AI for Climate Change

Heating, ventilation, and air conditioning of buildings accounts alone for nearly 40% of the global energy demand. PLEASE CHECK FOOTNOTE [1]

The need for Energy Savings has become increasingly fundamental to fight Climate Change.

We have been working on a cloud-based RL algorithm that can retrofit existing HVAC controls to obtain substantial results.

In the last decade, a new class of controls which relies on Artificial Intelligence have been proposed. In particular, we are going to highlight data-driven controls based on Reinforcement Learning (RL) since they showed from the very beginning promising results as HVAC controls.

There are two main ways to upgrade with RL the air conditioning systems: to implement RL on new systems or retrofit the existing ones. The first approach is suitable for heating and air-conditioning systems, while the latter can be applied to any existing plant that can be controlled remotely.

We designed a Cloud-Based RL algorithm that continuously learns how to optimize power consumption by remotely reading the environmental data and defining the HVAC set-points. The cloud-based solution is suitable to scale to a significant number of buildings.

Our test demonstrated a reduction between 5.4% and 9.4% in primary energy consumption for two different locations, guaranteeing the same thermal comfort of state-of-the-art controls.

[1] Kindly provided by Paolo Magrassi:

Enrico Busto you may want to modify the premise of the article as it risks jeopardizing its credibility. By far and large it is not true that building HVAC "accounts alone for nearly 40% of the global energy demand."

Perhaps you have just <electricity> (not all energy) in mind: but even in that case, the number seems way off the mark. Generation of all electricity in the world (not just for buildings) is about 25% of global energy demand, and clearly only a (minor) part of that is for HVAC. Then buildings need another 6% for other uses... Please look up e.g. here https://www.epa.gov/ghgemissions/global-greenhouse-gas-emissions-data#Sector

Please read my full article on Medium: Reinforcement Learning to Reduce Building Energy Consumption.