Node-similarity distributions not only characterize different types of complex networks, but also offer insights in the structural predictability of complex networks, and even facilitate prediction tasks in complex networks. By means of the generating function, we propose a framework to calculate the common neighbor based similarity (CNS) distributions, offering theoretical results of similarity distributions of various complex networks. Furthermore, we apply node-similarity distributions to link prediction, a key task in network analysis. Specifically, by deriving analytical solutions for two metrics: i) precision and ii) area under the receiver operating characteristic curve (AUC), we give theoretical evaluation of link prediction. Also, by analyzing i) the expected prediction accuracy of similarity scores and ii) optimal prediction priority of unconnected node pairs, we optimize link prediction with similarity distributions. Simulation results confirm our findings and also validate the proposed methods for evaluating and optimizing link prediction.

It is a promising technology to replace traditional transceiver design with neural network (NN)-based autoencoder to realize end-to-end communication. The joint optimization of multiple blocks helps the communication system to achieve better performance. However, this approach needs a differentiable channel modeling to train both NNs at the transceiver. For a non-differentiable channel in a real scenario, gradient backpropagation cannot be performed. In this paper, we propose a Kalman-based autoencoder framework to achieve gradient estimation and backpropagation by adding a control layer at the last layer of the encoder NN, which combines the rich feature representations learned by the NN with the Bayesian filter method based on Extended Kalman Filter (EKF) and Cubature Kalman Filter (CKF). According to simulation results, the proposed framework has a fast convergence rate and strong robustness in both additive white Gaussian noise (AWGN) and Rayleigh block fading (RBF) of perturbation scenarios.

To improve the system performance towards the Shannon limit, advanced radio resource management mechanisms play a fundamental role. In particular, scheduling should receive much attention, because it allocates radio resources among different users in terms of their channel conditions and QoS requirements. The difficulties of scheduling algorithms are the tradeoffs need to be made among multiple objectives, such as throughput, fairness and packet drop rate. We propose a smart scheduling scheme based on deep reinforcement learning (DRL). We not only verify the performance gain achieved, but also provide implementation-friend designs, i.e., a scalable neural network design for the agent and an offline training framework. With the scalable neural network design, the DRL agent can easily handle the cases when the number of active users is time-varying without the need to redesign and retrain the DRL agent. Training the DRL agent offline first and using it as the initial version in the practical usage help to prevent the system from suffering from performance and robustness degradation due to the time-consuming training. Through both simulations and field tests, we show that the DRL-based smart scheduling outperforms the conventional scheduling method and can be adopted in practical systems.

In this paper, the downlink packet scheduling problem for cellular networks is modeled, which jointly optimizes throughput, fairness and packet drop rate. Two genie-aided heuristic search methods are employed to explore the solution space. A deep reinforcement learning (DRL) framework with Advantage actor-critic (A2C) algorithm is proposed for the optimization problem. Several methods have been utilized in the framework to improve the sampling and training efficiency and to adapt the algorithm to a specific scheduling problem. Numerical results show that DRL outperforms the baseline algorithm and achieves similar performance as genie-aided methods without using the future information.

The applications of artificial intelligence (AI) and machine learning (ML) technologies in wireless communications have drawn significant attention recently. AI has demonstrated real success in speech understanding, image identification, and natural language processing domains, thus exhibiting its great potential in solving problems that cannot be easily modeled. AI techniques have become an enabler in wireless communications to fulfill the increasing and diverse requirements across a large range of application scenarios. In this paper, we elaborate on several typical wireless scenarios, such as channel modeling, channel decoding and signal detection, and channel coding design, in which AI plays an important role in wireless communications. Then, AI and information theory are discussed from the viewpoint of the information bottleneck. Finally, we discuss some ideas about how AI techniques can be deeply integrated with wireless communication systems.

Accurate prediction of fading channel in the upcoming transmission frame is essential to realize adaptive transmission for transmitters, and receivers with the ability of channel prediction can also save some computations of channel estimation. However, due to the rapid channel variation and channel estimation error, reliable prediction is hard to realize. In this situation, an appropriate channel model should be selected, which can cover both the statistical model and small scale fading of channel, this reminds us the natural languages, which also have statistical word frequency and specific sentences. Accordingly, in this paper, we take wireless channel model as a language model, and the time-varying channel as talking in this language, while the realistic noisy estimated channel can be compared with mumbling. Furthermore, in order to utilize as much as possible the information a channel coefficient takes, we discard the conventional two features of absolute value and phase, replacing with hundreds of features which will be learned by our channel model, to do this, we use a vocabulary to map a complex channel coefficient into an ID, which is represented by a vector of real numbers. Recurrent neural networks technique is used as its good balance between memorization and generalization, moreover, we creatively introduce sequence-to-sequence (seq2seq) models in time series channel prediction, which can translate past channel into future channel. The results show that realistic channel prediction with superior performance relative to channel estimation is attainable.

A special permutation group of polar codes based on$N$/4-cyclic shift is designed and analyzed for practical use. A permutation-transformation equivalence is firstly introduced to transfer the effect of permutation on the codeword side to the uncoded side. Then, we introduce the$N$/4-cyclic shift permutation and analyze the conditions under which it can permute a codeword to another for polar codes that even do not fully respect partial order. We also reveal that the value assignment of frozen bits should follow specific rules related to the permutation pattern. Finally, a novel polar-specific implicit indication method is presented by applying the$N$/4-cyclic shift permutation group to the practical wireless communication scenarios such as Physical Broadcasting Channel (PBCH) of a cellular network, which significantly simplifies the detection algorithm.

In this paper, we propose a comprehensive Polar coding solution that integrates reliability calculation, rate matching and parity-check coding. Judging a channel coding design from the industry's viewpoint, there are two primary concerns: (i) low-complexity implementation in application-specific integrated circuit (ASIC), and (ii) superior \& stable performance under a wide range of code lengths and rates. The former provides cost- \& power-efficiency which are vital to any commercial system; the latter ensures flexible and robust services. Our design respects both criteria. It demonstrates better performance than existing schemes in literature, but requires only a fraction of implementation cost. With easily-reproducible code construction for arbitrary code rates and lengths, we are able to report ``1-bit'' fine-granularity simulation results for thousands of cases. The released results can serve as a baseline for future optimization of Polar codes.

Polarization weight (PW) is a novel construction method for polar codes, which results in universal reliability ordering efficiently and yields imilar performance as other channel dependent construction methods. In this paper, we interpret PW method or algorithm from a rate allocation perspective of channel polarization to show its effectiveness. Take the AWGN channel as an example, we show that the rate allocation for information bits by PW method coincides with the capacities of channel polarization. Furthermore, some properties of PW algorithm, including the universal and fractal of the reliability ordering, are illustrated, which facilitate the implementation in practice. Comprehensive simulation results with various code rates, code lengths and list sizes are also shown to validate the effectiveness of PW method.

Three 5G enabling technologies, i.e, sparse code multiple access (SCMA), Polar codes and filtered OFDM (f-OFDM), are implemented into a massive MIMO system in the field trial conducted by HUAWEI and NTT DOCOMO to investigate their impacts on the system spectral efficiency. Taking massive MIMO with OFDMA and Turbo codes as the baseline, we observe about 30% downlink spectral efficiency improvement in the trial. Results from test field are summarized and analyzed in this paper, which verified that SCMA, Polar codes and f- OFDM are also feasible for massive MIMO systems in terms of spectral efficiency improvement.

A large scale field trial is conducted to investigate the integrated performance of massive multiple-input multiple-output (MIMO) and polar code, which are two key technologies for 5th generation (5G) mobile system. A more simple and effective algorithm named polarization weight (PW) is used in polar construction. Based on uplink and downlink channel reciprocity in the time-division duplex (TDD) mode, the practical performance of single user (SU) massive MIMO prototype with 64 independent RF channels and 200 MHz bandwidth is investigated under different user equipment (UE) deployments, different layer numbers and moving speeds. Compared to massive MIMO with turbo code, it is shown that significant performance gains can be obtained in TDD massive MIMO system with polar code. For 3 layers scheduled in massive MIMO system with polar code, the maximum user throughput of 1.64 Gbps and spectrum efficiency of 11.64 bit/s/Hz can be achieved. Based on these observations, the feasibility and performance of TDD massive MIMO system with polar code are verified.

Spectral efficiency is always a key factor to be improved and optimized along mobile communication networks evolving generation by generation. 5G enabling technologies must take spectral efficiency into consideration. In this paper, we show the performance of three key 5G technologies in sense of spectral efficiency improvement. Sparse code multiple access, polar codes, and filtered orthogonal frequency-division multiplexing are novel multiple access technology, channel coding scheme, and waveform, respectively. The combination of them is implemented in a 5G field trial testbed by NTT DOCOMO and Huawei for the first time. According to the field test results, we achieve over 100% spectral efficiency improvement comparison with baseline, where orthogonal frequency-division multiple access and turbo coding as LTE are used.

5G IoT communications have some new requirements on the whole system design, e.g., low cost, low power consumption, long distance coverage and massive connection. To fulfill all these requirements, a narrow-band SCMA scheme is proposed. Narrow band pulse shaping is employed, so that the coverage can be expanded with low-cost and low-power devices. Two types of waveforms are provided, both of which use SCMA to enlarge the number of supported devices. Simulation results show that, comparing to the existing narrow band techniques, narrow-band SCMA scheme can support more dense connectivity without any other performance degradation.

To support delay-sensitive traffic in multi-channel cognitive radio systems, designing a channel access scheme faces two major challenges, namely, the long waiting time due to continuous channel occupancy of primary users (PUs) and the performance degradation due to transmission collisions among secondary users (SUs). To address both issues, we propose a two-phase channel access scheme, which consists of a distributed channel negotiation phase and a hopping-based channel access phase for each SU. Specifically, in its first phase, an SU attempts to negotiate a specific initial slot/channel differing from the ones chosen by other SUs. Then, in its second phase, the SU chooses a channel in each time slot in a hopping-based manner to transmit data, where the hopping starts from its initial channel and follows a common hopping sequence. Virtual channels are introduced to accommodate the situation when the number of SUs is larger than that of actual channels. The average maximal waiting time due to the channel negotiation phase is derived, and the effective capacity of the service process for each SU in the channel access phase is analyzed. Numerical results show that the proposed scheme can support a higher traffic load under the statistical delay constraint, as compared with fixed or random channel access schemes.

In multi-channel multi-user cognitive radio systems, there are two main challenges to support traffic with delaysensitive QoS requirements, namely, the coordination among the secondary users (SUs) and the long channel occupancy time of the primary users (PUs). In this paper, we propose a hopping-based channel access scheme for SUs to improve their performance. Each SU chooses one of the channels allocated to PUs in a hopping-based manner in each time slot to opportunistically sense and transmit. This scheme not only avoids collisions among SUs, but also reduces the effect of the long channel occupancy time of PUs on the QoS performance of the SUs' delay-sensitive applications. We analyze the effective capacity of SU's service process with our proposed scheme. Numerical results show that our proposed scheme can achieve a higher effective capacity compared to random or fixed channel allocation.

In this paper, we investigate the TCP throughput performance enhancement for cognitive radio networks (CRNs) through lower-layer configurations. There is an interaction between TCP and the lower-layer operations. The TCP sending rate at the transport layer determines the packet arrival rate of the lower-layer buffer, and meanwhile it is influenced by the average round trip time and packet loss rate, which are determined by the lower-layer mechanisms and configurations. Therefore, an iteration process is employed to investigate the TCP throughput under given channel condition and lower-layer configurations. For each iteration, queueing analysis is done to derive the packet loss rate and average delay on wireless link, which are then used to calculated the TCP throughput. Through derivations and numerical evaluations, the impacts of lower-layer parameters, primary user (PU) activities and channel conditions on the TCP throughput are discussed. Moreover, the way how these factors influence the TCP throughput is tracked. By using the proposed analytical method, TCP throughput enhancement can be achieved through appropriately setting lower-layer configurations.

In this paper, the queue dynamics of secondary users (SUs) in a multi-SU and multi-channel cognitive radio network is analyzed to obtain the expressions of quality of service (QoS) metrics. Specially, in the analysis, we take several lower-layer mechanisms and settings into account, including automatic repeat request (ARQ), finite-size buffer, adaptive modulation and coding (AMC) and non-ignorable spectrum sensing errors. By modeling the queue dynamics as a Markov chain, we derive the analytical expressions of queue length, packet dropping rate and packet collision rate. Based on these expressions, the QoS metrics including delay, packet loss rate and throughput are calculated further. Through simulation, our queueing analysis is verified and the QoS metrics are investigated.

For mitigating inter-symbol interference (ISI) and inter-carrier interference (ICI) caused by insufficient cyclic prefix (CP), per-tone equalizer (PTEQ) outperforms traditional time domain equalizer (TEQ) since each tone is equalized independently. However, PTEQ with equal number of taps (equal length) for all the tones can not achieve the optimal performance because channel conditions of different tones between different transmit and receive antennas are not the same. Variable-length PTEQ can make full use of each tap, however it is difficult to design for MIMO-OFDM because its design needs exhaustive search and results in extremely high complexity. In this paper, a novel algorithm of designing variable-length PTEQ is proposed. The design is realized in two steps--tap number allocation and tap coefficient calculation, so that the complexity is low. The tap number allocation and the optimal coefficient calculation are based on channel conditions, so that better system performance can be achieved than using equal-length PTEQ. Simulation is carried out and main parameters are investigated.