Arloid using AI to optimise HVAC performance

2136 0

Technology said to reduce energy use by up to 30%, using AI to intelligently and precisely adjust HVAC system settings

Arloid Automation, based in London, Dubai and Singapore, is using artificial intelligence (AI) to help reduce energy consumption in buildings. The company’s technology optimises the performance of existing building management and HVAC systems by learning what is required for optimum comfort and efficiency.

Arloid builds a ‘Digital Twin’ that takes into account construction materials, occupancy rates, pollution levels, past, present and predicted weather data, and thermal zones.

Once the digital model is complete the AI can begin to learn. gathers live data on the correct responses to an array of changing conditions and occupancy levels. It runs 300,000 iterations to calibrate the model and learn about the building’s thermal behaviour. Optimum settings can then be found for each microzone to reduce energy, coolant and carbon emissions. According to Arloid, savings of up to 30% can be seen in just 60 days.

Arloid Automation is looking to remove the financial barriers for its service by implementing the process with no upfront costs. Instead, a fee is agreed from the resultant savings and if there are no savings then there is no fee. uses Deep Reinforcement Learning to automatically manage the operation of HVAC systems in a wide range of buildings via a secure Virtual Private Network (VPN). It then makes decisions based on reinforcement behaviour and real-time data to provide faster optimisation and better HVAC performance.

By controlling each HVAC device in the system and dividing the building into distinct heating and cooling micro-zones, is designed to provide more control of the environment and better user comfort.