본문 바로가기
  • Home

AI-Based Association Control System for QoS in Dense Wireless LANs

  • Journal of Internet of Things and Convergence
  • Abbr : JKIOTS
  • 2025, 11(4), pp.35~41
  • Publisher : The Korea Internet of Things Society
  • Research Area : Engineering > Computer Science > Internet Information Processing
  • Received : July 4, 2025
  • Accepted : August 1, 2025
  • Published : August 31, 2025

Chang-Hyun Jung 1 Sang-Hui Lee 2 Jaewook Lee 1

1국립부경대학교
2이상희

Accredited

ABSTRACT

In dense WLAN environments, user association concentrated on a single Access Point (AP) can severely degrade the overall Quality of Service (QoS). This issue arises from the conventional architecture in which each AP independently handles user associations without coordination. To address this problem, we propose an intelligent user association control system based on deep reinforcement learning (DRL). The proposed system employs a centralized controller that collects real-time status information from user stations (STAs) and recommends the optimal AP for each user. By learning and predicting the best association strategies, the system effectively balances traffic loads across APs and minimizes unnecessary handovers, thereby enhancing QoS. One of the key advantages of our approach is its compatibility with existing WLAN infrastructure, requiring no hardware modifications. We demonstrated its effectiveness through real-world experiments.

Citation status

* References for papers published after 2024 are currently being built.