Efficiency optimization of AI automatic control systems via heuristic scheduling in edge computing environments

The rapid growth of AI and IoT has increased data and computation demands, creating latency, bandwidth, and privacy challenges for traditional cloud models. This research proposes an edge-computing-based AI control framework using two heuristic algorithms: RD-TDC for maximizing task collection under resource limits and TS-BRD for reducing waiting time through adaptive scheduling. Together, they improve data handling and resource allocation. Simulations show up to 30% better deadline satisfaction, CPU usage, and task completion compared to FCFS and EDF. The framework is scalable for large, latency-sensitive edge environments and supports efficient AI-edge integration.