<p>As global energy demands surge and the urgency for sustainable solutions intensifies, optimizing the scheduling of renewable energy sources (RES) and energy storage systems (ESSs) in power systems becomes increasingly important in these networks. Integrating energy storage systems (ESSs) is essential for achieving energy security and mitigating the adverse effects of climate change. This paper proposes a network-constrained stochastic dispatch model to coordinate compressed Air energy storage (CAES) with high renewable energy penetration, ensuring day-ahead power system scheduling while maintaining operational cost-effectiveness. This work also examines the proposed Genetic Algorithm (GA) for optimal decision-making and the Support Vector Machine (SVM), which offers an accurate forecast of RES generation. While the GA learns various decisions to cut costs, SVM maximizes accuracy by using patterns in both previous and current data. A comprehensive assessment of economic and environmental aspects is conducted. The results indicate an overall system cost reduction of 13.43% with uncertain RES, CAES, and demand response (DR) programs in scheduling costs, along with a CAES cost reduction of 19.91% respectively. Smart technologies, including CAES units and DR, are integrated into the power system to create a flexible system, aiming to decrease total cost, wind curtailment, and load shedding as the primary objectives of this study. Simulation experiments based on a standard IEEE 33-bus and 118-bus distribution systems using MATLAB will validate the advantages of the proposed model in terms of robustness and economic performance and demonstrate the superior computational performance of the proposed algorithm.</p>