The future of climate is at a crossroads. There is a growing awareness of the challenging targets of a 55% reduction in CO2 emissions by 2030 and total abatement by 2050.


The future of climate is at a crossroads. There is a growing awareness of the challenging targets of a 55% reduction in CO2 emissions by 2030 and total abatement by 2050.

The time to act is now

In recent years, the evolution of new technologies has made great strides: the Internet of Things and cloud solutions have been part of our surroundings for some time now. Although this development would suggest that the technology is widespread everywhere, the building management services sector is still far behind, whether the buildings are tertiary, industrial or apartments.

They work closely with European research centres to respond promptly to the various challenges posed by the European community itself in terms of innovation and sustainability of our cities.

Enerbrain’s R&D team works on the integration of technologies, in order to maximise energy efficiency on one hand, and on the other hand to make the solution more and more scalable.
The R&D team is composed of mathematicians, physicists, electronic engineers, energy engineers and computer scientists. The goal is to create a tightly-knit interdisciplinary team to develop energy-efficient solutions that are easily installed for immediate impact.

Innovating HVAC systems

Enerbrain’s research focuses specifically on the regulation of HVAC systems, because their consumption is a major component in the overall building consumption breakdown. This is particularly true in the non-residential sector, even if significant energy efficiency improvements have been made in recent years.

One of the main challenges related to the optimal management of HVAC systems is to manage the variance over time of variables such as indoor occupation or external temperature and weather conditions.

Therefore, researchers have focused their attention on innovative control strategies for HVAC systems that can maintain indoor thermal comfort conditions and, at the same time, reduce energy consumption. These strategies must also be able to manage signals from the electrical grid in order to meet power requirements and improve grid reliability and stability.

These opportunities have been provided by the introduction of smart Automated System Optimization (ASO) tools, which can contribute significantly to improving a building’s energy flexibility. Energy flexibility is a key characteristic of smart buildings that define their ability to adapt and respond to grid demands, weather conditions, and user needs.

The evolution of control algorithms

Today, PIDs are the most common lower-level control systems, while Rule-Based Controller (RBC) control is considered the standard for optimizing high-level management of HVAC systems, but the resulting energy savings are limited. Indeed, in RBC control, strategies are fixed and not scalable to different climate conditions or building characteristics, unable to predict changes in HVAC systems.

To overcome these limitations, the application of model-based control strategies has been explored in recent years. In particular, Model Predicted Control (MPC) has become the dominant control strategy in intelligent building operation research.

However, although the implementation of MPC has demonstrated its excellent ability to improve thermal comfort and reduce energy consumption, its model-based nature is a critical issue in some cases.

Indeed, a significant problem with MPC is related to the dependence of performance on a model definition for optimizing the control strategy, which is often difficult to design with good accuracy. In addition, it is difficult to generalise its use to different types of plants and buildings. As a result, MPC controllers have not been adopted as expected in the construction industry, despite promising results.

Research has also focused on the development of model-free controllers based on Machine Learning (ML), which has shown great potential for improving building performance, particularly when based on Reinforcement Learning (RL). Interest in RL-based control strategies is growing, and Enerbrain is contributing to research in this area.

Research projects we’re involved in


Help2Grow-Innovative technologies for cybernetic agricultural:

Help2Grow intends to introduce cybernetic agriculture for the farm of the future (Farm 4.0), proposing new technologies and renewable resources managed by AI algorithms to make farms more energy efficient and grow crops using fewer phytosanitary products.

Ongoing, March 2020-March 2022

PRISM-E, F.E.S.R. tender 2014/2020, Piedmont Regional Authority

Industrial partners: ATM SERVICE S.R.L.

Research institutes
Turin University – AGROINNOVA Centre; Turin Polytechnic – Department of Applied Science and Technology; University of Milano-Bicocca – Department of Materials Science


Accelerating Carbon Neutrality

AI4CITIES is an EU-funded Pre-Commercial Procurement (PCP) project, aiming to help cities accelerate their transition towards carbon neutrality. The project leverages AI solutions to reduce greenhouse gas emissions in the fields of mobility and energy, two domains responsible for 82% of all greenhouse gas emissions in European cities.

July 2021-ongoing

This is part of the AI4Cities project that has received funding from the European Union’s Horizon 2020 Research and Innovation Programme.


Smartness to existing Buildings

Smart2B is an EU-funded project, which aims to upgrade the smartness levels of existing buildings through coordinated control of legacy equipment and smart appliances. The goal is to enable smart buildings to interact with their occupants and the grid in real-time to fully exploit energy efficiency and local flexibility.

September 2021- ongoing

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 101004152.