A deep-learning-based MAC for integrating channel access, rate adaptation and channel switch

TL;DR

DL-MAC introduces a cross-layer MAC that integrates channel access, rate adaptation, and channel switch using spectrum-sensing data in dense, heterogeneous unlicensed bands. It combines a DNN for channel selection with an LSTM-based RNN for joint channel access and MCS choice on the selected channel, and extends to multi-channel operation via channel switching. The approach is trained and validated on real-world 2.4 GHz ISM data, showing superior throughput and lower latency than traditional CSMA/CA-based methods and robustness to channel-switch overhead, with a semi-distributed gateway variant for multi-device coordination. The work demonstrates that joint design and data-driven channel decisions can substantially improve spectrum efficiency and adaptability in dynamic wireless environments, paving the way for more intelligent MAC protocols in heterogenous networks.

Abstract

With increasing density and heterogeneity in unlicensed wireless networks, traditional MAC protocols, such as carrier-sense multiple access with collision avoidance (CSMA/CA) in Wi-Fi networks, are experiencing performance degradation. This is manifested in increased collisions and extended backoff times, leading to diminished spectrum efficiency and protocol coordination. Addressing these issues, this paper proposes a deep-learning-based MAC paradigm, dubbed DL-MAC, which leverages spectrum sensing data readily available from energy detection modules in wireless devices to achieve the MAC functionalities of channel access, rate adaptation and channel switch. First, we utilize DL-MAC to realize a joint design of channel access and rate adaptation. Subsequently, we integrate the capability of channel switch into DL-MAC, enhancing its functionality from single-channel to multi-channel operation. Specifically, the DL-MAC protocol incorporates a deep neural network (DNN) for channel selection and a recurrent neural network (RNN) for the joint design of channel access and rate adaptation. We conducted real-world data collection within the 2.4 GHz frequency band to validate the effectiveness of DL-MAC, and our experiments reveal that DL-MAC exhibits superior performance over traditional algorithms in both single and multi-channel environments and also outperforms single-function approaches in terms of overall performance. Additionally, the performance of DL-MAC remains robust, unaffected by channel switch overhead within the evaluated range.

Figures (13)

• Figure 1: A toy example of traditional and intelligent protocol transmission.
• Figure 2: Coexistence of devices utilizing various protocols within the 2.4 GHz frequency band.
• Figure 3: Overview of DL-MAC framework.
• Figure 4: Illustration of data labeling and RNN.
• Figure 5: Illustration of data labeling and DNN.