Proactive Radio Resource Allocation for 6G In-Factory Subnetworks

TL;DR

The paper addresses the challenge of maintaining information freshness in 6G In-Factory Subnetworks by predicting future AoI with a decentralized Bayesian Ridge Regression model and using predictive uncertainty to drive proactive radio resource allocation. By learning the dynamic relation between AoI, transmission power, and interference, the proposed method minimizes the probability that AoI exceeds a predefined threshold, achieving substantial reliability gains in simulations. The approach balances exploration (gaining knowledge of dynamics) and exploitation (reducing AoI violations) through a dual objective that incorporates predictive variance. The results demonstrate a dramatic reduction in AoI violation probability compared to baselines, with practical implications for stability and accuracy of industrial control loops, while pointing to future work on weight tuning and interference scenarios.

Abstract

6G In-Factory Subnetworks (InF-S) have recently been introduced as short-range, low-power radio cells installed in robots and production modules to support the strict requirements of modern control systems. Information freshness, characterized by the Age of Information (AoI), is crucial to guarantee the stability and accuracy of the control loop in these systems. However, achieving strict AoI performance poses significant challenges considering the limited resources and the high dynamic environment of InF-S. In this work, we introduce a proactive radio resource allocation approach to minimize the AoI violation probability. The proposed approach adopts a decentralized learning framework using Bayesian Ridge Regression (BRR) to predict the future AoI by actively learning the system dynamics. Based on the predicted AoI value, radio resources are proactively allocated to minimize the probability of AoI exceeding a predefined threshold, hence enhancing the reliability and accuracy of the control loop. The conducted simulation results prove the effectiveness of our proposed approach to improve the AoI performance where a reduction of 98% is achieved in the AoI violation probability compared to relevant baseline methods.

Figures (4)

• Figure 1: InF-S control system consisting of $N$ subnetworks.
• Figure 2: CCDF comparison of the AoI with $M=300$ and $\delta=10$ ms.
• Figure 3: RMSE and AoI violation probability under varying dataset sizes.
• Figure 4: Average AoI and AoI violation probability under varying $\alpha_i$.