High-capacity Networks Research Articles

Improving Optical Transmission Performance in Multi-Channel Networks Utilizing Convolutional Neural Network-Enabled Digital Signal Processing to Mitigate Four-Wave Mixing

ABSTRACT The rapid growth of online services and the global transition to digital platforms, accelerated by the COVID-19 pandemic and the emergence of AI-based services, have led to a surge in demand for high-capacity optical communication networks (OCNs). However, this transition exacerbates the issue of fiber nonlinearity, notably four-wave mixing (FWM), which can significantly impact signal integrity in long-distance OCN transmissions with multiple channels. To address this challenge, this paper presents a novel approach leveraging a convolutional neural network (CNN)-based digital signal processing (DSP) model to mitigate the nonlinear effects of FWM on signal quality. The proposed CNN model, designed with three convolutional layers and trained on a comprehensive dataset of simulated OCN transmissions, demonstrates significant improvement in reducing nonlinear distortions caused by FWM. Our method is compared with traditional compensation techniques, such as digital back-propagation and Volterra series-based equalizers, showing a reduction in power penalties by 1 dB and an enhancement in the power budget by 2 dB. Simulation results indicate that the bit error rates (BERs) remain consistently below the critical threshold of 10−9 across various transmission distances, outperforming conventional methods. The simulation analysis, conducted on a 100 km multi-channel OCN testbed, confirms the CNN equalizer’s efficacy in reducing crosstalk and improving power efficiency, with a demonstrated 15% reduction in required launch power. Moreover, the analytical models used to evaluate the CNN-based DSP model show high accuracy in predicting performance, underscoring the model’s capability to achieve high-quality transmission with lower power requirements. These findings advocate for the integration of our CNN-based DSP model into OCNs, offering a fruitful solution for managing multi-channel, long-distance, and high-data-rate optical transmissions in real-world systems.

Efficient Privacy-Preserving Machine Learning with Lightweight Trusted Hardware

In this paper, we propose a new secure machine learning inference platform assisted by a small dedicated security processor, which will be easier to protect and deploy compared to today's TEEs integrated into high-performance processors. Our platform provides three main advantages over the state-of-the-art: (i) We achieve significant performance improvements compared to state-of-the-art distributed Privacy-Preserving Machine Learning (PPML) protocols, with only a small security processor that is comparable to a discrete security chip such as the Trusted Platform Module (TPM) or on-chip security subsystems in SoCs similar to the Apple enclave processor. In the semi-honest setting with WAN/GPU, our scheme is 4X-63X faster than Falcon (PoPETs'21) and AriaNN (PoPETs'22) and 3.8X-12X more communication efficient. We achieve even higher performance improvements in the malicious setting. (ii) Our platform guarantees security with abort against malicious adversaries under honest majority assumption. (iii) Our technique is not limited by the size of secure memory in a TEE and can support high-capacity modern neural networks like ResNet18 and Transformer. While previous work investigated the use of high-performance TEEs in PPML, this work represents the first to show that even tiny secure hardware with very limited performance can be leveraged to significantly speed-up distributed PPML protocols if the protocol can be carefully designed for lightweight trusted hardware.

Advancements in Terahertz Communication: Harnessing the 300GHz Band for High-Efficiency, High-Capacity Wireless Networks

Advancements in Terahertz Communication: Harnessing the 300GHz Band for High-Efficiency, High-Capacity Wireless Networks

Enhancing C+L-band transmission performance through OSNR flatting and link damage recovery algorithms

The rapid growth of data-intensive services has driven the need for high-capacity optical networks. C+L band optical communication systems have emerged as a potential solution by extending the operational bandwidth. However, the wider spectrum introduces significant stimulated Raman scattering (SRS) effects that impact signal power profile, Kerr nonlinearity, and amplified spontaneous emission (ASE) noise. To address these challenges, this paper proposes an optical power control strategy designed to achieve a flat optical signal-to-noise ratio (OSNR) across all transmitted channels, which is particularly effective in mitigating SRS effects in C+L band systems. Furthermore, a link damage recovery algorithm is developed to ensure system robustness against localized fiber degradations. Extensive simulations are conducted to compare the performance of the proposed strategy with the conventional flat launch power approach under single-span and multi-span transmission scenarios. The results demonstrate that the proposed strategy achieves a higher minimum generalized signal-to-noise ratio (GSNR), exhibits stronger resilience to link damage across a wide range of transmission conditions.

IQ-channel multiplexed DP-4ASK signal using power loading for downlink coherent PON system with access-span length difference

This study explores the integration of dual-polarized (DP) four-level amplitude shift keying (4ASK) signals within an intensity and quadrature division multiplexing framework, mainly focusing on coherent passive optical network (PON) systems. The primary objective is to address the challenges associated with distance disparities in downstream transmissions, which are prevalent in coherent PON architectures. We introduce a novel approach that significantly reduces the power consumption of digital-to-analog converters by implementing power loading strategies tailored explicitly for IQ channel division multiplexing (IQDM)-DP-4ASK signals. Our simulations confirm that ASK standard frequency offset compensation is adaptable to these signals, providing a robust method for managing frequency offsets in a dynamic network environment. Moreover, we propose and empirically validate an energy-efficient adaptive downlink solution capable of supporting 128 Gb/s per optical network unit (ONU), utilizing IQ-imbalanced DP-4ASK signals. This solution is particularly advantageous for systems where the transmission conditions include a 10 km variance in access span lengths between ONUs. Results from our experimental setup demonstrate that reducing the digital-to-analog converter output current for the Q channel by 137 mA is feasible without compromising signal integrity or system performance. Additionally, the research verifies the effectiveness of the automatic bias controller on the transmitter side, ensuring stable operation across varying conditions. Equally, the receiver-side digital signal processing effectively handles polarization separation, illustrating the system's capability to maintain high data integrity and reliability under diverse operational scenarios. These findings highlight the technical feasibility and operational benefits of using IQDM-DP-4ASK signals in coherent PON systems and underscore the potential for significant power savings and enhanced system efficiency in optical networks. The study paves the way for future research into scalable, energy-efficient solutions suitable for high-capacity optical access networks striving for increased sustainability and reduced operational costs.

Optimized CNN and adaptive RBFNN for channel estimation and hybrid precoding approaches for multi user millimeter wave massive MIMO

ABSTRACT The millimetre-wave (mmWave) communication satisfies the demand for high data rates due to the characteristic of wide bandwidth. Using massive multiple-input multiple-output (MIMO) technology, a significant propagation loss of mmWave communication is effectively compensated. However, it is challenging to provide a specialised radio frequency chain for each antenna due to the constrained physical area with closely spaced antennas and prohibitive power consumption in mmWave massive MIMO systems. This paper presents novel approaches for effective channel estimation and hybrid precoding in mmWave communication systems. To address the challenges of channel estimation, a convolutional neural network (CNN) is utilised, and network parameters are optimised using enhanced whale optimization algorithm (EWOA). The proposed CNN-based channel estimation method aims to accurately estimate the channel in mmWave systems with enhanced efficiency and reduced complexity. By training CNN using EWOA optimisation algorithm, the network parameters are fine-tuned to improve accuracy and generalisation capability of channel estimation process. Furthermore, hybrid precoding is achieved using adaptive radial-basis function neural networks (adaptive RBFNNs) which enables efficient precoding while minimising complexity. Moreover, the adaptive RBFNN approach determines the optimal precoding weights based on channel state information, resulting in a improved performance and a reduced computational overhead. The performance analysis is validated using the MATLAB/Simulink software and offers to provide effectual and reliable mmWave communication systems, facilitating the realisation of high-speed and high-capacity wireless networks.

Scalable solutions for implementing satellite-based sensor networks

The importance of sensor networks in the field of IoT cannot be overstated, especially with the growing demand for IoT solutions. The new Internet protocols such as IPv6 and 5G mobile provide high-capacity communication networks, demonstrating the relevance and potential applications of IoT in the future. However, with new demands come new challenges. This paper aims to explore the challenges of Satellite-based Sensor Networks, a new topic with various applications. This article explores the challenges and constraints of implementing a scalable satellite-based sensor network. We examined the hardware and software limitations of the Iridium satellite SBD protocol and proposed tailored solutions using design flow algorithms to tackle flexibility, power consumption, bandwidth, and scalability issues. Satellite-based sensor networks face challenges in data transmission and sensor lifespan. In this study, we introduce event-driven and compression algorithms to address these challenges. By implementing clustering, we achieved a significant increase in the number of nodes within each cluster. Our proposed methods were validated using simulated datasets derived from temperature and location data. A unique data transmission method, based on event count, was introduced. Notably, the Differential Huffman compression algorithm resulted in an 81 % reduction in data transmission compared to traditional methods. This demonstrates about 62 % improvement in efficiency over existing techniques. Our approach not only paves the way for future advancements in this domain but also highlights the untapped potential of satellite-based sensor networks.

Contrasting approaches to very highcapacity network regulation and policy: a comparative analysis of France, Portugal, Spain and the UK (2008–2020)

Purpose The purpose of this paper is to examine the factors that may have contributed to different levels of very high-capacity network (VHCN) coverage, with a particular focus on the role of regulation and State aid. Design/methodology/approach A comparative empirical study based on multiple case studies was conducted in France, Portugal, Spain and the UK. Findings Although France, Portugal and Spain initially adopted similar regulatory strategies for VHCN deployment, the outcomes differed significantly. The UK, with a more demanding regulation, achieved a residual coverage. This study highlights the importance of the regulatory approach to VHCN access in balancing private and public investment and emphasizes the importance of State aid in the policy agenda for nationwide VHCN deployment projects. Research limitations/implications Research on complex phenomena, such as the impact of regulation on investment or the effectiveness of State aid procedures, may focus on specific events to the detriment of others, which could bias the results. Practical implications The findings of this study provide insights for policymakers involved in State aid decisions and regulators by understanding the importance of timely State aid interventions, efficient governance and the impact of regulation on investment incentives. Originality/value This paper extends the literature on the impact of regulation on investment incentives and State aid as a tool to complement private investment for VHCN deployment through in-depth case studies.

High-Capacity Coherent WDM Networks Empowered by Probabilistic Shaping and End-to-End Deep Learning

To optimize the functionality of coherent optical fiber communication (OFC) systems and enhance their capacity related to long-haul transmissions, wavelength-division multiplexing (WDM) and probabilistic constellation shaping (PCS) techniques have been used. This paper develops an end-to-end (E2E) deep learning (DL)-based PCS algorithm, i.e., autoencoder (AE) for a high-order modulation format WDM system that minimizes nonlinear effects while ensuring high capacity and considers system parameters, in particular those related to the OFC channel. Only the AE of the central channel is trained to meet the specified performance objective, as the system design employs identical AEs in each WDM channel. The simulation results show that the architecture should consist of two hidden layers, with thirty two nodes per hidden layer and a ”32×modulation order” batch size to obtain optimal system performance, when designing AE using a dense layer neural network. The behavior of the AE is examined to determine the optimum launch-power ranges that enhance the system's performance. The developed AE-based PCS-WDM provides a 0.4 shaping gain and outperforms conventional solutions.

Increase in Modulation Speed of Silicon Photonics Modulator with Quantum-Well Slab Wings: New Insights from a Numerical Study

A Silicon Photonics modulator is a high-speed photonic integrated circuit for optical data transmission in high-capacity optical networks. Silicon Photonics modulators in the configuration of a Mach–Zehnder interferometer, in which a PN-junction rib-waveguide phase shifter is inserted in each arm of the interferometer, are studied in this paper because of their superior performance of high-quality optical data generation in a wide range of spectral bands and their simplicity in fabrication processes suitable to production in foundries. Design, fabrication, and fundamental characteristics of Silicon Photonics Mach–Zehnder modulators are reviewed as an introduction to these high-speed PICs on the Silicon Photonics platform. Modulation speed, or modulation bandwidth, is a key performance item, as well as optical loss, in the application to high-speed optical transmitters. Limiting factors on modulation speed are addressed in equations. Electrical resistance–capacitance coupling, which causes optical modulation bandwidth–optical loss trade-off, is the most challenging limiting factor that limits high-speed modulation. Expansion of modulation bandwidth is not possible without increasing optical loss in the conventional approaches. A new idea including quantum-mechanical effect in the design of Silicon Photonics modulators is proposed and proved in computational analysis to resolve the bandwidth loss trade-off. By adding high-mobility quantum-well overlayers to the side slab wings of the rib-waveguide phase shifter, the modulation bandwidth is doubled without increasing optical loss to achieve a 200 Gbaud modulation rate.

Nominal GSM-R Radio Network Design for Signalling and Train Control Systems: Case Study Dar-Moro Electrified SGR Line in Tanzania

The recent development of High-Speed Trains (HST) operations requires real-time information transfer, high network capacity, and reliable communication for train signalling and control purposes. Rail operators face challenges as the high-speed railroad traffic grows. In a high-speed driving profile, the communication must be able to overcome fast handover, large Doppler shift, high penetration losses, limited visibility in tunnels, and the harsh electromagnetic environment. Global System for Mobile Communications for Railway (GSM-R) is still a standard-bearer for railway signalling communications. The link capacity and coverage prediction of the predefined Base Transceiver Station (BTS) locations are simulated using the Radio Planner RF planning tool and Matlab®. The terrain map and the signal levels along the railway corridor are observed. The analysis of the GSM-R for a fast-moving train is performed. Signal level coverage prediction, Doppler-shift effect and the received carrier frequencies due to Doppler shift along Dar–Pugu stations have been presented. The critical sites (locations) with weak signals of the first three BTSs have been identified. It is also observed that the Doppler effect may limit the proposed speed.

Orbital Angular Momentum Multiplexing Architecture for OAM/SDM Passive Optical Networks

Optical Angular Momentum multiplexing (OAM) is a technology of communication systems that enables high-capacity optical communication networks. One of the most important determinants of this technology is the channel capacity, loss of power, and BER that accompany the transmission. This article proposed an OAM/SDM G-PON architecture for a MIMO-type communication system that supports (OAM/SDM G-PON)Technology. The proposed architecture is used to multiplex the downstream OAM channels and the upstream SDM channels, and an OAM multiplexer/demultiplexer (OAM-MUX/DEMUX) is used to multiplex and demultiplex the OAM channels. In the OAM/SDM G-PON system, the signal will propagate through three different mediums, each one having its own nature in influencing the power of the signal that passes through that medium. The experimental study has bidirectional transmissions with the DS/US data rate of 2.4 Gbps and Binary Phase Shift Keying (BPSK) downstream and 1.2 Gbps upstream. The observed results showed that the bit-error rate (BER) is a function of coupling angles and increases with the increasing in the OAM ring size

Minimization of dispersion and non-linear effects in WDM based long-haul high capacity optical communication systems

Abstract Chromatic dispersion and nonlinear impairments pose challenges in high-capacity optical transmission systems, leading to signal distortions, channel interference and diminished the transmission performances. This paper explores the utilization of dispersion compensating fibers (DCF) using different schemes to mitigate the dispersion that accumulates along the length of a fiber in a 16 × 10 Gbps high-capacity long haul WDM system over a range of 500 km. When different wavelengths of light pulses are transmitted through an optical fiber, they experience varying speeds due to the refractive index’s wavelength dependency. As a result, the light pulses become temporally spread out as they travel through the fiber, and this dispersion persists throughout the fiber’s length. Considering non-linear effects such as self-phase modulation (SPM) and cross-phase modulation (XPM), this paper analyze and compare the three compensation schemes of DCF in a 16 channel WDM system. Moreover the impact of non-linearities based on fiber length are also analyzed and compared. The results are evaluated by comparing metrics such as Q-factor, bit error rate (BER) and eye height. The analysis concludes that the symmetrical compensation scheme of DCF outperforms the pre- and post-compensation scheme. This finding suggests that the symmetrical compensation method offers a promising solution for high-capacity access networks, providing high spectral efficiency, cost-effectiveness, and improved flexibility.

Factor graph-based deep reinforcement learning for path selection scheme in full-duplex wireless multihop networks

A wireless multihop network (WMN) is set of wirelessly connected nodes without an aid of centralized infrastructure that can forward any packets via intermediate nodes by a multihop fashion. In the WMN, there are still some issues that need to be resolved, like due to any source node may choose an uncertainty path to send their packets through the multihop fashion and this leads to the performance of network capacity can degrade drastically. To solve this problem, in this research, we propose two novel path selection algorithms called SNR-based learning path selection (NLPS) algorithm and SINR-based learning path selection (INLPS) algorithm, which are incorporated with the deep reinforcement learning (DRL) to select the best multihop path from any source node to a destination node with highest end-to-end (E2E) throughput. Besides that, a factor graph (FG) approach and a nested lattice code (NLC) representation are used to reduce the computation time. According to the numerical studies with the NLC is applied, our simulation results reveal that the proposed NLPS and INLPS algorithms can improve the overall average network capacity up to 3.1 times and 10.5 times compared to FG, respectively. However, the overall average computation time are highly increased for NLPS and INLPS, i.e., about 0.627 s and 1.221 s, respectively compared to FG, which is about 0.006 s. In other words, both NLPS and INLPS algorithms can achieve high network capacity and moderate computation time.

Experimental demonstration of a multi-core fiber seeded comb optical network (MCF-SCON)

We propose and experimentally demonstrate an optical network architecture that uses wideband optical frequency comb (OFC) sources synchronized with transmitted network broadcast seed signals. All network nodes are connected by multi-core fibers (MCFs) which are used for data transmission and seed distribution. The nodes that connect the data transmission and seed distribution layers contain an OFC that may be operated in master or slave mode to provide carriers both for modulation and local oscillators for coherent detection. Nodes are able to switch, amplify, split, and regenerate the seed lightwave for full network distribution over large areas. Using OFCs with 25 GHz spacing covering the C- and L-bands, we experimentally investigate a range of scenarios compatible with metro or inter-data-center network architectures. These scenarios include single span transmission, bi-directional transmission, and multi-hop seed and data transmission including seed amplification, splitting, and regeneration with laser injection locking within network nodes, and a maximum transmission distance of 130 km. We show that MCF seed and data distribution with spatial-switching enables identical network-wide transceiver combs with the potential for reducing the complexity of digital signal processing as well as significant hardware sharing. Data-rates of approximately 100 Tb/s/core and 600 Tb/s per fiber are measured showing the potential of this architecture for high-capacity networking with OFCs replacing hundreds of transmitter and local oscillator lasers in each node.

Scheme for a WDM-PON with colorless optical network units based on a flat optical frequency comb.

A new, to the best of our knowledge, scheme for a wavelength division multiplexing passive optical network (WDM-PON) based on a flat optical frequency comb (OFC) is proposed. Using an OFC as the optical source of the system can realize the colorlessness of optical network units (ONUs), and the direct detection of the downlink data further simplifies the ONU structure. The coherent demodulation of the uplink data improves the system performance due to the coherence of the comb lines. In this research, the proposed system is studied for its performance and power budgeting. The results show the flexibility, effectiveness, and practicability of the proposed scheme, which can be applied to future high-capacity optical access networks.

Power-aware high-capacity elastic optical networks

The power consumption of telecommunication equipment has been identified as a relevant contributor to global energy consumption. In fact, new-generation optical transponders employ power-intensive electronic application-specific integrated circuits (ASICs) for digital signal processing (DSP). DSP design has traditionally prioritized meeting transmission requirements over power consumption optimization. In general, the evolutions of transmission techniques and network design have always been mainly driven by traffic increase; in this context, in order to operate network resources more efficiently, margin reduction has been investigated in the past few years. Indeed, traditionally, high physical layer margins are used to ensure reliability over an extended period, resulting in overprovisioning the optical connections for both physical layer conditions and capacity. On the other hand, super-channels have emerged as a suitable solution for accommodating the continuous traffic growth. However, power consumption has not been deeply considered in the optimization of super-channel transmission. This paper first investigates the power efficiency of super-channels operated with designed and reduced margins. Low-margin operation is enabled by adapting sub-carrier spacing and filter bandwidth. Power-aware super-channel optimization is then experimentally demonstrated leveraging a 600 Gbit/s transponder in the SDN-controlled elastic optical network (EON). The results have identified a trade-off between power consumption and spectrum efficiency. Furthermore, the ongoing bandwidth demand has motivated the investigation of multi-band (MB) transmission for scaling the capacity of the existing infrastructures. However, novel networking devices (e.g., optical amplifiers operating beyond the C- and L-bands) will affect the overall power consumption. In this context, experimental power analysis of a thulium doped fiber amplifier (TDFA) is performed based on the traffic load and corresponding configuration. The results show that TDFA power consumption varies with configuration and increases with output power.

Reconfigurable Intelligent Surface Assisted Non-Orthogonal Multiple Access Network Based on Machine Learning Approaches

In the upcoming beyond fifth-generation (B5G), the surging demand on high network capacity and numerous access devices can hardly be satisfied by the scarce spectrum resources. Capable of sharing the same spectrum resource among multiple users, non-orthogonal multiple access (NOMA) provides an efficient method to enhance the spectrum efficiency, serving as a strong candidate for next generation multiple access (NGMA). To achieve a better performance gain of NOMA, reconfigurable intelligent surface (RIS) provides an effective leverage by reconstructing the channel conditions. Since the increasingly computational complexity and elusive communication environment in RIS-aided NOMA networks, we employ machine learning (ML) to improve network performance. In this article, we first present an overview of the NOMA, RIS, and ML. Based on the good compatibility between NOMA and RIS, we then provide a series of emerging application scenarios and associated challenges of RIS-aided NOMA. After that, we discuss the potential of ML approaches to cope with the challenges in RIS-aided NOMA. Finally, evaluation results are provided to illustrate the superiority of the RIS-aided NOMA network based on ML.

A High-Capacity Optical Metro Access Network: Efficiently Recovering Fiber Failures with Robust Switching and Centralized Optical Line Terminal.

This study proposes and presents a new central office (CO) for the optical metro access network (OMAN) with an affordable and distinctive switching system. The CO's foundation is built upon a novel optical multicarrier (OMC) generation technique. This technique provides numerous frequency carriers that are characterized by a high tone-to-noise ratio (TNR) of 40 dB and minimal amplitude excursions. The purpose is to accommodate multiple users at the optical network unit side in the optical metropolitan area network (OMAN). The OMC generation is achieved through a cascaded configuration involving a single phase and two Mach Zehnder modulators without incorporating optical or electrical amplifiers or filters. The proposed OMC is installed in the CO of the OMAN to support the 1.2 Tbps downlink and 600 Gbps uplink transmission, with practical bit error rate (BER) ranges from 10-3 to 10-13 for the downlink and 10-6 to 10-14 for the uplink transmission. Furthermore, in the OMAN's context, optical fiber failure is a main issue. Therefore, we have proposed a possible solution for ensuring uninterrupted communication without any disturbance in various scenarios of main optical fiber failures. This demonstrates how this novel CO can rapidly recover transmission failures through robust switching a and centralized OLT. The proposed system is intended to provide users with a reliable and affordable service while maintaining high-quality transmission rates.

A High-Capacity and High-Security Image Steganography Network Based on Chaotic Mapping and Generative Adversarial Networks

With the enhancement of information volume, people are not satisfied with transmitting only a single secret image at a time but chase to hide multiple secret images in a single picture; however, the large-capacity steganographic scale can easily lead to the degradation of the quality of the image, which attracts the attention of eavesdroppers. In this paper, we propose a Chaotic mapping-enHanced imAge Steganography nEtwork (CHASE), which pioneers to hide colour images in grey images and reduces the difference between the container image and the cover image through the image permutation method, so as to enhance the security of the steganography. The method demonstrates excellent steganalysis resistance in experiments and introduces Generative Adversarial Networks (GANs) to improve the image fidelity in large-capacity steganographic scales. The fusion of chaotic mapping and GAN optimisation enables the steganographic network to simultaneously balance security and image quality. The experimental results show that CHASE can keep the secret image with good invisibility under large-capacity steganographic scales, and at the same time, it can reveal the secret image with high fidelity, and its steganalysis-resistant capability is much better than other state-of-the-art methods.