Energy-Efficient Scheduling of Deadline-Sensitive and Budget-Constrained Workflows in the Cloud

Tarafdar, Anurina; Karmakar, Kamalesh; Khatua, Sunirmal; Das, Rajib

doi:10.1007/978-3-030-65621-8_4

Cited by 6 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The time or cost of transferring data TTij between any two tasks such as ti and tj in a workflow, where ti is parent to tj, depends on the amount of data sent from ti to tj, and the network bandwidth. TTij is zero if ti and tj are assigned to the same VM [31]. The data transfer time is calculated as follows [32]:…”

Section: Evaluation Metricmentioning

confidence: 99%

Optimized scheduling of scientific workflows based on iterated local search

Jihad

Al-Janabi

Yassen

2022

IJEECS

View full text Add to dashboard Cite

Recent years have witnessed a great interest in scientific applications with large data and processing-intensive, so cloud computing is used which provides the resources needed to implement and run these applications. One of the challenges in the management of scientific workflow applications is scheduling them to solve many combinatorial optimization problems, including reducing execution time, cost, resource utilization, and energy consumption. Due to the fact that the iterated local search algorithm (ILS) has been successfully applied to solve many combinatorial optimization problems, this paper investigates the performance of ILS in solving the scientific workflow scheduling problem which is a highly constrained problem. The main components that are different from one problem to others are the ILS parameters, local search, and perturbation, which must be carefully designed. The performance of the standard ILS has been examined and compared with the latest technology. The experimental results show that the proposed algorithm (ILS) obtained good results compared to the best-known results in the literature. This is due to the ILS being an adaptable metaheuristic, which can be simply adapted to diﬀerent search situations and instances.

show abstract

Section: Evaluation Metricmentioning

confidence: 99%