The impact of time of use (ToU)-awareness in energy and opex performance of a cloud backbone

Cloud computing is becoming a leading edge business model by migrating the resources such as software, storage and platform to remote locations in the Internet cloud. Data centers, as the main hosts of these cloud services, receive massive amount of demands and transmit services towards Internet routers, consequently consuming enormous bandwidth in the downstream. Due to high computing power, as well as the cooling power, data centers contribute to a significant amount of the power consumption and the operational expenditures (Opex) of the data center operator. In the Internet backbone where the services are transported between the users and the data centers, IP routers make the dominating portion of the power consumption and Opex associated with the network operator. In this paper, we study the impacts of Time of Use (ToU)-awareness on the Opex and energy-efficiency of the cloud network by introducing a Mixed Integer Linear Programming (MILP)-based design scheme for the cloud backbone, which aims at minimizing the network and data center power consumption. Furthermore, the optimization scheme takes advantage of the varying ToU rates in different locations of the cloud network so that Opex is minimized for the network and data center operators. Numerical results approve that Opex savings through ToU-aware provisioning are at the expense of increased delay per demand. Furthermore, by the end of the day, power-minimized provisioning introduces more savings to the network operator as upstream data center demands are transported towards the data centers at the off-peak locations, which in return leads to higher utilization of network components in longer routes.