A New Social Volunteer Computing Environment With Task-Adapted Scheduling Policy (TASP)

摘要

Volunteer computing (VC) has become a relatively mature technique of distributed computing. It is based on exploiting the idle time of ordinary online machines with the consent of their owners. Target applications are generally scientific projects requiring a huge amount of computational resources. Existing VC platforms raise several challenges. This work attempts to bring solutions for two defeats. The first one is the involvement of volunteers; the decreasing of participants affects the global performances. To cope with this, a new social volunteer computing environment is proposed in order to involve more volunteers. The second addressed problem is the task scheduling, which aims to optimize the use of resources. The proposed algorithm generates for each resource's class, a number of tasks whose cost of execution reflects the momentary capacity of the resources. The new solutions are validated through a theory of number's project, called “Collatz Conjecture.”.