<p>Addressing DC optimal power flow (DCOPF) challenges in power systems with a high penetration of renewable energy sources (RES) necessitates innovative solutions due to the limitations of data accessibility, dynamic network adaptability, and worst-case scenario planning, including load shedding and RES curtailment. Traditional datasets for neural network training often fall short in quality and relevance, impeding the accurate modeling of machine learning solutions for energy distribution. This study introduces a robust deep neural network model that integrates physics-based constraints (via Karush–Kuhn–Tucker parameters) to effectively manage high levels of RES integration by solving the DCOPF problem. The proposed model simulates DCOPF without running the DCOPF equations, thereby minimizing the maximum deviation between its predictions and actual DCOPF results. By leveraging a dataset derived from DCOPF configurations in a multibus power grid, the model demonstrates superior performance compared to conventional neural network approaches, as confirmed through evaluations with real-world data. The proposed framework has been validated on multiple bus systems, including Garver’s 6, IEEE 9-, 14-, and 30-bus systems, confirming its scalability in increasingly complex networks. Although the simulation focuses on the IEEE 30-bus system, the promising results indicate potential applicability to larger networks. Nevertheless, this method relies on deterministic assumptions, which offer a practical first step for verifying its robustness and scalability in high-RES scenarios.</p>