ABSTRACT Accurate probabilistic wind speed forecasting is crucial for mitigating the adverse effects of wind variability on power systems and facilitating large‐scale wind energy integration. Existing studies have primarily focused on deterministic predictions and ignore the guidance of physical laws for probabilistic prediction. This research proposes a novel physics‐informed interval forecasting approach that combines temporal convolutional networks (TCN) with Transformer architectures and quantile regression (QR) methodology. Furthermore, the energy conservation and the ideal gas equation of state ensure that the model follows physical laws during the training process. Comprehensive experiments use multiple datasets across different seasons and different quantile levels ( α = 0.05 and α = 0.1). The results demonstrate that the TCN–Transformer model consistently outperforms four benchmark methods in both single‐step and multi‐step predictions. For instance, the proposed model maintains a PICP (coverage probability of predictive interval [PI]) value of 0.969 and a PINAW (PI‐normalised average width) value of 0.341 for single‐step winter predictions at PINC = 0.95, while the PICP values of other benchmark models are less than 0.95. These results establish the TCN–Transformer framework as an advanced solution for probabilistic wind speed forecasting in power system applications.

ABSTRACT This paper presents a hierarchical control strategy for inverter‐dominated multi‐microgrid systems, structured into two distinct control layers: (1) the microgrid layer and (2) the multi‐microgrid (MMG) layer. In the microgrid layer, decentralised primary control ensures accurate power distribution among inverter‐based distributed generators (IBDGs), while distributed secondary control restores voltage and frequency to their reference values. Furthermore, within the MMG layer, the optimal active power reference for each IBDG is calculated, and consensus coefficients (CCs) are adaptively tuned to ensure system stability. Eigenvalue analysis within this layer identifies modes with low damping coefficients, which are classified as critical modes (CMs) and pose a threat to the system's stability. This research demonstrates that the CCs of specific secondary controllers play a significant role in the formation of CMs. This paper proposes a novel adaptive iterative method for increasing the damping ratio to enhance system stability. In each iteration, the CCs with the most significant contribution to CM formation are identified using the participation factor method. Their values are then adjusted to increase the damping of these modes, transitioning them from critical to non‐critical modes. MATLAB simulations confirm the effectiveness of the proposed strategy, highlighting its ability to enhance system stability.

ABSTRACT With the increasing scale of offshore wind farms, the spatial‐temporal correlation of wind turbines is commonly considered in predicting wind power generation. Meanwhile, the seasonal variation of offshore wind conditions necessitates the consideration of the spatial relationship of wind farms with dynamic changes. This paper proposes a new power prediction model for offshore wind farms, namely the feature attention graph convolutional neural network with temporal transformers (FAGTTN). Specifically, the feature attention module is utilised to extract important features from the offshore wind power supervisory control and data acquisition (SCADA) system data. Then, the adaptive graph convolutional neural network (AGCN) is employed to learn the embedding of multiple wind turbine nodes, uncovering the hidden spatial dependence in the data to express the dynamic spatial relationship of offshore wind farms. Besides, the temporal transformer is used to capture time dependence and temporal patterns in the time series. The proposed method is validated using the real‐world data from the offshore wind farm at Donghai Bridge, demonstrating its validity and superiority. The results show that the proposed offshore wind turbine graph topology network can effectively utilise the geographic location information of wind turbines and outperform existing methods in terms of accuracy and interpretability for offshore wind turbine output prediction.

ABSTRACT Operational optimisation and predictive maintenance are essential for upgraded reliability and cost‐efficiency in renewable energy systems. This study proposed an integrated model combining physics‐informed neural networks (PINNs), adaptive decision‐making and transfer learning to improve the performance of solar farms and wind turbines. The model leverages domain knowledge to capture precise fault identification, enlarge failure prediction lead times and enable rapid deployment across geographically diverse installations with nominal site‐specific data. Field evaluations across multiple solar and wind installations illustrate that the PINN‐based framework achieves up to 87.3% accuracy in component fault prediction with lead times of 14.2 days for blade issues and 21.3 days for gearbox failures, outperforming commercial condition monitoring systems and conventional machine learning. Innovative algorithms to optimise the cleaning of solar panels have shown improved energy production (8.3%), reduced water consumption (31.2%) and decreased labour requirements (34.1%). The architecture that has been used for the edge‐computing systems supports analytics in real time and has had an impact on maintaining operational capabilities above 93.2% even with disruption in communication. This forecast also indicates that through the use of the model's ability to perform transfer learning; it provides the opportunity to capture more than 85% of the initial model's performance when installing on new installations with only 65.1% of the necessary initial training samples while overcoming the cold‐start challenge. Although there are limitations due to the reliance on detailed component specifications, environmental variability, and the length of time required for system adaptation, the results have demonstrated significant economic and operational advantages. The practical and scalable implementation of this concept will allow for the continued implementation of Predictive and Resource‐Efficient Renewable Energy Operations.

ABSTRACT Generating a substantial set of long‐term operational scenarios for wind power, photovoltaic (PV) power, and load sequences is the data foundation for planning high‐penetration renewable energy power systems. The existing scenario generation methods (SGMs) have some defects, such as neural network–based approaches requiring a large amount of historical data and lack of preservation of the characteristics of extreme scenarios. In response to the above challenge, this paper proposes an SGM for wind/PV power outputs and load sequences, which is able to preserve the characteristics of extreme scenarios. Specifically, the method extracts extreme scenarios via an iterative procedure and generates conventional scenarios using a double‐layer Markov chain model. By combining the iterative extraction process with the double‐layer model, the proposed framework effectively incorporates extreme scenario characteristics into the scenario generation process. The results of the case study from a northern province of China demonstrate that the proposed method effectively preserves the statistical characteristics of the original data and extracts representative extreme scenarios, providing diverse scenarios for evaluating high‐penetration renewable energy power systems.

ABSTRACT The large‐scale integration of renewable energy sources such as photovoltaic and wind farms presents significant challenges to voltage stability and fault‐ride through capability, particularly in weak transmission networks characterized by low inertia and high impedance. Advancing carbon neutrality and energy sustainability demands flexible and adaptive control strategies capable of supporting diverse renewable technologies. This research introduces a cascaded control parameter optimization framework to enhance system stability and resilience in scenarios with high renewable energy penetration. Central to this framework is developing a novel dynamic resilience metric, which guided the optimization process by minimizing transient, extending permissible fault‐clearing times, and strengthening post‐recovery. An enhanced particle swarm optimization algorithm is employed to concurrently optimize parameters across plant models, electrical systems, and generator controllers, all in alignment with the PJM model development guidelines. This framework is validated on the Simplified 14 Generator Test System (Area 5), representative of Southeast Australia's grid, and verified for compliance with AEMC fault‐clearing requirements and IEEE 1947‐2003 standard. Case studies demonstrate its effectiveness and adaptability, with voltage overshoot reduced from 25%–40% to 6%–25%, and fault clearing times extended from 55–70 ms to 255–270 ms. These results confirm that the proposed approach offers a robust solution for integrating renewables into weak grids, enhancing reliability and supporting the shift toward a sustainable energy future.

ABSTRACT Background : Increasing Electric Vehicle (EV) possession has resulted in an abundance of Charging Stations (CSs), which nurtures load demands and causes grid interruptions in peak hours. By using an effective Energy Management Strategy (EMS), microgrids provide a workable solution to these problems with the electrical distribution infrastructure. DC microgrids powered by renewable energy present a promising alternative, but their efficacy is limited by the fluctuating availability of renewable energy sources (RES) and the erratic demand for EV charging. Therefore, to ensure cost‐effective, reliable, and environmentally sustainable EV charging, an efficient and adaptive EMS is required. Methods : This research proposes an advanced hybrid energy management approach for DC microgrids powered by RES that incorporate EV charging stations. The method optimises power flow among solar systems, fuel cells, battery storage, and EV loads by combining a Dwarf Mongoose–Zebra Optimisation tuned Proportional–Integral controller with Fuzzy Logic Control (DMZO‐PI+Fuzzy). The hybrid Dwarf Mongoose–Zebra Optimisation algorithm is utilised to optimise PI controller gains. The control signal from the fuzzy control and the DMZO Optimised PI controller are combined to enhance the controller performance in the proposed model of EVCS. MATLAB/Simulink simulations are used to validate the proposed DMZO‐PI+Fuzzy method under various operating conditions. Results : The proposed DMZO‐PI+Fuzzy strategy performs significantly better than traditional approaches, according to simulation results. With a minimum tariff of 0.034 USD/kWh during off‐peak hours, charging costs can be lowered by up to 75.56%. On weekdays and weekends, average charging rates drop to 0.086 and 0.088 USD/kWh, respectively, representing cost savings of 45.26% and 56.11%. Also, under dynamic operating conditions, enhanced convergence speed and DC bus voltage stability are observed, and optimal renewable utilisation results in a maximum GHG emission reduction of 55.75%. Conclusion : The proposed DMZO‐PI+Fuzzy energy management framework offers an effective, reliable, and economical feasible EV charging solution for DC microgrids powered by renewable energy. The approach improves both economic and environmental performance by simultaneously optimising charging costs, the use of renewable resources, and efficient power management (PM) in DC MGs.

ABSTRACT With fast growing renewable generations, source‐grid‐load‐storage (SGLS) integrated systems have emerged in recent years. The economical feasibility of SGLS system is still a challenge in many power systems. This paper proposes a multi‐period source‐storage coordinated planning model for SGLS system project considering spatio‐temporal complementarity and dynamic source cost. In order to capture demand for flexible resource and wind‐solar complementarity, the model develops hourly operation constraints for wind power, photovoltaic output, and load. It incorporates annually changing investment costs for photovoltaic generators, wind turbine, and energy storage, determining the optimal investment timing. A concept of self‐declared capacity is proposed to coordinately minimize the capacity fee by leveraging local resources. Case study with real‐data demonstrates that the proposed model can reduce total life‐cycle costs by 7.54% to 9.67% and capacity costs by approximately 7.6%, compared to the original project, while assisting the main grid in peak shaving and valley filling. The results reveal that wind farms tends to be built in the early stages, while PV generator and energy storage tend to defer investments. A high proportion of PV generator has seen an increase in the share of energy storage, while energy storage is most sensitive to cost reductions.

ABSTRACT This paper proposes a two‐layer, tri‐objective optimization structure for the daily operation of integrated energy systems. The proposed structure integrates the water system into the electrical, thermal and cooling systems to model the energy‐water nexus in modern energy systems. The first layer of the proposed model is formulated in MATLAB software and is responsible for modelling the uncertainty of renewable energies using a stochastic model. The second layer utilizes a hybrid classic weighted compromise programming to provide a sustainable and economic operation for the energy system. The second layer is solved using GAMS software to ensure optimality. The carbon capture, protection from underground sources and the cost of the system are the objective function. The main aim of the proposed model is to prevent the excess extraction of water from underground sources. To this end, the water storage tank and desalination systems are considered to meet the needed potable water. To show the effectiveness of the proposed model, it is tested on a general integrated energy system. The numerical results show that the proposed model improves water extraction and carbon emissions by 86.7% and 3.03%, respectively, while increasing the operating cost by 3.96%.

ABSTRACT This study develops a transparent MATLAB‐based numerical model for simulating lead‐free perovskite solar cells (PSCs), providing full equation‐level control and reproducible device analysis. Unlike black‐box tools such as SCAPS‐1D, the framework offers open access to all physical parameters and faster computation. Validation against reported CsGeI 3 /TiO 2 /Cu 2 O/Ni (∼25% PCE) and CsSnCl 3 /MZO/C 6 TBTAPH 2 /Au (∼32% PCE) structures shows <5% deviation from benchmark results, confirming model accuracy. By combining SnF 2 passivation, MoO x dipole contact, and a multi‐layer anti‐reflection coating, the optimised Pb‐free design (Model C) achieves ∼35% efficiency—a 12.5% gain in PCE—with 3% higher Voc and 2% higher fill factor when compared to previous Sn‐based PSC models. For Pb‐free PSCs, this is the first MATLAB‐based open‐access modelling framework that combines optical and interfacial engineering, providing researchers and students with a scalable, instructive, and repeatable platform to investigate next‐generation photovoltaic design.