In this paper, we present a novel Multi-Objective Ant Colony System algorithm to optimize Cost, Performance, and Reliability (MOACS-CoPeR) in the cloud. The proposed algorithm provides a metaheuristic-based approach for the multi-objective cloud-based software component deployment problem. MOACS-CoPeR explores the search-space of architecture design alternatives with respect to several architectural degrees of freedom and produces a set of Pareto-optimal deployment configurations. Two salient features of the proposed approach are that it is not dependent on a particular modeling language and it does not require an initial architecture configuration. Moreover, it eliminates undesired and infeasible configurations at an early stage by using performance and reliability requirements of individual software components as heuristic information to guide the search process. We also present a Java-based implementation of our proposed algorithm and compare its results with Non-dominated Sorting Genetic Algorithm II (NSGA-II). We evaluate the two algorithms against a cloud-based storage service, which is loosely based on a real system. The results show that MOACS-CoPeR outperforms NSGA-II in terms of number and quality of Pareto-optimal configurations found.
Adnan Ashraf, Benjamin Byholm, Ivan Porres (Åbo Akademi University): Towards a Multi-Objective ACS Algorithm to Optimize Cost, Performance, and Reliability in the Cloud.