An SDN Focused Approach for Energy Aware Traffic Engineering in Data Centers.

Area of Science:

• Computer Science
• Electrical Engineering
• Environmental Science

Background:

• Information Communication Technologies (ICT) industry faces pressure to reduce CO2 emissions.
• Data Centers (DCs) are significant energy consumers within service provider networks.
• Optimizing network device operation is key to reducing DC energy usage.

Purpose of the Study:

• To develop and verify an algorithm for optimizing power consumption in network devices within DCs.
• To implement energy-aware traffic engineering for reduced energy demands.
• To demonstrate the feasibility of deploying such an algorithm in production environments.

Main Methods:

• Developed a mixed integer programming (MIP) algorithm.
• Applied the algorithm to optimize power consumption in network devices.
• Verified the approach through simulations of DC network topologies.

Main Results:

• Demonstrated clear benefits in power consumption reduction.
• Achieved significant gains across various network sizes and traffic volumes.
• Algorithm showed potential for practical implementation.

Conclusions:

• The developed MIP algorithm effectively optimizes DC network device power consumption.
• Energy-aware traffic engineering is a viable strategy for reducing ICT's environmental impact.
• The algorithm's compatibility with Software-Defined Networking (SDN) facilitates production deployment.