Modern buildings consume significant amounts of electricity through air conditioning systems. However, many conventional setups rely on static schedules or simple rule-based controls that do not adapt to dynamic factors such as external weather, occupancy, or usage patterns. This often results in higher energy costs, reduced occupant comfort, and unnecessary wear on air conditioning equipment - highlighting the growing need to improve aircon energy efficiency across facilities.
To address these challenges, the technology owner has developed an advanced air-conditioning optimisation system that leverages real-time sensor data, weather forecasts, and machine learning to dynamically regulate operations. The system features intelligent temperature detection that maintains an optimal balance, neither too cold nor too hot, while automatically controlling air-conditioning and heating in real time, thereby improving aircon energy efficiency, supporting ESG practices, and ensuring a consistently comfortable indoor environment.
Designed for seamless installation and operation via a user-friendly interface, the solution is suitable for both small-scale users and large facilities managing multiple air conditioning systems. When integrated with central air control systems, it reduces manual workload for operators while optimising energy use across entire buildings. Successfully deployed in retail stores, offices, and warehouses in Korea, the technology has demonstrated proven value across diverse environments.
The technology owner is seeking industrial partners for test-bedding and adoption of their AIoT solution. They are also keen to collaborate with HVAC companies and air handling unit (AHU) manufacturers to co-develop integrated solutions that create win-win opportunities and drive sustainable growth.
Key technical features of this solution include:
Integrated Hardware and Software: Consists of a hub, controller, and sensors, powered by an AI engine and operating system that enable intelligent management of air-conditioning units
Human-Centric Sensing: Unlike conventional systems, the sensor captures temperature and humidity data directly around occupants, ensuring comfort is monitored and managed where it matters most
Comprehensive Data Inputs: Integrates both indoor sensor data and external weather forecasts, referencing inputs from the nearest outdoor weather station
Predictive, Data-Driven Control: Utilises machine learning to predict changes in indoor temperature, humidity, and heat load. The system determines the optimal operation strategy of air conditioners, such as which units to activate, set-point temperatures, modes, and wind speeds, to maintain stable indoor comfort
["Automated Operation","Optimization","Improving System","Intelligence","Decision Making","Energy Saving","Digitalization","Management"]