Network Traffic Management Research Articles

Selection of Potential Regions for the Creation of Intelligent Transportation Systems Based on the Machine Learning Algorithm Random Forest

The planning and management of traffic flow networks with multiple input data sources for decision-making generate the need for a mathematical approach. The program of measures for the development of the transport infrastructure of the Russian Federation provides for the selection of pilot regions for the creation of intelligent transportation systems. With extensive knowledge of theoretical and applied mathematics, it is important to select and adapt mathematical methods for solving problems. In this regard, the aim of the study is to develop and validate an algorithm for solving the problem of classifying objects according to the potential of creating intelligent transportation systems. The main mathematical apparatus for classification is the «random forest» machine learning algorithm method. A bagging machine learning meta-algorithm for high accuracy of the algorithm was used. This paper proposes the author’s method of sequential classification analysis for identifying objects with the potential to create intelligent transportation systems. The choice of using this method is justified by its best behavior under the large number of predictor variables required for an objective aggregate assessment of digital development and quality of territories. The proposed algorithm on the example of Russian regions was tested. A technique and algorithm for statistical data processing based on descriptive analytics tools have been developed. The quality of the classification analysis algorithm was assessed by the random forest method based on misclassification coefficients. The admissibility of retrained algorithms and formation of a «fine-grained» «random forest» model for solving classification problems under the condition of no prediction was proven to be successful. The most productive models with the highest probability of correct classification were «reached» and «finalized» on the basis of logistic regression analysis of relationships between predictors and categorical dependent variables. The regions of class 1 with «high potential for the creation of intelligent transportation systems» are most likely to be ready for the reorganization of infrastructure facilities; the introduction of digital technologies in the management of traffic flows was found.

A spatiotemporal graph wavelet neural network for traffic flow prediction

The traffic flow prediction is fast becoming a key instrument in the transportation system, which has achieved impressive performance for traffic management. The graph neural network plays a critical role in the development of the traffic network management. However, it is worthwhile mentioning that the complexity of road networks and traffic conditions makes it unable to obtain sufficient spatiotemporal information. In view of capturing precise environment characteristics, the context could have a precise effect on the prediction results while previous methods rarely took this into account. Besides, the nonlinear characteristics of the graph neural network are hard to quantify with fine granularity and to eliminate overfitting. To stack these challenges, in this paper, we present a spatiotemporal graph wavelet neural network to improve the ability of representations. Specifically, we introduce the wavelet transforms into the deep learning model according to the strong nonlinear optimization ability. Furthermore, we dig the location and time patterns to evaluate the temporal dependence and the spatial proximity correlation. In addition, we introduce a historical context attention mechanism giving fine-grained historical context grade evaluation to ease the phenomenon of over-smoothing. The experimental results on real-world datasets show that our work gets considerable results compared with the baseline and start-of-the-art models. Moreover, our work has better learning performance by employing the connection and interaction of graphs.

Probabilistic and distributed traffic control in LPWANs

Low-power, low data transmission rates, and long-range wireless networks, also known as LPWANs, are intended to work best with equipment that uses few resources and can be used for many years thanks to their long battery life operation. This type of networks can handle traffic from nearly 1,000 nodes while maintaining a duty cycle of less than 1%. However, as the nodes become denser, the number of collisions increases and network traffic management becomes mandatory. To address this concern, we propose a Distributed and Probabilistic Traffic Control algorithm (DiPTC) that allows nodes to change their traffic in response to the application requirements (e.g., acquiring K measurements over a period of time) while being agnostic to the number of nodes or the network topology. When this requirement is not achieved, the gateway sends a feedback message to all the nodes so that they may adapt their traffic. We compare the proposed solution to LoRaWAN and to a Centralized Optimal Traffic Control solution (COTraC), in simulation. Compared to LoRaWAN, our algorithm proved successful in achieving the objective while minimizing collisions and extending the network lifetime threefold.

Application-Aware Network Traffic Management in MEC-Integrated Industrial Environments

The industrial Internet of things (IIoT) has radically modified industrial environments, not only enabling novel industrial applications but also significantly increasing the amount of generated network traffic. Nowadays, a major concern is to support network-intensive industrial applications while ensuring the prompt and reliable delivery of mission-critical traffic flows concurrently traversing the industrial network. To this end, we propose application-aware network traffic management. The goal is to satisfy the requirements of industrial applications through a form of traffic management, the decision making of which is also based on what is carried within packet payloads (application data) in an efficient and flexible way. Our proposed solution targets multi-access edge computing (MEC)-integrated industrial environments, where on-premises and off-premises edge computing resources are used in a coordinated way, as it is expected to be in future Internet scenarios. The technical pillars of our solution are edge-powered in-network processing (eINP) and software-defined networking (SDN). The concept of eINP differs from INP because the latter is directly performed on network devices (NDs), whereas the former is performed on edge nodes connected via high-speed links to NDs. The rationale of eINP is to provide the network with additional capabilities for packet payload inspection and processing through edge computing, either on-premises or in the MEC-enabled cellular network. The reported in-the-field experimental results show the proposal feasibility and its primary tradeoffs in terms of performance and confidentiality.

An IoT Environment Based Framework for Intelligent Intrusion Detection

Software-defined networking (SDN) represents a paradigm shift in network traffic management. It distinguishes between the data and control planes. APIs are then used to communicate between these planes. The controller is central to the management of an SDN network and is subject to security concerns. This research shows how a deep learning algorithm can detect intrusions in SDN-based IoT networks. Overfitting, low accuracy, and efficient feature selection is all discussed. We propose a hybrid machine learning-based approach based on Random Forest and Long Short-Term Memory (LSTM). In this study, a new dataset based specifically on Software Defined Networks is used in SDN. To obtain the best and most relevant features, a feature selection technique is used. Several experiments have revealed that the proposed solution is a superior method for detecting flow-based anomalies. The performance of our proposed model is also measured in terms of accuracy, recall, and precision. F1 rating and detection time Furthermore, a lightweight model for training is proposed, which selects fewer features while maintaining the model’s performance. Experiments show that the adopted methodology outperforms existing models.

Deployment of Inductive Loop Vehicle Traffic Counters Along Trunk Roads in Tanzania

As Tanzania's population grows, there is a greater demand for efficient, effective, and strong road design, as well as a smooth transportation system with a balanced traffic management network architecture. To plan for maintenance and expansion of such a vast network, a credible data inventory and network condition must be established. The deployment of vehicle inductor loop counters along Tanzanian trunk roads is presented in this paper. At test sites, inductor loop sensors and control cards were used to capture vehicle traffic data, which was then wirelessly sent using GSM technology for vehicle classification verification and storage for future road traffic management. The traffic count statistics from selected test sites acquired by the base station monitoring software were examined in real-time and the findings over a one-year period were provided. According to the study's findings, inductive loop vehicle counter technology can count and categorize vehicles along a section of roadway and provide reliable performance indicators for monitoring progress at the local, state, and national levels. The vehicle traffic data collected by this system will be used to project future situations within a transportation system and to keep a record of historical trends that will be used to project into the future what is likely to happen based on actual observations of the past and using other socio-economic data obtained from census information or economic indicators.

The role of intelligent transportation systems in solving traffic problems and reducing environmental negative impact of urban transport

Information technology has produced many modern systems in the field of intelligent transportation systems that aim to integrate existing and new systems for the management of transportation and traffic networks to respond to changing (dynamic) traffic conditions. These systems have been applied in many Western countries for several purposes, the most important of which is traffic safety and the reduction of losses resulting from poor planning of these networks. Many transport systems in developing countries continue to suffer from many problems, such as high accident rates, traffic congestion, and pollution from car exhaust. This paper aims to use multi-criteria decision-making methods to help select the best technology to overcome the traffic problems in Libya. A hybrid model of Analytic Hierarchical Process (AHP) and the Measurement Alternatives and Ranking according to COmpromise Solution (MARCOS) method was used. The AHP method was used to determine the weights of six technologies for intelligent systems, with the results showing that the most appropriate technology was surveillance cameras, with a weight of 28%. The resulting weights were used to rank the impact of these technologies on safety, environment and efficiency. This study can help decision makers on selection of the best systems that can be used to overcome the current problems faced by the transportation system.

Smart Traffic Scheduling for Crowded Cities Road Networks

With the fast-expanding number of vehicles in smart cities, the management of road intersections and traffic congestion has grown to be major problems. Drivers often express their opinion that putting traffic lights on while taking traffic flows into account will have a significant impact on how traffic moves. This paper presents a smart Road traffic Control management system termed Urban Traffic Control (UTC) keeping real-time dynamic traffic flow in mind which helps in upgrading the level of road traffic network management. To provide an organized traffic arrangement, UTC presents methodologies such as vehicle counting, controlling process, and evaluation of lanes keeping status in mind, this whole procedure is implemented by taking the complete traffic network into an account instead of just considering intersections. The primary goal of our system is to lessen traffic jams by cutting down on the trip and waiting times vehicles spend at crossings and intersections. We need to assign a plan for traffic flow that has the least amount of traffic congestion and vehicle waiting time, for this purpose some indicators and models are introduced in this study. Lane weight, traffic jam indicator, and vehicle priority are among these models. As this work is an improvement on the current Road Network without much changing, we integrate our system on normal traffic lights which allow each lane a chance to move and we also considered the no-interference lane movement. To simulate our idea, we introduced a smart road traffic control system consisting of multi-agents, by using a NetLogo stimulator. To compare the fixed cycle traffic light, several vehicles (150 in total) with random behaviour were generated and scattered over 25 different intersections for the time duration of 9 h. This setting was used to test our smart traffic control solution on both lane flow and no interference movement flow. According to the obtained results, there was a 25.98% reduction in total average waiting time over simulation period for all vehicles and a reduction of 34.16% for no interference movement flow. These observations clearly state that suggested method is better suited for today's complex traffic conditions where change in infrastructure is minimal.

Optimization of Network paths in congested SDN using Genetic Algorithm

Computer network and Communication over such networks become integral part of human life from the very beginning of twenty first century. From the very first radio communication in the beginning of 19th Century to the latest wireless and Software Defined Network (SDN) communication over the satellite and local allied computer networks, caused increase in more and more traffic over the computer network. Internet was not only provided over the copper, fiber optics cables, but rather it becomes a commercial service sector over the low earth orbit satellites across the globe. Majority of the contents flowing over such networks are either academic, research, corporate data bases like banking, finance, IT services, social media, and also specially of the entertainment industry. Every small to large organization in corporate and research and development organization faced problems of computer network congestion over the time. As the demand for more data access is required hence the congestion over the network started to increase. Every nation and individual organization have their own policy to control domestic network traffic as bandwidth is limited and commercial aspects are involved. Various algorithms have focused to regulate network, but very few algorithms exist which focuses on providing alternative paths for better network traffic management. This paper focuses on using modern Genetic Algorithms like Ants colony optimization to first identify congestions over the network and then using such insights to find alternative paths through mutation and cross over. The proposed solution was executed, and generated result comparatively proved that use of Genetic Algorithm has helped to find alternative paths more effectively over the SDN.

Intelligent Parameter Tuning using Deep Q-network in Adaptive Queue Management Systems

Network traffic has risen in recent years to the point that it is obviously and astonishingly in 2020, with the increase predicted to double in the following days. Up to 23 Teraa bit every month is an incredible amount. The Active Queue Management (AQM) algorithm is one of the most significant study areas in network congestion control; nevertheless, new self-learning network management algorithms are needed on nodes to cope with the huge quantity of traffic and minimize queuing latency, used reinforcement learning for automatic adaptive parameter with the AQM algorithm for effective network management, and present a novel AQM algorithm that focuses on deep reinforcement learning to deal with latency and the trade-off between queuing delay and throughput; choose Deep Q-Network (DQN) as the foundation for our scheme and equate it with Random Early Detection (RED) Results based on Network simulation (NS3) simulation suggest that the DQN algorithm has good and better results were obtained from RED, where the difference reached a drop rate of 2%, and this percentage is considered good, in addition to the percentage of throughput and the packet transfer rate of 3% is better in the proposed algorithm. Index Terms— Adaptive Queue Management, Network congestion, Network Traffic Management, Deep Q-Network, Reinforcement Learning.

Unified network tRaffic management frAmework for fully conNected and electric vehicles energy cOnsumption optimization (URANO)

Cooperative control in the presence of connected and automated vehicles has attracted substantial attention due to its pronounced benefits on the network compared with human-driven vehicles. They make possible a significant reduction of travel time/waiting time, energy consumption and emissions. In this context of new emerging technologies, traffic lights are still recognized as one of the most effective strategies in terms of energy and environmental benefits, which can be further improved by considering the integration with greener powertrains. The paper proposes a cooperative network traffic management framework for Electric Vehicles (EVs) based on a multi-objective optimization aimed at minimizing the total time spent (TTS) and energy consumption (EC) of EVs. Such framework is composed of i) a traffic control model that incorporates traffic lights design, ii) a traffic flow model to estimate TTS as a network performance indicator, and iii) an EVs model to estimate EC at the intersections. The EC function has been derived from a VT-CPEM model to simulate consumptions and thoroughly calibrated based on real-world individual trajectories. The optimization framework was implemented on a nine-node network and the results of the multi-criteria optimization (aiming at minimizing the TTS and EC of EV) are compared with results of the benchmark mono - criterion optimization (aiming at minimizing the TTS) and the mono-criterion optimization combined with the speed advisory (GLOSA; Green Light Optimized Speed Advisory). All the proposed analyses were carried out for different powertrain vehicle categories; ICEVs, and EVs.

VeNet: Hybrid Stacked Autoencoder Learning for Cooperative Edge Intelligence in IoV

Emerging applications of the Internet of Vehicles (IoV) require the wireless transmission of growing amounts of data, e.g., vehicle location and sensor data, over unreliable and increasingly congested wireless links between the mobile vehicles and the Road Side Units (RSUs); also, urban areas are becoming increasingly congested with vehicle road traffic. Road traffic management and data network traffic management to address these challenges require accurate representations of the road and network traffic, which are difficult due to the wide temporal and spatial correlations in the road and network traffic. We address this representation problem by designing, implementing, and evaluating the VeNet deep learning system to exploit the wirelessly transmitted data to predict future vehicle locations and network traffic. We develop the novel VeNet hybrid learning system that employs a stacked autoencoder (AE) consisting of a central AE and multiple local AEs that jointly feed into a Long-Short Term Memory (LSTM). We propose a new training algorithm for the hybrid VeNet learning system. The novel VeNet hybrid learning system conducts spatial learning that accounts for the spatial and temporal correlations in the dataset gathered from the mobile vehicles. Evaluations that involve measurements with custom-made Raspberry Pi vehicles indicate that the VeNet learning model significantly reduces the required signalling network traffic and prediction errors (down to approx. three quarters) compared to existing prediction models. At the same time, VeNet reduces the energy consumption on the vehicles as well as the learning delay.

Multi-Agent-Based Traffic Prediction and Traffic Classification for Autonomic Network Management Systems for Future Networks

Recently, a multi-agent based network automation architecture has been proposed. The architecture is named multi-agent based network automation of the network management system (MANA-NMS). The architectural framework introduced atomized network functions (ANFs). ANFs should be autonomous, atomic, and intelligent agents. Such agents should be implemented as an independent decision element, using machine/deep learning (ML/DL) as an internal cognitive and reasoning part. Using these atomic and intelligent agents as a building block, a MANA-NMS can be composed using the appropriate functions. As a continuation toward implementation of the architecture MANA-NMS, this paper presents a network traffic prediction agent (NTPA) and a network traffic classification agent (NTCA) for a network traffic management system. First, an NTPA is designed and implemented using DL algorithms, i.e., long short-term memory (LSTM), gated recurrent unit (GRU), multilayer perceptrons (MLPs), and convolutional neural network (CNN) algorithms as a reasoning and cognitive part of the agent. Similarly, an NTCA is designed using decision tree (DT), K-nearest neighbors (K-NN), support vector machine (SVM), and naive Bayes (NB) as a cognitive component in the agent design. We then measure the NTPA prediction accuracy, training latency, prediction latency, and computational resource consumption. The results indicate that the LSTM-based NTPA outperforms compared to GRU, MLP, and CNN-based NTPA in terms of prediction accuracy, and prediction latency. We also evaluate the accuracy of the classifier, training latency, classification latency, and computational resource consumption of NTCA using the ML models. The performance evaluation shows that the DT-based NTCA performs the best.

Summary of Cascading Failure in Urban Traffic Network

Cascading failure of urban transportation network will cause serious traffic problems and have a huge negative impact on the lives of the inhabitants and economic development. This paper summarizes the research on cascading failure of transportation network by scholars at home and abroad. Firstly, this paper summarizes the research results of many scholars on the causes of cascading failure in transportation networks. Secondly, it combs the relevant literature on the reasonable evaluation of the degree of cascading failure. Finally, it summarizes how to alleviate the negative impact of cascading failure in traffic network. This paper provides a more scientific and reasonable reference for the realization of network traffic management.

Traffic Optimization with Software-Defined Network Controller on a New User Interface

Software-defined networking (SDN) has emerged as a solution to the cumbersome structures of classical computer networks. It separates control and data planes to give independence to devices with respect to either traffic routing or network management. The two isolated planes communicate with each other via the help of software modules, which are located in an SDN controller, such as Floodlight, NOX, or Ryu. In this study, Floodlight is used and an SDN topology with 20 switches is constructed with Python code in Mininet. All algorithms have been coded with Java. The default routing algorithm in Floodlight is Dijkstra’s algorithm. Four different network optimization algorithms, namely Bellman-Ford, Ford-Fulkerson, Auction, and Dual Ascent algorithms, are utilized in ordinary network routing instead of Dijkstra’s algorithm. None of these four algorithms were used in SDN before and network implementations using Ford-Fulkerson, Auction, or Dual Ascent algorithms were scarce in the literature. The results are analyzed with multiple types of normalization on a new user interface communicating with Floodlight part via HTTP requests. There has not been a user interface that performs the same operations in Floodlight. In the future, this study may possibly be improved with considering normalization processes based on various proportions among the metric values and accounting the computational time of the algorithms.

Research on the evolution law of incidental traffic congestion based on CTM

This paper takes the urban road network as the research object to study the temporal and spatial characteristics and evolution mechanism of incidental traffic congestion. Firstly, the improved cell transmission model (CTM) is proposed considering the traffic flow delay phenomenon and the boundary conditions of the cell at the intersection. Secondly, considering the delay time of vehicles at the intersection, the A * path-finding algorithm is proposed, and a dynamic path selection model based on real-time road impedance is established. Finally, combined with the improved CTM and dynamic path selection model, starting from the severity of the incident and the frequency of information induction and update, the traffic flow is simulated by MATLAB software to simulate the traffic flow in the road network under different conditions and analyze the diffusion characteristics of congestion under sudden events. The simulation results show that during the simulation time period, when the traffic capacity caused by the severity of the incident is only 1/2, 1/4 and 1/8 of the original, the maximum number of congestion cells in the network is 9, 26 and 35, and the maximum delay per unit time stepping is 290, 1.31*103 and 2.41*103 vehicles, and the total delay in the road network is 2.73*105, 7.19*105, and 1.50*106 vehicles, after 320δ, 578δ and 588δ the congestion cells in the road network completely disappear. At the information induced update time of 30s, 120s and 600s, the maximum number of congestion cells in the road network is 5, 10 and 23, the maximum number of delayed vehicles is 162, 254 and 985 vehicles - time stepping, the total delay is 1.25*105, 1.68*105 and 5.84*105 vehicles. The findings of the study can provide reference for urban road network design and traffic management.

Energy and Resource Efficiency by User Traffic Prediction and Classification in Cellular Networks

There is a lack of research on the analysis of peruser traffic in cellular networks, for deriving and following traffic-aware network management. In fact, the legacy design approach, in which resource provisioning and operation control are performed based on the cell-aggregated traffic scenarios, are not so energy- and cost-efficient and need to be substituted with user-centric predictive analysis of mobile network traffic and proactive network resource management. Here, we shed light on this problem by designing traffic prediction tools that utilize standard machine learning (ML) tools, including long shortterm memory (LSTM) and autoregressive integrated moving average (ARIMA) on top of per-user data. We present an expansive empirical evaluation of the designed solutions over a real network traffic dataset. Within this analysis, the impact of different parameters, such as the time granularity, the length of future predictions, and feature selection are investigated. As a potential application of these solutions, we present an ML-powered Discontinuous reception (DRX) scheme for energy saving. Towards this end, we leverage the derived ML models for dynamic DRX parameter adaptation to user traffic. The performance evaluation results demonstrate the superiority of LSTM over ARIMA in general, especially when the length of the training time series is high enough, and it is augmented by a wisely-selected set of features. Furthermore, the results show that adaptation of DRX parameters by online prediction of future traffic provides much more energy-saving at low latency cost in comparison with the legacy cell-wide DRX parameter adaptation.

An MFD Construction Method Considering Multi-Source Data Reliability for Urban Road Networks

Road network traffic management and control are the key mechanisms to alleviate urban traffic congestion. With this study, we aimed to characterize the traffic flow state of urban road networks using the Macroscopic Fundamental Diagram (MFD) to support area traffic control. The core property of an MFD is that the network flow is maximized when network traffic stays at an optimal accumulation state. The property can be used to optimize the temporal and spatial distribution of traffic flow with applications such as gating control. MFD construction is the basis of these MFD-based applications. Although many studies have been conducted to construct MFDs, few studies are dedicated to improving the accuracy considering the reliability of different sources of data. To this end, we propose an MFD construction method using multi-source data based on Dempster–Shafer evidence (DS evidence) theory considering the reliability of different data sources. First, the MFD was constructed using VTD and CSD, separately. Then, the fused MFD was derived by quantifying the reliability of different sources of data for each MFD parameter based on DS evidence theory. The results under real data and simulated data show that the accuracy of the constructed MFDs was greatly improved considering the reliability of different data sources (the maximum MFD estimation error was reduced by 22.3%). The proposed method has the potential to support the evaluation of traffic operations and the optimization of signal control schemes for urban traffic networks.

Fulfilment of the Essential Requirements of the Control-command and Signalling Trackside Subsystem on the Railway Infrastructure of Transhipment Terminals

The implementation of many railway investments indicates as the main goal increasing the efficiency of the railway system, and thanks to its features it becomes easier to integrate it in the competitive transport market. Increasing the integration of the transport sector is one of the cornerstones of the completion of the internal market and rail is an important part of the transport sector moving towards sustainable mobility. The modernized railway lines, which are part of the Trans-European Transport Network (TEN-T) or European Rail Traffic Management System (ERTMS) corridors, also constitute the network of rail freight corridors (RFC). Pursuant to the requirements of European law, setting the dates for implementing interoperability, the infrastructure of comprehensive networks will be forced to adapt to these requirements. Using the example of the control-command and signalling subsystem, this article outlines the scale of the problem related to the implementation of interoperability in relation to rail-road terminals constituting the comprehensive network of the RFC network. Keywords: core network, comprehensive network, certification, control-command and signalling subsystem, ETCS, GSM-R

The influence of average speed ratio on multilayer traffic network

In traffic network design, operation and management, operation speed is one of the key indicators. However, only a few studies are based on traffic dynamics on networks with the consideration of different operation speeds, and less reflected the influence of multilayer networks, which illustrate and represent different appropriate urban traffic modes. In this paper, we constructed a multilayer traffic network model with time weighted adjacency matrix. Then with the study of the influence of different network operation speed ratios on the corresponding characteristics of the comprehensive traffic network, we can clearly know that the change of network operation speed ratio will have very obvious impact on the travel time between nodes, the average travel times, the cooperation strength, the accessibility, and the network community numbers. This research has connected the rencent related study of multilayer traffic network and network operation speeds, the findings of the study afford to improve the current design and operation of traffic integrated models, and can provide some suggestions for urban and urban agglomeration development.