Spectrum sharing enables multiple wireless technologies—either from different standards (e.g., 4G and 5G) or different protocols of the same standard (e.g., IEEE 802.11 family of protocols)—to operate within the same frequency band with minimal interference. A wireless system that shares spectrum with signal/protocol awareness can allocate more spectrum for dynamic channel access. This paper introduces a Transformer-Based algorithm developed specifically for Wireless Local Area Network (WLAN) radio protocol recognition, leveraging low-cost SDR-based spectrum sensing capabilities. Unlike traditional approaches that require gigabytes of training data, our method achieves satisfactory results using only 100k (approximately 100–400megabytes of data) samples in total. The paper makes three key contributions: First, the model is trained on only 33k samples per protocol using a customized Transformer tailored for protocol classification. Second, over-the-air test datasets demonstrated near-perfect detection accuracy (exceeding 99%) at 20 dB signal-to-noise ratio (SNR) and above, enabling SDR-based spectrum sensing. Third, experiments conducted with real WLAN traffic generated using development boards achieved detection accuracy of at least 96%. We compared our Transformer-Based model with CNN and MLP classifiers and found that it consistently outperformed them in protocol recognition, even with minimal training data. Our findings suggest that intelligent spectrum sensing is achievable using low-cost devices, and that algorithms trained on compact datasets can attain state-of-the-art detection accuracy.

To achieve radio spectrum awareness for current and next generation wireless communication systems, it is critical to develop the capability of super-wideband spectrum sensing with low-cost devices. In this paper, we report a novel wideband sensing structure that uses an analog-to-digital converter (ADC) board and a band-pass-filter (BPF) to form a spectrum sensor, which achieves several gigahertz (GHz) of sensing bandwidth and includes spectrum sensing in the 6 GHz unlicensed band as one application example. This structure uses direct radio frequency (RF) sampling with the ADC board, and the BPF passes only the RF band of interest that lies in the high-order Nyquist zone, which is then aliased to the baseband and captured. This method avoids the use of RF mixers or downconverters. To test its feasibility and performance, we develop customized software-defined radio (SDR) functions that allows an SDR transmitter to send multiple arbitrary waveforms on its multiple transmission ports over a large carrier frequency range simultaneously. We use the ADC board to capture several signals transmitted in the 6 GHz band for spectrum analysis and RF parameter estimation, such as the center frequency, bandwidth, and signal-to-noise ratio (SNR) of each signal. We compare the signal parameters of the data captured by this method with those reported by a high-end, commercial-grade spectrum analyzer (SA). The measurement results show that this method can achieve a satisfactory quality of signal detection, and verify the feasibility of the super-wideband spectrum sensing approach with a simplified structure.

The mmWave radio frequency (RF) spectrum allocations provide a large bandwidth and an excellent dynamic spectrum sharing (DSS) opportunity for emerging 5G NewRadio unlicensed (NR-U) and Wireless Gigabit (WiGig) services. To support constructive DSS, we outline a new modeling and analytical method to jointly evaluate the effects of a multiplebeam directional listen-before-talk (MB-DLBT) protocol, intercell interferences (ICIs), and spectrum sensing errors on the NR-U and WiGig DSS system performance. Available works did not provide a systematic and analytical approach to evaluate these effects, but only relied on computer simulations. Our numerical evaluation provides an insightful observation on the performance advantage of the MB-DLBT over the single-beam DLBT and omni-directional LBT schemes. This result provides a powerful tool to support performance analysis and optimization of mmWave DSS schemes.

Radio spectrum is a scarce resource. To meet demands, new wireless technologies must operate in shared spectrum over unlicensed bands (coexist). We consider coexistence of Long-Term Evolution (LTE) License-Assisted Access (LAA) with incumbent Wi-Fi systems. Our scenario consists of multiple LAA and Wi-Fi links sharing an unlicensed band; we aim to simultaneously optimize performance of both coexistence systems. To do this, we present a technique to continuously estimate the Pareto frontier of parameter sets (traces) which approximately maximize all convex combinations of network throughputs over network parameters. We use a dimensionality reduction approach known as active subspaces to determine that this near-optimal parameter set is primarily composed of two physically relevant parameters. A choice of two-dimensional subspace enables visualizations augmenting explainability and the reduced-dimension convex problem results in approximations which dominate random grid search.

The radio spectrum is becoming an increasingly scarce and valuable resource to such an extent that sharing the unlicensed bands is inevitable. In this work, we consider a multi-cell, multi-user massive multiple-input multiple-output (MIMO) coexistence scenario where multiple 5G New Radio Unlicensed (NR-U) and Wireless Gigabit (WiGig) links share an unlicensed millimeter-wave band. Our aim is to enhance the performance of coexisting networks by maximizing the overall network throughput via hybrid beamforming. This throughput is a function of both operators' medium access control protocols and physical layer parameters. To maximize the overall network throughput we propose a novel hidden node aware hybrid beamforming design. The hybrid precoders and combiners are optimal in the sense that they simultaneously maximize the signal power at desired users while minimizing the received inter-cell and intra-cell interferences at undesired users (leakage). The performance of the proposed scheme is examined through simulation. A comparison among the proposed method, a beam-steering solution, and an optimal unconstrained precoding design indicates the efficiency of the proposed algorithm.

To meet the ever-growing demands of data throughput for forthcoming and deployed wireless networks, new wireless technologies like Long-Term Evolution License-Assisted Access (LTE-LAA) operate in shared and unlicensed bands. However, the LAA network must co-exist with incumbent IEEE 802.11 Wi-Fi systems. We consider a coexistence scenario where multiple LAA and Wi-Fi links share an unlicensed band. We aim to improve this coexistence by maximizing the key performance indicators (KPIs) of these networks simultaneously via dimension reduction and multi-criteria optimization. These KPIs are network throughputs as a function of medium access control protocols and physical layer parameters. We perform an exploratory analysis of coexistence behavior by approximating active subspaces to identify low-dimensional structure in the optimization criteria, i.e., few linear combinations of parameters for simultaneously maximizing KPIs. We leverage an aggregate low-dimensional subspace parametrized by approximated active subspaces of throughputs to facilitate multi-criteria optimization. The low-dimensional subspace approximations inform visualizations revealing convex KPIs over mixed active coordinates leading to an analytic Pareto trace of near-optimal solutions.

Future unlicensed spectrum sharing scenarios involve multi-cell, multi-tier access of incumbent and emerging wireless systems, such as wireless local area network (WLAN), New-Radio unlicensed (NR-U), and Long-Term Evolution (LTE) with Licensed-Assisted Access (LAA). Listen-before-talk (LBT) medium access control (MAC) is a common technique used for channel sensing and access control. Despite intense research efforts, the majority of available results have not accurately analyzed multi-cell LBT with imperfect spectrum sensing. Furthermore, while past studies involved two major spectrum sharing strategies - shared cell access (SCA) and exclusive cell access (ECA), they missed a systematic comparison between the two. In this paper, we develop a unified analytical approach which maps the effects of imperfect spectrum sensing and multi-cell, multi-tier LBT to the key performance indicators (KPIs) of LAA and WLAN cells. We provide an analytical comparison between the SCA and ECA schemes, and show that the SCA can provide a significantly higher system throughput than the ECA as a function of sensing thresholds. We program the SCA and ECA algorithms with a new simulation method and implement Monte Carlo simulations, which verify our analytical results. Numerical results provide insightful observations on effects of various parameters. These results provide powerful analytical and simulation tools to evaluate the performance of multi-tier LBT coexistence systems with imperfect sensing, and effectively support coexistence system optimization.

Dynamic spectrum access (DSA) to achieve spectrum sharing in unlicensed bands is a promising approach for meeting the growing demands of forthcoming and deployed wireless networks, such as long-term evolution license-assisted access (LTE-LAA) and IEEE 802.11 Wi-Fi systems. In this paper, we consider a coexistence scenario where multiple LAA and Wi-Fi links compete for spectrum sharing subchannel access. We introduce a reinforcement-learning-based subchannel selection technique which allows access points (APs) and eNBs to select best subchannel distributively considering their medium access control (MAC) channel access protocols along with the physical layer parameters. The performance of this scheme is investigated through simulations, including the convergence property and sum throughput. Numerical results show that the proposed reinforcement-learning scheme converges fast and the sum throughput of the LAA and Wi-Fi systems is reasonably close to the result based on exhaustive search.

Massive multiple input multiple output (MIMO) systems are a promising technology for next generation wireless communications due to their ability to increase capacity and enhance both spectrum and energy efficiency. To utilize the benefit of massive MIMO systems, accurate downlink channel state information at the transmitter (CSIT) is essential. Conventional approaches to obtain CSIT for frequency-division duplex (FDD) multi-user massive MIMO systems require downlink training and uplink CSI feedback. However, such training results in large overhead for massive MIMO systems because of the large dimensionality of the channel matrix. In this paper, we investigate the channel estimation problem in FDD multi-user massive MIMO systems with spatially correlated channels and develop an efficient channel estimation algorithm that exploits the sparsity structure of the downlink channel matrix. The proposed algorithm selects the best features from the measurement matrix to obtain efficient CSI acquisition that can reduce the downlink training overhead compared with the conventional LS/MMSE channel estimators. We compare the performance of our proposed channel estimation method with traditional ones in terms of normalized mean square error (MSE). Simulation results verify that the proposed algorithm can significantly reduce the pilot overhead and has better performance compared with the traditional channel estimation methods.

Reservoir computing (RC) is a class of neuromorphic computing approaches that deals particularly well with time-series prediction tasks. It significantly reduces the training complexity of recurrent neural networks and is also suitable for hardware implementation whereby device physics are utilized in performing data processing. In this paper, the RC concept is applied to detecting a transmitted symbol in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. Due to wireless propagation, the transmitted signal may undergo severe distortion before reaching the receiver. The nonlinear distortion introduced by the power amplifier at the transmitter may further complicate this process. Therefore, an efficient symbol detection strategy becomes critical. The conventional approach for symbol detection at the receiver requires accurate channel estimation of the underlying MIMO-OFDM system. However, in this paper, we introduce a novel symbol detection scheme where the estimation of the MIMO-OFDM channel becomes unnecessary. The introduced scheme utilizes an echo state network (ESN), which is a special class of RC. The ESN acts as a black box for system modeling purposes and can predict nonlinear dynamic systems in an efficient way. Simulation results for the uncoded bit error rate of nonlinear MIMO-OFDM systems show that the introduced scheme outperforms conventional symbol detection methods.

A cloud radio access network (Cloud-RAN) is a network architecture that holds onto the promise of meeting the explosive growth of mobile data traffic. Cloud-RAN consists a central processor (CP) connecting to multiple multi-antenna base stations (BSs) via finite-capacity backhaul links. To reduce the backhaul traffic, BS-level caching technique is utilized in which the popular contents are pre-fetched in memories at each BS. This technique plays an important role in future wireless big data processing due to its simplicity, low cost, and natural integration with big data analytical tools. Considered the tradeoff between the backhaul and the transmission power cost, in this paper we define the network cost of the system as a normalized weighted sum. The problem of minimizing the network cost with respect to both the precoding matrix and the cache placement matrix is formulated subject to the quality of service (QoS), peak transmission power, and cache capacity constraints. The l0-norm in the objective function along with the QoS constraints renders the optimization problem non-convex. Additionally, since the entries of cache placement matrix take binary values, the optimization problem falls into a mixed integer nonlinear programming (MINLP) which is a NP-hard problem. An iterative coordinated data assignment algorithm is introduced which achieves a stationary point of the problem. Simulations are conducted to illustrate the performance of introduced algorithm. It suggests that the introduced scheme can significantly reduce the total network cost of the underlying Cloud-RAN network and demonstrate the importance of considering the designing of cache placement matrix.

Reservoir computing (RC) is attracting widespread attention in several signal processing domains owing to its nonlinear stateful computation. It deals particularly well with time-series prediction tasks and reduces training complexity over recurrent neural networks. It is also suitable for hardware implementation whereby device physics are utilized in performing data processing. In this paper, the RC concept is applied to modeling a Multiple-Input Multiple-Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system. Due to the harsh propagation environment, the transmitted signal undergoes severe distortion that must be compensated for at the receiver. The nonlinear distortion introduced by the power amplifier at the transmitter further complicates this process. An effective channel estimation scheme is therefore required. In this paper, we introduce a MIMO-OFDM channel estimation scheme utilizing Echo State Network (ESN). Echo State Networks are powerful recurrent neural networks that can predict time-series very well. They acts as a black-box for system modeling purposes and models nonlinear dynamic systems efficiently. Simulation results for the bit error rate of the nonlinear MIMO-OFDM system show that the introduced channel estimator outperforms commonly used channel estimation schemes.

To suppress the co-channel interference in a multi-cell multi-user multiple-input-multiple-output downlink cellular network, a novel interference alignment transceiver beam-forming design along with a low complexity iterative coordinated beam-forming scheme is introduced. While the latter combats the intra-cell interference, the former is utilized to mitigate the inter-cell interference. The proposed schemes consider the codebook-based feedback, which is adopted in the LTE/LTE-advanced systems. Optimal downlink user-specific and cell-specific beam-forming matrices are characterized to maximize the lower bound of expected signal-to-leakage-plus-noise ratio and to minimize the residual inter-cell interference, respectively. Moreover, closed-form expressions for these beam-forming matrices under limited channel state information feedback and in the presence of the quantization error are identified. Simulations are conducted to investigate the performance of the proposed strategy. The results indicate that our scheme can significantly improve the average spectral-efficiency of the underlying network when compared with existing ones where the quantization error is neglected. Furthermore, for a fixed payload size of the codebook, unlike zero-forcing beam-forming in which the sum throughput is bounded as the signal-to-noise ratio (SNR) increases, in our scheme, the performance gap between rank 2 feedback and perfect feedback remains approximately constant as SNR increases.

Coordinated multi-point (CoMP) transmission and reception are introduced as a promising technology in the 3GPP LTE-advanced standard, to manage interference, improve the overall system performance, and enhance system reliability. In this paper, a resource allocation problem is studied for downlink CoMP coordinated beamforming systems, where each base station (BS) serves its own mobile stations. Multiple-input-multiple-output (MIMO) transmit precoding and resource allocation are linked to the underlying proportional-fair scheduling to ensure a good trade-off between cell-average and cell-edge user spectral-efficiency. Due to the coupled interference among mobile stations, the resulting proportional-fair resource allocation optimization problem becomes nonconvex. To solve for optimal operating point for MIMO CoMP network, a parallel successive convex approximation-based algorithm is introduced. The introduced scheme enables all BSs to update their optimization variables in parallel by solving a sequence of strongly convex subproblems. Closed-form expressions of the locally optimal solution in both the high and low signal-to-noise regimes are characterized. The performance of the introduced scheme is also investigated through simulations. Numerical results show the efficiency of the introduced algorithm.