Power-aware routing in networks with delay and link utilization constraints

Abstract

Current network infrastructures are over-provisioned and thus exhibit poor power efficiency at low traffic load. In this paper, we consider networks comprising of bundled links, whereby each link has one or more physical cables that can be switched off independently. The problem at hand is then to switch off redundant cables during off peak periods, while retaining the QoS provided to existing traffic demands. Unfortunately, the problem to maximally shutdown redundant cables is an NP-complete problem. Henceforth, we design a fast heuristic, called Multiple Paths by Shortest Path First (MSPF), that aims to maximize the number of switched-off cables subject to satisfying maximum link utilization (MLU) and end-to-end delay requirements. We have extensively evaluated the performance of MSPF on both real and synthetic topologies and traffic demands. Further, we have compared its performance against two state-of-the-art techniques: GreenTE usable only when each link has one cable, and FGH that supports bundled links but usable only for networks without MLU and delay constraints. MSPF improves the energy saving on average by 5% as compared to GreenTE incurring only 1% the CPU time. While yielding equivalent energy savings, MSPF requires only 0.35% of the running time of FGH. Finally, for MLU at most 50% and end-to-end delay no longer than the network diameter, MSPF reduces the power usage of the GÉANT topology up to 91% and bundled links consisting of ten cables.

On the effects of energy-aware traffic engineering on routing reliability

“…With respect to the MIP, for SSPF, the flow in (2) is routed through only one path. Specifically, Equation (2) is replaced with the following constraint: (6) where is a binary variable that is set to 1 (0) when the traffic d is routed (not routed) through link (i, j); see [26] for more detail explanation. With respect to the MIP, TLDP ignores constraint (4), but includes constraint T max -the percentage of the total number of paths that have at least one two link-disjoint paths.…”

“…GreenTE aims to produce G' by turning off the maximum number of links from G such that all traffic in D are satisfied, each link has utilization no more than 50%, and each demand is re-routed through one or more paths with hop counts no longer than a given constraint. The MSPF solution [26] generalizes FGH and GreenTE; it considers bundled links similar to FGH as well as the two constraints used in GreenTE.…”

“…In [28], when a demand cannot be rerouted using a single path, the authors propose to reroute it using two-link disjoint paths to improve its throughput and fault tolerance. Note that the multiple paths used in FGH, GreenTE and MSPF [17,18,26] may not be linkdisjoint. While all solutions [17,18,26,27,28] are able to turnoff significant number of redundant links/cables to reduce power consumption, none of them reported their impact on network reliability.…”

“…Henceforth, this paper studies the impact of switching off cables using five recent energy-aware routing mechanisms, namely FGH, GreenTE, MSPF, SSPF, and TLDP [17,18,26,27,28], on two reliability measures, i.e., 2-terminal reliability and path reliability. The first reliability measures the probability of obtaining at least one operational path that can be used for route restoration in case of link failures, while the second computes the reliability of each path used to route traffic.…”

Energy-aware traffic engineering with reliability constraint

“…To this extent, many green solutions [6][7][8][9][10][11] have been proposed to reduce the energy consumption of networks. Of particular interest are approaches such as [6] that consider line cards that have active/idle toggling capability, and are connected by multiple physical cables.…”