“…In this sense, a low computational complexity detector emerges as an essential requirement in LS‐MIMO systems. Many low‐complexity LS‐MIMO detectors have been proposed in recent literature, including detectors based on (i) local neighbourhood search , such as likelihood ascent search algorithm [4], and reactive tabu search algorithm [5]; (ii) message passing algorithms, based on belief propagation technique, such that LS‐detectors inspired in graphical models, as factor graph [6] and Markov random fields [7]; (iii) minimum mean square error (MMSE) approximation techniques [8, 9], which result in low complexity at the price of achieving good performance only at low system loading factor; (iv) Markov chain Monte Carlo (MCMC) techniques, which are based on Gibbs sampling (GS) [10], emerging as a promising approach to deal with LS‐MIMO structures [11–15], since such techniques demonstrate a near‐optimum performance while require a moderate complexity (quadratic order), also presenting a simple and effective way to solve the large‐scale detection problem.…”
Section: Introductionmentioning
confidence: 99%
“…Also, the results do not consider the performance behaviour in high‐order modulation schemes. More recently, the MCMC detector with QR decomposition was addressed in [14, 18], which can reduce the number of operations due to the lower triangular matrix feature. Besides, based on the multiple random parallel Markov chains, the work in [13] proposes a MR strategy through parallel chains; such strategy reduced the algorithm's running time compared to MGS‐MR, despite the increasing of the number of real operations per symbol.…”
This work proposes a low‐complexity detector for medium‐ and high‐order modulation large‐scale multiple‐input multiple‐output (LS‐MIMO) systems based on the set of Markov chain Monte‐Carlo techniques. Such efficient signal detection algorithm is based on the mixed Gibbs sampling with multiple restarts (MGS‐MR) strategy with sample‐averaged approach during the coordinate updating process, named averaged MGS (aMGS). The proposed strategy applies multiple samples average procedure to restrict the range of the random solution, which comes from the mixture proposed by the original MGS. Numerical simulation results considering higher‐order M ‐QAM demonstrated that the proposed detection method can substantially improve the convergence of the MGS‐MR algorithm, while no extra computational complexity is required. The proposed aMGS‐based detector suitable for medium‐ and high‐order modulation LS‐MIMO further exhibits improved performance when the system loading is high, i.e. when (K /N) ≥ 0.75. In addition, the proposed numerical simulation analyses have shown that the optimal value of the mixing ratio parameter can vary regarding system and channel configuration scenarios, resulting somewhat different from the 1/2K value disseminated in the literature.
“…In this sense, a low computational complexity detector emerges as an essential requirement in LS‐MIMO systems. Many low‐complexity LS‐MIMO detectors have been proposed in recent literature, including detectors based on (i) local neighbourhood search , such as likelihood ascent search algorithm [4], and reactive tabu search algorithm [5]; (ii) message passing algorithms, based on belief propagation technique, such that LS‐detectors inspired in graphical models, as factor graph [6] and Markov random fields [7]; (iii) minimum mean square error (MMSE) approximation techniques [8, 9], which result in low complexity at the price of achieving good performance only at low system loading factor; (iv) Markov chain Monte Carlo (MCMC) techniques, which are based on Gibbs sampling (GS) [10], emerging as a promising approach to deal with LS‐MIMO structures [11–15], since such techniques demonstrate a near‐optimum performance while require a moderate complexity (quadratic order), also presenting a simple and effective way to solve the large‐scale detection problem.…”
Section: Introductionmentioning
confidence: 99%
“…Also, the results do not consider the performance behaviour in high‐order modulation schemes. More recently, the MCMC detector with QR decomposition was addressed in [14, 18], which can reduce the number of operations due to the lower triangular matrix feature. Besides, based on the multiple random parallel Markov chains, the work in [13] proposes a MR strategy through parallel chains; such strategy reduced the algorithm's running time compared to MGS‐MR, despite the increasing of the number of real operations per symbol.…”
This work proposes a low‐complexity detector for medium‐ and high‐order modulation large‐scale multiple‐input multiple‐output (LS‐MIMO) systems based on the set of Markov chain Monte‐Carlo techniques. Such efficient signal detection algorithm is based on the mixed Gibbs sampling with multiple restarts (MGS‐MR) strategy with sample‐averaged approach during the coordinate updating process, named averaged MGS (aMGS). The proposed strategy applies multiple samples average procedure to restrict the range of the random solution, which comes from the mixture proposed by the original MGS. Numerical simulation results considering higher‐order M ‐QAM demonstrated that the proposed detection method can substantially improve the convergence of the MGS‐MR algorithm, while no extra computational complexity is required. The proposed aMGS‐based detector suitable for medium‐ and high‐order modulation LS‐MIMO further exhibits improved performance when the system loading is high, i.e. when (K /N) ≥ 0.75. In addition, the proposed numerical simulation analyses have shown that the optimal value of the mixing ratio parameter can vary regarding system and channel configuration scenarios, resulting somewhat different from the 1/2K value disseminated in the literature.
In this study, we consider the application of deep learning (DL) to tabu search (TS) detection in large multiple-input multiple-output (MIMO) systems. First, we propose a deep neural network architecture for symbol detection, termed the fast-convergence sparsely connected detection network (FS-Net), which is obtained by optimizing the prior detection networks called DetNet and ScNet. Then, we propose the DL-aided TS algorithm, in which the initial solution is approximated by the proposed FS-Net.Furthermore, in this algorithm, an adaptive early termination algorithm and a modified searching process are performed based on the predicted approximation error, which is determined from the FS-Net-based initial solution, so that the optimal solution can be reached earlier. The simulation results show that the proposed algorithm achieves approximately 90% complexity reduction for a 32 × 32 MIMO system with QPSK with respect to the existing TS algorithms, while maintaining almost the same performance.
Index TermsMIMO, deep learning, deep neural network, tabu search.
“…Besides that, these results did not considered the performance behavior in high-order modulation systems. A QR decomposition approach within the MCMC detector was addressed in [16], [17], which demonstrated to reduce the number of operations due to the lower triangular matrix feature. Furthermore, based on the concept of multiple random parallel Markov chains, work in [18] proposes a MR strategy through parallel chains; such strategy reduced the algorithm's running time compared to MGS-MR, despite the increasing of the number of real operations per symbol.…”
A neighborhood restricted Mixed Gibbs Sampling (MGS) based approach is proposed for lowcomplexity high-order modulation large-scale Multiple-Input Multiple-Output (LS-MIMO) detection.The proposed LS-MIMO detector applies a neighborhood limitation (NL) on the noisy solution from the MGS at a distance d -thus, named d-simplified MGS (d-sMGS) -in order to mitigate its impact, which can be harmful when a high order modulation is considered. Numerical simulation results considering 64-QAM demonstrated that the proposed detection method can substantially improve the MGS algorithm convergence, whereas no extra computational complexity per iteration is required.The proposed d-sMGS-based detector suitable for high-order modulation LS-MIMO further exhibits improved performance × complexity tradeoff when the system loading is high, i.e., when K N ≥ 0.75. Also, with increasing the number of dimensions, i.e., increasing number of antennas and/or modulation order, a smaller restriction of 2-sMGS was shown to be a more interesting choice than 1-sMGS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.