<p>An optimal scheduling framework for integrated energy systems (IES) under wind-solar generation uncertainties is developed to reduce operational costs and carbon emissions while improving overall energy utilization efficiency. Latin hypercube sampling is first applied to generate a comprehensive set of stochastic scenarios from historical data, and clustering-based scenario reduction is conducted to obtain representative wind-solar uncertainty profiles, thereby improving computational efficiency while preserving uncertainty characteristics. A multi-objective optimization model is subsequently formulated with total operating cost, CO₂ emissions, and energy utilization efficiency as the objective functions, explicitly incorporating the variability of renewable energy outputs. To address the complexity of the optimization problem, a Q-learning-based memetic algorithm is designed to obtain the Pareto-optimal solution set and determine the optimal compromise strategy. Simulation results verify that the proposed method effectively manages renewable energy intermittency and load fluctuations, thereby demonstrating the robustness and practicality of the scheduling scheme under multi-source uncertainties. In the context of the uncertainties associated with wind and solar energy, the proposed method achieves an economic cost of RMB 4.51 million, a carbon emission volume of 4.21 million tons, and an energy efficiency of 98.02%, further confirming the effectiveness of the proposed Q-MOMA-based scheduling framework for integrated energy systems under multi-source uncertainties.</p>