Abstract
In previous study, deep learning and autoencoder have been applied for data detection of NOMA systems, rather than the resource allocation of OFDMA/NOMA systems. In previous work, we proposed the use of non-deep-learning-based cross-layer resource allocation for OFDMA/NOMA video communication systems. In this paper, we apply a deep neural network and supervised learning to an OFDMA subcarrier assignment and NOMA user grouping problem in downlink video communication systems. The resource allocation results from our previous work are used as training data at the training stage. At the testing stage, we propose a conversion algorithm to map the result of the sigmoid activation function (values between [0,1]) of the output layer of the DNN to either zero (unassigned) or one (assigned), in order to meet two hard constraints. The PSNR performance is very close (within 0.2dB) to that but has lower complexity, due to the non-iterative approach used in the testing stage of the DNN.
Highlights
In recent years, non-orthogonal multiple access (NOMA) has emerged [1], [2] and is used in the 3GPP standard [3] and the digital television standard ATSC 3.0 [4]
Since IP video traffic is expected to account for 82% of all IP traffic by 2022, up from 75% in 2017 according to a recent Cisco report [9], it is important to improve the performance of NOMA multimedia transmissions
In the proposed resource allocation of orthogonal frequency division multiple access (OFDMA)/NOMA video transmission systems, there are neither the spatial correlation addressed by convolutional neural network (CNN) nor the temporal correlations assumed by recurrent neural network (RNN), and the fully connected deep neural network (DNN) model is the most appropriate
Summary
Non-orthogonal multiple access (NOMA) has emerged [1], [2] and is used in the 3GPP standard [3] and the digital television standard ATSC 3.0 [4]. Tseng et al.: Deep-Learning-Aided Cross-Layer Resource Allocation of OFDMA/NOMA Video Communication Systems in the application layer. In order to go beyond both the physical and application layers, the work in [22] proposes a cross physical/application layer resource assignment that jointly considers the application layer RD function and the physical layer CSI to minimize the total video distortion (mean square error, MSE) for UL OFDMA video transmission systems. In our recent work [2], we propose the cross-layer resource allocation of DL OFDMA/NOMA video transmission systems to increase the average PSNR. In the proposed resource allocation of OFDMA/NOMA video transmission systems, there are neither the spatial correlation addressed by CNN nor the temporal correlations assumed by RNN, and the fully connected DNN model is the most appropriate. The resource allocation of an OFDMA system is to assign each OFDMA subcarrier (resource) to a user, and this is a classification task (either assigned or unassigned for each subcarrier/user pair)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
