Toward Traffic Engineering in Anonymous Communication Networks: A Meta-Routing Learning Approach

A traffic classification-based traffic engineering framework in software-defined networking

A traffic classification-based traffic engineering framework in software-defined networking

Integrating topology and traffic engineering to maximize throughput in reconfigurable networks

A study of Al-Rayhanna Bridge (Iraq, Anbar Province) concerned with examining elastomeric bearing pad dynamic behaviour against changes in traffic speed and girder deflection. The areas of maximum deflection were being located at midspans of the girders, especially under truck or underneath truck lanes. One of the key contributions of the work was the application of the deflection measurements of the Linear Variable Differential Transformer (LVDT) for the estimation of car speeds, and a very welcoming mean value of 40.95 km/h (the visual timing correlations being >95 per cent), showed that structural measurement can be employed in reliable traffic analysis. The new bridge was defined by reduced damping ratio (3-4 % compared to 5-6 % of the old bridge) accounting for varying abilities to absorb and release energy. Thus, the new bridge appeared to require less balance restoration energy (1.5-2 seconds / 0.5-0.67 Hz) than the old bridge exhibiting faster stabilization (1-1.5 seconds / 0.67-1 Hz). The rate of amplitude decay also varied quite radically: 20-25 per cent per cycle for the new bridge compared to 30-35 per cent for the old bridge. Structural design and climatic dependent factors , indicates the significant role played by adopting dynamic factors - such as damping, energy dissipation and deflection patterns in bridge structure design and maintenance to guarantee long-lasting structural integrity and safety. These observations give conclusive feedback on upcoming resilient bridge construction, also the field of material science and traffic engineering

Space Division Multiplexing Elastic Optical Networks (SDM-EONs) are increasingly exposed to unpredictable link-layer and core network outages, which can significantly impair service quality and increase traffic blocking probabilities. Currently, survivability schemes rely on reactive approaches that restore network integrity only after link or core network disruptions occur. To address this issue, this paper proposes an AI-based real-time risk prediction system designed to proactively anticipate network impairments before they happen. The system estimates the risk of impairment and the time-to-failure for each network entity by comprehensively analyzing various temporal-spatial characteristics, such as crosstalk dynamics, fragmentation trends, occupancy variability, and data center loads. A novel graph-based learning framework with compressed temporal feature processing is developed for real-time risk prediction, applicable to SDN-managed optical transport systems. Upon identifying a critical risk situation, the proposed system proactively provides optimized path preparation, managed traffic engineering, or localized network defragmentation, effectively minimizing network recovery times. Simulation analysis clearly indicates that risk prediction for survivability improves network robustness, representing a major advancement in dynamic self-healing for SDM-EONs.

Software-Defined Networks (SDN) provide centralized control for programmable routing, yet traditional algorithms like OSPF and ECMP struggle with dynamic traffic patterns, congestion hotspots, and QoS demands in large-scale deployments. This paper conducts a systematic review of machine learning (ML) techniques— including supervised classifiers, reinforcement learning (RL) agents, and graph neural networks (GNNs)— applied to SDN routing and performance optimization, highlighting their roles in traffic classification (up to 99.81% accuracy), predictive KPI forecasting, and adaptive path selection. We propose the Hybrid Causal-RL-GNN (HCRG) framework, which fuses Graph Attention Networks (GAT) for topology-aware state encoding with a causality-enhanced Soft Actor-Critic (SAC) agent to quantify action impacts and maximize a composite reward function balancing latency, packet loss, and throughput. Trained offline on Mininet-emulated NSFNET and Fat-Tree topologies with Ryu controllers, HCRG deploys via OpenFlow for real-time flow rule installation, incorporating hyperparameters like learning rate 0.001 and discount factor 0.99 over 20,000 episodes. Extensive evaluations under normal, congested, and failure scenarios demonstrate HCRG's superiority: 28% latency reduction (22 ms vs. 45 ms baselines), 22% throughput increase (2.2 Gbps), and 35% loss mitigation (1.6%), outperforming ROAR, RouteNet, and ECMP by 15-35% while maintaining <5 ms inference latency at scale. This work advances autonomous SDN traffic engineering, with implications for 5G/6G and edge computing, paving the way for federated extensions in multi-domain environments.

Purpose This article introduces an innovative approach to applying a Type 2 fuzzy logic system for Median U-Turn (MUT) traffic control, particularly for implementation by field controllers like Advanced System Controller 3 (ASC/3). A MUT is an alternative intersection which implies a shift of left-turn conflicts by at least 250 feet from the main intersection to the new downstream U-turn intersections. The study addresses the need for adaptable traffic control methods that can effectively manage the unique characteristics of MUT intersections, especially during periods of fluctuating traffic demand. Design/methodology/approach Simulation techniques are utilized (in Vissim–microsimulation software) to evaluate the performance of the proposed, Type 2 fuzzy logic-based control strategy under various traffic demand scenarios. In this article, the oversaturated traffic conditions at MUT were not addressed. Findings While fixed-time control is generally suitable for controlling traffic demand at alternative intersections, it lacks flexibility to address significant fluctuations. This article presents new, semi-actuated Type 2 fuzzy logic system for MUT intersections. Simulation results demonstrate that this control strategy surpasses conventional traffic control methods. Considering conducted tests, Type 2 fuzzy logic outperforms fixed-time control by 11.84% and actuated-time control by 48.58%. Research limitations/implications This study contributes to the field of traffic engineering by introducing a novel approach to traffic control at MUT intersections using Type 2 fuzzy logic. By demonstrating the effectiveness of this approach through simulation experiments, we provide valuable insights into the potential of fuzzy logic systems for optimizing traffic management in urban environments. Practical implications This study contributes to the field of traffic engineering with a novel, Type 2 fuzzy logic-based approach to traffic control at MUT intersections. By demonstrating the effectiveness of this approach through simulation experiments, we provide valuable insights into the potential of Type 2 fuzzy logic systems for optimizing traffic management in urban environments. Social implications Five experimental scenarios were created to examine the effectiveness of the suggested fuzzy control logic, focusing on control delay, number of stops per vehicle, fuel consumption and CO2 and NOx emissions. Obtained results showed that proposed fuzzy control logic can decrease CO2 and NOx emissions. Originality/value We confirm that this work is original and has not been published elsewhere, nor is it currently under consideration for publication in any other journal or conference proceedings.

Modern data centers serve as the backbone of cloud computing infrastructure, supporting millions of concurrent users and mission-critical applications that demand exceptional reliability and performance. The network fabric within these facilities represents a complex interconnection of switches, routers, and links that must maintain seamless connectivity even during catastrophic failure events. Network fabric simulation (NFS) has emerged as an essential methodology for evaluating routing convergence behavior under various failure scenarios before deployment in production environments. Software-defined networking (SDN) technologies have revolutionized how data center operators manage and orchestrate network resources, enabling programmable control planes that can rapidly respond to topology changes. This review examines the current state of simulation frameworks, validation methodologies, and convergence analysis techniques employed in modern data center networks. We analyze how discrete event simulation (DES) and hybrid simulation approaches enable realistic modeling of large-scale failures affecting multiple network components simultaneously. The review covers critical aspects including fabric topology designs, routing protocol implementations, failure detection mechanisms, and performance metrics used to assess convergence speed and stability. We synthesize findings from recent research on Byzantine fault tolerance (BFT) mechanisms, multipath routing strategies, and traffic engineering solutions that enhance network resilience. Particular emphasis is placed on validation techniques that ensure simulation results accurately reflect real-world network behavior under stress conditions. The analysis reveals that while significant progress has been made in simulation accuracy and scalability, challenges remain in modeling complex interactions between control plane and data plane during cascading failures

Operations Research (OR) provides powerful mathematical and algorithmic tools to optimize resource allocation, routing, and scheduling. In the context of modern computer networks especially with the rise of Software-Defined Networking (SDN), 5G/6G and cloud infrastructures—OR methods can significantly enhance performance, reliability, and energy efficiency. This article explores how classic OR techniques (e.g., linear/integer programming, queuing theory, flow optimization) and modern hybrid approaches integrate into network problems, with examples from traffic engineering, resource allocation, and energy-aware routing. We also identify challenges and propose future directions for applying OR in next-generation networks. Keywords: Operations Research, Computer Networks, Network Optimization, Traffic Engineering

Modern networks must manage dynamic traffic driven by 5G, IoT, and cloud services. Traditional traffic en- gineering (TE) technologies such as static routing cannot react in real time, leading to congestion and degraded performance. Predictive and adaptive capabilities come through artificial in- telligence (AI) to overcome these shortcomings. This article compares three classic TE technologies: Segment Routing over IPv6 (SRv6), SoftwareDefined Wide Area Network- ing (SD-WAN), and Multiprotocol Label Switching (MPLS). Each has unique trade-offs: MPLS provides deterministic QoS at a high cost and limited flexibility; SD-WAN provides cost-effective flexibility but does not provide guaranteed QoS; SRv6 makes source routing programmable at the cost of header overhead and scalability demands. To address these drawbacks, we present a TE framework based on AI that leverages predictive analytics for predicting flows and RL to provide adaptive path selection choices. The model was evaluated with simulated enterprise-scale topologies supporting composite traffic mixtures of voice, video, and data. Outcomes demonstrate that AI-driven TE significantly reduces latency and packet loss while improving throughput and cost savings over static TE controls. Predictive rerouting, in particular, achieved double-digit latency savings, while RL dynamically distributed load between MPLS, SD-WAN, and SRv6 paths. These findings confirm that AI-based TE enhances perfor- mance, scalability, and flexibility and is a suitable solution for future heterogeneous and high-traffic networks.

BGP communities are widely used by operators to encode routing metadata for traffic engineering, policy enforcement, and operational debugging. However, ≈90% of observed communities lack public documentation, limiting their utility for research and operational analysis. Among these, city-level communities offer valuable geographic insight into routing behavior, yet remain largely untapped. In this paper, we develop a scalable method to infer the geographic meaning of undocumented city communities using BGP data. We validate our approach against a ground truth dataset covering 1,482 city communities and through operator feedback. Applied to data from May 2025, our algorithm infers the locations of 80% of city communities with a precision of 70 km or better. We publish all code and datasets to support reproducibility and further research.

This study was focused on the development and testing of luminescent composite based on alkali-activated granulated blast furnace slag. The composite was intended for use as a secondary luminescent layer of visual safety elements in transport infrastructure applications. The evaluation included compressive and flexural strengths, adhesion to different substrates (concrete and asphalt), slip resistance, bulk density, and fresh mortar consistency. The results show that the compressive and flexural strengths, as well as slip resistance, are sufficient for intended application. Experiments also revealed unexpectedly long initial and final setting times and relatively low adhesion values, which may pose challenges for the proposed use. Further research in terms of durability is needed. For use in traffic engineering, future testing should include frost resistance and resistance to de-icing agents.

The rapid proliferation of heterogeneous applications, from latency-critical video delivery to bandwidth-intensive file transfers, poses increasing challenges for modern communication networks. Traditional traffic engineering approaches often fall short in meeting diverse Quality of Experience (QoE) requirements under such conditions. To overcome these limitations, this study proposes a QoE-driven distribution framework for mixed traffic in Software-Defined Networking (SDN) environments. The framework integrates flow categorization, adaptive path selection, and feedback-based optimization to dynamically allocate resources in alignment with application-level QoE metrics. By prioritizing delay-sensitive flows while ensuring efficient handling of high-volume traffic, the approach achieves balanced performance across heterogeneous service demands. In our 15-RSU Mininet tests under service number = 1 and offered demand = 10 ms, JOGAF attains max end-to-end delays of 415.74 ms, close to the 399.64 ms achieved by DOGA, while reducing the number of active hosts from 5 to 3 compared with DOGA. By contrast, HNOGA exhibits delayed growth of up to 7716.16 ms with 2 working hosts, indicating poorer suitability for latency-sensitive flows. These results indicate that JOGAF achieves near-DOGA latency with substantially lower host activation, offering a practical energy-aware alternative for mixed traffic SDN deployments. Beyond generic communication scenarios, the framework also shows strong potential in Intelligent Transportation Systems (ITS), where SDN-enabled vehicular networks require adaptive, user-centric service quality management. This work highlights the necessity of coupling classical traffic engineering concepts with SDN programmability to address the multifaceted challenges of next-generation networking. Moreover, it establishes a foundation for scalable, adaptive data distribution strategies capable of enhancing user experience while maintaining robustness across dynamic traffic environments.

Research Objective: This study analyzes the budget quotas and sample cases of traffic engineering and landscaping projects to address the following issues: low accuracy and inability to reflect the cost levels of enterprises in the existing cost estimation techniques. It constructs a historical database and utilizes Python and BIM to develop a BP neural network intelligent estimation system, aiming to provide data and decision support for intelligent and visual cost estimation in traffic landscaping projects. Research conclusions: This study focuses on the construction drawing budget estimation for transportation engineering and landscape ecological engineering projects. Data were collected through questionnaires administered to scholars and practitioners, with key factors influencing pricing units identified using SPSS factor analysis. Subsequently, extensive historical data on road transportation and greening engineering were gathered and standardized through temporal and regional adjustments. Quantitative feature analysis was then conducted to establish a historical database of construction drawing budgets for completed transportation landscape ecological projects, based on construction enterprises. The cosine similarity method was employed to retrieve highly similar sample cases from the database for target projects. A BP neural network-based intelligent estimation system was developed using Python and BIM technology, providing reliable data support and technical assurance for cost estimation, decision-making, and ongoing maintenance endeavors pertaining to transportation landscape and ecological engineering projects.

Understanding vehicle acceleration behavior during intersection departures is critical for advancing traffic safety, sustainable mobility, and intelligent transport systems. This study presents a high-resolution kinematic analysis of 714 vehicle departures from signalized intersections, encompassing straight crossings, left turns, and right turns, and involving a diverse sample of internal combustion engine (ICE), hybrid electric (HEV), and battery electric vehicles (BEV). Using synchronized Micro Electro-Mechanical Systems (MEMS) accelerometers and Real-Time Kinematic (RTK)-GPS systems, the study captures longitudinal acceleration and velocity profiles over fixed distances. Results indicate that BEVs exhibit significantly higher acceleration and final speeds than ICE and HEV vehicles, particularly during straight crossings and longer left-turn maneuvers. Several mathematical models—including polynomial, arctangent, and Akçelik functions—were calibrated to describe acceleration and velocity dynamics. Findings contribute by modeling jerk and delay propagation, supporting better calibration of AV acceleration profiles and the optimization of intersection control strategies. Moreover, the study provides validated acceleration benchmarks that enhance the accuracy of forensic engineering and road accident reconstruction, particularly in scenarios involving intersection dynamics, and demonstrates that BEVs accelerate more rapidly than ICE and HEV vehicles, especially in straight crossings, with direct implications for traffic simulation, ADAS calibration, and urban crash analysis.

This article examines the strategic role of overt policing by the Paraná Military Police (PMPR) in preventing and mitigating traffic accidents on state highways, highlighting its importance as a public safety and life-saving tool. Based on an analysis of official statistical data, operational regulatory guidelines, and practical experience reports from police officers, the study investigates how the active and visible presence of the Paraná Military Police (PMPR) directly influences driver behavior, reduces violations and accidents, and enhances the sense of safety among road users. The study also discusses the main obstacles faced in carrying out these activities, such as staff shortages, logistical limitations, excessive workloads, road infrastructure failures, and the need for ongoing training for specialized personnel. Finally, proposals are presented for improving police performance, including the adoption of onboard technologies such as mobile radars, drones, and predictive analytics systems; expanding partnerships with traffic and road engineering agencies; and strengthening education and awareness programs for the public. The article argues that strengthening overt policing is essential for creating safer, more efficient, and more humane traffic on Paraná's highways.

The article introduces the Guarantee-Based Bandwidth Traffic Engineering Queue (GB(Bw)-TEQ) and Guarantee-Based Utilization Traffic Engineering Queue (GB(U)-TEQ) models for queue management on router interfaces. These models implement the principles of Traffic Engineering Queues and support both DiffServ and IntServ. Their novelty lies in the ability to provide guarantees either for the bandwidth allocated to a class queue or for its utilization coefficient. Such guarantees stabilize and control the average queue length, positively affecting key Quality of Service (QoS) indicators, particularly average delay and packet loss probability. The unreserved portion of the interface bandwidth is allocated among queues in proportion to their classes. Therefore, the higher-priority queues have lower utilization, while lower-priority queues operate with higher utilization, which is consistent with DiffServ principles. The models are formulated as a mixed-integer linear programming problem with an optimality criterion and a system of constraints. Computational experiments confirmed the operability and efficiency of GB(Bw)-TEQ and GB(U)-TEQ compared to the known analogue CB-TEQ model, which does not provide service-level guarantees. The results demonstrate that the proposed models achieve the stated guarantees and enable differentiated service without blocking the lowest-class queues. These solutions can be applied to automate queue management in IP/MPLS switches and routers as well as in software-defined networks.

This work focuses a wide range of modules centered ‎on latency-aware optimization strategies in order to ‎meet the increasing need for low-latency ‎communication in contemporary networks. The ‎system incorporates sophisticated congestion ‎control algorithms including LEDBAT, TCP Vegas, ‎and BBR, which regulate transmission rates more ‎efficiently than conventional loss-based techniques ‎by using delay-based metrics like round-trip time ‎‎(RTT) and queuing delay. To guarantee effective ‎path selection under latency limitations, traffic ‎engineers use multipath routing strategies as ECMP ‎and MPTCP, modified Dijkstra's algorithm with ‎latency weights, and constraint-based shortest path ‎first (CSPF). Utilizing the programmability of ‎Software-Defined Networking (SDN), the system ‎integrates metaheuristic methods including genetic ‎algorithms, ant colony optimization, and particle ‎swarm optimization along with intelligent routing ‎strategies utilizing reinforcement learning. By using ‎real-time latency feedback, these techniques allow ‎for dynamic and adaptive routing decisions. ‎OpenFlow and P4 flow rerouting features improve ‎the system's responsiveness to network conditions ‎even more. Mechanisms for monitoring and ‎feedback are essential for facilitating accurate ‎decision-making. The SDN controller's RTT ‎measurement modules continuously measure ‎connection latency, and exponential weighted ‎moving average (EWMA) methods smooth the ‎data gathered to prevent overreactions to brief ‎variations. These components work together to ‎create a strong framework for next-generation ‎network environments that optimize latency‎.

The article presents a new method for multi-agent traffic flow balancing. It is based on the MAROH multi-agent optimization method. However, unlike MAROH, the agent’s control plane is built on the principles of human decision-making and consists of two layers. The first layer ensures autonomous decision-making by the agent based on accumulated experience—representatives of states the agent has encountered and knows which actions to take in them. The second layer enables the agent to make decisions for unfamiliar states. A state is considered familiar to the agent if it is close, in terms of a specific metric, to a state the agent has already encountered. The article explores variants of state proximity metrics and various ways to organize the agent’s memory. It has been experimentally shown that an agent with the proposed two-layer control plane SAMAROH-2L outperforms the efficiency of an agent with a single-layer control plane, e.g., makes decisions faster, and inter-agent communication reduction varies from 1% to 80% depending on the selected similarity threshold comparing the method with simultaneous actions SAMAROH and from 80% to 96% comparing to MAROH.