Large-scale wind power grid connection increases the uncertainty of the power system, which reduces the economy and security of power system operations. Wind power prediction technology provides the wind power sequence for a period of time in the future, which provides key technical support for the reasonable development of the power generation plan and the arrangement of spare capacity. For large-scale wind farm groups, we propose a cluster model of wind power prediction based on multi-task learning, which can directly output the power prediction results of multiple wind farms. Firstly, the spatial and temporal feature matrix is constructed based on the meteorological forecast data provided by eight wind farms, and the dimensionality of each attribute is reduced by the principal component analysis algorithm to form the spatial fusion feature set. Then, a network structure with bidirectional gated cycle units is constructed, and a multi-output network structure is designed based on the Multi-gate Mixture-of-Experts (MMoE) framework to design the wind power group prediction model. Finally, the data provided by eight wind farms in Jilin, China, was used for experimental analysis, and the predicted average normalized root mean square error is 0.1754, meaning the prediction precision meets the scheduling requirement, which verifies the validity of the wind power prediction model.
Hydrogen energy is a crucial support for China’s low-carbon energy transition. With the large-scale integration of renewable energy, the combination of hydrogen and integrated energy systems has become one of the most promising directions of development. This paper proposes an optimized scheduling model for a hydrogen-coupled electro-heat-gas integrated energy system (HCEHG-IES) using generative adversarial imitation learning (GAIL). The model aims to enhance renewable-energy absorption, reduce carbon emissions, and improve grid-regulation flexibility. First, the optimal scheduling problem of HCEHG-IES under uncertainty is modeled as a Markov decision process (MDP). To overcome the limitations of conventional deep reinforcement learning algorithms—including long optimization time, slow convergence, and subjective reward design—this study augments the PPO algorithm by incorporating a discriminator network and expert data. The newly developed algorithm, termed GAIL, enables the agent to perform imitation learning from expert data. Based on this model, dynamic scheduling decisions are made in continuous state and action spaces, generating optimal energy-allocation and management schemes. Simulation results indicate that, compared with traditional reinforcement-learning algorithms, the proposed algorithm offers better economic performance. Guided by expert data, the agent avoids blind optimization, shortens the offline training time, and improves convergence performance. In the online phase, the algorithm enables flexible energy utilization, thereby promoting renewable-energy absorption and reducing carbon emissions.
Numerical weather prediction (NWP) global horizontal irradiance (GHI) suffers from inherent biases that are drastically amplified under transitional weather, severely compromising day-ahead photovoltaic (PV) power forecasting accuracy. To address this issue, this study proposes a day-ahead PV forecasting method based on dual-stage NWP GHI correction with transitional weather classification. First, a dual-sliding-window approach identifies GHI turning points and categorizes weather-transition trends. Second, trend-specific attention-bidirectional gated recurrent unit (BiGRU) models perform the first-stage correction of NWP GHI. The residual errors are then decomposed via the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) into multiscale components, each corrected by a second-stage sttention-BiGRU to compensate for frequency-band errors. Finally, the dual-stage-corrected GHI serves as a key input for accurate day-ahead PV power forecasting. Case studies using operational data from Hebei, China show that the proposed method reduces mean absolute error (MAE) by up to 39% and achieves an approximately 10% relative improvement in R2 compared with raw NWP data at station 1 for day-ahead forecasting. These improvements are particularly pronounced under transitional weather, demonstrating the method’s effectiveness in enhancing forecast reliability and supporting grid dispatch and renewable energy integration.