Minimum outage probability provisioning in an energy-efficient cloud backbone

Cloud computing offers the flexibility of accessing to a shared pool of resources based on the pay as you go fashion. Data centers, being the main hosts of cloud services, play the key role in the delivery of cloud services while energy consumption and resiliency are two main drivers of the operational expenses of the operators. In this paper, we consider the interconnection of cloud data centers over a wide area network, namely the US National Backbone, via IP over elastic optical transport medium. Initially, we present a numerical model to analyze the outage probability of various demand types such as down-stream data center, upstream data center and data center-to-data center demands. Then, we propose two provisioning schemes, namely, Minimum Outage Probability Provisioning (Min-OPP) and Resilient Provisioning with Minimum Power Consumption (RPMPC) where the latter is an extension of the former incorporating energy-awareness. Through numerical results, we show that energy-awareness in the resilient design reduces the power consumption in the cloud backbone by approximately 7% when compared to Min-OPP with significantly lower (45%~97%) outage probabilities for data center demands when compared to a naïve energy-minimized provisioning. Furthermore, RPMPC introduces shorter path delays which are not higher than those introduced by Min-OPP.