# Implementing energy saving algorithms for Ethernet link aggregates with ONOS

## TL;DR

This paper demonstrates how SDN capabilities via ONOS can implement energy-saving algorithms for Ethernet link aggregates, dynamically adapting traffic to reduce power consumption by utilizing Low Power Idle states.

## Contribution

It introduces an ONOS application that enables energy-aware traffic scheduling for Ethernet bundles, leveraging SDN to improve energy efficiency in telecommunication networks.

## Key findings

- The application effectively adapts to traffic patterns.
- It reduces energy consumption by consolidating traffic.
- Unused ports remain in Low Power Idle mode.

## Abstract

During the last few years, there has been plenty of research for reducing energy consumption in telecommunication infrastructure. However, many of the proposals remain unim-plemented due to the lack of flexibility in legacy networks. In this paper we demonstrate how the software defined networking (SDN) capabilities of current networking equipment can be used to implement some of these energy saving algorithms. In particular, we developed an ONOS application to realize an energy-aware traffic scheduler to a bundle link made up of Energy Efficient Ethernet (EEE) links between two SDN switches. We show how our application is able to dynamically adapt to the traffic characteristics and save energy by concentrating the traffic on as few ports as possible. This way, unused ports remain in Low Power Idle (LPI) state most of the time, saving energy.