Channel estimation is one of the most fundamental and performance-limiting operations in fifth-generation (5G) and emerging sixth-generation (6G) wireless networks, where ultra-massive MIMO arrays, millimetre-wave and terahertz carrier frequencies, and non-Gaussian hardware-induced noise combine to render classical least-squares and minimum mean squared error estimators inadequate. Deep learning has narrowed the performance gap, yet it offers no information-theoretic guarantee on how close any particular network architecture is to the fundamental noise floor. This paper introduces the AI-Quantum Channel Modeling and Estimation (AQCME) framework, which integrates variational quantum circuits, quantum signal processing, and a quantum eigenspace denoising operator into a unified trainable architecture for simultaneous channel estimation and noise suppression in MIMO-OFDM systems. The defining theoretical result is a quantum Cramer-Rao lower bound on normalised mean squared error, grounded in the quantum Fisher information matrix of the encoded channel state, together with a rigorous proof that the AQCME estimator approaches this bound as training data grows – to the best of our knowledge the first constructive achievability result of its kind in the wireless channel estimation literature. The framework is supported by formal analysis of quantum channel state preparation, quantum kernel universality with an explicit barren-plateau trainability discussion, ergodic spectral efficiency, Nakagami-m outage probability, and convergence of the hybrid quantum-classical gradient descent. Monte Carlo simulations over 50,000 channel realisations, reported with 90 percent confidence intervals throughout, validate every theoretical prediction. Ablation studies across circuit depths and qubit counts, a hardware-noise sweep over gate error rates from 1e-4 to 1e-2, and hyperparameter sensitivity analysis confirm robustness. At 20 dB signal-to-noise ratio, AQCME reduces normalised mean squared error by 4.8 dB over MMSE and by 2.1 dB over the best deep learning baseline; under emulated near-term noisy quantum hardware conditions it still outperforms MMSE by 2.6 dB. All quantum results in this work are obtained by exact classical statevector emulation of the variational circuit; no physical quantum processor was used, and reported hardware-noise behaviour is modelled by a depolarising channel. Spectral efficiency improves by up to 22.4 percent in massive MIMO scenarios, the URLLC outage target of 1e-5 is met at 6.2 dB lower signal-to-noise ratio than with MMSE, and inference complexity scales logarithmically with antenna count rather than quartically as with MMSE matrix inversion.
Channel estimation is one of the most fundamental and performance-limiting operations in fifth-generation (5G) and emerging sixth-generation (6G) wireless networks, where ultra-massive MIMO arrays, millimetre-wave and terahertz carrier frequencies, and non-Gaussian hardware-induced noise combine to render classical least-squares and minimum mean squared error estimators inadequate. Deep learning has narrowed the performance gap, yet it offers no information-theoretic guarantee on how close any particular network architecture is to the fundamental noise floor. This paper introduces the AI-Quantum Channel Modeling and Estimation (AQCME) framework, which integrates variational quantum circuits, quantum signal processing, and a quantum eigenspace denoising operator into a unified trainable architecture for simultaneous channel estimation and noise suppression in MIMO-OFDM systems. The defining theoretical result is a quantum Cramer-Rao lower bound on normalised mean squared error, grounded in the quantum Fisher information matrix of the encoded channel state, together with a rigorous proof that the AQCME estimator approaches this bound as training data grows – to the best of our knowledge the first constructive achievability result of its kind in the wireless channel estimation literature. The framework is supported by formal analysis of quantum channel state preparation, quantum kernel universality with an explicit barren-plateau trainability discussion, ergodic spectral efficiency, Nakagami-m outage probability, and convergence of the hybrid quantum-classical gradient descent. Monte Carlo simulations over 50,000 channel realisations, reported with 90 percent confidence intervals throughout, validate every theoretical prediction. Ablation studies across circuit depths and qubit counts, a hardware-noise sweep over gate error rates from 1e-4 to 1e-2, and hyperparameter sensitivity analysis confirm robustness. At 20 dB signal-to-noise ratio, AQCME reduces normalised mean squared error by 4.8 dB over MMSE and by 2.1 dB over the best deep learning baseline; under emulated near-term noisy quantum hardware conditions it still outperforms MMSE by 2.6 dB. All quantum results in this work are obtained by exact classical statevector emulation of the variational circuit; no physical quantum processor was used, and reported hardware-noise behaviour is modelled by a depolarising channel. Spectral efficiency improves by up to 22.4 percent in massive MIMO scenarios, the URLLC outage target of 1e-5 is met at 6.2 dB lower signal-to-noise ratio than with MMSE, and inference complexity scales logarithmically with antenna count rather than quartically as with MMSE matrix inversion.
Accurate channel estimation is a fundamental requirement for high-performance wireless communication systems, where conventional deep learning approaches often suffer from excessive trainable parameters and high memory cost as antenna and subcarrier dimensions scale up. This paper proposes a quantum machine learning (QML)-based channel estimation framework that addresses this scalability challenge through a compact hybrid quantum-classical architecture. An 8-qubit quantum neural network (QNN) based on a parameterized quantum circuit (PQC) encodes received pilot-domain features using both Cartesian and polar components through Hadamard initialization and rotation-based quantum encoding, and learns channel representations using trainable variational rotations and controlled-Z (CZ) entanglement. The Pauli-Z measurement outputs are then processed by a lightweight classical dense head to produce the final channel estimate. The proposed QNN is compared with a classical deep neural network (DNN) and a QNN without hidden dense layers over a 2 × 1 Rayleigh fading multiple-input single-output (MISO) channel across an SNR range of 10 dB to 30 dB. Simulation results show that the proposed hybrid QNN achieves the lowest normalized mean square error (NMSE) across the entire evaluated SNR range while using only 1,012 trainable parameters, compared with 3,356 for the DNN. At 30 dB SNR, the proposed QNN achieves the lowest NMSE of approximately − 20.24 dB, compared with approximately − 17.54 dB for the DNN baseline. An ablation study further confirms that the dense post-processing head is essential for accurate regression from raw quantum measurement outputs. These results suggest that compact hybrid quantum-classical estimators offer a promising direction for accurate and parameter-efficient channel estimation in next-generation wireless communication systems.
Networks built to sixth-generation (6G) targets will have to hold sub-millisecond latency, push spectral efficiency past what today's massive MIMO deployments achieve, and manage resources across highly heterogeneous nodes with little human supervision. Those targets place a hard demand on the optimizer. Channel estimation, adaptive modulation, beamforming and decoding all involve searching large, non-convex parameter spaces, and the search has to finish inside a coherence interval that may last only a few hundred microseconds. This paper surveys quantum-inspired signal processing (QISP), a family of classical algorithms that borrow structure from quantum computation, including amplitude-weighted superposition sampling, quantum-walk-style exploration, Ising-model formulations and tensor-network compression, but that run entirely on conventional processors. We group the literature under four headings: algorithmic foundations, communication-system architectures, optimization strategies, and implementation constraints. We then propose a reference architecture in which a quantum-inspired optimization engine sits beside a conventional OFDM/MIMO transmit-receive chain and reconfigures modulation, beam-selection and decoding parameters from channel-state feedback. An illustrative simulation grounds the discussion: a representative QISP optimizer is compared against a conventional adaptive baseline over a 4×4 MIMO, QPSK, AWGN-channel OFDM link at signal-to-noise ratios (SNR) from 0 to 20 dB. These numbers demonstrate methodology and are not measurements taken from physical hardware. Within that caveat, the QISP optimizer achieves a lower biterror rate (BER) at low and moderate SNR, and the throughput and latency trends are consistent with the parameter-search efficiency reported in the wider literature. The paper concludes with open problems such as scalability, algorithmic complexity, explainability and standardized benchmarking, and research directions on hybrid quantum-classical processors, reconfigurable intelligent surfaces (RIS), semantic communications, and edge-native QISP inference.
Massive multiple-input multiple-output (MIMO) systems are a key enabling technology for 5G-Advanced and emerging 6G networks, yet their performance is fundamentally constrained by high-dimensional, non-convex optimization problems arising from beamforming, power allocation, and user scheduling under imperfect channel state information (CSI).This paper proposes a hybrid quantum-classical optimization framework that formulates discrete and continuous massive MIMO resource allocation problems using Quadratic Unconstrained Binary Optimization (QUBO) and variational quantum algorithms.Discrete beam selection is addressed using quantum annealing, while continuous power control and hybrid beamforming are refined using variational quantum circuits within a classical feedback loop.Simulation results demonstrate improvements in aggregate spectral efficiency, runtime scalability, and robustness under imperfect CSI compared to conventional ZF and WMMSE baselines.The benefits of using the proposed solution include scalable runtime performance with respect to larger numbers of antennas; thus, it highlights the potential of optimizing quantum-assisted technologies for the future of wireless networks based on realistic assumptions regarding near-term NISQ-era performance.
Abstract The paper explores the field of quantum-enhanced channel estimation of terahertz (THz) cell-free massive multiple-input multiple-output (MIMO) systems. Although quantum sensing has been suggested to be used in wireless communications, its practical benefit over classical techniques is not well known. We identify systematically the signal-to-noise ratio (SNR) regime in which quantum sensing is able to offer an advantage. The results demonstrate that THz systems operating in the low pilot SNR regime ( ∼ ∼ 3 dB) achieve 14–103.1% sum-rate improvement with quantum-enhanced estimation, compablack to only 2–5% at millimeter-wave (mmWave) frequencies where pilot SNR exceeds 13 dB. The 6–33 × × greater quantum advantage at THz frequencies stems from the fundamental difference in operating regimes: THz systems are noise-limited due to severe path loss ( ∼ ∼ 100 dB at 10 m), while mmWave systems are interference-limited with near-perfect classical estimation. Our results identify THz cell-free multiple-input multiple-output (MIMO) as a compelling application for quantum-enhanced wireless communications and provide design guidelines for practical deployment in future sixth-generation (6G) networks.
Massive MIMO beamforming for 6G networks faces a fundamental tradeoff between solution quality and computational complexity. Exhaustive search guarantees optimal antenna selection; however, this becomes prohibitively expensive for arrays exceeding 16 elements, while polynomial-time classical heuristics sacrifice 15–25% performance to achieve practical scalability. This paper introduces a quantum-enhanced optimization framework using the Quantum Approximate Optimization Algorithm (QAOA) to address this challenge for IoT-integrated 6G massive MIMO systems. Our approach combines quantum solution exploration with classical parameter optimization, integrating realistic 3GPP TR 38.901 channel models across 28–60 GHz bands and heterogeneous IoT device characteristics (mMTC, URLLC, eMBB). The framework incorporates an adaptive penalty mechanism that achieves constraint satisfaction within five iterations while maintaining polynomial complexity. Statistical validation across 50 independent channel realizations demonstrates significant advantages: 10–20% spectral efficiency improvement over classical heuristics (p<0.001, Cohen’s d=1.24), 35–42% IoT energy reduction, and 90–95% near-optimal solution quality compared to 65–85% for polynomial-time classical methods. Hardware validation on IBM quantum platforms (127–133 qubits) confirms practical feasibility for medium-scale systems with M≤16 antennas, achieving 89.3% of ideal performance with 22% measurement success rate. Current hardware limitations restrict deployment to proof-of-concept demonstrations, with full-scale 6G implementations requiring quantum error correction projected for 2030+.
A reconfigurable intelligent surface (RIS) is a promising technology for beyond-fifth-generation (B5G) and sixth-generation (6G) wireless communications, but its passive reflection and two-hop double-fading structure make cascaded channel estimation challenging. Conventional convolutional neural network (CNN) estimators require many trainable parameters, while a single shallow parameterized quantum circuit (PQC) may have limited feature representation. Deep quantum circuits can also suffer from noise and barren-plateau effects on noisy intermediate-scale quantum (NISQ) devices. To address these issues, this paper proposes a multi-filter quantum convolutional neural network (MF-QCNN) for cascaded channel estimation in RIS-assisted multi-user uplink systems. The proposed model uses multiple independent shallow PQC filters in parallel, concatenates their measured features, and estimates the cascaded channel through a compact classical dense head, with the total trainable-parameter count scaling as 182F+696 for F parallel filters. Simulation results, compared with a single-filter quantum convolutional neural network (QCNN), CNN, and multilayer perceptron (MLP) baselines, show that at a signal-to-noise ratio (SNR) of 20 dB, the 3-filter MF-QCNN reduces the normalized mean squared error (NMSE) by approximately 22.9, 8.1, and 4.6 dB relative to the single-filter QCNN, CNN, and MLP baselines, respectively, while using only about 19.3% of the CNN trainable parameters. Under zero-forcing (ZF) precoding, it achieves the highest achievable sum rate among the learning-based estimators; at SNR = 30 dB, it improves the achievable sum rate by approximately 17.4% and 12.8% over the CNN and MLP baselines, respectively. These simulation results suggest that the parallel shallow-PQC design can serve as a compact quantum-aided estimator for RIS channel estimation and may provide a useful basis for future studies on AI-native transceiver design in B5G/6G networks.