In this letter, we investigate an intelligent reflecting surface (IRS) aided device-to-device (D2D) offloading system, where an IRS is employed to assist in computation offloading from a group of users with intensive tasks to another group of idle users. To minimize the system latency while cutting down the heavy overhead in exchange of channel state information (CSI), we study the joint design of beamforming and resource allocation on mixed timescales. Specifically, the high-dimensional passive beamforming vector at the IRS is updated in a frame-based manner based on the channel statistics, where each frame consists of a number of time slots, while the offloading ratio and user matching strategy are optimized relied on the low-dimensional real-time effective channel coefficients in each time slot. A novel mixed-integer stochastic successive convex approximation (MISSCA) algorithm is proposed to tackle the challenging problem. The convergence property and the computational complexity of the proposed algorithm are then examined. Simulation results show that our proposed algorithm significantly outperforms the conventional benchmarks.

中文翻译：

---

智能反射表面辅助 D2D 卸载系统中的延迟最小化


在这封信中，我们研究了一种智能反射表面（IRS）辅助设备到设备（D2D）卸载系统，其中IRS用于协助将计算从一组执行密集任务的用户卸载到另一组空闲用户。为了最大限度地减少系统延迟，同时减少信道状态信息（CSI）交换的繁重开销，我们研究了混合时间尺度上波束成形和资源分配的联合设计。具体来说，IRS处的高维无源波束形成向量基于信道统计以基于帧的方式更新，其中每个帧由多个时隙组成，同时依赖于优化分流比和用户匹配策略。每个时隙的低维实时有效信道系数。提出了一种新颖的混合整数随机逐次凸逼近（MISSCA）算法来解决这一具有挑战性的问题。然后检查所提出算法的收敛性和计算复杂度。仿真结果表明，我们提出的算法显着优于传统基准。