Using AI for good: TELUS and Vector Institute partner to reduce climate impacts from data centres with new Energy Optimization System

TORONTO - TELUS and the Vector Institute, today announced the launch of the Energy Optimization System (EOS), a timely move that will help reduce operational costs and minimize electricity use in commercial buildings, namely data centres, across Canada. This collaborative development uses model-based reinforcement learning (MBRL) to fine tune the heating, ventilation, and air conditioning (HVAC) systems across network locations, allowing for energy-efficient temperature control.

Annually, an estimated 40 per cent of energy consumed across TELUS network locations is directed towards cooling telecommunications equipment, which is critical to maintaining optimal network performance. TELUS team members collaborated with the Vector Institute to build and test a solution to reduce this number and create a more sustainable use of HVAC equipment in 24/7 data centers.

By optimizing HVAC systems with this new AI technology, it is possible to achieve significant energy savings in data centres and other network locations, reducing the overall environmental impact. Results from a pilot test showed a decrease of almost 12 per cent in reduced annual electricity consumption in a small data centre.

“We wanted to find the most efficient opportunity for temperature control in data centres, one that considered both the environmental and economic costs, while also providing the best service for our customers,” said Jaime Tatis, Vice-president, Data Strategy and Enablement, TELUS. “Using MBRL to develop an AI agent that chose specific actions based on rewards, we were able to allow for quick learning by machines to create new effective and efficient policies for controlling HVAC systems.”

The algorithm also considers the weather forecast to make a decision when to run cooling (either more expensive compressor cooling or less expensive free cooling) or heating to ensure a consistent temperature and better regulate temperatures during shoulder seasons.

TELUS and Vector have elected to open source this new algorithm as a contribution to the energy conservation community, furthering commitments by both tech leaders to leverage AI to create better outcomes for Canadians and our environment.

“After three years of working on EOS with a focus on using AI for good, this partnership recognized the value of open sourcing the MBRL algorithm for cost reduction and to create efficiencies for other industries and organizations,” said Deval Pandya, Director of AI Engineering at Vector. “This is a brilliant example of how, together, our expertise in research and engineering can create value and make it easier to deploy leading AI research outcomes. Now we want to amplify the project’s value by open sourcing it for others to adopt.”

As a founding sponsor of the Vector Institute, TELUS has committed to using this partnership to advance the AI ecosystem across Canada, producing an economic boost and creating meaningful impacts with technology. As an example of responsible AI, this program is a demonstration of TELUS’ commitment to fostering innovation, while increasing trust with our customers by addressing privacy, security, and ethical risks.

To learn more visit: https://github.com/VectorInstitute/MBRL-HVAC-Energy-Optimization