Energy efficiency in HVAC systems through AI technology

Rohit Kochar, Founder, Executive Chairman & CEO, Bert Labs

Commercial buildings have HVAC (Heating, Ventilation, Air Conditioning) systems that help to keep the premises at a comfortable atmospheric condition by maintaining the temperature and relative humidity. These HVACs consume high amount of power and any reduction in this can benefit the industry, not only in cost savings but also moving to being a green building and achieving their sustainability goals.

The existing Building Management Systems are effective to certain extent in maintaining the atmosphere in the building and also improve the energy efficiency. This alone will not be sufficient to meet the mandate for zero carbon. The new age BMS has to be Artificial Intelligence (AI) handled, Machine Learning (ML) enabled and IoT equipped to address sustainability, energy management and decarbonization issues for the commercial building. AI technology can build on top of the existing BMS infrastructure and start giving benefits immediately on deployment. If there is no BMS system in place and everything is manually controlled, then IoT technology combined with AI can provide seamless automated controls.

The crucial thing required for AI is data. The challenge for AI companies is to get quality data with high granularity for them to build models for Air Handling Units (AHUs), chillers and other equipment that form part of HVAC system. A hybrid model of first principles physics-based modelling combined with data-based machine learning models can bridge the gap of data not available to great extent. Through this a Digital Twin of the each of equipment in HVAC, like AHU, chiller can be built. This is an accurate prediction model that predicts, for e.g., the AHU operational parameters in the next instance and in the future. An integrated HVAC model is built combining the high side and low side. Once the future state is known, powerful AI models can work on the predicted state and build an optimization strategy for achieving the energy efficiency and in turn reduce carbon footprint.

It is critical for real estate/property companies to build their digital transformation infrastructure and adopt AI into their routine practice. It brings about seamless uninterrupted automated execution bringing about energy optimization, thereby saving cost. Digital transformation infrastructure should (a) Sense i.e., real time capture of high granularity, high coverage, high quality, high variety, high volume of all relevant monitoring and controllable data points, operational, health, energy of process and utility equipment data.  IoT devices can capture the real time temperature and humidity and provide data for fine control of the HVAC. (b) Connect i.e., real time transmission of upstream and downstream data with no cost towards control and network cables and (c) Act i.e., real time actuation of control commands, along with centralized location for real time and historical data storage, real time data processing for business intelligence and report generation & highly interactive, intuitive visual analytics. The beauty of centralized data repository is that it can store all the data that is generated and can provide integrated energy dashboards and reports customized to the end stakeholder like a Property Manager, Facility Supervisor, CEO/CXO.

The AI models deployed on the HVAC system learns continuously from the real time data and improves its performance over the years. Thus, the company continues to benefit and can see reduction in energy consumption, achieve sustainability goals. Thus, it is the right time now for all real estate/commercial building companies to invest in AI technologies which can provide both the digital infrastructure and the AI technology that can make a huge impact in its objective to 'Go Green'. The early adopters of this technology stand to gain immensely and will have a great first mover advantage in this highly competitive sector.

Case Study-1: AI in airport building

Airports are always bustling with activity 24 hours a day on all days, and the HVAC systems have to continuously be on uptime and maintain the required environment for giving the passengers and airport community the best in thermal comfort. AI powered Digital Twins for airport AHUs, chillers, VAVs and other equipment give accurate prediction up to 97% of output parameters like air flow rates, supply water temperature, return air temperature, relative humidity, etc. The Reinforcement Learning Agent Optimization Algorithm will use the predicted values and give the best combination of control parameters like fan speed, chilled water valve, primary, secondary and condenser water flow, etc to maintain the required environment in the airport and reduce the energy consumption of HVAC. The results are savings of 30% on electricity.

Case study-2: AI in hotel building

HVAC systems in hotels are very critical. It is essential that the systems are running at their best to maintain the customer comfort. Energy efficiency many times gets compromised for the patron's thermal comfort. But AI/IoT technologies can achieve both objectives. AI powered Digital Twins for hotel AHUs, chillers, cooling towers and other equipment give accurate prediction up to 97% of output parameters like air flow rates, real time heat load, return air temperature, chilled water flow, etc. The Reinforcement Learning Agent Optimization Algorithm will use the predicted values and give the best combination of control parameters like fan speed, chilled water set points and chilled water valve opening, primary, secondary and condenser water flow, etc to maintain the required environment in the hotel and reduce the energy consumption of HVAC. The results are savings of 40% on electricity.

Case study-3: AI in office complex

Office complexes have peak activity during weekdays and less during nights and weekends. HVAC are required to adjust their operating parameters considering the heat load. AI powered Digital Twins for building AHUs, chillers, TFA and other equipment give accurate prediction up to 97% of output parameters like air flow rates, return air temperature, supply water temperature, relative humidity, zone temperature etc. The Reinforcement Learning Agent Optimization AHU fan speed, chilled water valve, primary, secondary and condenser water flow etc to maintain the required environment in the office complex and reduce the energy consumption of HVAC. The results are savings of 50% on electricity.

There is great opportunity in the real estate sector to reduce energy consumption while also reducing environmental impact through AI technologies. The impact on the energy efficiencies of HVAC systems in commercial buildings/properties range from 30% to 50% reduction and thus help companies in their sustainability journey for achieving carbon footprint reduction targets and green transition.

Hits: 28