Deep Reinforcement Learning Based Ultra Reliable and Low Latency Vehicular OCC

In this paper, we present a deep reinforcement learning (DRL) framework for vehicular optical camera communication (OCC) systems that ensures ultra-reliable and low-latency communication (uRLLC). We first formulate a throughput maximization problem that aims at optimizing speed of vehicles, channel code rate, and modulation order while respecting the uRLLC requirements. We model reliability by satisfying a target bit error rate and latency as transmission latency. To improve the transmission rate and provide high reliability and low latency, our scheme uses low-density parity-check codes and adaptive modulation. We then solve the optimization problem using the actor-critic-based DRL scheme with Wolpertinger framework. We employ a deep deterministic policy gradient algorithm to operate over continuous action spaces. The evaluation confirms that our proposed DRL-based optimization scheme achieves superior performance compared to radio frequency-based communication systems as well as variants of the proposed scheme. Finally, we verify through simulations that our proposed solution can maximize the communication rate while meeting the uRLLC constraints.