Showing papers on "Network traffic simulation published in 2022"

Deep Learning-Based Network Traffic Prediction for Secure Backbone Networks in Internet of Vehicles

Abstract: Internet of Vehicles (IoV), as a special application of Internet of Things (IoT), has been widely used for Intelligent Transportation System (ITS), which leads to complex and heterogeneous IoV backbone networks. Network traffic prediction techniques are crucial for efficient and secure network management, such as routing algorithm, network planning, and anomaly and intrusion detection. This article studies the problem of end-to-end network traffic prediction in IoV backbone networks, and proposes a deep learning-based method. The constructed system considers the spatio-temporal feature of network traffic, and can capture the long-range dependence of network traffic. Furthermore, a threshold-based update mechanism is put forward to improve the real-time performance of the designed method by using Q-learning. The effectiveness of the proposed method is evaluated by a real network traffic dataset.

A Comparative Study on Traffic Modeling Techniques for Predicting and Simulating Traffic Behavior

Abstract: The significant advancements in intelligent transportation systems (ITS) have contributed to the increased development in traffic modeling. These advancements include prediction and simulation models that are used to simulate and predict traffic behaviors on highway roads and urban networks. These models are capable of precise modeling of the current traffic status and accurate predictions of the future status based on varying traffic conditions. However, selecting the appropriate traffic model for a specific environmental setting is challenging and expensive due to the different requirements that need to be considered, such as accuracy, performance, and efficiency. In this research, we present a comprehensive literature review of the research related to traffic prediction and simulation models. We start by highlighting the challenges in the long-term and short-term prediction of traffic modeling. Then, we review the most common nonparametric prediction models. Lastly, we look into the existing literature on traffic simulation tools and traffic simulation algorithms. We summarize the available traffic models, define the required parameters, and discuss the limitations of each model. We hope that this survey serves as a useful resource for traffic management engineers, researchers, and practitioners in this domain.

Research on Satellite Network Traffic Prediction Based on Improved GRU Neural Network

Abstract: The current satellite network traffic forecasting methods cannot fully exploit the long correlation between satellite traffic sequences, which leads to large network traffic forecasting errors and low forecasting accuracy. To solve these problems, we propose a satellite network traffic forecasting method with an improved gate recurrent unit (GRU). This method combines the attention mechanism with GRU neural network, fully mines the characteristics of self-similarity and long correlation among traffic data sequences, pays attention to the importance of traffic data and hidden state, learns the time-dependent characteristics of input sequences, and mines the interdependent characteristics of data sequences to improve the prediction accuracy. Particle Swarm Optimization (PSO) algorithm is used to obtain the best network model Hyperparameter and improve the prediction efficiency. Simulation results show that the proposed method has the best fitting effect with real traffic data, and the errors are reduced by 26.9%, 37.2%, and 57.8% compared with the GRU, Support Vector Machine (SVM), and Fractional Autoregressive Integration Moving Average (FARIMA) models, respectively.

A Multitask Learning-Based Network Traffic Prediction Approach for SDN-Enabled Industrial Internet of Things

Abstract: With the rapid advance of industrial Internet of Things (IIoT), to provide flexible access for various infrastructures and applications, software-defined networks (SDNs) have been involved in constructing current IIoT networks. To improve the quality of services of industrial applications, network traffic prediction has become an important research direction, which is beneficial for network management and security. Unfortunately, the traffic flows of the SDN-enabled IIoT network contain a large number of irregular fluctuations, which makes network traffic prediction difficult. In this article, we propose an algorithm based on multitask learning to predict network traffic according to the spatial and temporal features of network traffic. Our proposed approach can effectively obtain network traffic predictors according to the evaluations by implementing it on real networks.

Link-based Traffic Estimation and Simulation for Road Networks using Electronic Registration Identification data

Abstract: Traffic estimation and traffic simulation are essential parts of the intelligent transportation system. In recent years, massive traffic data has brought many data-based traffic estimation methods, but few are utilized in traffic simulation. The cause is that the data-based traffic simulation has high requirements for data quality, needing the trip information of all vehicles, not met by common traffic data. Fortunately, the electronic registration identification (ERI) data of the vehicle can satisfy. Therefore, we utilize ERI data to study the traffic estimation and simulation for the road network. The core of this research is the travel time estimation model, which is constructed by combining traffic theory models and the deep neural network. The traffic theory models are a group of linear models, which represent the relationship between traffic flow or traffic density and travel time. The deep neural network can extract the temporal and spatial characteristics of the road network traffic by Moving Average Convergence-Divergence (MACD) and Graph Convolutional Network (GCN), respectively. We named the travel time estimation model MGCN. Then, we employed MGCN for traffic simulation. In the experiment section, we employed Chongqing ERI data to verify the research content. Compared with some baseline methods, our method is superior in travel time estimation and traffic simulation.

A Novel Method for Improved Network Traffic Prediction Using Enhanced Deep Reinforcement Learning Algorithm

Abstract: Network data traffic is increasing with expanded networks for various applications, with text, image, audio, and video for inevitable needs. Network traffic pattern identification and analysis of traffic of data content are essential for different needs and different scenarios. Many approaches have been followed, both before and after the introduction of machine and deep learning algorithms as intelligence computation. The network traffic analysis is the process of incarcerating traffic of a network and observing it deeply to predict what the manifestation in traffic of the network is. To enhance the quality of service (QoS) of a network, it is important to estimate the network traffic and analyze its accuracy and precision, as well as the false positive and negative rates, with suitable algorithms. This proposed work is coining a new method using an enhanced deep reinforcement learning (EDRL) algorithm to improve network traffic analysis and prediction. The importance of this proposed work is to contribute towards intelligence-based network traffic prediction and solve network management issues. An experiment was carried out to check the accuracy and precision, as well as the false positive and negative parameters with EDRL. Also, convolutional neural network (CNN) machines and deep learning algorithms have been used to predict the different types of network traffic, which are labeled text-based, video-based, and unencrypted and encrypted data traffic. The EDRL algorithm has outperformed with mean Accuracy (97.20%), mean Precision (97.343%), mean false positive (2.657%) and mean false negative (2.527%) than the CNN algorithm.

Automated Calibration of Traffic Demand and Traffic Lights in SUMO Using Real-World Observations

Abstract: Virtual traffic environments allow for evaluations of automated driving functions as well as future mobility services. As a key component of this virtual proving ground, a traffic flow simulation is necessary to represent real-world traffic conditions. Real-world observations, such as historical traffic counts and traffic light state information, provide a basis for the representation of these conditions in the simulation. In this work, we therefore propose a scalable approach to transfer real-world data, exemplarily taken from the German city Ingolstadt, to a virtual environment for a calibration of a traffic flow simulation in SUMO. To recreate measured traffic properties such as traffic counts or traffic light programs into the simulation, the measurement sites must first be allocated in the virtual environment. For the allocation of historical real-world data, a matching procedure is applied, in order to associate real-world measurements with their corresponding locations in the virtual environment. The calibration incorporates the replication of realistic traffic light programs as well as the adjustment of simulated traffic flows. The proposed calibration procedure allows for an automated creation of a calibrated traffic flow simulation of an arbitrary road network given historical real-world observations.

A top-down approach for building realistic reference scenarios and simulation framework for LTE C-V2X communications

Abstract: Many vehicle-to-everything (V2X) applications and use cases require their feasibility to be simulated, tested, and validated in realistic traffic scenarios and under various network conditions before real-time testbed implementation. As cellular-V2X (C-V2X) becomes a superior technology for future connected and autonomous vehicles, the need for a simulation framework, which integrates traffic and network simulators with a realistic channel model, becomes more evident. The challenge is to overcome existing simulation platforms’ weaknesses and improve simulation results’ accuracy while preserving flexibility with manageable implementation complexity. This paper proposed a top–down approach for building reference scenarios with macroscopic and microscopic layers, which interweaves traffic, network, and channel simulators. The basis for the proposed simulation framework is realistic scenario data, which provides the input to the road traffic simulator and the radio channel simulator. The core of the whole simulator is the network simulator interacting with the two other simulators via dedicated interfaces. The road traffic simulator generates the vehicles’ positions and is forwarded to the network simulator, which requests the radio channel simulator for the path loss values on the transmitter–receiver (TX-RX) link. As a proof of concept, the simulation results focused on the load and interference analysis in the absence and presence of V2X traffic.

Research on integrated simulation platform for urban traffic control connecting simulation and practice

Abstract: Though effective in theoretical simulation, the established traffic control models and optimization algorithms will result in model mismatch or even control strategy failure in actual application. However, they are commonly adopted in traffic signal control research, resulting in the unavailability of many exceptional control algorithms in practice. Simulation should function as a bridge between theoretical research and actual application, allowing the gap between the two to be communicated and made up for. However, an effective connection between the two has yet to be established to enable simulation methods in existing traffic control research. To this end, we designed and developed a simulation platform for "Online Application-HILS (Hardware-in-the-Loop Simulation)-Practice" integration over traffic signal control. In this paper, the architecture and characteristics of the integrated simulation platform were described. Besides, the function of each module of the platform was detailed, followed by listing simulation examples for six complex scenarios, with the active control scenario being selected for simulation comparison analysis. The findings demonstrated extensive road network simulation with the integrated simulation platform, multidimensional control variables, control strategies with support, as well as stable and reliable operation. It can be used to verify several sorts of traffic control simulation with variable dimensions.

Network Traffic Prediction: Apply the Transformer to Time Series Forecasting

Abstract: Along with the development of technology and social progress, the Internet is increasingly widely used in life. Mobile communication, fiber optic broadband, and other essential Internet networks have gradually become indispensable in everyday life. The task of further improving and optimizing the quality of Internet network links and improving the efficiency of Internet networks has been on the agenda. This paper proposed a deep learning-based network traffic prediction model, which can capture the characteristics of network traffic information changes by inputting past network traffic data to achieve the effect of future network traffic prediction. The model structure is flexible and variable, which improves the problems of other methods that cannot capture long time series prediction features and cannot parallelize the output. It also has apparent advantages in time complexity and model convergence speed without the evident disadvantage of time lag. Based on this network traffic prediction model, it can help Internet service providers optimize network resource allocation, improve network performance, and allow Internet data centers to provide abnormal network warnings and improve user service level agreements.

Physics-Informed Neural Networks (PINNs)-Based Traffic State Estimation: An Application to Traffic Network

Abstract: Traffic state estimation (TSE) is a critical component of the efficient intelligent transportation systems (ITS) operations. In the literature, TSE methods are divided into model-driven methods and data-driven methods. Each approach has its limitations. The physics information-based neural network (PINN) framework emerges to mitigate the limitations of the traditional TSE methods, while the state-of-art of such a framework has focused on single road segments but can hardly deal with traffic networks. This paper introduces a PINN framework that can effectively make use of a small amount of observational speed data to obtain high-quality TSEs for a traffic network. Both model-driven and data-driven components are incorporated into PINNs to combine the advantages of both approaches and to overcome their disadvantages. Simulation data of simple traffic networks are used for studying the highway network TSE. This paper demonstrates how to solve the popular LWR physical traffic flow model with a PINN for a traffic network. Experimental results confirm that the proposed approach is promising for estimating network traffic accurately.

Data-Driven Network Path Simulation with iBox

Abstract: While network simulation is widely used for evaluating network protocols and applications, ensuring realism remains a key challenge. There has been much work on simulating network mechanisms faithfully (e.g., links, buffers, etc.), but less attention on the critical task of configuring the simulator to reflect reality. We present iBox ("Internet in a Box"), which enables data-driven network path simulation, using input/output packet traces gathered at the sender/receiver in the target network to create a model of the end-to-end behaviour of a network path. Our work builds on recent work in this direction [2, 6] and makes three contributions: (1) estimation of a lightweight non-reactive cross-traffic model, (2) estimation of a more powerful reactive cross-traffic model based on Bayesian optimization, and (3) evaluation of iBox in the context of congestion control variants in an Internet research testbed and also controlled experiments with known ground truth. This paper represents an abridged version of [3].

NTAM-LSTM models of network traffic prediction

Abstract: Accurate prediction of network traffic is very important in allocating network resources. With the rapid development of network technology, network traffic becomes more complex and diverse. The traditional network traffic prediction model cannot accurately predict the current network traffic within the effective time. This paper proposes a Network Traffic Prediction Model----NTAM-LSTM, which based on Attention Mechanism with Long and Short Time Memory. Firstly, the model preprocesses the historical dataset of network traffic with multiple characteristics. Then the LSTM network is used to make initial prediction for the processed dataset. Finally, attention mechanism is introduced to get more accurate prediction results. Compared with other network traffic prediction models, NTAM-LSTM prediction model can achieve higher prediction accuracy and take shorter running time.

Current Trends in Road Traffic Network Division for Distributed or Parallel Road Traffic Simulation

Abstract: Road traffic simulation is one of the useful tools, which can help to cope with steadily increasing intensity of road traffic. A distributed or parallel computing environment can significantly speedup the simulation execution, but the road traffic network division is usually required. There are many existing methods for road traffic network division based on various approaches. However, there is a lack of surveys mapping these methods. For this reason, this paper is a survey of existing methods for road traffic network division published in last two decades. It is not a systematic review, as it does not try to answer specific scientific questions. Its purpose is to map and categorize the existing methods for road traffic network division and to summarize their common features. Such a survey can be useful as a good starting point for the related work exploration for any teams or individuals dealing with road traffic network division and distributed or parallel road traffic simulation.

Network Traffic Prediction Based on the Feature of Newly-Generated Network Flows

Abstract: Network traffic prediction is essential for intelligent network management, such as resource reservation and burst warning. Existing prediction approaches are vulnerable in accurately capturing the sudden surge or plunge, uniformly denoted as the traffic burst. To solve this problem, we extract the time series of the number of newly-generated network flows (NoNGF) from the network flow information, explaining the intrinsic mechanism of network traffic bursts. We use time-lagged cross-correlation analysis to identify directionality between the NoNGF series and traffic series. It proves that we can perceive the future fluctuation and burst of network traffic by NoNGF in advance. The comprehensive prediction experiments of the whole network traffic and three application-level network traffic demonstrate that our proposed approach exhibits a significant performance improvement over the original LSTM and TCN models. Our approach can accurately capture the moment of network burst and the predicted value much more precisely when the burst occurs. In summary, our proposed traffic prediction based on NoNGF can significantly improve the prediction accuracy, especially for network burst traffic.

Application of Fast P2P Traffic Recognition Technology Based on Decision Tree in the Detection of Network Traffic Data

Abstract: With the rapid development of large-scale enterprise informatization construction, the network scale has become huge and complex, and the data traffic carried by the network is increasing. Accurate network traffic identification is the basis of network management and is of great significance to enterprise informatization construction and operation and maintenance. In response to the network operation and maintenance requirements of large enterprises, this paper analyzes the network architecture and network traffic distribution of large enterprise groups from the perspective of enterprise network operators and introduces the current operation and maintenance process of enterprise network performance failures. Maintenance process optimization and reengineering are carried out to plan and find out the shortcomings of the current process links and put forward corresponding solutions. Based on the research of traffic identification in recent years, a fast P2P network traffic anomaly identification algorithm based on decision tree model is proposed, which improves the efficiency and accuracy of network traffic application identification and network traffic anomaly data identification.

Co-simulation of Power Grid, Information Network and Transportation Network Simulation System

Abstract: The three-network integration of power grid, information network and transportation network has become a global issue and trend. However, the current research on triple play is still in its infancy. Most of the researches define the concept of triple play, and lack of simulation research on the power grid-information network-transportation network coupling system. Therefore, this paper studies the key technologies of power grid-information network-transportation network co-simulation. The key technologies of simulation are data interaction method and time synchronization method. By building a simulation prototype system, it provides simulation support for the theoretical study of the power grid-information network-transportation network coupling system.

An Online Traffic Simulation Modeling Framework for Real-Time Road Traffic Control and Management

Abstract: Online traffic simulation feeds from online information to simulate vehicle movement in real-time, which has recently seen substantial advancement in road traffic control and management. It has been a challenging problem due to three aspects: 1) the diversity of traffic patterns caused by heterogeneous layouts of urban intersections; 2) the complexity of spatiotemporal correlations; 3) the requirement of adjusting traffic model parameters in a real-time system. To cater to these challenges, this paper proposes an online traffic simulation modeling framework via a meta-learner. In particular, simulation models with various intersection layouts are automatically generated using an open-source simulation tool, SUMO, according to static traffic geometry attributes. Through a meta-learning technique, the proposed modeling framework enables an automated learning process for estimating model settings capable of adapting traffic model parameters according to dynamic traffic information in real-time. Such a process is featured with various traffic scenarios and different spatiotemporal correlations. Through computational experiments, we demonstrate that the meta-learning-based framework is able to self-adapt its effectiveness according to real-time traffic data.

Forecasting Busy-Hour Downlink Traffic in Cellular Networks

Abstract: The dramatic growth in cellular traffic volume requires cellular network operators to develop strategies to carefully dimension and manage the available network resources. Forecasting traffic volumes is a fundamental building block for any proactive management strategy and is therefore of great interest in such a context. Differently from what found in the literature, where network traffic is generally predicted in the short-term, in this work we tackle the problem of forecasting busy hour traffic, i.e., the time series of observed daily maxima traffic volumes. We tackle specifically forecasting in the long term (one, two months ahead) and we compare different approaches for the task at hand, considering different forecasting algorithms as well as relying or not on a cluster-based approach which first groups network cells with similar busy hour traffic profiles and then fits per-cluster forecasting models to predict the traffic loads. Results on a real cellular network dataset show that busy hour traffic can be forecasted with errors below 10% for look-ahead periods up to 2 months in the future. Moreover, when clusters are available, we improve forecasting accuracy up to 8% and 5% for look-ahead of 1 and 2 months, respectively.

Data-Driven Network Path Simulation with iBox

Abstract: While network simulation is widely used for evaluating network protocols and applications, ensuring realism remains a key challenge. There has been much work on simulating network mechanisms faithfully (e.g., links, buffers, etc.), but less attention on the critical task of configuring the simulator to reflect reality. We present iBox ("Internet in a Box"), which enables data-driven network path simulation, using input/output packet traces gathered at the sender/receiver in the target network to create a model of the end-to-end behaviour of a network path. Our work builds on recent work in this direction [2, 6] and makes three contributions: (1) estimation of a lightweight non-reactive cross-traffic model, (2) estimation of a more powerful reactive cross-traffic model based on Bayesian optimization, and (3) evaluation of iBox in the context of congestion control variants in an Internet research testbed and also controlled experiments with known ground truth. This paper represents an abridged version of [3].

Short-Term Network Traffic Prediction with Multilayer Perceptron

Abstract: The constantly increasing internet traffic and rising network requirements trigger fast development and implementation of new networking architectures and technologies. Predictability of network traffic can bring significant benefits in many areas, such as network planning, network security, dynamic bandwidth allocation, and predictive congestion control. This paper studies the problem of short-term traffic forecasting in application-aware backbone optical networks. The proposed method is based on the Multilayer Perceptron (mlp). Multiple neural network architectures are evaluated using three datasets with diverse characteristics, representing different types of internet traffic in a real-world backbone network. An extensive examination is performed to find the best neural network architecture for each traffic type. The proposed method revealed high prediction quality, achieving the mean absolute percentage errors between 2% and 10%, depending on the traffic type. The proposed neural networks outperform the baseline regression model in all considered types of traffic.

Traffic simulation in the LoRaWAN network

Abstract: LoRaWAN is one of the most commonly used technologies serving the internet of things (IoT) and machine-to-machine (M2M) devices. The traffic growth in the LoRaWAN network gives rise to many problems, which are solved using mathematical modelling. The actual task, in this case, is the development of a traffic simulation model in the LoRaWAN network. This article discusses the issues of traffic simulation in the LoRaWAN network and its research using the MATLAB system. The authors have developed a LoRaWAN network server model as a queuing system with incoming self-similar traffic in the MATLAB system using a separate subsystem for the input traffic modelling allowing to change the number of sources in the LoRaWAN network. The simulation results made it possible to establish the dependences of the network server’s buffer memory, the probability of packet loss from the incoming self-similar traffic parameters, and reveal the possibilities of traffic modelling in the MATLAB system.

Traffic Analysis of Partially Observable Bearer Network under RouteNet based GNN Model

Abstract: The expansion of the bearer network and the massive growth of network traffic data make it difficult to evaluate network performance. RouteNet proposes a graph neural network (GNN) model to solve such problems and achieves good results. Due to the black-box nature of GNNs, the relationship between topology and routing is not clear. This paper proposes a linear fitting model based on Graph Representation to represent the relationship between origin-destination (OD) traffic and link traffic. Based on this model, the paper proposes a traffic analysis scheme architecture for partially observable bearer networks. The architecture can analyze critical links and important OD traffic in the network. Based on this architecture, network node aggregation can also be performed, the network scale can be reduced, and the large-scale network performance evaluation problem can be solved. Numerical tests verify the accuracy and effectiveness of the proposed method in the traffic analysis problem of the bearer network.

A novel hybrid deep learning approach for 5G network traffic control and forecasting

Abstract: 5G is planned to link not just traditional devices such as tablets and smartphones, but also smart devices, smart homes, autonomous vehicles, and industry 4.0 which significantly increases the amount of traffic over the network. Network function virtualization and software defined networks will be used heavily to create scalably and on‐demand 5G architecture using virtual network functions. In this article, we proposed a unique approach to scaling 5G core network resources by predicting traffic load fluctuations using a hybrid model. Most researchers have presented deep learning models to anticipate regular traffic to improve services, however, these recommended models have failed to estimate traffic load during festivals to unexpected changes in traffic conditions. To solve this issue, we introduced CNN+LSTM, a hybrid model that combines CNN, and LSTM to forecast cumulative network traffic across particular intervals to scale up and properly estimate the availability of 5G network resources by leveraging traffic load variations. The suggested model surpasses the other tested deep learning models and existing techniques that forecast the output in both normal and abnormal traffic conditions, according to a comparison of the produced output with existing techniques.

Effectiveness of classification of computer network traffic analysis applications using machine learning methods

Abstract: The article considers the relevance of network traffic research, which is explained by the introduction of computer networks into the life of every person. The rapid development of computer networks has caused increased attention to issues of quality and reliability of their work. The study of computer network traffic analysis is relevant for ensuring the quality of wired and wireless communication, information resources and information search. The study of network traffic indicates the need for its classification to display network data into traffic classes and application types. It is advisable to use machine learning methods, which facilitates the adaptation of the system to constantly changing Internet resources, taking into account the specifics of network traffic. Network traffic analysis indicates that to successfully classify network traffic, all traffic passing through the network must be stored or processed. It was determined that the classification of network traffic is an important task in the field of computer networks. The purpose of network traffic classification is to map the flow of network data into specific application types or traffic classes. An overview of network traffic classification methods was conducted. The results of a comparison of modern approaches to the classification of network traffic are given. Despite the range of methods, the classification of network traffic is still at the stage of development. It should be noted that modern methods, in particular based on machine learning, prove effective results.

Interactive Web-Based Visual Analysis on Network Traffic Data

Abstract: Network traffic data analysis is important for securing our computing environment and data. However, analyzing network traffic data requires tremendous effort because of the complexity of continuously changing network traffic patterns. To assist the user in better understanding and analyzing the network traffic data, an interactive web-based visualization system is designed using multiple coordinated views, supporting a rich set of user interactions. For advancing the capability of analyzing network traffic data, feature extraction is considered along with uncertainty quantification to help the user make precise analyses. The system allows the user to perform a continuous visual analysis by requesting incrementally new subsets of data with updated visual representation. Case studies have been performed to determine the effectiveness of the system. The results from the case studies support that the system is well designed to understand network traffic data by identifying abnormal network traffic patterns.

Road Traffic Network Division for a Parallel Dynamic Network Loading Algorithm

Abstract: In this paper, we describe the method for the Road Traffic Network Division for Dynamic Network Loading (RTND-DNL), which is based on our formerly developed Imp-roved Dividing Genetic Algorithm with Graph Coarsening and Refining (IDGA-GC-R) method. The IDGA-GC-R method was originally designed for a detailed distributed road traffic simulation. Hence, some modifications were necessary to meet slightly different requirements of the dynamic network loading. However, the RTND-DNL method still employs a genetic algorithm, a graph coarsening, and a refining. The description of the RTND-DNL method along with its testing is the main contribution of this paper.

A Network Traffic Analysis System based on Big Data

Abstract: With the rapid development of network technology, network applications are becoming more and more popular. In order to ensure the availability of network and the stable operation of key business, the methodology of network traffic analysis appeared accordingly. Compared with the normal non-big data traffic analysis, using big data for traffic analysis and monitoring can solve the problems of single data source, difficulty in chart expansion horizontally and chart customization, etc. Based on big data technology to build a unified platform on traffic analysis and monitoring, it is able to integrate with the network analysis of data and other dimensions of the associated monitoring information to achieve efficient service on fault warning and navigating location.

Network Traffic Prediction for Intelligent Transportation Systems: A Reinforcement Learning Approach

Abstract: Vehicular Ad-Hoc Networks (VANETs), as the cru-cial support of Intelligent Transportation Systems (ITS), have received a great attention in recent years. Network traffic prediction is useful for network management and security in VANETs, such as network planning and anomaly detection. Due to the movement of nodes, the traffic flow in VANETs consists of a great number of irregular fluctuations, which is the main challenge for network traffic prediction. This paper proposes a novel algorithm, which combines Deep Q-Learning (DQN) and Generative Adversarial Networks (GAN) for network traffic prediction. We use DQN to carry out network traffic prediction, in which GAN is involved to represent Q-network. Meanwhile, the generative network can increase the number of samples to improve the prediction error. We evaluate the performance of our method by implementing it on two real network traffic data sets. Finally, we compare the two state-of-the-art competing methods with our method.