Differential energy saving algorithms in a distributed router architecture

A distributed multistage software router (MSSR) is composed by several interconnected software routers running on personal computers (PCs). The MSSR architecture overcomes scalability and performance issues of single software router by providing parallel forwarding paths. Like many networking devices, a MSSR must be sized for peak traffic load, which implies energy inefficiency at low loads. Thus, we focus on energy saving schemes to improve the router energy efficiency by dynamically adapting the MSSR architecture to the currently offered load. We first introduce an optimal energy saving algorithm defined as a mixed integer linear programming (MILP) optimization model. Then, heuristic solutions, named differential algorithms are discussed. While the optimal approach provides higher energy savings, the heu-ristics avoid the complete MSSR reconfiguration, thus reducing forwarding delays and minimizing service interruption. The performance evaluation shows that the proposed heuristic algorithms, that gracefully modifies the internal MSSR configuration, preserve the load proportional energy demand characteristics of the optimal algorithm, with a minimal loss of efficiency, largely compensated by algorithm simplicity. Although ICT can make a major contribution to support energy savings and to face climate changes, it is responsible for roughly 2% of global carbon emissions – a figure close to the worldwide airline industry consumption. Since the ICT sector is growing at a faster rate [1], the CO 2 emission by ICT industry will reach an estimated of 6% by 2020 [2,3]. Telecom infrastructures and devices contribute to about 25% of the total ICT consumption. Today the energy consumption in networking devices is proportional to the installed capacity rather than to traffic demands. Thus, dynamically resizing the system capacity to match traffic demands may significantly enhance network energy efficiency. Distributed router architectures, being composed by many independently powered components, are perfectly suited to provide the flexibility needed to dynamically resize the router architecture to match input traffic demands. This research work focuses on the problem of reducing the energy consumption of distributed router architectures, with emphasis on a multistage software router (MSSR) architecture [4] shown in Fig. 1. The MSSR architecture is a distributed software router architecture proposed to overcome single PC-based software router performance limitations. The main benefits of the MSSR architecture, discussed in [4], include scalability, flexibility, pro-grammability, enhanced performance and low cost. The architecture exploits classical PCs as elementary switching elements to build a high-performance software router (SR). The MSSR architecture is organized in three stages: (i) a front-end stage …