Air conditioning (AC) is the most effective means for the cooling of indoor space. However, its increased global use is problematic. Earth is getting hotter. All these HVAC (Heating, Ventilation and Air Conditioning) units increase greenhouse gas emissions through excessive energy use, but they also leak hydrofluorocarbons (HFCs), which are thousands of times more potent that carbon dioxide.
Now companies utilizing self-adapting artificial intelligence to proactively optimize the energy consumption of one of the largest climate change contributors: Buildings. They offer a unique technology combining deep learning, cloud-based computing and autonomous decision making to support a 24/7 self-operating building. This solution enables the HVAC system in a building to operate autonomously, in real-time, generating up to a 25% reduction in total energy costs, 20-40% reduction in carbon footprint and 60% increase in occupant comfort.
HVAC structures are still designed as fixed systems, or programmed for a fairly static environment, even though the weather and seasons are fluid and dynamic. This static organization is costly, both for business – since inefficient systems can contribute to higher energy bills and maintenance costs – and the environment. In fact, HVAC systems account for 51% of the total energy usage in commercial buildings. Inefficient and poorly managed systems are also responsible for occupant discomfort and a major contributor to rising levels of greenhouse gases.
This system is designed to deliver significant savings and dramatically reduce carbon emissions. HVAC systems account for 45% of total energy usage in commercial buildings. Inefficient and poorly designed systems are costly to manage, often ineffective at maintaining comfort levels and major producers of greenhouse gases. Now, commercial real estate operators can move from reactive to pre-emptive operations management of their buildings.
Smartly being use deep learning, cloud-based computing, algorithms and a proprietary process to support a 24/7 self-operating building that requires no human intervention and enables maximum energy efficiency. Pre-commercialization tests have demonstrated that enables a 25-35% reduction in total energy costs in less than three months, with low to no CAPEX needed from property owners. It also improves occupant comfort by 60% and decreases the carbon footprint of a building by 20-40%. This is actually very magical.
This technology optimizes a building’s existing HVAC system by analyzing information from a multitude of internal and external data points, combining time series data with deep learning engines and deriving high-quality predictions for each zone of the building. This enables it to make exceptionally accurate predictions about the built environment, empowering the deployment of algorithms to drive the HVAC system in real time. The combination of highly precise AI predictions, as well as advanced algorithms (that are based on the knowledge of mechanical engineers and control experts), delivers continuous commissioning at a fraction of the cost of manual, human interventions.
The result is a 24/7 self-operating building that requires no human intervention and functions at optimal efficiency and ensures maximum comfort.
As part of its technology development process, BrainBox AI company is partnering with the National Renewable Energy Laboratory (NREL), an organization funded by the United States Department of Energy that focuses on the development of creative answers to today’s energy challenges. To effectively map out a building’s HVAC control points and ensure all data labels used follow Haystack conventions. NREL and BrainBox AI are working together for the development of an automapping AI tool which is being referred to as Autobots. This new AI tool should accelerate the deployment time of the solution throughout buildings, reducing the onboarding time and generating a clean dataset from day one.
Future of HVAC control
Over the last couple of years, we’ve witnessed an explosion in the market of analytics solutions (FDD, EIS, EMIS, etc.) using AI, and other data analysis techniques, to generate insights for building managers. This technology wave pushed data handling and formatting to the forefront, and it became a trending topic of interest. Thanks to the Haystack initiative, we are now making good progress on that front. The same data is currently being utilized for many new purposes, moving from the sharing of insights to enabling AI to operate a building’s HVAC system in real time. This is the first step towards a real autonomous building. As the car industry advances from the GPS to the self-driving car, our industry is starting to shift as well. It is evolving from a fix control sequence to an autonomous control sequence, thus dynamically changing the control sequence code every minute and learning as it evolves in time without any human intervention.