The assessment of wind energy resources is critical for the transition from fossil fuel to renewable energy sources. Using the outputs from high-resolution global climate models (GCMs), such as the High Resolution Model Intercomparison Project (HighResMIP) of the Coupled Model Intercomparison Project Phase 6 (CMIP6), has become one of the most important tools in wind energy research. This study evaluated the reliability of the 22 GCMs available in the HighResMIP-PRIMAVERA project by simulating the wind energy climatology and variability over the Tibetan Plateau (TP) with reference to observations and investigated the differences in performance of the GCMs between high-resolution (HR) and low-resolution (LR) simulations. The results show that most models performed relatively well in simulating the probability distribution of the observed wind speed over the TP, but nearly half of the models generally underestimated the wind speed, whereas the others tended to overestimated the wind speed. Compared with the wind speed, the GCMs showed larger biases in reproducing the wind power density (WPD) and other wind energy resources, whereas the biases in multi-model ensembles were relatively smaller than those in most individual models. With respect to interannual variability, both the HR and LR models failed to capture interannual variations in WPD over the TP. Furthermore, more than half of the HR GCMs had a reduced bias relative to the corresponding LR GCMs, indicating the good performance of most HR models in simulating wind energy resources over the TP in terms of spatial pattern and temporal variability. However, the overall performance of HR GCMs varied among models, which suggests that solely improving the horizontal resolution is not sufficient to completely solve the uncertainties and deficiencies in the simulation of wind energy over complex terrain.

This paper proposes a stepwise expert-teaching reinforcement learning framework for intelligent frequency control in hydro–thermal–wind–solar–compressed air energy storage (CAES) integrated systems under high renewable energy penetration. The proposed method addresses the frequency stability challenge in low-inertia, high-volatility power systems, particularly in Southwest China, where large-scale renewable-energy-based energy bases are rapidly emerging. A load frequency control (LFC) model is constructed to serve as the training and validation environment, reflecting the dynamic characteristics of the hybrid system. The stepwise expert-teaching PPO (SETP) framework introduces a stepwise training mechanism in which expert knowledge is embedded to guide the policy learning process and training parameters are dynamically adjusted based on observed performance. Comparative simulations under multiple disturbance scenarios are conducted on benchmark systems. Results show that the proposed method outperforms standard proximal policy optimization (PPO) and traditional PI control in both transient response and coordination performance.

With the rapid increase in renewable energy penetration and the expansion of multi-regional interconnected power systems, there is a growing need to forecast the power output of renewable energy power plant clusters within a region. Existing methods primarily utilize spatio-temporal correlations between stations to directly predict cluster output, but they still have the following shortcomings: (1) lack of analysis and utilization of the similar output characteristics between wind and solar power stations; and (2) inadequate integration of individual plant characteristics and adaptability across different prediction spatial scales. Therefore, this study proposes a method for forecasting and correcting daily power generation zones of wind–solar clusters based on output similarity clustering. First, the output similarity characteristics of wind and solar plants within the cluster are evaluated, and a similarity matrix is constructed to cluster the plants into sub-clusters. Second, a single-site power prediction model based on the BiLSTM model and multi-task learning is constructed to aggregate preliminary power prediction results from individual sites within sub-clusters. Finally, a cluster power prediction correction model based on the GCN-Transformer model is developed to refine preliminary predictions using spatio-temporal correlations between sub-clusters. Simulation results demonstrate that the proposed method, through its integrated approach combining clustering partitioning, multi-task learning, and spatio-temporal correlation correction within a comprehensive forecasting workflow, achieves improvements of 15.2323%, 19.0581%, and 0.0283% over the baseline GCN model in terms of MAE, RMSE, and R-score, respectively. This effectively enhances the accuracy of power forecasting for wind-solar power plant clusters.