Power Allocation for Relayed OFDM with Index Modulation Assisted by Artificial Neural Network

TL;DR

This paper introduces a neural network-based power allocation method for relayed OFDM with index modulation, achieving near-optimal performance with reduced complexity.

Contribution

It presents a novel ANN and deep learning approach for power allocation in relayed OFDM-IM systems, reducing computational complexity while maintaining performance.

Findings

Achieves comparable performance to optimal solutions

Reduces computational complexity of power allocation

Effective in diverse statistical channel conditions

Abstract

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.