A Genetic Algorithm for Dynamic Cloud Application Brokerage

Cloud Service Brokers (CSBs) may abstract complex resource allocation decisions for efficiently mapping demands of tenants into offers of providers. Nowadays, both demands and offers could be considered in dynamic environments, representing particular challenges in cloud computing markets. This work studies a broker-oriented Virtual Machine Placement (VMP) in dynamic environments such as: (1) variable resource offers and (2) pricing, from providers and (3) dynamic requirements of tenants. A genetic algorithm is proposed for an efficient and scalable resolution of the considered problem. Experimental results demonstrate good quality of solutions obtained by the proposed algorithm when compared to a state-of-the-art Integer Linear Programming (ILP) algorithm. Additionally, experimental results also demonstrate the good level of scalability of the proposed algorithm for large instances of the considered problem.

[1]  Johan Tordsson,et al.  Cloud brokering mechanisms for optimized placement of virtual machines across multiple providers , 2012, Future Gener. Comput. Syst..

[2]  Benjamín Barán,et al.  A Virtual Machine Placement Taxonomy , 2015, 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing.

[3]  Johan Tordsson,et al.  Modeling for Dynamic Cloud Scheduling Via Migration of Virtual Machines , 2011, 2011 IEEE Third International Conference on Cloud Computing Technology and Science.

[4]  Benjamín Barán,et al.  Multi-objective Virtual Machine Placement with Service Level Agreement: A Memetic Algorithm Approach , 2013, 2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing.

[5]  David E. Goldberg,et al.  Genetic algorithms and Machine Learning , 1988, Machine Learning.

[6]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.