Cloud-based Evolutionary Algorithms: An algorithmic study

TL;DR

This paper investigates how cloud-based and asynchronous evolutionary algorithms perform on difficult problems, focusing on load-balancing and speed improvements in distributed settings.

Contribution

It provides an empirical analysis of the impact of load-balancing and asynchrony on the performance of cloud-based evolutionary algorithms.

Findings

Load-balancing improves evaluation speed.

Asynchrony enhances problem-solving efficiency.

Distributed algorithms scale well with multiple computers.

Abstract

After a proof of concept using Dropbox(tm), a free storage and synchronization service, showed that an evolutionary algorithm using several dissimilar computers connected via WiFi or Ethernet had a good scaling behavior in terms of evaluations per second, it remains to be proved whether that effect also translates to the algorithmic performance of the algorithm. In this paper we will check several different, and difficult, problems, and see what effects the automatic load-balancing and asynchrony have on the speed of resolution of problems.