Research on Optimal Trading Strategy and New Energy Consumption of Wind-Solar-Thermal Coupled System in Spot Market
As the “dual-carbon” targets are set and the energy sector accelerates its shift toward green and low-carbon development, renewable sources such as wind power are being integrated at an unprecedented scale. This trend has imposed considerable strain on the stability and reliability of the evolving power system. To tackle this challenge, this study introduces a hybrid dynamic wind power forecasting approach that integrates machine learning with optimization algorithms. Furthermore, by incorporating a self-correcting parameter estimation process, a hybrid model is constructed. By continuously tuning the grid’s transmission capacity in real time, the proposed framework remains responsive to variations in wind power output. Based on observed fluctuation patterns, the framework continuously updates its system parameters, guaranteeing that the power grid operates optimally even under intricate and shifting environmental conditions. Using real-world data for validation, the proposed approach demonstrates clear strengths in both forecast precision and the operational efficiency of the power grid. By strengthening the grid’s resilience to wind power variability, this approach contributes to maintaining reliable and stable system operation. This technique offers tangible engineering backing for the seamless and efficient incorporation of wind energy into power grids.