic goal of fostering socio-economic development through sustainable infrastructure. Within this transformative landscape, Microgrids (MGs) have solidified their role as a cornerstone technology, enabling the seamless integration of Distributed Energy Resources (DERs), with a pronounced emphasis on renewables, into the traditional utility grid framework. A defining operational characteristic of microgrids is their ability to decouple from the main grid and sustain power autonomously in "island mode," a feature paramount for ensuring the reliability of critical loads during outages. To orchestrate the complex interplay of generation, storage, and consumption within a microgrid, an intelligent Energy Management System (EMS) is not just beneficial but essential. This review paper presents a critical synthesis of the diverse decision-making paradigms and optimization algorithms that form the core of modern microgrid EMS. It further consolidates methodological approaches for quantifying and managing the inherent uncertainties stemming from renewable intermittency and stochastic load profiles. The discourse extends to an evaluation of the communication architectures that underpin EMS functionality, analyzing their cost-effectiveness. Finally, the paper draws insights from real-world implementations and projects future research trajectories and evolving trends in the field.

A reflective reasoning and distributed mitigation-based collaborative scheduling framework for secure and resilient smart grids