Honeywell machine learning optimises buildings
- March 3, 2020
- imc

Honeywell has launched Forge Energy Optimization, a cloud-based, closed-loop, machine learning system that continuously studies a building’s energy consumption patterns and automatically adjusts to optimal energy saving settings without compromising occupant comfort levels.
This autonomous building system is focused on decreasing energy consumption, and could deliver double-digit energy savings, decrease a building’s carbon footprint, and be implemented without significant upfront capital expenses or changes to a building’s operational processes.
During a pilot at Hamdan Bin Mohammed Smart University (HBMSU) in Dubai, Honeywell demonstrated an initial ten per cent energy savings. HBMSU (pictured) is the first accredited smart university in the UAE and is known for its technology and innovation programmes.
Forge Energy Optimization was applied to HBMSU’s existing building management system, which uses different technology to demonstrate the platform’s open architecture and hardware-agnostic capabilities. The additional energy savings are significant because HBMSU is regarded as a smart, energy efficient building with fully connected lighting, cooling, building management, power and efficiency control that are optimised based on real-time occupancy. The pilot also uncovered local control issues with the chiller plant and fresh air handling unit that were not adjusting to set points.
“As a smart university, we look to deploy the latest technology across our campus and ensure our buildings are efficient,” said Mansoor Al Awar, chancellor of HBMSU. “We were pleasantly surprised by the results we saw from Honeywell Forge and its ability to drive further energy savings beyond our achievable optimisation with the techniques we have.”
He said that further partnership with Honeywell would help to support the advancement of artificial intelligence (AI) modelling for building automation and provide students with first-hand applications of how AI and machine learning could drive operational efficiencies in buildings.
“Buildings aren’t static steel and concrete,” said David Trice, vice president at Honeywell Connected Buildings. “They’re dynamic ecosystems and their energy needs fluctuate based on ever-changing variables like weather and occupancy. With Honeywell Forge Energy Optimization, we’re evolving building operations far beyond what would be possible even with a robust team of engineers and the rules they code in their building management system. By employing the latest self-learning algorithms coupled with autonomous control, we can help building portfolio owners fine-tune their energy expenditures to drive efficiencies and create more sustainable practices for our customers.”
Energy consumption in commercial buildings is a significant issue because these buildings account for more than 36% of global final energy consumption and nearly 40% of total direct and indirect CO2 emissions. Additionally, HVAC often presents the largest opportunity for energy savings in a commercial building.
Forge Energy Optimization autonomously and continually optimises a building’s internal set points across hundreds of assets every 15 minutes to evaluate whether a building’s HVAC system is running at peak efficiency. When it finds a need to make an adjustment, it analyses factors such as time of day, weather, occupancy levels and dozens of other data points to determine the optimal settings per building and makes calculated decisions 96 times a day for every building in a portfolio, 365 days a year across the system of assets. Repeated results have shown double-digit reductions of HVAC-related consumption while not impacting customer comfort.
Traditional HVAC controls incorporate varying levels of sophistication. The most basic involve static set points that don’t account for variable factors such as occupancy or weather. The second, and most common, rely on scheduled set-point adjustments using estimated occupancy and climate conditions. Finally, set points can be managed by a certified energy manager; however, most facilities have not found that this produces a viable return on investment due to the sheer volume of variables involved and the difficulty in producing accurate calculations in any scalable manner.
Forge Energy Optimization is said to be simple for building portfolio owners to deploy with plug-and-play capabilities. No changes to business mechanics are needed and there’s no need to rip and replace systems to add it to a building.








