[Edaily Reporter Han Kwangbeom ] LG Uplus(032640)announced on the 8th that it has successfully validated “Edge AI”-based home network automatic recovery technology, in which AI directly analyzes and optimizes network status within a home router.

This demonstration was conducted using the “Wi-Fi 8” platform, a next-generation wireless communication standard. The company validated “Edge AI” technology, in which AI analyzes and optimizes network status at the home router level rather than on a cloud server. This is significant because it confirms the feasibility of an intelligent home network where AI detects signs of abnormalities and automatically optimizes settings and resolves issues (self-healing) before customers even notice a decline in internet quality.

With the recent surge in the use of services requiring high bandwidth and ultra-low latency—such as generative AI, extended reality (XR), cloud gaming, and ultra-high-definition IPTV—the importance of maintaining stable network quality within the home has grown rapidly. Consequently, AI-based smart home network technology that autonomously monitors and optimizes network conditions has emerged as a key priority.

To validate this technology, LG Uplus established a partnership with Broadcom, a global semiconductor company. Broadcom provided a Wi-Fi 8 platform equipped with a Neural Processing Unit (NPU) that supports AI computations, while LG Uplus optimized its network quality prediction AI model—previously operated in the cloud—to run on routers.

Through this pilot, the two companies verified a process in which AI analyzes network quality data in real time on home routers and proactively detects signs of failure. They demonstrated that, in situations where a decline in internet quality is anticipated, the system can optimize network settings and perform automatic recovery to maintain stable quality without service interruptions or delays.

This pilot is also noteworthy for expanding the role of the router from a simple device for facilitating internet access to an AI-based intelligent quality management platform. It confirms that routers can evolve into core devices capable of independently analyzing and managing network status.

Starting with this demonstration, LG Uplus plans to continuously validate and refine various technologies that enable AI to reliably manage networks in Wi-Fi 8 environments.

Shin Nam-seung, Executive Vice President of Wireless Broadband Sales at Broadcom Korea, stated, “Through this demonstration, we have proven that routers can be expanded into intelligent quality management platforms by directly running AI models on Broadcom’s Wi-Fi 8 platform,” adding, “As a technology partner supporting next-generation home network innovation, Broadcom will continue to expand its collaboration with LG Uplus.”

Lee Jin-hyuk, Senior Vice President of the Consumer Service Development Lab at LG Uplus, remarked, “This demonstration is a meaningful achievement that confirms the potential of edge AI technology, which runs AI directly within network equipment.” He added, “As we have taken the first step toward realizing an intelligent home network where AI autonomously manages the quality experienced by customers, we will expand our collaboration with global technology partners to continuously advance these technologies.”