Travel Distance Aware ISAC Enabled IoV: An Intelligent Power Allocation Solution

Integrated sensing and communication (ISAC) is a key technology for next-generation wireless networks, and the problem of dynamic resource allocation in Internet of vehicles (IoV) scenarios needs to be studied. In this paper, we study the problem of power allocation in an ISAC enabled IoV scenario based on deep reinforcement learning techniques. Specifically, we consider an ISAC base station that senses information about multiple vehicles on the road while sending the sensed vehicle information as well as information about the surrounding environment to the vehicles on the road. The spectral efficiency of communication, as well as the sensed mutual information, is chosen as the quality of service (QoS) metrics for both communication and sensing, with the objective of minimizing the maximum distance traveled by the vehicles during the duration of the message sending. To solve this problem, we propose a proximal policy optimization (PPO)-based intelligent power allocation scheme, which minimizes the objective while satisfying the communication and sensing QoS. Simulation results show that our proposed scheme outperforms other compared schemes.