A Self-adaptive Greedy Scheduling Scheme for a Multi-Objective Optimization on Identical Parallel Machines
A self-adaptive greedy scheduling scheme is presented to solve a Multi-Objective Optimization on Identical Parallel Machines. The primary objective is to minimize the makespan, while the secondary objective makes the schedule more stable. Actual experiments revealed that the scheme obtained the optimal primary and secondary objectives for most cases. Moreover, schedules produced by the scheme were more robust, with smaller makespans. Additionally, it has been applied to parallelize one major component of EMAN, one of the most popular software packages for cryo-electron microscopy single particle reconstruction. Besides, it can also be used in practice to parallelize other similar applications.
KeywordsMulti-objective programming Load balancing Scheduling scheme Parallel computing
Unable to display preview. Download preview PDF.
- 1.Frank, J.: Three-dimensional electron microscopy of macromolecular assemblies, pp. 1–13. Oxford University Press, Oxford (2006)Google Scholar
- 5.Yu, X., Jin, L., Zhou, Z.H.: 3.88Ǻ structure of cytoplasmic polyhedrosis virus by cryo-electron microscopy. Nature 452 (2008) doi:10.1038Google Scholar
- 8.Hochbaum, D.S.: Approximation algorithms for NP Hard problems, pp. 1–17. PWS publishing company (1998)Google Scholar
- 9.Graham, R.L.: Bounds for certain multiprocessing anomalies. Bell System Technical Journal 45, 1563–1581 (1966)Google Scholar
- 15.Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to algorithms, pp. 1043–1049. The MIT Press, Cambridge (2002)Google Scholar
- 16.Maheswaran, M., Ali, S., Siegel, H.J., Hensgen, D., Freund, R.: Dynamic matching and scheduling of a class of independent tasks onto heterogeneous computing systems. In: 8th Heterogeneous Computing Workshop (HCW 1999) (April 1999)Google Scholar