Artificial Immune Systems Applied to Multiprocessor Scheduling

We propose an efficient method of extracting knowledge when scheduling parallel programs onto processors using an artificial immune system (AIS). We consider programs defined by Directed Acyclic Graphs (DAGs). Our approach reorders the nodes of the program according to the optimal execution order on one processor. The system works in either learning or production mode. In the learning mode we use an immune system to optimize the allocation of the tasks to individual processors. Best allocations are stored in the knowledge base. In the production mode the optimization module is not invoked, only the stored allocations are used. This approach gives similar results to the optimization by a genetic algorithm (GA) but requires only a fraction of function evaluations.