Energy aware anycast routing in optical networks for cloud computing applications

Abstract

Optical networks are emerging as attractive candidates capable of meeting the computing, storage and highspeed data transfer needs of current and future cloud based applications. There has been much focus, in recent years, on the development of “green” techniques that reduce the energy consumption of the computing and storage facilities at the network nodes. However, it is becoming increasingly important to consider the energy overhead incurred in the process of transmitting large amounts of data over the network. Energy aware design techniques for optical networks, which is expected to be the fundamental infrastructure for cloud computing, should be developed to reduce the power requirement for these core networks. In cloud based systems, a request can often be serviced at one of several possible destination nodes. This is known as anycasting, and in this paper we propose a new approach for energy aware resource allocation in optical networks that exploits the inherent flexibility of anycasting. We consider dynamic lightpath allocation and present a new integer linear program (ILP) formulation that selects the destination node and performs routing and wavelength assignment (RWA) in an integrated manner to minimize the overall energy consumption. Simulation results clearly demonstrate that properly exploiting the anycast principle can lead to significant energy savings, not only compared to traditional energy-unaware RWA techniques but also over energy-aware unicast methods.