A greedy algorithm for load balancing jobs with deadlines in a distributed network

Abstract

One of the most challenging issues when dealing with distributed networks is the efficiency of jobs load balancing. This paper presents a novel algorithm for load balancing jobs that have a given deadline in a distributed network assuming central coordination. The algorithm uses a greedy strategy for global and local decision making: schedule a job as late as possible. It has an increased overhead over other well-known methods, but the load balancing policy provides a better fit for jobs.