Routing Scheme Research Articles

Tiered Cloud Routing: Methodology, Latency, and Improvement

Large cloud providers including AWS, Azure, and Google Cloud offer two tiers of network services to their customers: one class uses the providers' private wide area networks (WAN-transit) to carry a customer's traffic as much as possible, and the other uses the public internet (inet-transit). Little is known about how each cloud provider configures its network to offer different transit services, how well these services work, and whether the quality of those services can be further improved. In this work, we conduct a large-scale study to answer these questions. Using RIPE Atlas probes as vantage points, we explore how traffic enters and leaves each cloud's WAN. In addition, we measure the access latency of the WAN-transit and the inet-transit service of each cloud and compare it with that of an emulated performance-based routing strategy. Our study shows that despite the cloud providers' intention to carry customers' traffic on its WAN to the maximum extent possible, for about 12% (Azure) and 13% (Google) of our vantage points, traffic exits the cloud WAN early at cloud edges more than 5000km away from the vantage points' nearest cloud edges. In contrast, more than 84% (AWS), 78% (Azure), and 81% (Google) of vantage points enter a cloud WAN within a 500km radius of their respective locations. Moreover, we find that cloud providers employ different routing strategies to implement the inet-transit service, leading to transit policies that may deviate from their advertised service descriptions. Finally, we find that a performance-based routing strategy can significantly reduce latencies in all three cloud providers for 4% to 85% of vantage point and cloud region pairs.

A maintenance scheduling and non-full vessel routing strategy for offshore wind farms considering day-ahead environment interval forecasting

A maintenance scheduling and non-full vessel routing strategy for offshore wind farms considering day-ahead environment interval forecasting

Dynamic Packet Routing Algorithm Based on Multidimensional Information and Multiagent Reinforcement Learning

ABSTRACTPacket routing is one of the critical factors that affect network performance and security, with the goal of finding the optimal path for network packets from the source node to the destination node. However, with the diversification of network architectures, the differences in network application requirements, and the time‐varying characteristics of network topologies, the limitations of traditional model‐ and rule‐based routing algorithms in terms of computational overhead and flexibility are becoming increasingly apparent. This paper designs a packet routing strategy based on multiagent deep reinforcement learning (MIMRL). In MIMRL, each router node is abstracted as an independent agent with its own neural network. Multidimensional data such as the current location of the data packet, the number of nodes in the network, the length of the data packet received at the current location node, and the set of neighboring nodes are used as inputs to the neural network. Combined with a segmented reward function, the optimal routing action is determined. Experimental results under different network loads in static and dynamic networks show that the MIMRL algorithm significantly outperforms the benchmark algorithm in multiple metrics such as average delivery time and proportion of full capacity nodes.

Adaptive Extended Kalman Prediction-Based SDN-FANET Segmented Hybrid Routing Scheme

Adaptive Extended Kalman Prediction-Based SDN-FANET Segmented Hybrid Routing Scheme

Smart Logical Traffic Routing Technique for Control Plane Interface in Data Centers

ABSTRACT The complexity of data center (DC) structures requires a control plane interface for scheduling data to the appropriate hierarchical layer. However, hardware limitations of CPI confine DC efficiency. We propose a logical traffic routing scheme for CPI using OR-AND gating control by extracting priority signals from the packet header of incoming connection requests. The proposed architecture utilizes a semiconductor optical amplifier with an erbium-doped amplifier to diminish SOA non-linearity. The contrast, the extinction ratio for OR and AND logic is 20, 19.8 dB, and 33.7, 27.9 dB, respectively. The proposed structure shows its superiority with minimum insertion loss: 1.46 and 2.8 dB for OR and AND respectively.

An Improved Salp Swarm Algorithm for Solving a Multi-Temperature Joint Distribution Route Optimization Problem

In order to address the diverse and personalized needs of consumers for fresh products, as well as to enhance the efficiency and safety of fresh product delivery, this paper proposes an integer programming model aimed at minimizing total distribution costs. The model takes into account the cold storage multi-temperature joint distribution mode, carbon emission costs, and actual constraints associated with the distribution process of fresh products. To solve this model, an improved salp swarm algorithm (SSA) has been developed. The feasibility and effectiveness of both the proposed model and algorithm are demonstrated using R110 data from the Solomon standard calculation example. Research findings indicate that compared to traditional single-product temperature distribution modes, the multi-temperature joint distribution mode achieves reductions in total distribution costs and vehicle quantities by 45.4% and 72.2%, respectively. Furthermore, it is observed that total distribution costs increase with rising unit carbon tax prices; however, the rate of growth gradually diminishes over time. Additionally, a reduction in vehicle load capacity results in a continuous rise in total delivery costs after reaching a certain turning point. When compared to conventional SSAs and genetic algorithms, the proposed algorithm demonstrates superior performance in generating optimal multi-temperature joint distribution route schemes for fresh products.

Characterizing and Optimizing Network Slicing and Virtualization in 5G/6G Networks: A Case Study

This study explores how advanced network management strategies can enhance resource efficiency, ensure high-quality service (QoS), and reduce latency in networks that incorporate varying numbers of slices. The primary goal was to tackle issues such as network congestion and resource allocation, which become more complex as user demand increases. As networks expand, it is essential to manage resources effectively to provide uninterrupted service without sacrificing performance. A key area of focus is network slicing, which involves dividing a network into virtual segments that are customized for different user needs or services. The research specifically examined how increasing the number of slices, from 1 to 50, impacted factors like QoS, resource utilization, and latency. By simulating these scenarios, the study measured key performance indicators such as QoS, resource consumption, and latency at each slice level. The findings revealed that resource utilization improved considerably as the number of slices increased, rising from approximately 0.1 to 0.9 when the slices grew from 1 to 50. This improvement demonstrates the network's scalability and its ability to efficiently allocate resources to accommodate growing demand. While the number of slices increased, QoS remained relatively stable. It started at 95% and decreased to 80% when the number of slices reached 50, which illustrates the network management system's capacity to sustain service quality, even under conditions of heavy congestion. Additionally, latency experienced a substantial reduction, falling from 90 ms with just one slice to 10 ms when there were 50 slices, showcasing the effectiveness of enhanced routing and management strategies. In conclusion, this study highlights the potential of advanced network management to address the challenges posed by growing demands while optimizing resource allocation, maintaining high service quality, and minimizing latency. These insights are critical for developing future networks that can efficiently support a wide range of services at scale.

Energy‐Efficient Fuzzy Logic With Barnacle Mating Optimization‐Based Clustering and Hybrid Optimized Cross‐Layer Routing in Wireless Sensor Network

ABSTRACTRecent advancements in information technology have led to the widespread adoption of the Internet of Things (IoT) across various applications. Wireless sensor networks (WSNs), consisting of low‐cost, compact sensors, are crucial for IoT systems, enabling data collection for tasks like surveillance and tracking. A major challenge in WSNs is achieving energy efficiency while extending network lifetime (NLT), necessitating effective clustering and routing strategies. Numerous existing methodologies for energy‐efficient clustering and routing exhibit potential; however, they are hindered by constraints including inadequate adaptability to fluctuating network conditions, suboptimal selection of s cluster heads (CHs), and uneven energy consumption, resulting in diminished network longevity and efficacy. These issues require novel strategies to improve overall performance. To tackle this issues, this research presents a novel hybrid technique combining fuzzy logic with barnacles mating optimization (FL‐BMO) to identify the most optimal CHs by evaluating critical criteria like average sink distance, average intracluster distance, residual energy, and CH balance factor. The FL‐BMO methodology utilizes fuzzy logic to address uncertainties in sensor data, and the BMO algorithm, modeled after barnacle mating patterns, offers a resilient and adaptable optimization process, markedly enhancing energy efficiency and network longevity. In addition, an innovative natural‐inspired hybrid cross‐layer sunflower optimization routing (NiHCLR‐SFO) technique has been introduced that entails optimal routing path selection. This approach balances exploration and exploitation during a route selection process, integrating multiple layers of the network functionality which eventually results in improved routing efficiency and network throughput. Such a hybrid approach has been implemented in MATLAB. The proposed method is compared with fuzzy reinforcement learning based data gathering (FRLDG), neuro‐fuzzy‐emperor penguin optimization (NF‐EPO), bio‐inspired cross‐layer routing (BiHCLR), and fuzzy rule‐based energy‐efficient clustering and immune‐inspired routing (FEEC‐IIR) protocols. From these comparisons, it was observed that the method propagates definite NLT gains reaching 39.74%, 32.92%, 15.95%, and 4.8076%, respectively. The proposed method outperforms the existing approaches (FRLDG, NF‐EPO, FEEC‐IIR, and BiHCLR) across several performance parameters: 99% packet delivery ratio (PDR), 2.8 ms of end‐to‐end delay time (E2ED), 1 Mbps of throughput, 30 mJ of energy consumption, 6000 rounds NLT, 2% bit error rate (BER), 1.25 buffer occupancy ratio, and 0.5% of packet loss ratio (PLR).

An Innovative Algorithm for Multipath Routing and Energy Efficiency in IoT Across Varied Network Topology Densities

The biggest problem for IoT networks is sensor node data transport. Overuse of communication power shortens node lifespan. Therefore, network issues including QoS, security, network heterogeneity, congestion reduction, reliable routing, and energy efficiency must be addressed. Routing protocols are essential for corporate data transmission. Information collection and consolidation need data aggregation to minimize traffic congestion, operating expenses, energy usage, and network lifespan. Aggregating IoT data makes route planning dependable, energy-efficient, and difficult. NS2 simulation generated Disjoint & Scalable Multipath Routing (D &SMR), a novel routing architecture. The method measures delivery performance using decision trees and neural networks. During model training, we evaluate (D &SMR) routing scheme predictability, node popularity, power consumption, velocity, and location. Simulations show that (D &SMR) outperforms a reliable routing system in delivery success, message loss, overhead, and hop count. The proposed hybrid routing method includes cluster construction and intra-and inter-cluster routing. The research found that (D &SMR) outperforms previous studies in network resilience, packet transmission efficiency, latency, and energy usage.

Enhancing unmanned aerial vehicles logistics for dynamic delivery: a hybrid non-dominated sorting genetic algorithm II with Bayesian belief networks

Abstract To address the complexities of managing networks of unmanned aerial vehicles (UAVs) and Just-in-Time problem solving, this study introduces a cutting-edge multi-objective location-routing optimization model. This model integrates time window constraints, concurrent pick-up and delivery demands, and rechargeable battery functionality, significantly enhancing the efficiency of UAV operations. It reduces battery consumption and transportation costs while optimizing delivery times and reducing operational risks. The model improves the refinement of delivery schedules by accounting for uncertain traffic scenarios, thereby increasing its accuracy and reliability in dynamic environments. Additionally, a Bayesian belief networks approach for risk assessment introduces a new layer to operational risk management. The model’s performance and its trade-offs are demonstrated through advanced data visualizations such as 3D Pareto fronts, pair plots, and network graphs, with validation via the NSGA-II approach confirming its reliability and practical applicability. This research represents a major leap forward in drone routing strategies, focusing on efficiency, adaptability, and risk management in UAV logistics and provides a comprehensive framework that bridges the gap between theoretical exploration and practical application.

A scalable routing method for superconducting quantum processor

Routing design is an important aspect in aiding the completion of the Quantum Processing Unit (QPU) layout design for large-scale superconducting quantum processors. One of the research focuses is how to generate reliable routing schemes within a short time. In this study, we propose a superconducting quantum processor auto-routing method for supporting scalable architecture, which is mainly implemented through the bidirectional A star algorithm, the backtracking algorithm, and the greedy strategy. By using this method, the number of crossovers and corners can be reduced while efficiently completing the processor routing. To verify the effectiveness of our method, we selected 5 types of qubit numbers for processor routing experiments. The experimental results show that compared to the improved A star algorithm of Qiskit Metal, our method reduces the average execution time by at least 43.61% and 41.68% in serial and parallel, respectively. Compared with four other routing algorithms, our method has a minimum average reduction of 10.63% and 1.21% in the number of crossovers and corners, respectively. In addition, our method supports the processor routing design of planar and flip-chip architectures, and can automatically process both airbridge and insulation types of crossovers. Therefore, our method can provide efficient and reliable automated routing design to assist the development of large-scale superconducting quantum processors.

Machine Learning-Enhanced Hybrid Source Location Privacy Protocol for Improved Security and Network Longevity in IoT Networks

Efficient routing in IoT networks is critical for optimizing data transmission while addressing the inherent challenges of energy consumption, scalability, and resilience. Common routing techniques, such as flooding, tree-based, cluster-based, and geographic routing, each present unique advantages and limitations regarding energy efficiency, network congestion, and fault tolerance. In parallel, source location privacy protection (SLPP) has emerged as a pivotal concern in IoT applications like surveillance and environmental monitoring, where adversaries may exploit transmission patterns to identify sensitive source nodes. Despite advancements, current issues in SLP in IoT networks include balancing privacy with energy efficiency, ensuring scalability in dense network environments, and providing resilience against increasingly sophisticated adversarial models. Traditional SLP techniques, including phantom routing, random walks, and dummy packet generation, often impose trade-offs between privacy, energy consumption, and network longevity, limiting their practical application in large-scale IoT networks. Additionally, many existing protocols struggle with adapting to dynamic network topologies and fail to adequately address the challenges posed by hotspot formation, which can lead to uneven energy depletion and compromised privacy. Many SLP methods disrupt the Quality of Service (QoS) by introducing delays or reducing throughput, which can hinder the primary functions of IoT applications, particularly in time-sensitive scenarios. A new Hybrid Source Location Privacy (SLP) protocol that effectively integrates random walks, rumor routing, and Greedy Random Walks to obscure source node locations while optimizing energy consumption is implemented to overcome these limitations. The protocol employs a multi-layer grid framework, dynamic cluster head rotations, and phantom nodes to balance energy usage and reduce network hotspots. The new Hybrid SLP confuses adversaries by combining fake packet generation with adaptive routing strategies, enhancing privacy without compromising network performance. Simulations demonstrate that the Hybrid SLP protocol significantly outperforms existing techniques, achieving lower energy consumption, extended network lifetime, and robust privacy protections, making it ideal for privacy-sensitive IoT applications. The proposed Hybrid SLP protocol integrates a machine learning-based anomaly detection system to enhance its performance and security, highlighting the novelty of the proposed work. This novel combination of advanced routing strategies and machine learning strengthens network resilience against various threats.

Adaptive Routing Algorithms of Network-on-Chip: A Literature Review

To solve the challenges in the field of integrated circuits (IC) or system-on-chip (SoC) design, network-on-chip (NoC) has been recognized as a core concept. A routing algorithm is one of the key research among all the aspects NoC relates. Therefore, finding an optimal routing algorithm can help enhance the networks performance, reduce latency, increase scalability, decrease power consumption, limit expenditure, and so on. Due to its importance, we delve deeper into the area of routing algorithms for NoC designs. In this paper, we will review and summarize three mesh-based adaptive routing algorithms used for NoC, and provide a simple comparison and evaluation between these algorithms. Specifically, Neighboron-path (NoP) is used as the fundamental algorithm in our paper. Then the two advanced routing algorithms, regional ant colony optimization-based cascaded adaptive routing (RACO-CAR) and destination-based selection strategy (DBSS), will be analyzed and compared with NoP.

Enhancing Network Performance: A Comprehensive Analysis of Hybrid Routing Algorithms

Recent years have seen the proposal of numerous routing algorithms for potential use in a variety of application areas. In many network types, such as Wireless Sensor Networks (WSNs), Mobile Ad Hoc Networks (MANETs), and other dynamic contexts, routing is a crucial difficulty. By fusing the benefits of proactive (table-driven) and reactive (on-demand) routing techniques, hybrid routing algorithms have become a notable breakthrough. Researchers have focused on hybrid routing algorithms since traditional ones frequently fail to adjust to the changing network conditions present in MANETs. These novel methods strive to maximize speed while reducing overhead by combining the best features of proactive and reactive routing strategies. It provided a thorough analysis of these algorithms in this work, emphasizing their mechanisms, benefits, limitations, and security features. Also focused especially on the analysis of hybrid routing algorithms in a range of applications.

Low-latency hierarchical routing of reconfigurable neuromorphic systems.

A reconfigurable hardware accelerator implementation for spiking neural network (SNN) simulation using field-programmable gate arrays (FPGAs) is promising and attractive research because massive parallelism results in better execution speed. For large-scale SNN simulations, a large number of FPGAs are needed. However, inter-FPGA communication bottlenecks cause congestion, data losses, and latency inefficiencies. In this work, we employed a hierarchical tree-based interconnection architecture for multi-FPGAs. This architecture is scalable as new branches can be added to a tree, maintaining a constant local bandwidth. The tree-based approach contrasts with linear Network on Chip (NoC), where congestion can arise from numerous connections. We propose a routing architecture that introduces an arbiter mechanism by employing stochastic arbitration considering data level queues of First In, First Out (FIFO) buffers. This mechanism effectively reduces the bottleneck caused by FIFO congestion, resulting in improved overall latency. Results present measurement data collected for performance analysis of latency. We compared the performance of the design using our proposed stochastic routing scheme to a traditional round-robin architecture. The results demonstrate that the stochastic arbiters achieve lower worst-case latency and improved overall performance compared to the round-robin arbiters.

A prize-dependent loitering time approach to UAS routing: application to South China Sea maritime domain awareness

This article advances the geographic grid approach to military unmanned aircraft systems (UAS) routing featured in the existing literature. Its contributions are twofold. First, it demonstrates an empirical scoring system to determine the most important areas for maritime domain awareness-focused intelligence, surveillance, and reconnaissance collection, applying the method to the South China Sea. Second, it introduces what we call the “team orienteering problem with prize-dependent loitering times” (TOP-PDLT) and uses that model to identify optimal UAS collection routes in the South China Sea. Compared with other grid-based UAS routing schemes that use service time-dependent profits, TOP-PDLT is shown to be particularly applicable to military use-cases.

An Innovative Priority Queueing Strategy for Mitigating Traffic Congestion in Complex Networks

Optimizing transportation in both natural and engineered systems, particularly within complex network environments, has become a pivotal area of research. Traditional methods for mitigating congestion primarily focus on routing strategies that utilize first-in-first-out (FIFO) queueing disciplines to determine the processing order of packets in buffer queues. However, these approaches often fail to explore the benefits of incorporating priority mechanisms directly within the routing decision-making processes, leaving significant room for improvement in congestion management. This study introduces an innovative generalized priority queueing (GPQ) strategy, specifically designed as an enhancement to existing FIFO-based routing methods. It is important to note that GPQ is not a new queue scheduling algorithm (e.g., deficit round robin (DRR) or weighted fair queuing (WFQ)), which typically manage multiple queues in broader queue management scenarios. Instead, GPQ integrates a dynamic priority-based mechanism into the routing layer, allowing the routing function to adaptively prioritize packets within a single buffer queue based on network conditions and packet attributes. By focusing on the routing strategy itself, GPQ improves the process of selecting packets for forwarding, thereby optimizing congestion management across the network. The effectiveness of the GPQ strategy is evaluated through extensive simulations on single-layer, two-layer, and dynamic networks. The results demonstrate significant improvements in key performance metrics, such as network throughput and average packet delay, when compared to traditional FIFO-based routing methods. These findings underscore the versatility and robustness of the GPQ strategy, emphasizing its capability to enhance network efficiency across diverse topologies and configurations. By addressing the inherent limitations of FIFO-based routing strategies and proposing a generalized yet scalable enhancement, this study makes a notable contribution to network optimization. The GPQ strategy provides a practical and adaptable solution for improving transportation efficiency in complex networks, bridging the gap between conventional routing techniques and emerging demands for dynamic congestion management.

Distributed Anti-Cascading Routing Scheme Based on Fuzzy Logic in LEO Satellite Networks

Distributed Anti-Cascading Routing Scheme Based on Fuzzy Logic in LEO Satellite Networks

Comparison of distributed and centralized quantum key management systems for meshed QKD networks

Recent developments in quantum key distribution (QKD) demonstrate the maturity of securing sensitive data against the emerging quantum computing threat. For QKD-secured long-haul and meshed optical transport networks (OTNs), quantum key management systems (QKMSs) are essential to overcome current distance limitations of available QKD devices. In this work, we present and compare two implementations of QKMSs, analyzing their scalability with an emulated QKD network (QKDN) utilizing recorded performance metrics from deployed QKD devices. First, we use a state-of-the-art Internet routing scheme, i.e., open shortest path first (OSPF), demonstrating that key management entities (KMEs) can solve the key routing problem utilizing distributed routing. Second, we apply software-defined networking (SDN) to implement centralized routing with a SDN controller. This paper compares distributed with centralized key routing regarding scalability, throughput, and latency. Both schemes facilitate up to six key relays between any pair of nodes in parallel with average key relay durations per hop below 300 ms given the Nobel-Germany topology and any-to-any demand matrix. With a network-wide joint key routing optimization in the SDN controller, up to 16.7% higher demands can be served compared to distributed key routing. Within the inherent compatibility of our study to network-function virtualization (NFV), we guideline future integration of QKMSs into deployed OTNs.

Defying Social Inequality in the Gulf: Skilled Survivors’ Coping Routes, Racialized Capitalism, and Temporary Filipino Migrants in the UAE

How do temporary migrants cope with social inequality in the ‘illiberal’ host states of the Global South? While mainstream scholarly work on labor migration in the Gulf has historically traced the existence of structural violence, racialized hierarchy, and social inequality imposed on temporary migrants, it also frames migrants as ‘powerless’ and ‘rule-taker’ victims. In doing so, scholars overlook the diverse coping or mobility route strategies of temporary migrants. Temporary Filipino migrants, one of the largest Gulf-based ethnic minority groups in the United Arab Emirates, have employed diverse coping mobility strategies via inter-regional transit, intra-regional transit, and irregular routes to diminish social inequality. These strategies act as tools to capitalize on their Gulf labor market experience and manipulate complex migration systems to achieve their long-term goals (i.e. acquiring Western citizenship). To examine temporary migrants’ coping mobility strategies, the article draws on twenty semi-structured interviews with Filipino migrants, and content analysis of government, policy, and local UAE and Filipino newspaper publications. The article adds to the theoretical and empirical discussions on social inequality, racial capitalism, mobility pathways, and Gulf exceptionalism by nuancing migrant victimization narratives in South-South migration and shifting the perspective of migrants as powerless recipients to active, transnational mobile agents.