In this paper, we investigate the downlink robust precoding with imperfect channel state information (CSI) for massive multiple-input-multiple-output (MIMO) communications. With the estimated channel and channel error statistics, the general design of the robust precoder is to maximize the ergodic sum rate subject to the total transmit power constraint. To make the problem more tractable, we find a lower bound of the ergodic sum rate and propose the robust weighted minimum mean-squared-error (WMMSE) precoder to maximize the bound. We characterize the structure of the precoding vectors by low-dimensional parameters, which are learned directly from the available CSI through a neural network. As such, the precoding vectors can be immediately computed without iterations. To extend the deep learning design to multi-antennas users, we present a flexible approach that allows the various antenna configurations at the user side to be handled. Simulation results show that the deep learning design can significantly reduce the computational complexity compared with the existing precoder designs while achieving near optimal performance.

Abstract In this paper, massive multiple‐input‐multiple‐output (MIMO) wireless communication systems are considered to investigate joint transceiver beamforming. A base station (BS) equipped with a uniform planar array (UPA) serves several multi‐antennas users in a single cell. Based on the channel state information (CSI), the low complexity design of transceiver beamforming to minimize the transmit power subject to some quality of service (QoS) constraints is investigated. As the upper bound of the transmit power performance, the existing iteration‐based algorithms are leveraged as a reference. A general deep learning (DL)‐based framework and deep neural network (DNN) structure are proposed to reduce the complexity of the existing algorithms, where the properly trained DNN structure can learn directly from CSI. Consider the complexity of the DNN structure itself, a heuristic algorithm is proposed to replace the DNN structure, which takes the max‐eigenvalue‐eigenvector of the CSI as the direction of receive beamforming directly. The DNN structure is trained in the offline stage, therefore, only the complexity in the online stage is taken into consideration. Based on the numerical simulation, the complexity of the proposed DL‐based framework and the transceiver beamforming algorithms is reduced significantly while maintaining nearly the optimal performance compared with the existing iterative algorithms.

In this paper, we consider massive multiple-input multiple-output (MIMO) communication systems with a uniform planar array (UPA) at the base station (BS) and investigate the downlink precoding with imperfect channel state information (CSI). By exploiting both instantaneous and statistical CSI, we aim to design precoding vectors to maximize the ergodic rate subject to a total transmit power constraint. By maximizing an upper bound of the ergodic rate instead, we leverage the corresponding Lagrangian formulation and identify the structural characteristics of the optimal precoder as the solution to a generalized eigenvalue problem. As such, the high-dimensional precoder design problem turns into a low-dimensional power control problem. The Lagrange multipliers play a crucial role in determining both precoder directions and power parameters, yet are challenging to be solved directly. To figure out the Lagrange multipliers, we develop a deep learning approach underpinned by a properly designed neural network that learns directly from CSI. With the offline pre-trained neural network, the online computational complexity of precoding is substantially reduced compared with the existing iterative algorithm while maintaining nearly the same performance.

In this paper, we consider massive multiple-input-multiple-output (MIMO) communication systems with a uniform planar array (UPA) at the base station (BS) and investigate the downlink precoder design with imperfect channel state information (CSI). By exploiting channel estimates and statistical parameters of channel estimation error, we aim to design precoding vectors to maximize the utility function on the ergodic rates of users subject to a total transmit power constraint. By employing an upper bound of the ergodic rate, we leverage the corresponding Lagrangian formulation and identify the structural characteristics of the optimal precoder as the solution to a generalized eigenvalue problem. The Lagrange multipliers play a crucial role in determining both precoding directions and power parameters, yet are challenging to be solved directly. To figure out the Lagrange multipliers, we develop a general framework underpinned by a properly designed neural network that learns directly from CSI. To further relieve the computational burden, we obtain a low-complexity framework by decomposing the original problem into computationally efficient subproblems with instantaneous and statistical CSI handled separately. With the offline pre-trained neural network, the online computational complexity of precoder is substantially reduced compared with the existing iterative algorithm while maintaining nearly the same performance.

In this article, we investigate multi-cell scheduling for massive multiple-input-multiple-output (MIMO) communications with only statistical channel state information (CSI). The objective of multi-cell scheduling is to activate a subset of users so as to maximize the ergodic sum rate subject to per-cell total transmit power constraint. By adopting beam division multiple access based on the statistical CSI, i.e., channel-coupling matrix (CCM), we simplify multi-cell scheduling as a power control problem in the beam domain, by which the ergodic sum rate is maximized. To reduce the computational burden on finding the ergodic sum rate, we propose a learning-to-compute strategy, which directly computes the complex ergodic rate function from CCMs via a deep neural network. Specifically, by modeling the probability density function of the ordered eigenvalues of the Hermitian CCM matrices as exponential family distributions, a properly designed hybrid neural network makes the ergodic rate computation feasible. With the learning-to-compute strategy, the online computational complexity of multi-cell scheduling is substantially reduced compared with the existing Monte Carlo or deterministic equivalent (DE) based methods while maintaining nearly the same performance.

Link Adaptation can maximize system throughput while maintaining transmission reliability. With the growing demand for high-speed data transmission, multiple-input multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) technologies have been widely used in wireless communication systems. However, performing link adaptation in MIMO systems is challenging due to the complexity of channel and coupling among equalization, precoding, spatial mode, modulation and coding scheme (MCS). In this paper, we present a link adaptation scheme in MIMO systems through machine learning algorithms to maximize spectral efficiency while maintaining transmission reliability. We propose to use autoencoder model to extract feature from channel state information (CSI), combined with logical regression algorithms to select modulation and coding scheme. Spatial mode can be chosen based on the objective of maximizing the spectral efficiency. Simulation results demonstrate the improved performance and validate the application of the proposed learning based framework in MIMO systems.

The polythermal glacier is one of the dominant glaciers distributed widely in the transition zone of monsoon and continental climate, Tibetan Plateau. However, the glacier dynamics study of this type glacier is still limited in most of glaciated area due to the remote mountains, and high altitude issues. Meanwhile, the surface displacement of polythermal glacier appears strong variations both in seasonal and even shorter time-scales, based on the principles of glaciology mechanics. On one hand, this seasonal variations indicate drainage and movement of melting water between ice body and glacier bed. On the other hand, shorter variations relate to the amount of input water for this supraglacial drainage system. Here, we choose five typical polythermal type glaciers in Nyainqêntanglha Mountains, the south of Nam Co Lake, Tibetan Plateau for a case study. In this study we monitoring the ice surface displacement of these glaciers nearly two decades from 1993 to 2009 using features tracking method. Through this generation of ice motion maps, we intend to explore the association between spatial distribution of ice surface motion anomalies, and the possible patterns of ice speed variations during this period which responds to probable climate influence on surface melting.

Glaciers in the Tibetan mountains are expected to be sensitive to climate change. The change of glacier mass is locally depending on e.g. precipitation, melting and variation in ice flow. In this paper we analyze the data acquired by ICESat/GLAS laser altimetry, along several tracks over the glaciers of the Nyainqêntanglha range from February, 2003 to November, 2004. The surface characteristics are evaluated within laser footprints over the glacier outlines based on the glaciological inventory on the Tibetan Plateau constructed by CAREERI, CAS. For this purpose, we extract two waveform parameters: the waveform width and the number of modes. These parameters are compared with surface slope and roughness obtained from the ASTER GDEM (Global Digital Elevation Model).