Real-time scheduling of batch processes via agent-based modeling

We propose a novel agent-based method for real-time scheduling of network batch processes. The agent architecture is formulated based on the resource-task network (RTN) or state-task network (STN) representation so it is applicable to a wide range of network batch scheduling problems. A scheduling algorithm is developed based on the predicted objective function value by simulating another agent-based system. An embedded agent-based system is resulted in. The agent-based modeling provides an efficient heuristic method for solving a complicated batch scheduling problem. The case study demonstrates that the agent-based method is able to return a solution very close to the optimal one. However, the agent-based method significantly reduces the computational complexity. The efficiency enables the online real-time rescheduling under uncertainties.