Algorithms for efficient data management of component-based applications in cloud environments
Faculty of Sciences. Mathematics and Computer Science
New york :Ieee
2014 IEEE NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM (NOMS)
14th IEEE/IFIP Network Operations and Management Symposium (NOMS), MAY 05-09, 2014, Krakow, POLAND
, p. 1-8
, 8 p.
University of Antwerp
Cloud environments face a growing demand for application hosting, and applications consisting of multiple data-sources and storage components. The need to ensure service level agreements for these types of applications creates important challenges for cloud infrastructure providers. The main contribution of this paper is an optimal cost-effective model and two algorithms to map component-based data oriented applications to cloud platforms. The first algorithm is based on an Integer Linear Programming formulation and minimizes an objective function, taking into account the capacities of the available nodes and links, as well as the customer requirements. This algorithm is able to obtain the optimal solution, but shows a limited scalability. For this reason a heuristic algorithm is designed to solve the scalability issue. The experimental results thoroughly compare the execution times and obtained node usage for both algorithms.