The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
A Resource-Aware Dynamic Load-Balancing Parallelization Algorithm in a Farmer-Worker Environment
Abstract
This paper describes an algorithm for dynamically assigning tasks to processing entities in a world where each task has a set of resource or service requirements and each processing entity a set of resources or service capabilities. A task needs to be assigned to a node that offers all required services and the set of tasks is finished within a minimal execution time frame. Dependability and adaptability are inherent to the algorithm so that it accounts for the varying execution time of each task or the failure of a processing node. The algorithm is based on a dependable technique for farmer-worker parallel programs and is enhanced for modeling the time constraints in combination with the required configuration set in a multidimensional resources model. This paper describes how the algorithm is used for dynamically load balancing and parallelizing the nightly tests of a digital television content-processing embedded device.
Related Content
David Zelinka, Bassel Daher.
© 2021.
30 pages.
|
David Zelinka, Bassel Daher.
© 2021.
29 pages.
|
Narendranath Shanbhag, Eric Pardede.
© 2021.
31 pages.
|
Marc Haddad, Rami Otayek.
© 2021.
20 pages.
|
Reem A. ElHarakany, Alfredo Moscardini, Nermine M. Khalifa, Marwa M. Abd Elghany, Mona M. Abd Elghany.
© 2021.
23 pages.
|
Sanjay Soni, Basant Kumar Chourasia.
© 2021.
35 pages.
|
Lina Carvajal-Prieto, Milton M. Herrera.
© 2021.
20 pages.
|
|
|