In this letter, we propose a power allocation scheme for relayed orthogonal frequency division multiplexing with index modulation (OFDM-IM) systems. The proposed power allocation scheme replies on artificial neural network (ANN) and deep learning to allocate transmit power among various subcarriers at the source and relay nodes. The objective of the power allocation scheme is to minimize the overall transmit power under a set of constraints. Without loss of generality, we assume all subcarriers at source and relay nodes are independently distributed with different statistical distribution parameters. The relay node adopts the fixed-gain amplify-and-forward (FG AF) relaying protocol. We employ the adaptive moment estimation method (Adam) to implement back-propagation learning and simulate the proposed power allocation scheme. The analytical and simulation results show that the proposed power allocation scheme is able to provide comparable performance as the optimal solution but with lower complexity.

中文翻译：

---

人工神经网络辅助索引调制的中继OFDM功率分配

在这封信中，我们提出了一种用于具有索引调制的中继正交频分复用 (OFDM-IM) 系统的功率分配方案。所提出的功率分配方案依靠人工神经网络 (ANN) 和深度学习在源节点和中继节点的各个子载波之间分配发射功率。功率分配方案的目标是在一组约束条件下最小化总发射功率。不失一般性，我们假设源节点和中继节点的所有子载波都是独立分布的，具有不同的统计分布参数。中继节点采用固定增益放大转发（FG AF）中继协议。我们采用自适应矩估计方法 (Adam) 来实现反向传播学习并模拟所提出的功率分配方案。