Institutions | About Us | Help | Gaeilge
rian logo

Go Back
GeNePi: a multi-objective machine reassignment algorithm for data centres
Saber, Takfarinas; Ventresque, Anthony; Gandibleux, Xavier; Murphy, Liam
Data centres are facilities with large amount of machines (i.e., servers) and hosted processes (e.g., virtual machines). Managers of data centres (e.g., operators, capital allocators, CRM) constantly try to optimise them, reassigning `better' machines to processes. These man- agers usually see better/good placements as a combination of distinct objectives, hence why in this paper we de ne the data centre optimisa- tion problem as a multi-objective machine reassignment problem. While classical solutions to address this either do not nd many solutions (e.g., GRASP), do not cover well the search space (e.g., PLS), or even can- not operate properly (e.g., NSGA-II lacks a good initial population), we propose GeNePi, a novel hybrid algorithm. We show that GeNePi out- performs all the other algorithms in terms of quantity of solutions (nearly 6 times more solutions on average than the second best algorithm) and quality (hypervolume of the Pareto frontier is 106% better on average).
Keyword(s): data centres; machine reassignment; evolutionary algorithms; multi-objective optimisation
Publication Date:
Type: Conference item
Peer-Reviewed: Yes
Language(s): English
Institution: University of Limerick
Funder(s): Science Foundation Ireland
Citation(s): 9th International Workshop on Hybrid Metaheuristics [Lecture Notes in Computer Science];8457, pp. 115-129
Publisher(s): Springer
First Indexed: 2015-03-18 05:43:20 Last Updated: 2019-09-19 06:26:32