University campuses face a significant challenge with their wired and dense WiFi networks always being powered on, leading to high energy consumption and carbon dioxide emissions. To tackle this issue, a novel energy-saving method has been developed that integrates machine learning and idle cycling techniques to reduce energy usage efficiently in both ethernet and wireless components of the network simultaneously.
By categorizing network devices into two groups – those constantly powered on and those that can be dynamically turned on or off based on network performance – two algorithms have been formulated to manage the operation of access points. Leveraging Ward’s machine learning hierarchical clustering technique, the model has been optimized for energy savings at the Unidades Tecnológicas de Santander in Bucaramanga, Colombia, showcasing the potential for substantial energy savings of up to 21.5 kWh per day.
This innovative approach not only addresses the pressing issues of high energy bills and environmental impact but also sets a precedent for a more sustainable and efficient campus network infrastructure. By harnessing the power of machine learning and smart operational strategies, universities can pave the way for a greener and cost-effective network ecosystem, ensuring a more sustainable future for all.
