Pool vs. Island Based Evolutionary Algorithms: An Initial Exploration

Abstract

Abstract-This paper explores the scalability and performance of pool and island based evolutionary algorithms, both of them using as a mean of interaction an object store; we call this family of algorithms SofEA. This object store allows the different clients to interact asynchronously; the point of the creation of this framework is to build a system for spontaneous and voluntary distributed evolutionary computation. The fact that each client is autonomous leads to a complex behavior that will be examined in the work, so that the design can be validated, rules of thumb can be extracted, and the limits of scalability can be found. In this paper we advance the design of an asynchronous, fault-tolerant and scalable distributed evolutionary algorithm based on the object store CouchDB. We test experimentally the different options and show the trade-offs that pool and island-based solutions offer.

Efficient training set use for blood pressure prediction in a large scale learning classifier system

“…Fernández de Vega et al [25] go through customizable execution environments for evolutionary computation using BOINC+ virtualization. Merelo et al [15] discuss pool vs. island based evolutionary algorithms. IslandSofEA uses separate clients and a pool, this scales best of their tested methods.…”

Analyzing distributed file synchronization techniques for educational data

“…Fig. 3 The functioning of Rsync algorithm [16] Performing backup to the different disk by using Rsync is as following [1]: #!/bin/sh export PATH=/usr/local/bin:/usr/bin:/bin LIST="rootfs usr data data2" for d in $LIST; do mount /backup/$d rsync -ax --exclude fstab --delete /$d/ /backup/$d/ umount /backup/$d done DAY=`date "+%A"` rsync -a --delete /usr/local/apache /data2/backups/$DAY rsync -a --delete /data/solid /data2/backups/$DAY COUCHDB CouchDB [17][18][19] is a NoSQL database revealed in April 2005 by Damien Katz. CouchDB is written in Earlang language and license of project belongs to Apache.…”

Multi-Population Parallel Wolf Pack Algorithm for Task Assignment of UAV Swarm

“…In this model, each sub-population and its corresponding optimization algorithm are integrated together as a node. In other words, every node includes not only the state of the subpopulation but also the algorithmic process, and it sends and receives the state of specific To improve the means of communication, the Pool model [59], shown in Figure 7, uses a central Pool to store the individuals and the Pool is accessible by all nodes. Each node interchanges individuals with the Pool, so the communication between nodes will not be affected when adding or removing nodes.…”

“…Besides, the lack of flexibility makes it more difficult to add or remove nodes at runtime. To improve the means of communication, the Pool model [59], shown in Figure 7, uses a central Pool to store the individuals and the Pool is accessible by all nodes. Each node interchanges individuals with the Pool, so the communication between nodes will not be affected when adding or removing nodes.…”

“…An improved Pool model [60] extends the capabilities of the Pool and decouples the state of the sub-population and the algorithm as shown in Figure 8. In this model, the state of all sub-populations is stored in the Pool and a sub-population, which is sent to the corresponding algorithm as a parameter, which is generated by taking random samples of To improve the means of communication, the Pool model [59], shown in Figure 7, uses a central Pool to store the individuals and the Pool is accessible by all nodes. Each node interchanges individuals with the Pool, so the communication between nodes will not be affected when adding or removing nodes.…”