基于强化学习的无人机通信感知一体化能耗优化

Energy optimization algorithm for ISAC-enabled unmanned aerial vehicles system via reinforcement learning

  • 摘要: 通信感知一体化技术与灵活可控无人机通信技术结合将成为6G无线通信网络“万物智联”的潜在技术。针对无人机通信感知一体化系统中无人机能量受限问题,提出了一种基于强化学习的无人机功率分配和轨迹设计的联合优化算法。该算法在用户通信速率和目标感知波束图增益约束下,通过构建与无人机能耗、发射波束和通信速率相关的线性加权奖励函数,以实现智能化的无人机功率分配和轨迹设计,从而最小化无人机通信感知一体化系统的能耗。仿真结果表明,该方案相较于基准方案降低了12.36% ~ 21.08%的无人机能耗,并拥有更优的收敛性能。

     

    Abstract: Integrated sensing and communication (ISAC) technology combined with the cost-effective and flexibly controllable unmanned aerial vehicle (UAV) becomes the potential technology to enable a variety of applications for the future "Internet of Everything" in the sixth generation (6G) communication system. To reduce the energy consumption of ISAC-enabled UAV systems, a joint optimization algorithm based on reinforcement learning (RL) is proposed to design UAV’s trajectory and allocate the transmit power. Under constraints of user communication rate and the target sensing beam pattern gain, this algorithm can achieve intelligent decision-making for UAV trajectory and power allocation by constructing a linearly weighted reward function related to UAV energy consumption, transmit beamforming pattern gain, and communication rate. The simulation results indicate that the proposed scheme can reduce energy consumption by 12.36% to 21.08% in comparison to the benchmark schemes. Furthermore, the proposed scheme demonstrates superior convergence.

     

/

返回文章
返回