Deep learning based transceiver design for multi-colored VLC systems

Quek

IEEE Trans. Wireless Commun.

2020

Self Cite

This paper studies a deep learning (DL) framework for the design of binary modulated visible light communication (VLC) transceiver with universal dimming support. The dimming control for the optical binary signal boils down to a combinatorial codebook design so that the average Hamming weight of binary codewords matches with arbitrary dimming target. An unsupervised DL technique is employed for obtaining a neural network to replace the encoder-decoder pair that recovers the message from the optically transmitted signal. In such a task, a novel stochastic binarization method is developed to generate the set of binary codewords from continuous-valued neural network outputs. For universal support of arbitrary dimming target, the DL-based VLC transceiver is trained with multiple dimming constraints, which turns out to be a constrained training optimization that is very challenging to handle with existing DL methods. We develop a new training algorithm that addresses the dimming constraints through a dual formulation of the optimization. Based on the developed algorithm, the resulting VLC transceiver can be optimized via the end-to-end training procedure. Numerical results verify that the proposed codebook outperforms theoretically best constant weight codebooks under various VLC setups.

Section: Proposed Training Methodsmentioning

confidence: 99%

Section: A Related Work and Motivationmentioning

confidence: 99%

A Deep Learning Approach to Universal Binary Visible Light Communication Transceiver

Quek

IEEE Trans. Wireless Commun.

2020

Self Cite

“…New ways of thinking about communications as end-to-end reconstruction optimization tasks are introduced in [30], which utilize autoencoders to jointly learn transmitter and receiver implementations as well as signal encodings without any prior knowledge. Similar thoughts are applied in OFDM [31], massive MIMO systems [32], millimeter-wave communications [33], optical fiber communications [34] and multi-colored visible light communications [35]. DL for channel coding is also attracting attentions [36,37].…”

Section: Related Workmentioning

confidence: 97%

A novel deep neural network based approach for sparse code multiple access

et al. 2020

Sparse code multiple access (SCMA) has been one of non-orthogonal multiple access (NOMA) schemes aiming to support high spectral efficiency and ubiquitous access requirements for 5G wireless communication networks. Conventional SCMA approaches are confronting remarkable challenges in designing low complexity high accuracy decoding algorithm and constructing optimum codebooks. Fortunately, the recent spotlighted deep learning technologies are of significant potentials in solving many communication engineering problems. Inspired by this, we explore approaches to improve SCMA performances with the help of deep learning methods. We propose and train a deep neural network (DNN) called DL-SCMA to learn to decode SCMA modulated signals corrupted by additive white Gaussian noise (AWGN). Putting encoding and decoding together, an autoencoder called AE-SCMA is established and trained to generate optimal SCMA codewords and reconstruct original bits. Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed. Simulations show that the DNN SCMA decoder significantly outperforms the conventional message passing algorithm (MPA) in terms of bit error rate (BER), symbol error rate (SER) and computational complexity, and AE-SCMA also demonstrates better performances via constructing better SCMA codebooks. The performance of deep learning aided DCMA is superior to the SCMA.As depicted in Fig. 1, consider J users transmitting data bits over the same K sub-carriers of OFDM, here K < J such that overloading is provided. According to SCMA encoder, each user maps every m = log 2 (M ) bits into a K-dimensional complex codeword c with only N non-zero elements standing for QAM modulation and LDS spreading combination, here N < K. The overlapping degree is d f = JN K , and overloading ratio is λ = J K . There are M codewords forming a codebook for each user and each codebook is unique. The encoding procedure can be described by c = f (b), where b ∈ B log2(M ) and c ∈ C ⊂ C K with |C| = M . Function f is actually a mapping matrix which

“…Proposition 1 leads to a DNN structure φ C (a; θ C ) which can compute the dual variable via the update rule in (16). Based on (15) and (16), the DNN parameter θ…”

Section: The Maximum Number Of Nodes In Hidden Layers Is Bounded Bymentioning

confidence: 99%

“…At each iteration, minibatch set S ⊂ A of size S is either sampled from training set A or generated from the probability distribution of global observation vector a, if available. The update rules in (15) and (16) are replaced by…”

Section: The Maximum Number Of Nodes In Hidden Layers Is Bounded Bymentioning

confidence: 99%

Deep Learning for Distributed Optimization: Applications to Wireless Resource Management

IEEE J. Select. Areas Commun.

Quek

2019

Self Cite

118

This paper studies a deep learning (DL) framework to solve distributed non-convex constrained optimizations in wireless networks where multiple computing nodes, interconnected via backhaul links, desire to determine an efficient assignment of their states based on local observations. Two different configurations are considered: First, an infinite-capacity backhaul enables nodes to communicate in a lossless way, thereby obtaining the solution by centralized computations. Second, a practical finitecapacity backhaul leads to the deployment of distributed solvers equipped along with quantizers for communication through capacity-limited backhaul. The distributed nature and the nonconvexity of the optimizations render the identification of the solution unwieldy. To handle them, deep neural networks (DNNs) are introduced to approximate an unknown computation for the solution accurately. In consequence, the original problems are transformed to training tasks of the DNNs subject to non-convex constraints where existing DL libraries fail to extend straightforwardly. A constrained training strategy is developed based on the primal-dual method. For distributed implementation, a novel binarization technique at the output layer is developed for quantization at each node. Our proposed distributed DL framework is examined in various network configurations of wireless resource management. Numerical results verify the effectiveness of our proposed approach over existing optimization techniques.Index Terms-Deep neural network, distributed deep learning, primal-dual method, wireless resource management.