This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies. For more information, See our Privacy and Cookie Policy.
This function is disables on your cookie management.
To activate it, click on the link "Edit cookie settings" in the upper
right corner of this page.
LG.com Cookies
We use cookies to offer you a convenient web browsing experience, to suggest personalized ads for you, and to keep improving functions through traffic analysis.
By clicking on ‘ACCEPT ALL’, you consent to our use of cookies. Click ‘Cookie Settings’ to choose whether to accept or disable certain cookies. To find out more, please read our Privacy Policy. | Cookie Settings
These cookies are used to provide you with convenient functions, such as product reviews and product video playback, during your web browsing.
These cookies allows our website to keep improving functions through website traffic analysis and to suggest personalized content for you.
These cookies enable us to show you ads and other content that we think is most attuned to your interests and digital behavior.
This function is disables on your cookie management.
To activate it, click on the link "Edit cookie settings" in the upper
right corner of this page.
9/1/2025
1/9/2025
2025/09/01
The URL has been copied to the clipboard.
Institut Teknologi Bandung (ITB), one of Indonesia’s leading engineering universities, partnered with LG to test the AI-integrated MULTI V i system in a real academic environment. The objective was to measure how effectively it could reduce energy consumption and enhance indoor comfort.
In ITB’s Labtek VI building, fluctuating occupancy and uneven solar heat gain created inconsistent temperatures and high energy use. The previous HVAC system often ran unnecessarily, prompting the need for a solution that could adapt in real time.
LG installed one outdoor unit and four indoor units for a classroom and computer lab, configured for room size, load variations, and temperature differences. MULTI V i continuously monitors indoor conditions and adjusts operation automatically to maintain comfort and minimize energy waste.
The AI engine analyzes eight key variables, such as temperature, humidity, air flow, and set temperature. Through machine learning, it calculates the time to reach the target temperature and fine-tunes compressor frequency, refrigerant flow, and fan speed. This enables rapid cooling when the load is high and energy savings when it is low, which is ideal for spaces with varying occupancy.
The AI Indoor Space Care function groups indoor units according to environmental similarity. Units work together to balance temperature across the room, automatically activating or deactivating as needed. In the case of this site, temperature differences stayed within one degree Celsius without manual adjustments, preventing overcooling and saving energy.
The performance of MULTI V i was monitored over a 90-day period, with the system alternating daily between Normal mode and AI mode. The Monthly Energy Consumption results clearly show that AI mode consistently required less energy to operate, even while maintaining stable indoor comfort across classrooms and laboratories.
The data on total energy saving highlights the impact more directly. AI mode reduced overall power consumption by 49.2 percent and lowered electricity costs by about 49 percent compared to Normal mode.* These savings remained consistent across daily, weekly, and monthly patterns, confirming the efficiency of MULTI V i in a real-world academic setting.
*The results demonstrated in this article are based on the operation of one Multi V i (Model: ARUN140LTE6) and four DUAL Vane 4-Way Cassette units (Models: ARNU28GTBB4, ARNU42GTAB4) conducted from November 1st, 2024, to February 28th, 2025.
*These results are specific to the conditions and setup of the site, and may vary under different conditions.
ITB faculty praised the system’s performance, noting its ability to adapt and maintain comfort. For LG, the project showcased how AI-enabled HVAC can deliver measurable savings without compromising user experience, setting a strong precedent for data-driven climate control in institutional environments.