The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS
Transactions ID Number: 53-132
Full Name: Subashini Govindaraj
Position: Assistant Professor
Age: ON
Sex: Female
Address: Dept of IT, PSG College of Technology, Coimbatore
Country: INDIA
Tel: 9943039597
Tel prefix: +91422
Fax:
E-mail address: suba@ity.psgtech.ac.in
Other E-mails: suba_gr@yahoo.com,gr.subashini@gmail.com
Title of the Paper: Task Allocation in Distributed Computing Systems Using Multiobjective Adaptive Particle Swarm Optimization
Authors as they appear in the Paper: G.Subashini, M.C.Bhuvaneswari
Email addresses of all the authors: suba@ity.psgtech.ac.in,mcb@eee.psgtech.ac.in
Number of paper pages: 10
Abstract: Both parallel and distributed systems play a vital role in the improvement of high performance computing. A primary issue concerned with the performance of a parallel application executing on a distributed system is the distribution of the tasks comprising the application among the various processors in the distributed system. This paper presents an algorithm for allocating tasks to heterogeneous processors of a distributed system to obtain optimal solutions. The proposed algorithm investigates on the application of Particle Swarm Optimization (PSO), a robust stochastic search algorithm gaining popularity in several applications. As several conflicting factors influence the allocation strategy, the algorithm is designed to account for multiple objectives. The proposed algorithm is made adaptive by subjecting the PSO parameters to change within iterations. It also uses a fast non-dominated sorting approach to move the particle population towards the best non-domina!
ted set over many iteration steps. This multi objective adaptive PSO employing non-dominated sorting (MO-ANPSO) has been implemented and tested. The experiments are carried out on a simulated data set comprising several instances of task interaction graph with different levels of complexity. The results obtained reveal that the proposed method obtains a set of optimal allocations at an increased desired level of performance.
Keywords: Task allocation, multi-objective optimization, non-dominated sorting, dynamic inertia.
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: evolutionary computing, distributed scheduling,Particle swarm optimization, Multiobjective optimization
IP ADDRESS: 122.183.240.110
