The importance of resolving stability concerns in weak AC grid‐connected doubly fed induction generator (DFIG) wind energy systems during low‐voltage ride‐through (LVRT) events cannot be ignored, given the increasing popularity of wind power‐based microgrids. Furthermore, the emergence of generation loss and postfault oscillation within a microgrid (MG) due to grid faults has also become a significant concern. The static synchronous compensator (STATCOM) under consideration in this study is tuned using particle swarm optimization (PSO), the artificial hummingbird algorithm (AHA), and a hybrid approach incorporating both PSO and AHA. Faults of both a symmetrical and an asymmetrical nature have occurred on the power grid side. The proposed hybrid PSO‐AHA‐tuned STATCOM strategy aims to improve LVRT, minimize power generation loss during faults, and reduce oscillations after a fault by controlling the flow of reactive power between point of common coupling (PCC) and MG. The MATLAB simulation environment was used to simulate the 16 MW MG test system. The performance of the PSO‐AHA‐tuned STATCOM was assessed by comparing results with those from conventional STATCOM, PSO, and AHA optimizer‐tuned STATCOM in four fault situations. A comparison of the results shows that the proposed strategy performed better than other approaches mentioned in this paper and achieved the desired objectives.
Offshore ship charging station (OSCS) projects can help to address the current demand for electric ships for ocean voyages to a large extent. The proper selection of the energy source for power generation is a key part of the OSCS project. To select the optimal renewable energy for OSCS with many difficulties such as the ambiguity of the decision-making environment, the differences in group assessment information, and the conflict and compensation between criteria, this paper proposed a fuzzy multi-criteria decision-making (MCDM) framework. First, a comprehensive criteria system was constructed. Second, the intuitionistic fuzzy set (IFS) was introduced to express experts’ fuzzy cognition. Third, based on the quality of evaluation, a novel expert weighting method was proposed, and the generalized intuitionistic fuzzy weighted geometric interaction averaging (GIFWGIA) operator was used to aggregate the individual evaluations. Fourth, the criteria importance through intercriteria correlation (CRITIC) method, and the stepwise weight assessment ratio analysis II (SWARA II) method were introduced to determine the criteria weights. Fifth, considering criteria compensation, and individual and group ranks, the gained and lost dominance score (GLDS) method were used for ranking. Finally, to verify the applicability and reliability of the framework, a case study was conducted in Pingtan Island, Fujian Province. The results show that wind energy was the best alternative, followed by solar, wave and nuclear energy.
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.