The rapid growth in energy demand, along with escalating environmental concerns, highlights the necessity of developing and integrating renewable energy sources into modern power systems. In this context, economic dispatch can play a crucial role in optimizing resource utilization, minimizing operational costs, and ensuring reliable networks. This study provides a renewable-integrated framework using economic dispatching to minimize the total operation cost while achieving optimal utilization of distributed generation (DG) units in the state of Texas. In this study, an Artificial Neural Network (ANN) is employed for forecasting, while the GAMS software is utilized for optimization to perform economic dispatch. In the first stage, an ANN model is developed using historical data from the previous 72 hours to forecast the power output of wind turbines, photovoltaic systems, and electricity demand. The results demonstrated that the proposed model achieved high accuracy, with the Mean Absolute Percentage Error (MAPE) remaining below 5%. In the second stage, a Mixed-Integer Linear Programming (MILP) model was implemented in the GAMS environment to determine the optimal generation mix for each hour of the forthcoming 24-hour period. The optimization results indicated that the total electricity demand for the next day, amounting to 138.93 MWh, was supplied through an optimal combination of wind turbines (19.8%), photovoltaic systems (10.9%), gas micro turbines (4.3%), fuel cells (2.5%), and the main grid (62.5%). The total operational cost was calculated to be $18,434, representing an approximate 15% reduction compared to the existing supply scenario relying solely on the main grid.