Dynamic Load Balancing Inspired by Cemetery Formation in Ant Colonies

Abstract

Loosely connected distributed computing systems present a changing environment to the programs that they execute. Dynamic load balancing (DLB) algorithms are employed to address the problem of relocating tasks when parts of a distributed computing system become unavailable while other parts become idle. This paper presents a novel DLB algorithm based on cemetery formation in ant colonies. The algorithm builds on previous work to formulate ant-inspired DLB algorithms that aim to reduce the time needed to complete the parallel execution of multiple, independent tasks, where resources as well as tasks are diverse with respect to their performances and durations, respectively. The new algorithm is compared with its predecessors, based on division of labour in ant colonies, and pure, opportunistic load balancing, established as the baseline.