In this paper, we propose a new concept of a knowledge management framework to enable a self-optimizing and self-learning for wireless system operation in real time. The framework encapsulates both environment and intelligent agent to reach optimal operation through sensing, perception, reasoning, and learning in a truly autonomous fashion. The agent derives adequate knowledge from previous actions improving the quality of future decisions. Domain experience was provided to guide the agent while exploring and exploiting the set of possible actions in the environment. Thus, it guarantees low-cost learning and achieves a near-optimal network configuration addressing the non-deterministic polynomial-time hardness problem of joint channel and location optimization in a wireless system. Extensive simulations are run to validate its fast convergence, high throughput, and resilience to dynamic interference conditions. We deploy the framework on off-the-shelf wireless devices to propose autonomous self-optimization with knowledge management.

The 16 articles in this special section examine both licensed and unlicensed spectrum for 5G/B5G wireless networks. The incredible increase in connected appliances and downloaded applications has pushed mobile operators to the limits of their licensed spectrum bands. This has triggered the idea of evolving the current radio access network to use the underutilized unlicensed spectrum to extend spectrum resources beyond current usage charts. This mode of cellular access has raised a lot of questions about use cases, enabling technologies, and fairness to other native unlicensed users, such as WiFi. Nevertheless, unlicensed access is being accepted as one of the most significant solutions to improve the resource availability and system scalability in future fifth generation (5G)/beyond 5G (B5G) networks.

Currently, blockchain technology has been widely used due to its support of transaction trust and security in next generation society. Using Internet of Things (IoT) to mine makes blockchain more ubiquitous and decentralized, which has become a main development trend of blockchain. However, the limited resources of existing IoT cannot satisfy the high requirements of on-demand energy consumption in the mining process through a decentralized way. To address this, we propose a decentralized on-demand energy supply approach based on microgrids to provide decentralized on-demand energy for mining in IoT devices. First, energy supply architecture is proposed to satisfy different energy demands of miners in response to different consensus protocols. Then, we formulate the energy allocation as a Stackelberg game and adapt backward induction to achieve an optimal profit strategy for both microgrids and miners in IoT. The simulation results show the fairness and incentive of the proposed approach.

In this paper, a novel interference mitigation and power allocation (PA) scheme is investigated for downlink non-orthogonal multiple access (NOMA) with multiple input multiple output (MIMO) technology in heterogeneous networks (HetNets). The proposed scheme, named PA based interference alignment and coordinated beamforming (PA-IA-CB), consists of two stages. The first stage applies two steps of IA-CB; one step for canceling the inter-cluster and the co-tier interference among small cells, whereas the other step deals with the inter-cluster interference within the macro cell. In the second stage, the cross-tier interference is proposed to be managed by properly handling the allocated power to the macro base station (MBS) and the small base stations (SBSs). The PA problem is modeled as a non-cooperative game between the MBS and the SBS with the aim of increasing the system sum rate. Simulation results verify the efficiency of the proposed technique in terms of total system sum rate and outage probability compared to the conventional schemes.

This paper discusses technology and opportunities to embrace artificial intelligence (AI) in the design of autonomous wireless systems. We aim to provide readers with motivation and general AI methodology of autonomous agents in the context of self-organization in real time by unifying knowledge management with sensing, reasoning and active learning. We highlight differences between training-based methods for matching problems and training-free methods for environment-specific problems. Finally, we conceptually introduce the functions of an autonomous agent with knowledge management.

Network slicing, a key enabler for future wireless networks, divides a physical network into multiple logical networks that can be dynamically created and configured. In current IEEE 802.11 (Wi-Fi) networks, the only form of network configuration is a rule-based optimization of few parameters. Future access points (APs) are expected to have self-organizational capabilities, able to deal with large configuration spaces in order to dynamically configure each slice. Deep Reinforcement Learning (DRL) can achieve promising results in highly dynamic and complex environments without the need for an operating model, by learning the optimal strategy after interacting with the environment. However, since the number of possible slice configurations is huge, achieving the optimal strategy requires an exhaustive learning period that might yield an outdated slice configuration. In this paper, we propose a fast-learning DRL model that can dynamically optimize the slice configuration of unplanned Wi-Fi networks without expert knowledge. Enhanced with an off-line learning step, the proposed approach is able to achieve the optimal slice configuration with a fast convergence, which is attractive for dynamic scenarios.

Orthogonal frequency-division multiplexing (OFDM) is a popular multi-carrier technique used in many digital communication systems such as wireless fidelity (Wi-Fi), long term evolution (LTE) and power line communication systems. It can be designed using fast Fourier transform (FFT) or wavelet transform (WT). The major drawback in using WT is that it is computationally inefficient. In this study, we introduce a simple and computationally efficient WT, harmonic wavelet transform, for OFDM signal processing. The new WT uses the orthogonal basis functions of conventional FFT-OFDM except that it involves translation and dilation of the input signal; the new wavelets is referred to as harmonic wavelets (HW). When compared with pilot-assisted OFDM system in terms of reduction in the peak-to-average power ratio, the results show that HW-OFDM outperforms FFT-OFDM by 3 dB at 10−4 CCDF (complementary cumulative distribution function). Over Rayleigh fading channel with additive white Gaussian noise (AWGN), the bit error ratio of both FFT-OFDM and HW-OFDM perfectly matched, showing that the proposed HW-OFDM is better in terms of peak-to-average power ratio reduction.

The rapid growth of Internet-of-Things (IoT) in the current decade has led to the development of a multitude of new access technologies targeted at low-power, wide area networks (LP-WANs). However, this has also created another challenge pertaining to technology selection. This paper reviews the performance of LP-WAN technologies for IoT, including design choices and their implications. We consider Sigfox, LoRaWAN, WavIoT, random phase multiple access (RPMA), narrowband IoT (NB-IoT), as well as LTE-M and assess their performance in terms of signal propagation, coverage and energy conservation. The comparative analyses presented in this paper are based on available data sheets and simulation results. A sensitivity analysis is also conducted to evaluate network performance in response to variations in system design parameters. Results show that each of RPMA, NB-IoT, and LTE-M incurs at least 9 dB additional path loss relative to Sigfox and LoRaWAN. This paper further reveals that with a 10% improvement in receiver sensitivity, NB-IoT 882 MHz and LoRaWAN can increase coverage by up to 398% and 142%, respectively, without adverse effects on the energy requirements. Finally, extreme weather conditions can significantly reduce the active network life of LP-WANs. In particular, the results indicate that operating an IoT device in a temperature of −20 °C can shorten its life by about half; 53% (WavIoT, LoRaWAN, Sigfox, NB-IoT, and RPMA) and 48% in LTE-M compared with environmental temperature of 40 °C.

With the ever increasing cell densities in wireless networks, it is desired to enable more self-X features, such as self-configuration. Setting the network parameters in an autonomous manner is not only more time efficient but also increases network performance and reduces the probability of a human error. Among numerous network settings, one of the key parameters that requires such autonomous configuration is the cell ID (CID). It is used during fundamental procedures, such as network access, decoding, or handover, and therefore, its configuration is crucial for network operation. A complete CID management framework together with a centralized method for CID assignment is presented in this paper. It is not only applicable to multiple mobile standards but is also compatible with multi-vendor equipment, since it is based on the TR-069 management protocol. The proposed approach mitigates CID conflicts when there is a high level of reuse. Moreover, in the 4G case it also prevents neighbors from using different CID but with the same reference signal pattern, which avoids significant interference. The proposed method is evaluated in an enterprise small cell scenario, and in comparison with the baseline third generation partnership project approach, significant reductions of assignment conflicts are demonstrated.

Pilot contamination due to pilot reuse in adjacent cells is a very serious problem in massive multi-input multiple-output (MIMO) systems. Therefore, proper pilot allocation is essential for improving system performance. In this paper, we formulate the pilot allocation optimization problem so as to maximize uplink sum rate of the system. To reduce the required complexity inherent in finding the optimum pilot allocation, we propose a low-complexity pilot allocation algorithm, where the formulated problem is decoupled into multiple subproblems; in each subproblem, the pilot allocation at a given cell is optimized while the pilot allocation in other cells id held fixed. This process is continued until the achievable sum rate converges. Through multiple iterations, the optimum pilot allocation is found. In addition, to improve users’ fairness, we formulate fairness-aware pilot allocation as maximization problem of sum of user’s logarithmic rate and solve the formulated problem using a similar algorithm. Simulation results show that the proposed algorithms match the good performance of the exhaustive search algorithm, meanwhile the users’ fairness is improved. key words: pilot contamination, massive MIMO, pilot allocation

The lattice <inline-formula><tex-math notation="LaTeX">$\mathcal {L}(\boldsymbol{A})$</tex-math></inline-formula> of a full-column rank matrix <inline-formula><tex-math notation="LaTeX">$\boldsymbol{A}\in \mathbb {R}^{m\times n}$</tex-math></inline-formula> is defined as the set of all the integer linear combinations of the column vectors of <inline-formula><tex-math notation="LaTeX">$\boldsymbol{A}$</tex-math></inline-formula>. The successive minima <inline-formula><tex-math notation="LaTeX">$\lambda _i(\boldsymbol{A}),\,1\leq i\leq n,$</tex-math></inline-formula> of lattice <inline-formula><tex-math notation="LaTeX">$\mathcal {L}(\boldsymbol{A})$</tex-math></inline-formula> are important quantities since they have close relationships with the following problems: shortest vector problem, shortest independent vector problem, and successive minima problem. These problems arise from many practical applications, such as communications and cryptography. This paper first investigates some properties of <inline-formula><tex-math notation="LaTeX">$\lambda _i(\boldsymbol{A})$</tex-math></inline-formula>. Specifically, we develop lower and upper bounds on <inline-formula><tex-math notation="LaTeX">$\lambda _i(\boldsymbol{A})$</tex-math></inline-formula>, where <inline-formula><tex-math notation="LaTeX">$\boldsymbol{A}$</tex-math></inline-formula> are, respectively, the Cholesky factor of <inline-formula><tex-math notation="LaTeX">$\boldsymbol{G}_1+\boldsymbol{G}_2$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$(\boldsymbol{G}_1+\boldsymbol{G}_2)^{-1}$</tex-math></inline-formula> for two given symmetric positive definitive matrices <inline-formula><tex-math notation="LaTeX">$\boldsymbol{G}_1$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$\boldsymbol{G}_2$</tex-math></inline-formula>. The bounds are, respectively, expressed as the successive minima of <inline-formula><tex-math notation="LaTeX">$\mathcal {L}(\boldsymbol{A}_1)$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$\mathcal {L}(\boldsymbol{A}_2)$</tex-math></inline-formula>, and <inline-formula><tex-math notation="LaTeX">$\mathcal {L}(\hat{\boldsymbol{A}}_1)$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$\mathcal {L}(\hat{\boldsymbol{A}}_2)$</tex-math></inline-formula>, where <inline-formula><tex-math notation="LaTeX">$\boldsymbol{A}_1, \boldsymbol{A}_2, \hat{\boldsymbol{A}}_1$</tex-math></inline-formula> and <inline-formula><tex-math notation="LaTeX">$\hat{\boldsymbol{A}}_2$</tex-math></inline-formula> are, respectively, the Cholesky factors of <inline-formula><tex-math notation="LaTeX">$\boldsymbol{G}_1, \boldsymbol{G}_2, \boldsymbol{G}_1^{-1}$</tex-math></inline-formula>, and <inline-formula><tex-math notation="LaTeX">$\boldsymbol{G}_2^{-1}$</tex-math></inline-formula>. Then, we show how some properties of <inline-formula><tex-math notation="LaTeX">$\lambda _i(\boldsymbol{A})$</tex-math></inline-formula> are used to design a suboptimal integer-forcing strategy for cloud radio access network. Our approach provides much higher time efficiency while keeping the same achievable rate as the algorithm reported by Bakoury and Nazer (I. E. Bakoury and B. Nazer, “Integer-forcing architectures for uplink cloud radio access networks,” in <italic>Proc. 55th Annu. Allerton Conf. Commun. Control Comput.</italic>, Oct. 2007, pp. 67–75). Simulation tests are performed to illustrate our main results.

In this paper, a novel interference management technique based on compressive sensing (CS) theory is investigated for downlink non-orthogonal multiple access (NOMA) heterogeneous networks (HetNets). We mathematically formulate the interference management problem in terms of power and resource blocks (RBs) allocation to maximize the overall sum rate while considering both co-tier and cross-tier interferences and then explain its non-convexity. In this paper, we exploit the sparsity of the allocated RBs to relax the non-convexity of the formulated problem by transforming it into a sparse <inline-formula> <tex-math notation="LaTeX">$l_{1}$ </tex-math></inline-formula>-norm problem for a near-optimum solution. Then, based on the CS theory, an interference management technique with a restricted weighted fast iterative shrinkage-thresholding (R-WFISTA) algorithm is proposed to solve the equivalent sparse <inline-formula> <tex-math notation="LaTeX">$l_{1}$ </tex-math></inline-formula>-norm problem. The simulation results verify that compared with the conventional orthogonal multiple access (OMA) HetNets and conventional NOMA HetNets, the proposed technique improves the system performance in terms of overall sum rate and the outage probability.

In this paper, we propose an enhanced selected mapping (e-SLM) technique to improve the performance of OFDM-PLC systems under impulsive noise. At the transmitter, the best transmit sequence is selected from among possible candidates so as to minimize the weighted sum of transmit signal peak power and the estimated receive one, where the received signal peak power is estimated at the transmitter using channel state information (CSI). At the receiver, a nonlinear blanking is applied to hold the impulsive noise under a given threshold, where impulsive noise detection accuracy is improved by the proposed e-SLM. We evaluate the probability of false alarms raised by impulsive noise detection and bit error rate (BER) of OFDM-PLC system using the proposed e-SLM. The results show the effectiveness of the proposed method in OFDM-PLC system compared with the conventional blanking technique. key words: power-line communications (PLC), OFDM, impulsive noise blanking, peak-to-average power ratio (PAPR), selected mapping (SLM)

Vehicular communications provide effective means to improve road safety and traffic efficiency, as well as high definition onboard infotainment services, capable of scaling well from current connected cars to future autonomous driving. Dedicated short-range communications (DSRC) and Long Term Evolution vehicle-to-everything (LTE-V2X) are recognized as being the two most promising technologies to support such communications. For more than a decade, DSRC has been actively promoted by ETSI, IEEE, and other standards organizations. More recently, LTEV2X is being proposed as an alternative technology based on cellular standards by 3GPP. This article analyzes the ready-to-deploy DSRC and the promising LTE-V2X, compares them according to a set of significant technical and non-technical aspects, and outlines the limitations of both technologies.