Researchers have introduced FedQoS, a federated learning framework designed to predict and mitigate Quality of Service (QoS) degradation in dynamic indoor-outdoor wireless environments. This approach enables access nodes to learn locally from network data, such as radio measurements and traffic load, without centralizing user information. A global QoS-risk predictor is trained via federated aggregation to estimate the probability of QoS failure for candidate access links, allowing for more reliable access node selection. The framework was evaluated using synthetic datasets generated with the Sionna framework, demonstrating significant reductions in QoS failure rates compared to traditional methods. AI
IMPACT This research could lead to more stable and reliable wireless connections by improving access selection mechanisms in complex environments.
RANK_REASON The cluster describes a research paper published on arXiv detailing a new framework for wireless access selection.
Read on Hugging Face Daily Papers →
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
