Non-linear precoding outperforms linear precoding in a multi-user multi-input multi-output (MU-MIMO) system. The actual gain depends on multiple factors, including number of users, user distribution in the system, etc. Furthermore, to achieve the promised gain, non-linear precoding requires a higher implementation complexity which has prevented its adoption into the 3rd Generation Partnership Project (3GPP) standards. In many practical scenarios, the number of paired users for MU-MIMO remains low. When the number of paired scheduled users for MU-MIMO systems is low, the complexity of non-linear precoding becomes less significant. In this paper, we show that, even when, the number of paired users for MU-MIMO is not more than two, non-linear precoding can still offer a meaningful performance improvement over the linear precoding. For our study, under 3GPP new radio framework, we have evaluated and compared the performance of Tomlinson-Harashima non-linear precoding against a block diagonalized linear precoding.

The mobile communication enabled by cellular networks is the one of the main foundations of our modern society. Optimizing the performance of cellular networks and providing massive connectivity with improved coverage and user experience has a considerable social and economic impact on our daily life. This performance relies heavily on the configuration of the network parameters. However, with the massive increase in both the size and complexity of cellular networks, network management, especially parameter configuration, is becoming complicated. The current practice, which relies largely on experts' prior knowledge, is not adequate and will require lots of domain experts and high maintenance costs. In this work, we propose a learning-based framework for handover parameter configuration. The key challenge, in this case, is to tackle the complicated dependencies between neighboring cells and jointly optimize the whole network. Our framework addresses this challenge in two ways. First, we introduce a novel approach to imitate how the network responds to different network states and parameter values, called auto-grouping graph convolutional network (AG-GCN). During the parameter configuration stage, instead of solving the global optimization problem, we design a local multi-objective optimization strategy where each cell considers several local performance metrics to balance its own performance and its neighbors. We evaluate our proposed algorithm via a simulator constructed using real network data. We demonstrate that the handover parameters our model can find, achieve better average network throughput compared to those recommended by experts as well as alternative baselines, which can bring better network quality and stability. It has the potential to massively reduce costs arising from human expert intervention and maintenance.

In this paper, a statistical-based sphere decoding with increasing radius search (S-SD-IRS) algorithm is proposed, where the radiuses of the decoding hyperspheres are determined based on the statistical properties of the communication channel and additive noise. We show that the probability density functions (PDFs) of the q lowest squared distances in the closest lattice point problem can be approximated by Gumbel distributions with different parameters. Based on the obtained PDFs and by considering the characteristics of the fading channels and additive noise, we choose the radiuses for sphere decoding more efficiently than the conventional methods that ignore the characteristics of system. The performance achieved by the proposed algorithm is very close to the optimal maximum likelihood decoding (MLD) over a wide range of signal-to-noise ratios (SNRs), while the computational complexity, compared to existing sphere decoding variants, is significantly reduced. It is shown that the average number of lattice points inside the decoding hyperspheres drastically reduces in the proposed S-SD-IRS algorithm.

We consider the use of deep neural network (DNN) to develop a decision-directed (DD)-channel estimation (CE) algorithm for multiple-input multiple-output (MIMO)-space-time block coded systems in highly dynamic vehicular environments. We propose the use of DNN for k -step channel prediction for space-time block code (STBC), and show that deep learning (DL)-based DD-CE can remove the need for Doppler rate estimation in fast time-varying quasi stationary channels, where the Doppler rate varies from one packet to another. Doppler rate estimation in this kind of vehicular channels is remarkably challenging and requires a large number of pilots and preambles, leading to lower power and spectral efficiency. We train two DNNs which learn the real and imaginary parts of the MIMO fading channels over a wide range of Doppler rates. We demonstrate that by these DNNs, DD-CE can be realized with only priori knowledge about Doppler rate range and not the exact value. For the proposed DD-CE algorithm, we also analytically derive the maximum likelihood (ML) decoding algorithm for STBC transmission. The proposed DL-based DD-CE is a promising solution for reliable communication over vehicular MIMO fading channels without accurate mathematical models. This is because DNNs can intelligently learn the statistics of the fading channels. Our simulation results show that the proposed DL-based DD-CE algorithm exhibits lower error propagation compared to existing DD-CE algorithms which require perfect knowledge of the Doppler rate.

In this paper, a deep learning (DL)-based sphere decoding algorithm is proposed, where the radius of the decoding hypersphere is learned by a deep neural network (DNN). The performance achieved by the proposed algorithm is very close to the optimal maximum likelihood decoding (MLD) over a wide range of signal-to-noise ratios (SNRs), while the computational complexity, compared to existing sphere decoding variants, is significantly reduced. This improvement is attributed to the DNN's ability of intelligently learning the radius of the hypersphere used in decoding. The expected complexity of the proposed DL-based algorithm is analytically derived and compared with existing ones. It is shown that the number of lattice points inside the decoding hypersphere drastically reduces in the DL-based algorithm in both the average and worst-case senses. The effectiveness of the proposed algorithm is shown through the simulation for high-dimensional multiple-input multiple-output (MIMO) systems, using high-order modulations.

Locally repairable codes (LRCs) have been recently proposed and used in real-world distributed storage systems (DSSs) such as Microsoft Azure Storage and Facebook HDFS-RAID (Hadoop Distributed File System-Redundant Array of Independent Disks). Since information in DSSs is changed frequently, reducing update complexity (UC) of LRCs is of great interest. In this paper, we propose code design algorithms that can reduce UC of existing LRCs without sacrificing their important code parameters such as minimum distance, code rate, or locality. We establish bounds on UC, and use them to show that our algorithms can achieve optimal or near optimal UC for a large class of LRCs.

Erasure codes are recently used in real-world distributed storage systems (DSSs) such as Google File System,Microsoft Azure Storage, and Facebook HDFS-RAID for data reliability. When designing erasure codes for DSSs, special attention is given to the associated costs of data handling operations such as repair or update. For example, locally repairable codes (LRC) are designed and used in DSSs to allow for low-cost repair of failed blocks. Update complexity (defined as the number of blocks that need to be updated when an information block is changed) is yet another design parameter. This parameter can be seen as a measure of the computation, I/O and networking costs associated with updating an information block in a DSS. Since information is frequently updated by many applications, lowering update complexity can result in lower power consumptions in DSSs. In this work, we study the update complexity of LRCs. Based on our study, we propose an improvement over the LRC used by Facebook HDFS-RAID. Keeping the same code parameters including length, storage overhead, minimum distance and cost of repair (locality), we improve the update complexity by more than 16%. Moreover, we show that with these parameters achieving a lower update complexity is impossible.