Task scheduling in distributed real-time systems (DRTS) is a complex problem due to the heterogeneous nature of processors and the need for efficient resource utilization. This paper presents a novel hybrid model combining Ant Colony Optimization (ACO) and Genetic Algorithm (GA) to address the task scheduling problem. The proposed model aims to minimize system cost and response time while maximizing system reliability by leveraging the exploration capabilities of ACO and the solution refinement strength of GA. The hybrid algorithm operates in two phases: the first phase uses ACO to generate initial task assignments by dynamically exploring the search space based on pheromone trails and heuristic information. In the second phase, GA refines these solutions through crossover and mutation operators optimizing the task allocation further. Experimental results demonstrate that the proposed ACO-GA hybrid model significantly improves task scheduling performance compared to standalone algorithms by achieving better resource utilization, by reducing execution time, and by enhancing the system reliability. This approach is especially effective for real-time applications where optimal task assignment is critical to system performance.