To address the uncertainty of renewable energy, this paper proposes an optimization scheduling of Regional Integrated Energy Systems based on Data Driven-Information Gap Decision Theory. Firstly, a stepped carbon trading mechanism was constructed, which includes a Power to Gas Carbon Capture and Storage coupled model and systematically incorporates carbon emission reduction constraints. Secondly, the Mind Evolutionary Algorithm optimized Backpropagation (MEA-BP) optimization algorithm is used to construct wind and solar power output prediction models. Through iterative optimization of the training set and validation set, high-precision short-term wind and solar power output prediction results are obtained. Once again, the uncertainty of wind and solar power prediction errors is modeled through uncertain sets. A regional integrated energy system optimization scheduling model based on risk-averse information gap decision-making theory is then proposed to achieve a comprehensive balance between system robustness and economic efficiency. Finally, simulation results from different scenarios show that the proposed method significantly enhances the consumption capacity of wind and solar energy, reduces carbon emissions, and effectively improves the economic and robust operation of the system.