The EFFICIENT Project
The EFFICIENT project is a two-years Italian PRIN research project, funded by the Italian Ministry of Education, University and Research (MIUR) and started in March 2010. It is coordinated by the Prof. Franco Davoli (University of Genova), and it includes five research units:
- the University of Genova,
- the Technical University of Torino,
- the University of Roma “La Sapienza”,
- the University of Pisa, and
- the University of Piemonte Orientale.
The concept of green and energy-efficient networking has begun to spread over the past few years, gaining increasing popularity and interest among service and network providers, as well as equipment manufacturers. Besides a more widespread sensitivity to ecological issues, such interest also springs from heavy and critical economical needs, since both energy cost and network electrical requirements show a continuous growth, with an alarming trend over the past years. For example, energy consumption of the Telecom Italia network in 2006 has reached more than 2TWh (about 1% of the total Italian energy demand), increasing by 7.95% with respect to 2005, and by 12.08% to 2004.
Another explanatory example is represented by British Telecom, which absorbed about 0.7% of the total UK’s energy consumption in the winter of 2007, making it the biggest single power consumer in the nation. Moreover, about 10% of the UK’s entire power consumption in 2007 was related to operating IT equipment.
Similar trends can be generalized to a large part of the other telecoms and service providers, since they essentially depend on data traffic volume increase and new services being offered. To support new generation network infrastructures and related services for a rapidly increasing customer population, telecoms and service providers need an ever larger number of devices, with sophisticated architectures able to perform more and more complex operations in a scalable way.
A widespread opinion is that the sole introduction of low consumption silicon elements may not be sufficient to effectively curb tomorrow’s network energy requirements. It is well known that networks, links and devices are provisioned for busy or rush hour load, which typically exceeds their average utilization by a wide margin. While this margin is generally reached rarely and over short time periods, the overall power consumption in today’s networks remains more or less constant with respect to different traffic utilization levels. Against such flat energy wastes, the specific challenge for telecoms, network equipment manufacturers and the networking research community nowadays mainly regards the introduction of innovative criteria and technologies, able to save energy by dynamically adapting network capacities and resources to current traffic loads and requirements.
Starting from these considerations, the EFFICIENT project will focus on innovative solutions, mechanism and architectures, able to disruptively boost the network energy efficiency and to explicitly control and manage energy saving by exploiting network-specific features.
The project will face the energy efficiency issue through three main research activities, which will aim to study and to develop:
- innovative mechanisms and architectures to reduce energy consumption in next generation network devices (e.g., sleeping/idle optimizations, power management mechanisms, smart buffering/shaping schemes, etc.);
- protocols, algorithms and policies for dynamic network planning and resource allocation that exploit traffic variation to reduce energy consumption;
- network and services’ dynamic virtualization.
With respect to the action (1), the idea is to introduce power management mechanisms (i.e., sleeping and rate adaptation mechanisms) inside equipment architecture. Viable approaches would include modular solutions able to optimize the trade-off between network performance and power consumption, by working at different timescales. For example, at larger timescales, the packet forwarding capacity of network devices might be adapted to meet expected traffic processing requirements dictated by incoming network/link load.
At smaller time-scales, packet burstiness would be exploited in order to operate the device in standby mode during inter-burst periods. The latter approach can be possibly enhanced with suitable packet caching/buffering policies for optimizing inter-burst times, and consequently for reducing the overall energy waste.
Regarding the network-wise control and planning (2), the interest is mainly focused on designing feasible algorithms, policies and protocol extensions able to reduce the overall network energy consumption. The basic idea is to turn off part of telecommunication links and devices, when the network is underloaded, so that, at any instant, the amount of resources active in a network is dynamically adapted to the actual need.
Finally, with respect to virtualization (3), the main idea is to exploit recent energy-efficiency advancements in virtualization technologies in order to dynamically reconfigure and to smartly migrate advanced network-level and application-level services among active network devices and servers.