Abstract The integration of large-scale-distributed new energy resources has led to heightened source load uncertainty.As energy prosumers,microgrids urgently require enhanced real-time regulation capabilities over controllable resources amid uncertain environments,rendering real-time and rapid decision-making a critical issue.This paper proposes a tailored twin delayed deep deterministic policy gradient(TD3) reinforcement learning algorithm that explicitly accounts for source load uncertainty.First,following an expert experience-based methodology,Gaussian process regression was implemented using the radial basis function covariance with historical source and load data.The parameters were adaptively adjusted by maximum likelihood estimation to generate the expected curves of demand and wind solar power generation,along with their 95% confidence regions,which were treated as representative uncertainty scenarios.Second,the traditional scheduling model was transformed into a deep reinforcement learning (DRL) environment through a Markov process.To minimize the total operational cost of the microgrid,the tailored TD3 algorithm was applied to formulate rapid intraday scheduling decisions.Finally,simulations were conducted using real historical data from an actual region in Zhejiang province,China,to verify the efficacy of the proposed method.The results demonstrate the potential of the algorithm for achieving economic scheduling for microgrids.

more

Abstract Conventional droop control in multi-parallel grid-forming inverters exhibits poor reactive power sharing accuracy due to line impedance mismatches.In this study,we proposed a coordination control strategy integrating adaptive virtual impedance with dynamic Q-V droop regulation to overcome this issue.We established a coupling model between the line impedance and power allocation to determine the quantitative relationship between reactive power deviation and impedance difference and to analyze the mechanism of reactive power deviation formation.Based on this,we proposed a transformer neural network-based online identification method for adaptive virtual impedance and dynamic droop coefficients.The self-attention mechanism dynamically characterizes the spatial distribution features of the impedance parameters considering the real-time voltage/reactive power time-series data as inputs to realize the dynamic impedance compensation without communication interaction.The contradiction constraint between the voltage drop and distribution accuracy caused by the introduction of conventional virtual impedance is improved by dynamic droop coefficient reconstruction.Lastly,we established a hardware-in-the-loop simulation platform to experimentally validate the operational efficacy and dynamic performance of the proposed control strategy under various grid scenarios.

more

Abstract Given the power system balancing challenges induced by high-penetration renewable energy integration,this study systematically reviews international balancing mechanism practices and conducts an in-depth deconstruction of Germany’s balancing group mechanism(BGM).Building on this foundation,this research pioneers the integration of virtual power plants (VPPs) with the BGM in the Chinese context to overcome the limitations of traditional single-entity regulation models in flexibility provision and economic efficiency.A balancing responsibility framework centered on VPPs is innovatively proposed and a regional multi-entity collaboration and bi-level responsibility transfer architecture is constructed.This architecture enables cross-layer coordinated optimization of regional system costs and VPP revenues.The upper layer minimizes regional operational costs,whereas the lower layer enhances the operational revenues of VPPs through dynamic gaming between deviation regulation service income and penalty costs.Compared with traditional centralized regulation models,the proposed method reduces system operational costs by 29.1% in typical regional cases and increases VPP revenues by 24.9%.These results validate its dual optimization of system economics and participant incentives through market mechanisms,providing a replicable theoretical paradigm and practical pathway for designing balancing mechanisms in new power systems.

more

Abstract Regard to the real-time dynamic digital twin modelling problem of a new-type distribution network that includes distributed resources such as distributed photovoltaic,energy storage,charging pile,and electric vehicle,a new-type distribution network digital twin topology modeling method based on Common Information Model (CIM) specifications and spectral clustering is proposed.Firstly,according to the specifications of the CIM standard,the digital twin topology models of distributed resources are extended and established.Secondly,based on the digital twin topology models of distributed resources,a digital twin aggregation modelling method for new-type distribution network is proposed based on spectral clustering.Furthermore,an online linked update strategy for the digital twin model of new-type distribution network that integrates real-time topology states is proposed.Finally,a case study is conducted on a distribution network in a certain demonstration area in China,and the results verify the practicability and effectiveness of the method proposed in this paper.This lays the foundation for the application of electrical network twin analysis,such as power flow calculation,optimal power flow,economic dispatch,and safety check,in a new-type distribution network that includes diversified distributed resources.Peer review under the responsibility of Global Energy Interconnection Group Co.Ltd.

more

Abstract A multi-strategy Improved Multi-Objective Particle Swarm Algorithm (IMOPSO) method for microgrid operation optimization is proposed for the coordinated optimization problem of microgrid economy and environmental protection.A grid-connected microgrid model containing photovoltaic cells,wind power,micro gas turbine,diesel generator,and storage battery is constructed with the aim of optimizing the multi-objective grid-connected microgrid economic optimization problem with minimum power generation cost and environmental management cost.Based on the optimization of the standard multi-objective particle swarm optimization algorithm,four strategies are introduced to improve the algorithm,namely,Logistic chaotic mapping,adaptive inertia weight adjustment,adaptive meshing using congestion distance mechanism,and fuzzy comprehensive evaluation.The proposed IMOPSO is applied to the microgrid optimization problem and the performance is compared with other unimproved multi-objective gray wolf algorithm (MOGWO),multiobjective ant colony algorithm (MOACO),and MOPSO algorithms,and the total cost of the proposed method is reduced by 3.15%,8.34%,and 10.27%,respectively.The simulation results show that IMOPSO can more effectively reduce the cost and optimize power distribution,and verify the effectiveness of the proposed method.

more

Abstract This paper analyzes North American shifts in renewable energy finance and building energy technologies from 2022 to 2025.Fueled by net-zero targets and policy incentives,clean energy investment now surpasses fossil fuel spending.We examine key financial tools—green bonds,corporate power purchase agreements (PPAs),public–private partnerships,and tax credits—and parallel advances in smart meters,grid-interactive efficient buildings,battery storage,heat pumps,and net-zero construction.Through case studies of municipal retrofit financing,integrated smart homes,and net-zero campuses,we illustrate emerging finance–technology–policy ecosystems poised to accelerate the energy transition and bolster climate resilience.

more

Abstract Due to the climate-dependent nature of renewable energy sources (RESs),solving the optimal power flow (OPF) problem in power systems that integrate RESs,such as photovoltaic (PV) units and wind turbines (WTs),remains a significant challenge.To address this problem,this study presents an effective framework that incorporates solar and wind power generation.To manage the nonconvex and nonlinear characteristics of the OPF problem,a modified physics-inspired algorithm termed the Enhanced Coulomb’s and Franklin’s laws Algorithm (ECFA),is deployed.In the proposed OPF model,the power generated from RESs is considered a dependent variable,while voltages at buses equipped with RESs serve as decision variables.Real-time data on solar irradiation and wind speed are used to model the power outputs of PV units and WTs,respectively.Although the Coulomb’s and Franklin’s law algorithm (CFA) offers some advantages,it underperforms on complex optimization tasks compared to SSA,BA,SCA,ABC,and CFA.The enhanced version of the CFA improves the search process across the feasible space by incorporating diverse interaction methods and enhancing exploitation capabilities.The performance of the proposed ECFA is assessed through comprehensive comparisons with state-of-the-art methods for solving the OPF problem.

more

Abstract The increasing global adoption of electric vehicles (EVs) has led to a growing demand for a cost-effective and reliable charging infrastructure.This study presents a novel data-driven approach to assessing EV station performance by analyzing power consumption effi-ciency,station utilization rates,no-power session occurrences,and CO2 reduction metrics.A dataset of 17,500 charging sessions from 305 stations across a regional network was analyzed to identify operational inefficiencies and opportunities for infrastructure optimization.Results indicate a strong correlation between station utilization and energy efficiency,highlighting the importance of strategic station placement.The findings also emphasize the impact of no-power sessions on network inefficiency and the need for real-time station monitoring.CO2 reduction analysis demonstrates that optimizing EV charging performance can significantly contribute to sustainability goals.Based on these insights,this study recommends the implementation of predictive maintenance strategies,real-time user notifications,and diversified provider networks to improve station availability and efficiency.The proposed data-driven framework offers actionable solutions for policymakers,charging network operators,and urban planners to enhance EV infrastructure reliability and sustainability.

more

Abstract Forecasting energy demand is essential for optimizing energy generation and effectively predicting power system needs.Recently,many researchers have developed various models on tabular datasets to enhance the effectiveness of demand prediction,including neural networks,machine learning,deep learning,and advanced architectures such as CNN and LSTM.However,research on the CNN models has struggled to provide reliable outcomes due to insufficient dataset sizes,repeated investigations,and inappropriate baseline selection.To address these challenges,we propose a Tabular data-based Lightweight Convolutional Neural Network (TLCNN) model for predicting energy demand.It frames the problem as a regression task that effectively captures complex data trends for accurate forecasting.The BanE-16 dataset is preprocessed using normalization techniques for categorical and numerical data before training the model.The proposed approach dynamically selects relevant features through a two-dimensional convolutional structure that improves adaptability.The model’s performance is evaluated using MSE,MAE,and Accuracy metrics.Experimental results show that TLCNN achieves a 10.89%lower MSE than traditional ML algorithms,demonstrating superior predictive capability.Additionally,TLCNN’s lightweight structure enhances generalization while reducing computational costs,making it suitable for real-world energy forecasting tasks.This study contributes to energy informatics by introducing an optimized deep-learning framework that improves demand prediction by ensuring robustness and adaptability for tabular data.

more

Abstract Ensuring the reliability of wind energy as a dependable source requires overcoming challenges posed by the inherent volatility and stochastic nature of wind patterns.Long-term forecasting provides strategic advantages in managing energy generation projects,enabling the development of effective portfolio management strategies.The primary objective of this study was the development of forecasting methods to support strategic decision-making within the scope of wind energy operations,specifically targeting the Pindaí Wind Complex and its commercial dispatch.The study integrated Big Data analytics,data engineering,and computational techniques through the application of machine learning algorithms: including eXtreme Gradient Boosting,Multilayer Perceptron,Support Vector Regression,Ridge Regression,and Random Forests,aiming to generate forward-looking projections of the complex’s energy production for the year 2023.To this end,five supervised machine learning techniques were modeled and implemented.These techniques were grounded in their respective mathematical and structural formulations,and the empirical foundation for modeling was provided by historical power generation data from the Pindaí Wind Complex,combined with high-resolution realized and forecasted meteorological data retrieved via the Open-Meteo API.The models are trained using historical monthly generation data from the Pindaí Wind Complex,which has an installed capacity of 79.9 MW and is located in the northeastern region of Brazil,along with meteorological data from reanalysis models,such as air temperature,relative humidity,precipitation,surface pressure,wind speed at 10 m,wind speed at 100 m,and wind gusts.These methodologies are applied to forecast monthly wind generation for the year 2023,and the outputs are systematically compared using evaluation metrics to determine the most suitable modeling approach.The results highlight the superiority of the Multilayer Perceptron,Support Vector Regression,and eXtreme Gradient Boosting models,which achieved Kling-Gupta Efficiency (KGE) of 0.89,0.89,and 0.90,mean absolute scaled error (MASE) of 0.29,0.31,and 0.18,root mean square errors (RMSE) of 0.56,0.59,and 0.35,and mean absolute errors (MAE) of 0.48,0.52,and 0.29,respectively.

more

Abstract State this study looks at how well a three-phase bidirectional converter works for Vehicle-to-Grid (V2G) services by using both Adaptive Neuro-Fuzzy Inference System (ANFIS) and Proportional-Integral (PI) controllers.When compared with ANFIS controllers,traditional controllers such as PI and PID show challenges.They may not sufficiently react to changing conditions or non-linearity’s and use fixed gain values requiring hand tuning.By means of learning,ANFIS controllers can thus dynamically change their parameters,so providing enhanced accuracy and flexibility in real-time control.The main objectives are to control the DC link voltage,lower total harmonic distortion (THD),and lower the errors.The Synchronous Reference Frame (SRF) transformation changes three-phase AC into a two-axis (d-q) system,making it easier to control active and reactive power separately.We developed a thorough Simulink model in MATLAB 2023a to model the bidirectional off-board fast charger at a power level of 60 kW.After validation,a 5-kW hardware prototype was built in the lab.The main platform is an AC-DC converter,followed by a DC-DC converter.A programmable DC power supply,Chroma 62050H-600S,connected to the DC-DC converter,mimics the dynamic characteristics of a battery.The control algorithm,deployed on a Spartan-6 LX9 FPGA,manages both voltage and current,maintaining a stable DC link voltage of 800 V.The results obtained indicate that the ANFIS controller outperforms a conventional PI controller when handling dynamic load variations.

more

Abstract Permanent faults in medium-voltage cable joints significantly impact the reliability of distribution networks.Radial breakdowns caused by water ingress often lead to several self-extinguishing arc discharges—referred to as incipient faults—before developing into permanent faults.Effective monitoring of incipient faults can help reduce outage costs associated with permanent faults.However,the specific fault scenarios of incipient faults remain insufficiently understood.To address this gap,this study designed a simulation experiment replicating incipient fault conditions in medium-voltage cable joints under humid environments,based on actual operating scenarios.The experiment compared the insulation strength required to trigger incipient faults and examined both non-electrical fault characteristics,such as insulation damage and arc flame intensity,and electrical characteristics,such as fault current and impedance.Experimental observations show that,in cable joints,gaps without accumulated water retain sufficient insulation strength to prevent breakdown.However,the infiltration of accumulated water shortens the effective insulation path,thereby lowering the breakdown threshold.The peak current of an incipient fault can range from hundreds to thousands of amperes,with a duration of approximately 1/8 to 1/4 of a power–frequency cycle.During incipient faults,arc burning on the pore wall leaves conductive traces,which progressively reduce the insulation strength of the surrounding environment.As these traces accumulate over multiple events,the likelihood of breakdown increases,ultimately resulting in a permanent fault.Permanent faults are characterized by intense,sustained arc discharges that persist over a macroscopic time scale and exhibit flatshoulder waveforms within individual cycles,with discharge intensity increasing progressively over time.

more