Algorithm for AGC index management against crowded radio environment

TL;DR

The work tackles interference-induced packet loss in BLE/IEEE 802.15.4 by introducing a data-driven AGC strategy that predicts the optimal upper gain bound for the next packet using a sliding window of historical reception metrics. By forecasting $AGC_{optim}$ before the payload, the receiver gains resilience to interferers that may arrive during the gain-freeze period while maintaining high sensitivity. The approach is validated through a proof-of-concept and a detailed ML training pipeline using Bursted Wi-Fi profiles, showing improved PER performance in the presence of interferers compared to native AGC, particularly in Scenario 4. The practical impact is a PHY-layer enhancement for coexistence without additional wake-up delays, enabling more reliable operation in crowded radio environments.

Abstract

This paper describes a receiver that uses an innovative method to predict, according to history of receiver operating metrics (packet lost/well received), the optimum automatic gain control (AGC) index or most appropriate variable gain range to be used for next packet reception, anticipating an interferer appearing during the payload reception. This allows the receiver to have higher immunity to interferers even if they occur during the gain frozen payload reception period whilst still ensuring an optimum sensitivity level. As a result, the method allows setting the receiver gain to get an optimum trade-off between reception sensitivity and random interferer immunity.

Figures (15)

• Figure 1: IEEE 802.15.4 packet reception corruption Wi-Fi packet interferer occurring during payload reception period
• Figure 2: Benefits of proper AGC setting to get receiver higher immunity to interferers
• Figure 3: Receiver with ML aided AGC block diagram
• Figure 4: Flowchart of packet processing and ML training/test/validation
• Figure 5: Interferer arrival time versus AGC freeze event