Answers are grounded in this paper and cite their sources.
Evaluates task allocation efficiency in LEO satellite networks, suggesting improved resource management.
This paper proposes a Deadline Based Resource Balancing (DBRB) task allocation algorithm for heterogeneous LEO small satellite networks, in which each satellite is equipped with one or more resources and limited power. So in the task allocation process, the dispatcher needs to consider the deadlines of the tasks as well as the balance of different resources. As the Map-Reduce program model is broadly adopted, a task in this network can consists of multiple subtasks. This paper schedules the subtasks based on both task deadline and resource balance. The DBRB algorithm is deployed on the head node of a cluster. It gathers the status from each cluster member and calculates their Node Importance Factors (NIFs) from the carried resources, residue power and compute capacity. The algorithm calculates the number of concurrent subtasks based on the deadlines, and allocates the subtasks to the lower NIFs first to balance the resources. The simulation results show that when cluster members carry multiple resources, resource are more balanced and rare resources serve longer in DBRB than in an Early Deadline First algorithm. We also analyze the resource balancing and average task finish time with different task deadline settings. And we show that the algorithm performs well in service isolation by serving multiple tasks with different deadlines. Moreover, the average task response time with various cluster size settings is well controlled within deadlines as well.
No takes yet. Share an insight, caveat, or question.
Qin et al. (2013) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: