Q-learning-based Joint Design of Adaptive Modulation and Precoding for Physical Layer Security in Visible Light Communications

TL;DR

The paper addresses physical layer security in visible light communications by jointly designing adaptive $M$-PAM modulation and precoding to optimize secrecy capacity under PAM constraints. It introduces a utility $u = C_s - \delta p_{e,B} + \zeta p_{e,E}$ and employs a Q-learning-based framework to maximize this utility by selecting both the modulation order and a quantized precoder, under a realistic VLC channel model with LoS dominance. Simulation results across multiple indoor setups show the adaptive joint design achieves higher rewards than non-adaptive baselines while keeping Bob’s BER below the pre-FEC limit and Eve’s BER above a leakage threshold, indicating improved secrecy-performance trade-offs. The work provides a practical reinforcement-learning approach to balancing throughput and confidentiality in VLC systems without relying on tractable closed-form secrecy capacity expressions.

Abstract

There has been an increasing interest in physical layer security (PLS), which, compared with conventional cryptography, offers a unique approach to guaranteeing information confidentiality against eavesdroppers. In this paper, we study a joint design of adaptive $M$-ary pulse amplitude modulation (PAM) and precoding, which aims to optimize wiretap visible-light channels' secrecy capacity and bit error rate (BER) performances. The proposed design is motivated by higher-order modulation, which results in better secrecy capacity at the expense of a higher BER. On the other hand, a proper precoding design, which can manipulate the received signal quality at the legitimate user and the eavesdropper, can also enhance secrecy performance and influence the BER. A reward function that considers the secrecy capacity and the BERs of the legitimate user's (Bob) and the eavesdropper's (Eve) channels is introduced and maximized. Due to the non-linearity and complexity of the reward function, it is challenging to solve the optical design using classical optimization techniques. Therefore, reinforcement learning-based designs using Q-learning and Deep Q-learning are proposed to maximize the reward function. Simulation results verify that compared with the baseline designs, the proposed joint designs achieve better reward values while maintaining the BER of Bob's channel (Eve's channel) well below (above) the pre-FEC (forward error correction) BER threshold.

Figures (5)

• Figure 1: System model.
• Figure 2: Comparision of the secrecy capacity.
• Figure 3: Comparision of Bob's BERs.
• Figure 4: Comparision of Eve's BERs.
• Figure 5: Comparision of utility.