A review of swarm intelligence algorithms deployment for scheduling and optimization in cloud computing environments

Abstract

Background This review focuses on reviewing the recent publications of swarm intelligence algorithms (particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony (ABC), and the firefly algorithm (FA)) in scheduling and optimization problems. Swarm intelligence (SI) can be described as the intelligent behavior of natural living animals, fishes, and insects. In fact, it is based on agent groups or populations in which they have a reliable connection among them and with their environment. Inside such a group or population, each agent (member) performs according to certain rules that make it capable of maximizing the overall utility of that certain group or population. It can be described as a collective intelligence among self-organized members in certain group or population. In fact, biology inspired many researchers to mimic the behavior of certain natural swarms (birds, animals, or insects) to solve some computational problems effectively. Methodology SI techniques were utilized in cloud computing environment seeking optimum scheduling strategies. Hence, the most recent publications (2015–2021) that belongs to SI algorithms are reviewed and summarized. Results It is clear that the number of algorithms for cloud computing optimization is increasing rapidly. The number of PSO, ACO, ABC, and FA related journal papers has been visibility increased. However, it is noticeably that many recently emerging algorithms were emerged based on the amendment on the original SI algorithms especially the PSO algorithm. Conclusions The major intention of this work is to motivate interested researchers to develop and innovate new SI-based solutions that can handle complex and multi-objective computational problems.

Stochastic Komodo Algorithm

“…KMA is also a swarm intelligence. As a swarm intelligence, there are certain number of agents (Komodo) that act autonomously to find a near-optimal or sub-optimal solution within the problem space [21]. Although each agent acts autonomously, there is collective intelligence that is shared among them [21].…”

“…As a swarm intelligence, there are certain number of agents (Komodo) that act autonomously to find a near-optimal or sub-optimal solution within the problem space [21]. Although each agent acts autonomously, there is collective intelligence that is shared among them [21]. But in KMA, this swarm intelligence is hybridized with evolutionary intelligence, where better solutions are produced by combining some selected previous solutions.…”

Hybrid Pelican Komodo Algorithm

“…This algorithm consists of a certain number of agents (pelicans). As a swarm intelligence, collective intelligence is used or shared among the pelicans [22]. In this algorithm, the randomized target represents collective intelligence.…”

https://inass.org/wp-content/uploads/2022/05/2022083131-2.pdf

“…This algorithm consists of several autonomous agents that find a better solution in every iteration. This algorithm is also a swarm-based intelligence where collective intelligence is shared among agents [27]. In this context, this collective intelligence is the best and worst solution.…”