Data Center Network Design for Internet-Related Services and Cloud Computing

Abstract

We study an integrated data center network design problem for Internet-related services and cloud computing, of which the objective is to minimize total operating cost and service delay penalty by optimizing data center location, footprint allocation, and resource provisioning decisions, while incorporating essential features such as latency, power, multiple resources, configuration limits, and interdependent footprints. We formulate the optimal design problem as a nonlinear mathematical program. We analyze a queueing model to approximate the service latency and provide tractable reformulations. We further develop Lagrangian relaxation methods and generate strengthening cuts by exploiting the structural properties of the problem to enhance computational efficiency for large-scale problems. Our numerical studies demonstrate that the proposed integrated model, which jointly optimizes location, allocation, and resource provisioning, can significantly reduce cost and improve quality-of-service when compared with a hierarchical approach that optimizes these decisions sequentially. Moreover, our proposed solution methods outperform state-of-the-art commercial software in computational performance. Based on real-world data sets, the proposed model selects data centers that have been chosen by major cloud computing infrastructure providers. We also draw managerial insights that can be used as design guidelines in practice.