Investigating the Combination of Deep Learning for Channel Estimation and Power Optimization in a Non-Orthogonal Multiple Access System

Abstract

In a non-orthogonal multiple access (NOMA) system, the successive interference cancellation (SIC) procedure is typically employed at the receiver side, where several user’s signals are decoded in a subsequent manner. Fading channels may disperse the transmitted signal and originate dependencies among its samples, which may affect the channel estimation procedure and consequently affect the SIC process and signal detection accuracy. In this work, the impact of Deep Neural Network (DNN) in explicitly estimating the channel coefficients for each user in NOMA cell is investigated in both Rayleigh and Rician fading channels. The proposed approach integrates the Long Short-Term Memory (LSTM) network into the NOMA system where this LSTM network is utilized to predict the channel coefficients. DNN is trained using different channel statistics and then utilized to predict the desired channel parameters that will be exploited by the receiver to retrieve the original data. Furthermore, this work examines how the channel estimation based on Deep Learning (DL) and power optimization scheme are jointly utilized for multiuser (MU) recognition in downlink Power Domain Non-Orthogonal Multiple Access (PD-NOMA) system. Power factors are optimized with a view to maximize the sum rate of the users on the basis of entire power transmitted and Quality of service (QoS) constraints. An investigation for the optimization problem is given where Lagrange function and Karush–Kuhn–Tucker (KKT) optimality conditions are applied to deduce the optimum power coefficients. Simulation results for different metrics, such as bit error rate (BER), sum rate, outage probability and individual user capacity, have proved the superiority of the proposed DL-based channel estimation over conventional NOMA approach. Additionally, the performance of optimized power scheme and fixed power scheme are evaluated when DL-based channel estimation is implemented.

A Study on the Impact of Integrating Reinforcement Learning for Channel Prediction and Power Allocation Scheme in MISO-NOMA System

“…The network is assumed to work with equal length time intervals and each time interval includes one transmission, which contains either uplink or downlink transmissions. The pilot-assisted channel prediction is considered in this work, where pilot symbols can be identified by BS and UDs [ 15 , 17 ]. Each user device initially transmits its pilot symbols to BS via an uplink channel.…”

“…In contrast, signals related to user devices with good link conditions may not be separated and regarded as interference. According to the aforementioned assumptions, the superposition-coded signal sent from BS can be stated as follows [ 3 , 17 ]: where , and represent power factors given for a far device, middle device, and near device separately. Furthermore, , and refer to the signal vectors related to far, middle, and near users respectively.…”

“…It is supposed that the implemented channel model is stationary throughout one frame transmission of data and pilot signals and the channel parameters are varying from one frame to another. The basic architecture of the channel prediction scenario based on the developed Q -learning procedure employed in our examined network is illustrated in Figure 3 , which primarily consists of several stages [ 17 , 43 ].…”

“…The combination between a DNN as a tool for channel prediction and an optimized power scheme is explored in [ 17 ] for the purpose of multiuser detection in the NOMA system. The DNN based Long Short-Term Memory (LSTM) network is developed for channel prediction based on complex data processing.…”

“… As a reference comparison, four further simulation environments are established. (1) the standard minimum mean square error (MMSE) based channel prediction scheme (Neumann et al); (2) the DNN algorithm based on LSTM network for channel prediction applied in [ 17 ], (3) the RL based actor-critic procedure for channel prediction applied in [ 15 ], (4) the fourth simulation environment is dependent on applying RL based State-Action-Reward-State-Action (SARSA) procedure (Ahsan et al and Mu et al). The simulation outcomes of these environments are compared with the results of our proposed RL based Q-learning scheme, and the results emphasized that dependability can be assured by our developed Q-model for predicting channel parameters even when the number of devices in the cell is increased.…”