Scalable Network Research Articles

A Conceptual Study of Rapidly Reconfigurable and Scalable Bidirectional Optical Neural Networks Leveraging a Smart Pixel Light Modulator

We explore the integration of smart pixel light modulators (SPLMs) into bidirectional optical neural networks (BONNs), highlighting their advantages over traditional spatial light modulators (SLMs). SPLMs enhance BONN performance by enabling faster light modulation in both directions, significantly increasing the refresh rate of neural network weights to hundreds of megahertz, thus facilitating the practical implementation of the backpropagation algorithm and two-mirror-like BONN structures. The architecture of an SPLM-based BONN (SPBONN) features bidirectional modulation, simplifying hardware with electrical fan-in and fan-out. An SPBONN with an array size of 96 × 96 can achieve high throughput, up to 4.3 × 1016 MAC/s with 10 layers. Energy assessments showed that the SPLM array, despite its higher power consumption compared to the SLM array, is manageable via effective heat dissipation. Smart pixels with programmable memory in the SPBONN provide a cost-effective solution for expanding network node size and overcoming scalability limitations without the need for additional hardware.

A Scalable Sorting Network Based on Hybrid Algorithms for Accelerating Data Sorting

Sorting in sequential data mining is significantly improved through hardware acceleration, which becomes essential as data volume and complexity increase. This paper presents a scalable hybrid sorting network that maintains or improves performance while reducing computational load and hardware requirements. The network is composed of the pre-comparison odd–even sorting network (P-OESN) and the bidirectional insertion sorting network (BISN). A pre-comparison layer is introduced to the original OESN. This layer aims to place larger values in the first half of the input sequence and smaller values in the latter half. The number of iterations is reduced when the P-OESN transitions from fully parallel execution to iterative execution. A novel pipelined BISN architecture is proposed, which leads to enhanced operating frequency and throughput. The experimental results show that the pre-comparison layer reduces the number of iterations by 6% to 50%. Throughput is improved by more than four times, and operating frequency is increased by more than two times due to the pipelined BISN. The proposed hybrid sorting network reduces sorting time or resource usage, while enabling the sorting of large-scale data sets that other methods cannot support.

Spectral principle for frequency synchronization in repulsive laser networks and beyond.

Network synchronization of lasers is critical for achieving high-power outputs and enabling effective optical computing. However, the role of network topology in frequency synchronization of optical oscillators and lasers remains not well understood. Here, we report our significant progress toward solving this critical problem for networks of heterogeneous laser model oscillators with repulsive coupling. We discover a general approximate principle for predicting the onset of frequency synchronization from the spectral knowledge of a complex matrix representing a combination of the signless Laplacian induced by repulsive coupling and a matrix associated with intrinsic frequency detuning. We show that the gap between the two smallest eigenvalues of the complex matrix generally controls the coupling threshold for frequency synchronization. In stark contrast with attractive networks, we demonstrate that local rings and all-to-all networks prevent frequency synchronization, whereas full bipartite networks have optimal synchronization properties. Beyond laser models, we show that, with a few exceptions, the spectral principle can be applied to repulsive Kuramoto networks. Our results provide guidelines for optimal designs of scalable optical oscillator networks capable of achieving reliable frequency synchronization.

Dimensioning Space-Air-Ground Integrated Networks for In-Flight 6G Slice Orchestration

In this study, we present an in-depth analysis of communication services for commercial airline passengers, focusing on the challenges posed by increasing internet traffic demand. We explore the integration of satellite, airborne, and terrestrial networks, emphasizing the roles of Low Earth Orbit (LEO) satellites, High-Altitude Platform Station (HAPS), and Terrestrial Aviation Network (TAN)-based services. Our contribution includes a theoretical model for optimizing resource allocation and capacity planning in non-terrestrial wireless networks, using a bipartite graph approach and linear programming techniques. The model shows adaptability and efficiency, providing key insights through numerical analysis. Leveraging a detailed air traffic dataset, a machine learning-based aggregation method, and real-world network parameters, our research addresses current challenges, such as scalable network capacity dimensioning in high-density airspaces and meeting the demand for quality of service by robust resource provisioning, and advances the design of communication networks for Space–Air–Ground Integrated Network (SAGIN). Numerical results from European airspace suggest that complementing TAN and LEO satellite networks with HAPS-based services will be essential as airline passengers adopt ground-level internet usage patterns.

Retraction Notice: “Optimized shortest path algorithm for on-chip board processor in large scale networks” [Optik 271, December 2022, 170151

Retraction Notice: “Optimized shortest path algorithm for on-chip board processor in large scale networks” [Optik 271, December 2022, 170151

Dual multi scale networks for medical image segmentation using contrastive learning

Dual multi scale networks for medical image segmentation using contrastive learning

Clustered OLSR routing and FPGA parameter analysis for mobile ad hoc communication

ABSTRACT The research letter emphasises the hardware chip design of homogeneous clustered optimised link state routing (HMC-OLSR) protocol for Mobile Ad-hoc Networks (MANET). The homogeneously distributed clustering allows for parallel processing and distributes the burden evenly among the clusters to reduce the network complexity and computational time. The chip design is evaluated based on field programmable gate array (FPGA) performance metrics for the proposed HMC-OLSR protocol, which significantly reduced hardware utilisation by 27.45%, 48.8% of slices, 28.71%, 55.82% of flip-flops, 8.35%, 13.60% of look-up tables (LUTs), and 36.4% of input/output blocks (IoBs) compared to existing OLSR and destination-Sequenced distance vector (DSDV) protocols, respectively. The recommended protocol also outperformed OLSR and DSDV routing protocols in FPGA timing constraints such as minimum time before the clock, maximum time after the clock, and minimum propagation period. The novelty of the work is in the incorporation of an FPGA-integrated scalable network design that surpasses maximum throughput, packet delivery ratio (PDR), minimum power consumption, end-to-end delay, and control overhead.

Leveraging SDN for scalable and sustainable fat tree networks: a multi-objective performance and energy efficiency evaluation of an 8-pod fat tree data center

Modern data centers increasingly rely on Software-Defined Networking (SDN) to address challenges related to scalability, performance, and efficient resource management. This research investigates the scalability and performance optimization of fat-tree topology within SDN environments, focusing on the impact of a sleep mode technique on network efficiency and energy consumption. Using the Mininet emulator, an 8-pod fat-tree network is simulated and compared against traditional routing methods like Equal-Cost Multi-Path (ECMP) and Dijkstra’s algorithm. The findings show that the sleep mode technique improves bandwidth utilization and throughput by reducing energy consumption during low-traffic periods without significantly affecting data flow. In contrast, Dijkstra’s algorithm exhibited reduced throughput due to inefficient path management, while ECMP did not fully optimize load balancing or energy efficiency. The sleep mode approach efficiently redistributes traffic across active switches, preventing congestion and outperforming both Dijkstra and ECMP in terms of average load. The results demonstrate that implementing sleep mode in fat-tree SDN networks enhances both network performance and energy efficiency, offering a practical solution for large-scale data center operations. These findings provide valuable insights for optimizing SDN-based traffic management in modern network infrastructures.

Toward Enhancing Privacy Preservation of a Federated Learning CNN Intrusion Detection System in IoT: Method and Empirical Study

Enormous risks and hidden dangers of information security exist in the applications of Internet of Things (IoT) technologies. To secure IoT software systems, software engineers have to deploy advanced security software such as Intrusion Detection Systems (IDS) that are able to keep track of how the IoT devices behave within the network and detect any malicious activity that may be occurring. Considering that IoT devices generate large amounts of data, Artificial Intelligence (AI) is often regarded as the best method for implementing IDS, thanks to AI’s high capability in processing large amounts of IoT data. To tackle these security concerns, specifically the ones tied to the privacy of data used in IoT systems, the software implementation of a Federated Learning (FL) method is often used to improve both privacy preservation (PP) and scalability in IoT networks. In this article, we present an FL IDS that leverages a 1-Dimensional Convolutional Neural Network (CNN) for efficient and accurate intrusion detection in IoT networks. To address the critical issue of PP in FL, we incorporate three techniques: Differential Privacy, Diffie–Hellman Key Exchange, and Homomorphic Encryption. To evaluate the effectiveness of our solution, we conduct experiments on seven publicly available IoT datasets: TON-IoT, IoT-23, BoT-IoT, CIC IoT 2023, CIC IoMT 2024, RT-IoT 2022, and EdgeIIoT. Our CNN-based approach achieves outstanding performance with an average accuracy, precision, recall, and F1-score of 97.31%, 95.59%, 92.43%, and 92.69%, respectively, across these datasets. These results demonstrate the effectiveness of our approach in accurately identifying and detecting intrusions in IoT networks. Furthermore, our experiments reveal that implementing all three PP techniques only incurs a minimal increase in computation time, with a 10% overhead compared to our solution without any PP mechanisms. This finding highlights the feasibility and efficiency of our solution in maintaining privacy while achieving high performance. Finally, we show the effectiveness of our solution through a comparison study with other recent IDS trained and tested on the same datasets we use.

Reinforcement learning based route optimization model to enhance energy efficiency in internet of vehicles

The Internet of Vehicles (IoV) transforms the automobile industry through connected vehicles with communication infrastructure that improves traffic control, safety and information, and entertainment services. However, some issues remain, like data protection, privacy, compatibility with other protocols and systems, and the availability of stable and continuous connections. Specific problems are related to energy consumption for transmitting information, distributing energy loads across the vehicle’s sensors and communication units, and designing energy-efficient approaches to processing received data and making decisions in the context of the IoV environment. In the realm of IoV, we propose OptiE2ERL, an advanced Reinforcement Learning (RL) based model designed to optimize energy efficiency and routing. Our model leverages a reward matrix and the Bellman equation to determine the optimal path from source to destination, effectively managing communication overhead. The model considers critical parameters such as Remaining Energy Level (REL), Bandwidth and Interference Level (BIL), Mobility Pattern (MP), Traffic Condition (TC), and Network Topological Arrangement (NTA), ensuring a comprehensive approach to route optimization. Extensive simulations were conducted using NS2 and Python, demonstrating that OptiE2ERL significantly outperforms existing models like LEACH, PEGASIS, and EER-RL across various performance metrics. Specifically, our model extends the network lifetime, delays the occurrence of the first dead node, and maintains a higher residual energy rate. Furthermore, OptiE2ERL enhances network scalability and robustness, making it a superior choice for IoV applications. The simulation results highlight the effectiveness of our model in achieving energy-efficient routing while maintaining network performance under different scenarios. By incorporating a diverse set of parameters and utilizing RL techniques, OptiE2ERL provides a robust solution for the challenges faced in IoV networks. This research contributes to the field by presenting a model that optimizes energy consumption and ensures reliable and efficient communication in dynamic vehicular environments.

Life Cycle Assessment for Concrete and Asphalt Pavement at the Network Scale

In 2001 the Québec Ministry of Transportation (MTQ), Canada, has adopted a policy subdividing the existing pavement network into dedicated concrete and asphalt networks. Pavement designs for 16 Functional Class were compared for asphalt and concrete for a 50 years analysis period using a Life Cycle Cost Analysis (LCCA). In addition to LCCA, a multiple criteria analysis was performed to account for input factors not amenable to quantification in monetary terms. The 2010 policy was updated for cost and traffic demand. Environment issues were also addressed through a life cycle assessment (LCA) performed on 32 pavements designs. This paper presents the application of conventional LCA methodology to roads, salient inventory data and main comparative results with respect to midpoint and endpoint environmental impacts. Results are clearly in favour of asphalt pavements for three out of four endpoint impact, namely human health, climate change and ecosystem quality, whereas impacts on resource consumption is favorable to concrete pavement.

Longitudinal associations between informal caring, social network, and psychological distress among adolescents and young adults: modelling within-person effects

BackgroundInformal caring is associated with mental health deterioration among young people and impacts their help-seeking ability. Social network can provide social support and mitigate the impact of informal care. However, young carers may avoid identification and withdraw from social networks. Evidence regarding the reciprocal associations between caring, social network, and mental health is scarce. We aimed to investigate the directionality and specificity of the associations among the three factors in young people.MethodsThis study used three consecutive assessment data (2021–2023; T0–T2) from the Japan COVID-19 and Society Internet Survey. We included 5539 young persons aged ≤ 25 years and 25,445 adults aged 26–59 years. Social network was measured using the Lubben Social Network Scale. Psychological distress was evaluated using the Kessler Psychological Distress Scale. Caring status was retrospectively reported at T2. We employed a random intercept cross-lagged model to detect within-person prospective associations between informal caring, social network, and psychological distress.ResultsYoung persons showed significant directional relationships from increased social network and psychological distress at T0 to increased likelihood of caring at T1 (standardised coefficient: 0.131 and 0.176, respectively; 95% confidence interval, 0.015–0.247 and 0.071–0.282, respectively). Adults aged 26–59 years showed a reverse relationship from caring to increased psychological distress both from T0 to T1 (0.061, 0.009–0.112) and from T1 to T2 (0.042, 0.000–0.084).ConclusionsIncreased psychological distress and social network preceded the onset of informal caring among young persons. Incorporating psychological distress assessment may benefit the early identification of and support for young carers. The long-term interplay between social networking and informal caring needs further clarification.

Review of intermediate representations for quantum computing

Intermediate representations (IRs) are fundamental to classical and quantum computing, bridging high-level quantum programming languages and the hardware-specific instructions required for execution. This paper reviews the development of quantum IRs, focusing on their evolution and the need for abstraction layers that facilitate portability and optimization. Monolithic quantum IRs, such as QIR (Lubinski et al. in Front Phys 10:940293, 2022. https://doi.org/10.3389/fphy.2022.940293), QSSA (Peduri et al. in Proceedings of the 31st ACM SIGPLAN international conference on compiler construction. CC 2022. Association for Computing Machinery, New York, 2022), or Q-MLIR (McCaskey and Nguyen in Proceedings-2021 IEEE International Conference on Quantum Computing and Engineering, QCE, 2021), their effectiveness in handling abstractions, and their hybrid support between quantum-classical operations are evaluated. However, a key limitation is their inability to address qubit locality, an essential feature for distributed quantum computing (DQC). To overcome this, InQuIR (Nishio and Wakizaka in InQuIR: Intermediate Representation for Interconnected Quantum Computers, 2023. https://arxiv.org/abs/2302.00267) was introduced as an IR specifically designed for distributed systems, providing explicit control over qubit locality and inter-node communication. While effective in managing qubit distribution, InQuIR’s dependence on manual manipulation of communication protocols increases complexity for developers. NetQIR (Vázquez-Pérez et al. in NetQIR: An Extension of QIR for Distributed Quantum Computing, 2024. https://arxiv.org/abs/2408.03712), an extension of QIR for DQC, emerges as a solution to achieve the abstraction of quantum communications protocols. This review emphasizes the need for further advancements in IRs for distributed quantum systems, which will play a crucial role in the scalability and usability of future quantum networks.

Simulating fish autonomous swimming behaviours using deep reinforcement learning based on Kolmogorov–Arnold Networks

The study of fish swimming behaviours and locomotion mechanisms holds significant scientific and engineering value. With the rapid advancements in artificial intelligence, a new method combining deep reinforcement learning (DRL) with computational fluid dynamics has emerged and been applied to simulate the fish's adaptive swimming behaviour, where the complex fish behaviour is decoupled to focus on the fish's response to the hydrodynamic field, and the simulation is driven by reward-based objectives to model the fish's swimming behaviour. However, the scale of this cross-disciplinary method is directly affected by the efficiency of the DRL model. To promote it to more general application scenarios, there is a pressing need for further research on more efficient and economical network architectures to address the challenge of approximating state-value function in high-dimensional, dynamic, and uncertain environments. Building upon a previously proposed computational platform for the simulation of fish autonomous swimming behaviour, we integrated Kolmogorov-Arnold Networks(KANs) and tested their performance in point-to-point swimming and Kármán gait swimming environments. Experimental results demonstrated that, compared to long short-term memory Networks(LSTMs) and multilayer perceptron networks(MLPs), the introduction of KANs significantly enhanced the perception and decision-making abilities of the intelligent fish in complex fluid environments. With a smaller network scale, in the point-to-point swimming case, KANs effectively approximated the state-value function, achieving average reward improvements of up to 88.0% and 94.1% over MLPs and LSTMs networks, respectively, and increased by 766.7% and 105.6% in the Kármán gait swimming case. Under comparable network sizes, the intelligent fish with KANs exhibited faster learning capabilities and more stable swimming performance in complex fluid settings.

Scalable recurrence graph network for stratifying RhoB texture dynamics in rectal cancer biopsies

The scalable recurrence graph network (SRGNet) is introduced in this paper to improve the accuracy of predicting five-year survival outcomes in rectal cancer patients by analyzing RhoB texture dynamics in biopsies. RhoB, a key biomarker assessed via immunohistochemistry, is crucial in predicting responses to radiotherapy (RT), but variability in staining techniques and tumor heterogeneity often complicate these assessments. SRGNet integrates spatial statistics, nonlinear dynamics, graph theory, and graph convolutional networks to address these challenges. In testing, SRGNet outperformed 10 pre-trained convolutional neural networks, achieving 88% accuracy in biopsies from RT patients, with 67% accuracy for predicting survival under five years and 100% accuracy for survival over five years, along with 100% precision, an F1 score of 0.80, and an AUC of 0.73. For non-RT patients, SRGNet attained 91% accuracy, 100% precision for survival over five years, an F1 score of 0.86, and an AUC of 0.82. These results demonstrate SRGNet’s potential to enhance the precision and reliability of survival predictions in rectal cancer patients, overcoming challenges of RhoB expression variability and tumor heterogeneity.

Energy-Efficient Distributed Edge Computing to Assist Dense Internet of Things

The Internet of Things (IoT) represents a rapidly growing field, where billions of intelligent devices are interconnected through the Internet, enabling the seamless sharing of data and resources. These smart devices are typically employed to sense various environmental characteristics, including temperature, motion of objects, and occupancy, and transfer their values to the nearest access points for further analysis. The exponential growth in sensor availability and deployment, powered by recent advances in sensor fabrication, has greatly increased the complexity of IoT network architecture. As the market for these sensors grows, so does the problem of ensuring that IoT networks meet high requirements for network availability, dependability, flexibility, and scalability. Unlike traditional networks, IoT systems must be able to handle massive amounts of data generated by various and frequently-used resource-constrained devices, while ensuring efficient and dependable communication. This puts high constraints on the design of IoT, mainly in terms of the required network availability, reliability, flexibility, and scalability. To this end, this work considers deploying a recent technology of distributed edge computing to enable IoT applications over dense networks with the announced requirements. The proposed network depends on distributed edge computing at two levels: multiple access edge computing and fog computing. The proposed structure increases network scalability, availability, reliability, and scalability. The network model and the energy model of the distributed nodes are introduced. An energy-offloading method is considered to manage IoT data over the network energy, efficiently. The developed network was evaluated using a developed IoT testbed. Heterogeneous evaluation scenarios and metrics were considered. The proposed model achieved a higher energy efficiency by 19%, resource utilization by 54%, latency efficiency by 86%, and reduced network congestion by 92% compared to traditional IoT networks.

The Mediating Effect of Social Networks on the Impact of Health Perceptions on the Quality of Life in Older Adults.

Background/Objective: Social networks help improve psychosocial and quality-of-life outcomes among older adults. This study aimed to examine the mediating role of social networks in the effect of health perception on the quality of life of the elderly. Methods: The sample of the study consisted of 327 people over the age of 65 who applied to a family health center. The study data were collected using the "Personal Information Form", "Perception of Health Scale", "World Health Organization Quality of Life Instrument-Older Adults Module", and "Lubben Social Network Scale". Multivariate regression analyses and mediation effect examinations were conducted to explore the relationships between social networks, health perception, and quality-of-life outcomes. Results: According to the findings, social networks mediate the relationship between health perception and quality of life. Individuals with a high level of health perception and a high level of social networks have higher quality-of-life levels than others. Conclusions: The results of the study confirm the significant correlation between health perception and the quality of life, as well as any potential links between these factors and social networks that affect older people's quality of life.

Unveiling the effect of social networks on farmers' diversified energy-saving behaviors in the Tibetan plateau region of China.

An improved comprehension of the factors that influence farmers' diversified energy-saving behaviors makes significant sense for enacting potent energy policies and curbing rural energy consumption. This paper investigated the effect of social networks on diversified energy-saving behaviors adopted by farmers in the Tibetan Plateau region of China, by establishing a generalized Poisson regression model. A total of 480 farmers were randomly interviewed. The results indicate that farmers' social networks were relatively abundant in the study area, and the diversified energy-saving behaviors exhibited good performance at the overall level. Farmers' social networks are of paramount importance in the execution of diversified energy-saving behaviors. In particular, the scale and frequency of social networks are instrumental in the success of the implementation of diversified energy-saving behaviors. Farmers' sociodemographic characteristics, including gender, education level, household size, and residential housing area, also facilitate their adoption of diversified energy-saving behaviors. The findings contribute to the further exploration of the value of social networks in determining environmental actions in rural areas and provide an effective basis for policy formulation to save energy consumption in similar regions in other countries.

‘Buzz-and-Pipeline’ Dynamics in AI Innovation Network: A Case Study of Zhangjiang National Innovation Demonstration Zone, Shanghai

The success of a cluster depends on the interplay between intra- and inter-regional collaboration, while empirical research on the mechanisms through which intra- and inter-regional collaborations trigger cluster growth is rarely focused. Based on the local buzz–global pipelines framework and incorporating an evolutionary perspective, we explore how intra- and inter-regional innovation networks can be integrated to drive the growth of emerging industries. We draw on Zhangjiang, China’s most advanced AI industry cluster, using social network analysis and qualitative methods, combining patent data with semi-structured interviews. The results indicate that with the return of multinational corporations and the limitation of Western technology, universities have become the primary source of AI innovation in Zhangjiang. The government has played a pivotal role in propelling the accelerated growth of China’s AI industry, particularly through the backing of pioneering AI private enterprises and the calibration of the potential inefficiencies associated with a state-led model with the dynamism of market forces. The ‘Buzz-and-pipeline’ dynamics in the AI innovation network are shaped by four processes: local networking, market demand, resource integration, and policy synergy. This underscores the intricate interconnections between the national and local scales in AI innovation networks.

AI-Enhanced Traffic Prediction and Congestion Control: A Framework for CNF and VNF Networks

This article comprehensively analyzes artificial intelligence-driven approaches to traffic prediction and congestion control in Cloud-Native Functions (CNFs) and Virtual Network Functions (VNFs) based networks. This article examines recent advancements in predictive analytics and dynamic resource allocation, focusing on implementing deep learning frameworks such as Long Short-Term Memory (LSTM) networks for traffic pattern forecasting. This article demonstrates how continuous learning models and real-time telemetry data integration enable adaptive network responses to fluctuating traffic conditions. This article indicates that AI-enhanced load balancing and traffic shaping techniques significantly improve network performance, achieving a more efficient distribution of resources across network nodes while maintaining consistent Quality of Service (QoS). This article highlights the transformative potential of these innovations in meeting the demanding requirements of 5G networks and beyond, offering insights into cost-effective resource management strategies and scalable network solutions. Experimental results show substantial improvements in latency reduction and resource utilization efficiency, presenting a promising direction for next-generation telecom service optimization.