Network Traffic Demand Research Articles

Identifying the critical nodes in multi-modal transportation network with a traffic demand-based computational method

In the last decade, there has been an abundance of research on identifying critical nodes in single-modal transportation network, but less for multi-modal transportation network (MTN). In addition, none of them consider the effect of interactions between nodes in a transportation corridor on node importance. For this purpose, a modified weighted k-shell (MWKS) model is proposed for identifying the critical nodes of the MTN, which combines the network topology and traffic demand. It is modified by the differential contribution of the multi-order neighbor nodes embodied by the passenger volume and the transportation corridor idea. Then the effectiveness of MWKS is verified with an example of a real transportation system using susceptible-infected (SI) model and cascading failure model. The analysis proves that MWKS is suitable for identifying critical nodes in the MTN. Furthermore, the proposed contribution attenuation coefficient based on the idea of the transportation corridor outperforms the topology-based and constant. It demonstrates the necessity of capturing the difference in the contribution of each neighbor node based on traffic demand when calculating the node importance. The results can provide a research basis for traffic planning to improve network reliability.

COCAM: a cooperative video edge caching and multicasting approach based on multi-agent deep reinforcement learning in multi-clouds environment

The evolution of the Internet of Things technology (IoT) has boosted the drastic increase in network traffic demand. Caching and multicasting in the multi-clouds scenario are effective approaches to alleviate the backhaul burden of networks and reduce service latency. However, existing works do not jointly exploit the advantages of these two approaches. In this paper, we propose COCAM, a cooperative video edge caching and multicasting approach based on multi-agent deep reinforcement learning to minimize the transmission number in the multi-clouds scenario with limited storage capacity in each edge cloud. Specifically, by integrating a cooperative transmission model with the caching model, we provide a concrete formulation of the joint problem. Then, we cast this decision-making problem as a multi-agent extension of the Markov decision process and propose a multi-agent actor-critic algorithm in which each agent learns a local caching strategy and further encompasses the observations of neighboring agents as constituents of the overall state. Finally, to validate the COCAM algorithm, we conduct extensive experiments on a real-world dataset. The results show that our proposed algorithm outperforms other baseline algorithms in terms of the number of video transmissions.Graphical

FlexDATE: Flexible and Disturbance-Aware Traffic Engineering With Reinforcement Learning in Software-Defined Networks

Traffic Engineering (TE) is an important network operation that routes/reroutes flows based on network topology and traffic demands to optimize network performance. Recently, new emerging applications pose challenges to TE with dynamic network conditions, where frequent routing updates are required to maintain good network performance with Software-Defined Networking (SDN). However, flow rerouting operations could lead to considerable Quality of Service (QoS) degradation and service disruption, which is often neglected by existing TE solutions. In this paper, we apply a new QoS metric named network disturbance to measure the negative impact of flow rerouting operations performed by TE. To achieve near-optimal load balancing performance and mitigate network disturbance together in dynamic network scenarios, we propose a flexible and disturbance-aware TE solution called that combines Reinforcement Learning (RL) and Linear Programming (LP). Specifically, leverages RL to intelligently identify flexible numbers of critical flows for each traffic matrix and reroutes these critical flows based on LP optimization to improve network performance with low disturbance. Empowered by a customized actor-critic architecture coupled with Graph Neural Networks (GNNs), can generalize well to unseen traffic scenarios and remain resilient to single link failures. Extensive simulations are conducted on five real-world network topologies to evaluate with real and synthetic traffic traces. The results show that can achieve the performance target (i.e., 90% of optimal performance) in 99% of network scenarios and effectively mitigate the average and maximum network disturbance by up to 9.1% and 38.6%, respectively, compared to state-of-the-art TE solutions.

Pre-copy live virtual machine migration techniques in cloud computing using HDWHM algorithm

Live Virtual Machine (VM) migration is a legacy of server virtualization in cloud computing. One of the difficulties in a Virtual Machine (VM) Environment is load balancing, and the pre-copy migration strategy is both time-consuming and expensive. In this paper, we propose an efficient VM migration strategy to compute the parameters for Linear Adam Algorithm overload detection and Interquartile Range (IQR) under-loaded identification, the Central Processing Unit (CPU) utilization is sufficient. VMs require constant network traffic, storage, CPU, and memory demands. This study recommends using the novel Hamming Distance-Based Weighted Harmonic Mean (HDWHM) strategy for pre-copy live VM migration. We tested the suggested strategy using datasets from CloudSim-3.0.3 on a real PlanetLab. Simulations show that the suggested approach decreases host downtimes, energy consumption, VM migrations, and SLA degradation.

Exploring the relationship among traffic, topology, and throughput: towards a traffic-optimal optical network topology design

The design of optical networks for maximum throughput under diverse traffic demands is a long-standing NP-hard problem. In this paper, by parameterizing the relationship between the network topology and traffic demand, a polynomial-time objective function, the demand weighted cost (DWC), is introduced and evaluated for different scale networks and diverse traffic scenarios. It is shown that the proposed DWC is highly correlated to network throughput, while speeding up the topology evaluation process by some five to six orders of magnitude. The DWC was then applied as the optimization target with three different topology optimization algorithms (DWC-selection, genetic algorithm, and our hierarchical topology design), achieving 90% and 460% throughput increases, on average, for small-scale (14-node) and large-scale (100-node) topology designs, respectively. The proposed methods have the potential of maximizing throughput in the design of future optical network topologies.

A novel traffic controlling model for enhancing routing in mobile Ad-Hoc network

The advancement in the communication and services demand for better QoS, but in parallel the increase in network traffic demands for an effective and significant traffic controlling model to manage high network traffic and also reduce congestion. In case of MANET circumstances it is further difficult to control and manage due to high mobilizing nodes and limited resource restrictions. Even MANET’s dynamic mobility creates high maintenance overhead for effective communication. In the past most of the designed routing protocols utilize reactive routing mechanism, which are primary source driven. In case of a link failure and data failure it has to update the source node and source node only have to decide next course of action. This will generates an additional overhead in the network and may reduce throughput of the protocols. This paper aims to propose a novel Traffic Controlling Model (TCM) to efficiently manage the routing overhead in MANET. The TCM will handle heavy traffic, which is the main cause of network congestion and overhead. It first determines the network traffic and evaluates the probable Node Link Life (NLL) to recommend the TCM process. The analysis of the results generated through the experiment evaluation shows that the data routing has improved and substantiates the effectiveness of the proposal in compared to the existing routing approaches.

Efficient deployment of aerial relays in FSO-based backhaul networks

Using network flying platforms (NFPs) as aerial relays has been emerging as a promising solution for mobile backhaul frameworks in fifth generation and beyond wireless networks. Moreover, free space optics (FSO) technology has become the alternative to radio frequency technology for backhaul links due to its advantages of a high data rate, long transmission range, and negligible interference. In an FSO-based NFP relay backhaul network, due to the fragility of FSO links, how to deploy NFPs to satisfy network traffic demands is a challenging problem. Moreover, the establishment of non-essential FSO links leads to the extra deployment of NFPs due to the limited number of transceivers carried by each NFP, which makes the NFP deployment problem more complex. To solve these issues, we jointly consider the deployment of NFPs and the formation of network topology, the targets of which are to minimize the number of deployed NFPs and network congestion. The problem is formulated as mixed-integer nonlinear programming, which is hard to solve directly, and we linearize it based on transmission range simplification. A heuristic algorithm is proposed to solve the problem for large-scale network scenarios. Simulation results show that the joint optimization scheme of NFP deployment and network topology formation surpasses the single optimization scheme, and the proposed heuristic algorithm can solve the joint optimization problem efficiently in differently scaled networks.

Multiagent Meta-Reinforcement Learning for Adaptive Multipath Routing Optimization.

In this article, we investigate the routing problem of packet networks through multiagent reinforcement learning (RL), which is a very challenging topic in distributed and autonomous networked systems. In specific, the routing problem is modeled as a networked multiagent partially observable Markov decision process (MDP). Since the MDP of a network node is not only affected by its neighboring nodes' policies but also the network traffic demand, it becomes a multitask learning problem. Inspired by recent success of RL and metalearning, we propose two novel model-free multiagent RL algorithms, named multiagent proximal policy optimization (MAPPO) and multiagent metaproximal policy optimization (meta-MAPPO), to optimize the network performances under fixed and time-varying traffic demand, respectively. A practicable distributed implementation framework is designed based on the separability of exploration and exploitation in training MAPPO. Compared with the existing routing optimization policies, our simulation results demonstrate the excellent performances of the proposed algorithms.

Enforcing Multilevel Security Policies in Unstable Networks

Multilevel security (MLS) systems control access to data by formalizing permissible and impermissible information flows between data sources and destinations (e.g., database servers and clients) fixed with distinct security labels. In computer networks, MLS systems have been used to prevent unauthorized data disclosure in shared-infrastructure settings where network hosts and devices may fall within different trust domains (e.g., in multi-tenant cloud networks or wireless mesh networks). However, current MLS systems assume static network behavior—thus preventing the network from being practically usable in the presence of dynamic network events that frequent unstable network environments, including sudden changes in traffic patterns, link failures, and topology changes as a result of device movement or intermittent device connectivity. In this paper, we introduce <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MLS-Enforcer</monospace> , a software-defined networking (SDN) controller application that can efficiently deploy network-level MLS policies while retaining the ability to securely relabel network nodes under changing topology state and network traffic demands. We model network adaptivity as an integer linear programming problem that reflects a given security policy. We then introduce heuristic relabeling algorithms that achieve near-optimal performance and are more tractable and efficient for larger networks. We validate <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MLS-Enforcer</monospace> on several network topologies and traffic loads, demonstrating that it can relabel the network to route 90%+ of flows under normal conditions and quickly converge (on the order of seconds for the heuristic algorithms) under changing needs—from small network structure changes to catastrophic failures. This shows that formally secured networks can feasibly be deployed in diverse, changing, and unpredictable environments.

Flow-by-flow traffic matrix prediction methods: Achieving accurate, adaptable, low cost results

Traffic matrix (TM) prediction methods aim to accurately and efficiently predict future network traffic demands by using previous traffic matrices. These methods are critical for network operation and management. The recent research focuses on designing complex models to extract spatiotemporal correlations from TMs and network topologies using traffic volume datasets that consist of all the origin–destination (OD) flows sampled from the network. These entire-matrix models are confined to a specific network topology and are difficult to apply to other networks. To solve such problems, we investigate a flow-by-flow prediction method in this paper which utilizes the intra-flow temporal correlations. State-of-the-art results have been achieved by our method on Abilene and GÉANT datasets. Using only 10% of the OD flows as the training samples, the flow-by-flow models can outperform the previously achieved state-of-the-art prediction performance. This small sample greatly reduces the end-to-end traffic monitoring costs. In addition, the flow-by-flow models can achieve outstanding cross-dataset evaluation performance. We suggest that leveraging a large external dataset with a flow-by-flow method can be a better choice when the measurement environment is difficult on the target network. The source code for our prediction method is publicly available at https://github.com/FreeeBird/Flow-By-Flow-Prediction.

Intelligent interference management and secure communications for satellite-terrestrial integrated systems

Satellite-terrestrial integrated (STI) systems represent the right solution to meet complex requirements of several services and sharing of the limited spectral resources between satellite systems and terrestrial ones must be considered to optimize performance. Network architectures and traffic demand are different for the satellite component and for the terrestrial 5G/6G one, so that the requirements of spectral resources for satellite and terrestrial systems are expected to vary dynamically in a significant range.

Adaptive Approaches for Tidal-Flow Lanes in Urban-Road Networks

Every year, traffic congestion costs the global economy billions of dollars in lost productivity, particularly in urban areas. Traffic congestion is a complex problem, as traffic conditions may change at any time. Tidal-flow lanes can be utilised as a feasible traffic-congestion-mitigation strategy to balance the fluctuating traffic demands throughout the day. This paper proposes an adaptive-lane-reversal approach for tidal-flow lanes, to decrease the impact of traffic congestion in urban areas. In order to evaluate the adaptive approach under various traffic conditions, several algorithms and parameter sets are examined, using various network models and traffic demands. As a result, the total travel time of the vehicles in the various networks was decreased by up to 81%.

Towards energy efficient Smart city services: A software defined resource management scheme for data centers

With the rapid advancements in the services computing paradigm, cloud computing has been a fundamental requirement for enabling practically all sophisticated applications and services, particularly for Smart cities. However curbincs energy dissipation in the data centers (DC) has been a key effort, albeit while fulfilling the quality of service (QoS) requirement of DCs are characterized by complex interconnections among their servers. Maintenance of these servers under dynamic scenarios while ensuring scalability and performance demands Software Defined Networks (SDNs) for easy and efficient resource management. This paper addresses the QoS requirement and energy-efficient operation for Software-Defined DCs for resource management by means of (i) selectively activating a subset of switches, (ii) propounding multi-path routing for all scheduled flows, (iii) aggregating data and routing structure to avoid network congestion and (iv) installation of appropriate forwarding rules across the network switches. These issues are collectively put together in the outline of ILP problem, but due to its computational complexity, a heuristic optimization approach called particle swarm intelligence is articulated. The particle swarm intelligence (PSI) algorithm is employed for feature selection to obtain the minimum cost of the generated energy while satisfying the network traffic demand. The presented simulation result lay the efficacy of the proposed algorithm.

Energy-Efficient Method Based on Dynamic Topology Switching and Reliability in SDNs

Energy consumption is becoming a key issue in the research of future network. In practice, network traffic has a periodic time distribution that occurs most often at a low level. This feature provides the possibility of achieving network energy savings through topology switching. By considering the deficiencies in existing studies, such as the low adaptability between network working topology and traffic load, the abnormal topology switching caused by abnormal and unbalanced traffic, and the low reliability of energy-saving topology, this paper proposes an energy-efficient routing method for software-defined networks based on topology switching and reliability. The method involves two parts: a topology-switching method and a failure recovery method. The former adapts the network working topology to the network traffic demands through dynamic topology switching to decrease the network energy consumption. The latter adopts an active strategy for fast fault recovery to ensure network reliability in the energy-efficient topology. Two network typologies and their traffic data are used to experimentally verify the method. The results show that, compared with the static topology switching method TLS, the energy saving of the proposed method can be improved at most 2.07 times and 4.63 times in two typical typologies, respectively, while ensuring network reliability.

Physical Layer Security of Two-Way Ambient Backscatter Communication Systems

Achieving high network traffic demand in limited spectrum resources is a technical challenge for the beyond 5G and 6G communication systems. To this end, ambient backscatter communication (AmBC) is proposed for Internet-of-Things (IoT), because the backscatter device (BD) can realize communication without occupying extra spectrum resources. Moreover, the spectral efficiency can be further improved by using two-way (TW) communication. However, secure communication is a great challenge for accessing massive IoT devices due to the broadcasting nature of wireless propagation environments. In light of this fact, this article proposed a two-way ambient backscatter communication (TW-AmBC) network with an eavesdropper. Specifically, the physical layer security (PLS) is studied through deriving the analytical/asymptotic expressions of the outage probability (OP) and intercept probability (IP). Moreover, the outage probabilities (OPs) in high signal-to-noise ratio (SNR) regions are studied for the asymptotic behavior and the intercept probabilities (IPs) in high main-to-eavesdropping ratio (MER) regions as well. Through analysis and evaluation of simulation performance, the results show that (i) when considering the target node, the OP of the BD decreases with increasing SNR, that is, enhancing the reliability; (ii) an optimal value of BD’s reflection coefficient that maximize the reliability of backscatter link can be obtained; (iii) in high SNR regions, the OPs approach a constant; thus, the diversity orders are zero; (iv) when increasing the MER, the IP of target node decreases, suggesting the security enhances; (v) a trade-off exists between reliability and security which can be optimized by carefully designing the parameters.

Performance Oriented DSP for Flexible Long Haul Coherent Transmission

In long haul optical fiber communication networks, whichcan span thousands of kilometers, bandwidth is at a premium due to the relatively low availability of optical fibers when compared with network traffic demands. Therefore, these networks require the highest performance in the physical layer, with transceivers that are capable of extracting all the available capacity from each optical fiber. Digital coherent transmitters and receivers, which enhance optical transmission systems by using digital signal processing, are essential for achieving this goal. This tutorial discusses the digital signal processing techniques that are used in the design of high performance coherent modems to compensate for adverse channel effects such as fiber impairments and optoelectronic device non-idealities.

Deep Reinforcement Learning-Based Routing on Software-Defined Networks

With an exponential increase in network traffic demands requiring quality of services, the need for routing optimization has become more prominent. Recently, the advent of software-defined networking (SDN) technology enables centralized management and operation, and the networking resources such as switches become flexibly configurable through programmable interfaces. In this paper, we propose a deep reinforcement learning (DRL)-based routing optimization on an SDN. In the proposed method, the DRL agent learns the interdependency between the traffic load of network switches and the network performance, and decides an optimal set of link weights to make a balance between the end-to-end delay and packet losses of the network. The SDN controller determines the routing paths using the set of link weights and installs the flow-rules on the SDN-enabled switches. To overcome an extensively long learning process of DRL in a case of topology change, we develop an M/M/1/K queue-based network model and perform the learning process of DRL using the network model in an offline manner until it is converged. The simulation results demonstrate the proposed routing method outperforms a conventional hop-count routing and a traffic demand-based RL algorithm in several network topologies.

Shazam for bats: Internet of Things for continuous real‐time biodiversity monitoring

Biodiversity surveys are often required for development projects in cities that could affect protected species such as bats. Bats are important biodiversity indicators of the wider health of the environment and activity surveys of bat species are used to report on the performance of mitigation actions. Typically, sensors are used in the field to listen to the ultrasonic echolocation calls of bats or the audio data is recorded for post-processing to calculate the activity levels. Current methods rely on significant human input and therefore present an opportunity for continuous monitoring and in situ machine learning detection of bat calls in the field. Here, we show the results from a longitudinal study of 15 novel Internet connected bat sensors—Echo Boxes—in a large urban park. The study provided empirical evidence of how edge processing can reduce network traffic and storage demands by several orders of magnitude, making it possible to run continuous monitoring activities for many months including periods which traditionally would not be monitored. Our results demonstrate how the combination of artificial intelligence techniques and low-cost sensor networks can be used to create novel insights for ecologists and conservation decision-makers.

Urban Road Network Emergency: An Integrative Vulnerability Identification Method

The vulnerability of an urban road network is affected by many factors, such as internal road network layout, network structure strength, and external destructive events, which have great uncertainty and complexity. Thus, there is still no unified and definite vulnerability analysis scheme available to cities. This paper proposes an integrative vulnerability identification method for urban road networks, which mainly relates to the vulnerability connotation and characteristics analysis of urban road networks during emergency, and vulnerability comprehensive evaluation indices design based on urban road network connectivity, traffic efficiency and performance, and an empirical study on a vulnerability identification method of an urban road network. In the empirical case, a real road network and traffic operation data were used from Science and Technology Park of Shenzhen City, China. In the context of one certain emergency scenario, the stated preference survey method and maximum likelihood method are used to solve the road users’ random travel choice behavior parameters; subsequently, based on the traffic equilibrium distribution prediction, the traffic vulnerability identification methods of the road network in this region were verified before and after the emergency. The method presented here not only considers the impact of network topology changes on road network traffic function during emergency but also considers the impact of dynamic changes in road network traffic demand on vulnerability; therefore, it is closer to the actual distribution of urban road network traffic vulnerability.

Telecommunications network design: Technology impacts and future directions

AbstractDuring the past 50 years telecommunication network technology has raced ahead powered by exponential advances in computer chip and fiber optic technology. The introduction of packet‐switched networks and the Internet has increased network traffic demands exponentially and has nurtured a variety of new telecommunication services (e.g., email, web‐surfing, social media, streaming services, e‐commerce, the Internet of Things, etc.) over the past 30 years. This rapidly changing environment (along with certain technical considerations) has made it very difficult to give accurate forecasts of traffic demands for both the short‐term (intraday) and for the longer term (year‐to‐year). Telecommunications network design has evolved from the voice‐only networks of the 1970s where operations research (OR) methodology was indispensable to current multiservice packet‐switched data networks whose uncertainty and rapid evolution has reduced the utility of classical optimization models that rely on accurate traffic demand forecasts. After summarizing the major developments in telecommunications network design technologies/services, we describe some promising future research directions to address an environment where technology is ever‐changing and traffic forecasting is difficult. In particular, we focus on the public Internet and emphasize possible work where OR/optimization methodology may be useful in understanding and solving telecommunications network routing and design problems.