LG Uplus said on Aug. 9 it demonstrated home network auto-recovery technology using a Wi-Fi 8 platform in cooperation with Broadcom.

The demonstration applied “edge AI” technology in which AI analyses and optimises network conditions directly on a home router, not a cloud server.

Broadcom provided a Wi-Fi 8 platform equipped with a neural processing unit (NPU) that supports AI computing. LG Uplus slimmed down a network quality prediction AI model previously operated in the cloud so it can run on routers as well.

The companies confirmed through the demonstration that AI can analyse network quality data in real time on the router and detect signs of failure in advance. It said that in situations where internet quality deterioration is expected, the system can optimise network settings and automatically recover to maintain service quality.

LG Uplus emphasised that it confirmed the potential to expand routers from simple internet connection devices into AI-based quality management platforms. It expects use of the technology to increase as more services requiring stable networks, such as generative AI, extended reality (XR), cloud gaming and ultra-high-definition IPTV, become available.

LG Uplus plans to continue verifying and advancing related technologies so AI can manage networks stably in a Wi-Fi 8 environment.

Lee Jin-hyeok (이진혁), a managing director at LG Uplus' Consumer Service Development Lab, said the demonstration confirmed the potential of edge AI technology that runs AI directly inside network equipment. He said the company would expand cooperation with global technology partners and continue advancing the technology.

Shin Nam-seung (신남승), an executive director and head of wireless broadband sales at Broadcom Korea, said Broadcom would expand cooperation with LG Uplus as a technology partner supporting next-generation home network innovation.