Correlated Equilibrium based Online Real-time Distributed Dynamic Task Scheduler for Multi-agent Systems

Scheduling multiple tasks in a real-time, distributed fashion among multiple agents is indeed challenging. Scheduling becomes more challenging if task generation is dynamic in nature. This paper proposes an online real-time distributed dynamic task scheduling approach for multi-agent systems. The proposed scheduler is capable of rescheduling while the task generation is dynamic without hampering the current task execution, if any. The scalability of the proposed scheduler is realised by distributing all the agents into a number of groups. Distributed grouping makes the scheduler scalable for a large number of agents and tasks. Complexity analysis conveys that the time-complexity for scheduling is independent of agent count, but depends on the task count along with the agent’s payload. While the computational burden for the consensus formation varies linearly with the number of agents and is independent of task count. Simulation results confirm that the proposed scheduler outperforms the relevant reference scheduler in terms of successful consensus attained, average reward attained at consensus, task scheduled, task executed, dynamic scheduling, and scalability. One demonstration is shown in a typical warehouse environment.