Achieving ultra-low Bit Error Rate (BER) in Dense Wavelength Division Multiplexing (DWDM) systems is crucial for next-generation optical networks. This paper proposes a novel AI-enhanced QPSK-WDM System that integrates hybrid deep learning equalization and Schrödinger-informed digital backpropagation to mitigate fiber nonlinearities and noise impairments. A CNN-LSTM equalizer is employed to compensate for dispersion and nonlinear distortions, outperforming traditional DSP-based techniques. Additionally, a Neural Network-Based Quantum-inspired LDPC Decoder enhances error correction beyond conventional methods. We introduce a GAN-based Optical Noise Predictor to further optimize transmission performance, enabling proactive compensation for system impairments. Simulation results demonstrate a BER improvement to 10⁻¹³, significantly outperforming conventional equalization and FEC techniques. These findings suggest that AI-driven optical systems can enhance spectral efficiency and system robustness, paving the way for practical deployment in high-capacity optical networks.
Achieving ultra-low Bit Error Rate (BER) in Dense Wavelength Division Multiplexing (DWDM) systems is crucial for next-generation optical networks. This paper proposes a novel AI-enhanced QPSK-WDM System that integrates hybrid deep learning equalization and Schrödinger-informed digital backpropagation to mitigate fiber nonlinearities and noise impairments. A CNN-LSTM equalizer is employed to compensate for dispersion and nonlinear distortions, outperforming traditional DSP-based techniques. Additionally, a Neural Network-Based Quantum-inspired LDPC Decoder enhances error correction beyond conventional methods. We introduce a GAN-based Optical Noise Predictor to further optimize transmission performance, enabling proactive compensation for system impairments. Simulation results demonstrate a BER improvement to 10⁻¹³, significantly outperforming conventional equalization and FEC techniques. These findings suggest that AI-driven optical systems can enhance spectral efficiency and system robustness, paving the way for practical deployment in high-capacity optical networks.
Underwater quantum communication (UQC) has emerged as a promising approach for secure information transfer in oceanic environments by exploiting fundamental quantum mechanical principles. However, realizing UQC in practice remains highly challenging due to the inherently dynamic nature of the underwater optical channel, which is subject to wavelength-dependent absorption, multiple scattering, turbulence, and ambient noise—effects that collectively degrade photon transmission and induce quantum state errors. Conventional analytical models are insufficient to capture these nonlinear, time-varying channel characteristics, motivating the integration of artificial intelligence (AI) methods. Unlike previous surveys that focus narrowly on either underwater optical communications or quantum cryptography in isolation, this review uniquely synthesizes advances across quantum information science, ocean optics, and machine learning to address UQC-specific channel impairments. Specifically, we critically evaluate AI-driven approaches in three areas: (i) spatio-temporal deep learning models for data-driven channel estimation, demonstrating measurable improvements in channel prediction accuracy under realistic turbulence conditions; (ii) intelligent noise reduction and quantum error correction methods that reduce qubit error rates in high-scattering environments; and (iii) adaptive system optimization through reinforcement learning and hybrid optimization strategies that enhance operational fidelity and robustness. Based on this analysis, we identify key gaps in the field—including the absence of standardized underwater quantum datasets, limited experimental validation of AI-quantum hybrid frameworks, and the lack of end-to-end AI-quantum design tools—and outline concrete directions for future research. This review serves as a structured reference for researchers and practitioners working toward deployable, intelligent UQC systems.
Quantum computing is emerging as a transformative tool for communication systems, offering the potential to overcome long-standing physical limitations. In free-space optical networks, orbital angular momentum (OAM) multiplexing promises massive capacity gains, but its practical use is fundamentally constrained by multiphysics degradations such as atmospheric turbulence, volumetric Mie scattering, and stochastic quantum noise. These effects induce nonlinear modal crosstalk and severe beam distortions, against which classical approaches—most notably convolutional neural networks (CNNs)—provide only partial and non-scalable compensation. To address this gap, we report the first use of variational quantum neural networks (QNNs) for adaptive OAM beam compensation in realistic channels. By embedding parameterized entangling layers into a supervised regression pipeline, our QNN achieves end-to-end reconstruction of distorted Laguerre–Gaussian beams with topological charges l ∈ {1,4,8,12}. Using experimentally validated channel parameters, QNNs achieve mean squared error as low as 4.0 × 10− 6, SSIM above 0.99, and bit-error rates suppressed by > 99.9% (0.0125% BER). To ensure scalability, we introduce the quasi-quantum neural network (QqNN), a classical surrogate that emulates quantum dynamics via tensorial projections, achieving near-optimal performance (0.0375% BER) at reduced complexity. This hybrid framework positions QNNs as a quantum-resilient paradigm for OAM decoding and establishes QqNNs as the first scalable surrogate for near-term deployment.
In quantum noise stream cipher (QNSC) systems, it is difficult to compensate fiber nonlinearity by digital signal processing (DSP) due to interactions between chromatic dispersion (CD), amplified spontaneous emission (ASE) noise from erbium-doped fiber amplifier (EDFA) and Kerr nonlinearity. Nonlinearity equalizer (NLE) based on machine learning (ML) algorithms have been extensively studied. However, most NLE based on supervised ML algorithms have high training overhead and computation complexity. In addition, the performance of these algorithms have a lot of randomness. This paper proposes two clustering algorithms based on Fuzzy-logic C-Means Clustering (FLC) to compensate the fiber nonlinearity in quadrature amplitude modulation (QAM)-based QNSC system, including FLC based on subtractive clustering (SC) and annealing evolution (AE) algorithm. The performance of FLC-SC and FLC-AE are evaluated through simulation and experiment. The proposed algorithms can promptly obtain suitable initial centroids and choose optimal initial centroids of the clusters to achieve the global optimal initial centroids especially for high order modulation scheme. In the simulation, different parameter configurations are considered, including fiber length, optical signal-to-noise ratio (OSNR), clipping ratio and resolution of digital to analog converter (DAC). Furthermore, we measure the Q-factor of transmission signal with different launched powers, DAC resolution and laser linewidth in the optical back-to-back (BTB) experiment with 80-km single mode fiber. Both simulation and experimental results show that the proposed techniques can greatly mitigate the signal impairments.
Amidst the development of communication technologies, the limitations of 5G communication systems, particularly in security and resource management, have become increasingly apparent. As the 6G era approaches, there are growing demands for integrated systems that ensure robust security and optimize resource utilization. To address these challenges, this paper proposes a novel architecture that integrates classical communication channels and quantum key distribution (QKD) channels using wavelength-division multiplexing (WDM). This innovative approach allows classical and quantum channels to coexist within a single optical fiber, improving security and fiber utilization while reducing system complexity and cost. A key contribution of this work is introducing an AI-based prediction and management module, dynamically adjusting the quantum key generation rate according to real-time usage and forecasted demand. By leveraging machine learning, the module predicts quantum key consumption patterns, ensuring that the key generation rate aligns with the system’s security and performance requirements. This approach balances key generation and usage, minimizing resource waste and enhancing the system’s overall efficiency. The feasibility of the proposed architecture is validated through an analysis of spontaneous Raman scattering (SpRS), showing the architecture maintains high key generation rates and low quantum bit error rates (QBER) under optimal system conditions. Furthermore, an analysis reveals that the AI module meets the requirement of predicting key usage and managing the key generation rate. Lastly, the feasibility is further validated by an experiment. Overall, this study presents a comprehensive framework for integrating classical and quantum channels in future 6G networks, providing enhanced security, efficiency, and scalability.
The tremendous progress of 5G technology has transformed the landscape of the Internet of Things (IoT), allowing for fast data speeds, low delay, and widespread connection that is crucial for a variety of applications, including smart cities and industrial automation. In the context of 5G enabled IoT networks, colored noise introduces varying levels of interference across different frequency bands, which can significantly degrade the performance of 5G LDPC decoding. This paper presents a novel Deep learning approach for 5G channel LDPC code decoding tailored for next-generation IoT applications. The proposed method integrates an Iterative Normalized Min-Sum (NMS) algorithm with a Convolutional Neural Network (CNN) to enhance the performance of LDPC decoding in the presence of colored noise, a common interference in real-world communication channels. Through extensive simulations and analysis, our approach demonstrates a significant performance improvement, achieving a 3.8 dB enhancement at a Bit error rate of10−6. This is achieved by accurately estimating and mitigating channel noise, thereby ensuring reliable data transmission for critical IoT applications. The findings indicate that our approach to decoding technique not only enhances error correction capabilities but also adapts to varying channel conditions, optimizing IoT network performance and efficiency. This research contributes a robust solution to the challenges posed by colored noise in 5G-enabled IoT networks, promoting the deployment of more reliable and efficient IoT systems.
Because noise is inherent to all measurements, optical communication requires error identification and correction to protect and recover user data. Yet, error correction, routinely used in classical receivers, has not been applied to receivers that take advantage of quantum measurement. Here, we show how information uniquely available in a quantum measurement can be employed for efficient error correction. Our quantum-enabled forward error correction protocol operates on quadrature phase shift keying (QPSK) and achieves more than 80 dB error suppression compared to the raw symbol error rate and approximately 40 dB improvement of symbol error rates beyond the QPSK classical limit. With a symbol error rate below 10−9 for just 11 photons per bit, this approach enables reliable use of quantum receivers for ultra-low power optical communications. Limiting optical power improves the information capacity of optical links and enables scalable networks with coexisting quantum and classical channels in the same optical fiber.