An ACO-Based Approach for Task Assignment and Scheduling of Multiprocessor Control Systems
In order to solve whether a set of periodic tasks can be assigned to a set of identical processors in such a way that all timing constraints can be met, the model of travelling salesman problem is used to describe the task assignment and scheduling in real-time multiprocessor control systems. Combined with the scheduling characteristics of multiprocessor systems, a new feasible algorithm based on ant colony optimization metaheuristic is presented for solving this problem. Both the scheduling performance index and the control performance index are proposed and used as fitness functions of optimization. Simulation results show that the proposed approach can solve the task assignment and scheduling problem in multiprocessor control systems.
KeywordsSchedule Problem Travel Salesman Problem Travel Salesman Problem Task Assignment Control Task
Unable to display preview. Download preview PDF.
- 2.Kimbrel, T., Schieber, B., Sviridenko, M.: Minimizing migrations in fair multiprocessor scheduling of persistent tasks. In: Proc. of the fifteenth annual ACM-SIAM Symposium on Discrete Algorithms, Philadelphia, PA, USA, pp. 982–991 (2004)Google Scholar
- 6.Baruah, S.: Task partitioning upon heterogeneous multiprocessor platforms. In: Proc. of the 10th IEEE Real-Time and Embedded Technology and Applications Symposium, pp. 536–543 (2004)Google Scholar
- 10.Velasco, M., Fuertes, J.M., Lin, C., Marti, P., Brandt, S.: A control approach to bandwidth management in networked control systems. In: Proc. of 30th Annual Conf. of IEEE Industrial Electronics Society, Busan, Korea, vol. 3, pp. 2343–2348 (2004)Google Scholar
- 11.Chen, H., Cheng, A.M.K.: Applying ant colony optimization to the partitioned scheduling problem for heterogeneous multiprocessors. SIGBED Review 2(2) (2005); Special Issue on IEEE RTAS 2005 Work-in-ProgressGoogle Scholar