Traffic Changes Research Articles

KGDA: A Knowledge Graph Driven Decomposition Approach for Cellular Traffic Prediction

Understanding and accurately predicting cellular traffic data is vital for communication operators and device users, as it facilitates efficient resource allocation and ensures superior service quality. However, large-scale cellular traffic data forecasting remains challenging due to intricate temporal variations and complex spatial relationships. This article proposes a Knowledge Graph Driven Decomposition Approach (KGDA) for precise cellular traffic prediction. The KGDA breaks down the impact of static environmental factors and dynamic autocorrelations of cellular traffic time series, enabling the capture of overall traffic changes and understanding of traffic dependence on past values. Specifically, we propose an urban knowledge graph to capture the static environmental context of base stations, mapping these entities into the same latent space while retaining static environmental knowledge. The cellular traffic is divided into a regular pattern and fluctuating residual components, with the KGDA comprising four modules: a Knowledge Graph Representation Learning model, a traffic regular pattern prediction module, a traffic residual dynamic prediction module, and an attentional fusion module. The first leverages graph neural networks to extract spatial contexts and predict regular patterns, the second utilizes the Bi-directional Long Short-Term Memory (Bi-LSTM) model to capture autocorrelations of traffic time series, and the final module integrates the patterns and residuals to produce the final prediction result. Comprehensive experiments demonstrate that our proposed model outperforms state-of-the-art models by more than 10% in forecasting cellular traffic.

DFRDRL: a dynamic fuzzy routing algorithm based on deep reinforcement learning with guaranteed latency and bandwidth for software-defined networks

Traditional routing algorithms have several limitations that become increasingly significant in the context of Software-Defined Networking (SDN). Firstly, these algorithms often have limited support for Quality of Service (QoS) requirements, making them less suitable for handling diverse traffic types efficiently. Moreover, current SDN controllers leverage a default shortest-path routing approach, which does not allow for more dynamic and flexible traffic management based on real-time network policies. To address these issues, this paper introduces a Dynamic Fuzzy Routing algorithm based on Deep Reinforcement Learning (DRL) for SDN that provides guaranteed latency and bandwidth (DFRDRL). DFRDRL provides intelligent and efficient routing that adapts to dynamic traffic by considering path-state criteria and using DRL. Fuzzy logic mainly performs online routing between an ingress-egress pair. To adapt to dynamic traffic changes, DFRDRL can predict the traffic matrix in real time. Meanwhile, DFRDRL reduces the routing reliance on network topology by weighting the network based on critical nodes. Additionally, when the network experiences congestion based on the traffic matrix, a deferral mechanism is applied to prioritize requests with lower resource demands. This mechanism helps ensure efficient resource allocation by temporarily postponing or queuing higher-demand requests, thereby optimizing overall network performance during periods of congestion. The simulation results show that the performance of DFRDRL is better than the equivalent algorithms in terms of latency and throughput. Also, DFRDRL is about 2.5% more efficient than the best existing algorithm in terms of admission rate of routing requests.

The impact of the built environment on human mobility patterns during Covid-19: A study of New York City's Open Streets Program

This study uses the Open Streets Program in New York City as a natural experiment to test the effects of change in street use on foot traffic changes during COVID-19. In a two-stage-least-squares (2SLS) design, the Open Streets Program is used as an instrumental variable to isolate the exogenous effect of expanded streets for pedestrians on foot traffic patterns. We then estimate a difference-in-differences model that compares the change in foot traffic to public points-of-interests (POI) in neighborhoods that are part of the Open Streets Program with those that are not “before and after” the start of the city-wide program, in addition to other controls such as street types and weather characteristics to help reduce the error variance of the regression. We find that the Open Streets Program helped increase pedestrian activity at a neighborhood level, even when controlling for street types and other confounding temporal factors such as precipitation and temperature.

Popularity-Aware Service Provisioning Framework in Cloud Environment

To balance the tradeoff between quality of service (QoS) and operating expenditure (OPEX), the service provider should request the appropriate amount of resources to the cloud operator based on the estimated variation of service requests. This paper proposes a popularity-aware service provisioning framework (PASPF), which leverages the network data analytics function (NWDAF) to obtain analytics on service popularity variations. These analytics estimate the congestion level and list of top services contributing most of the traffic change. Based on the analytics, PASPF enables the service provider to request the appropriate amount of resources for each service for the next time period to the cloud operator. To minimize the OPEX of the service provider while keeping the average response time of the services below their requirements, we formulate a constrained Markov decision process (CMDP) problem. The optimal stochastic policy can be obtained by converting the CMDP model into a linear programming (LP) model. Evaluation results demonstrate that the PASPF can achieve less than 50% OPEX of the service provider compared to a popularity-non-aware scheme while keeping the average response time of the services below the requirement.

Analysing Urban Traffic Patterns with Neural Networks and COVID-19 Response Data

Accurate traffic prediction is crucial for urban planning, especially in rapidly growing cities. Traditional models often struggle to account for sudden traffic pattern changes, such as those caused by the COVID-19 pandemic. Neural networks offer a powerful solution, capturing complex, non-linear relationships in traffic data for more precise prediction. This study aims to create a neural network model for predicting vehicle numbers at main intersections in the city. The model is created using real data from the sensors placed across the city of Zilina, Slovakia. By integrating pandemic-related variables, the model assesses the COVID-19 impact on traffic flow. The model was developed using neural networks, following the data-mining methodology CRISP-DM. Before the modelling, the data underwent thorough preparation, emphasising correcting sensor errors caused by communication failures. The model demonstrated high prediction accuracy, with correlations between predicted and actual values ranging from 0.70 to 0.95 for individual sensors and vehicle types. The results highlighted a significant pandemic impact on urban mobility. The model’s adaptability allows for easy retraining for different conditions or cities, making it a robust, adaptable tool for future urban planning and traffic management. It offers valuable insights into pandemic-induced traffic changes and can enhance post-pandemic urban mobility analysis.

Multi-crowdsourced data fusion for modeling link-level traffic resilience to adverse weather events

Climate change leads to more frequent and intense weather events, posing escalating risks to road traffic. Crowdsourced data present new opportunities to monitor and investigate road traffic changes during adverse weather. This study utilizes two types of crowdsourced data: passively collected location data (PCLD) from mobile devices and actively collected user reports (ACUR) from the WAZE app, to examine the impact of floods, winter storms, and fog on road traffic. Three metrics derived from PCLD—speed change, event duration, and area under the curve (AUC)—along with an additional metric from ACUR, user-perceived severity, are utilized to assess link-level traffic resilience. All metrics are correlated with road characteristics such as functional class, number of lanes, divider types, road geometry, and historical traffic, to analyze underlying relationships and make forecasting. Using the Dallas–Fort Worth (DFW) metroplex in 2022 as a case, the study finds that overall, winter storms have the most substantial impact on road traffic, followed by floods and fog. Travel demand metrics, such as POI visits and traffic volume, experience a more significant decrease than traffic speed. The impact of weather also varies by road characteristics, with higher-class roads with greater volume and higher speed experiencing more substantial changes. Road geometry, such as minimal altitude and slopes, also significantly influences road traffic resilience under floods but not during winter storms. Moreover, the study reveals that ACUR may not accurately reflect the actual impact during extreme weather events, as few users are able to travel outside to actively act as “sensors”. In sum, this study evaluates a set of crowdsourced data for assessing link-level traffic resilience, designs various resilience metrics, and examines how they vary across road attributes and weather events, which are essential for guiding disaster preparedness, response, and recovery in road transportation systems.

Network Traffic Anomaly Detection Based on Spatiotemporal Feature Extraction and Channel Attention

To overcome the challenges of feature selection in traditional machine learning and enhance the accuracy of deep learning methods for anomaly traffic detection, we propose a novel method called DCGCANet. This model integrates dilated convolution, a GRU, and a Channel Attention Network, effectively combining dilated convolutional structures with GRUs to extract both temporal and spatial features for identifying anomalous patterns in network traffic. The one-dimensional dilated convolution (DC-1D) structure is designed to expand the receptive field, allowing for comprehensive traffic feature extraction while minimizing information loss typically caused by pooling operations. The DC structure captures spatial dependencies in the data, while the GRU processes time series data to capture dynamic traffic changes. Furthermore, the channel attention (CA) module assigns importance-based weights to features in different channels, enhancing the model’s representational capacity and improving its ability to detect abnormal traffic. DCGCANet achieved an accuracy rate of 99.6% on the CIC-IDS-2017 dataset, outperforming other algorithms. Additionally, the model attained precision, recall, and F1 score rates of 99%. The generalization capability of DCGCANet was validated on a subset of CIC-IDS-2017, demonstrating superior detection performance and robust generalization potential.

Assessment of genotoxicity of air pollution in urban areas using an integrated model of passive biomonitoring

Atmospheric pollution is a major public health issue and has become increasingly critical for human health. Urban atmospheric pollution is typically assessed through physicochemical indicators aligned with environmental legislation parameters, providing data on air quality levels. While the effects of pollution on sensitive organisms serve as a warning for public health decision-makers, there remains a need to explore the interpretation of environmental data on pollutants. The use of species adapted to urban environments as sentinels enables continuous and integrated monitoring of environmental pollution implications on biological systems. In this study, we investigated the use of the plant species Tradescantia pallida as a biomonitor to evaluate the genotoxic effects of atmospheric pollution under diverse vehicular traffic conditions. T. pallida was strategically planted at the leading urban intersections in Uberlândia, Brazil. During COVID-19 pandemic lockdowns, we compared indicators such as physical, biological, and traffic data at different intersections in residential and commercial zones. The reduction in vehicular traffic highlighted the sensitivity of plant species to changes in air and soil pollutants. T. pallida showed bioaccumulation of heavy metals Cd and Cr in monitored areas with higher traffic levels. Additionally, we established a multiple linear regression model to estimate genotoxicity using the micronucleus test, with chromium concentration in the soil (X1) and particulate matter (PM) in the atmosphere (X2) identified as the primary independent variables. Our findings provide a comprehensive portrait of the impact of vehicular traffic changes on PM and offer valuable insights for refining parameters and models of Environmental Health Surveillance.

Improving Data Delivery in Unreliable Networks Using Network Coding and Ant-Colony Optimization

Wireless Sensor Networks (WSNs) comprise interconnected wireless nodes that receive and transmit data across applications and platforms. This paper addressed the problem of link failures in WSNs that potentially could lead to the loss of data packets while still in transit. This was achieved through the use of network coding which is known to address capacity bottleneck problems in WSNs. In particular, a technique called Ant Agent-Assisted Network Coding (AAANC) is proposed that employs the ant colony optimization technique in addition to network coding operations. The main aim of AAANC is to facilitate the successful delivery and decoding of coded data packets in the presence of link failures. AAANC employs a packet route selection technique that is inspired by the social behavior of natural ants. For natural ants, a strong pheromone trail along a path indicates a promising route to a food source, and this is analogous to a reliable communication link for routing data packets in this paper. Through simulations, AAANC was compared to diagonal pseudorandom network coding (DNC) and triangular pseudorandom network coding (TNC), and it proved to have a superior performance in terms of packet delivery ratio and number of decoded packets. Significant performance gain can be achieved if AAANC algorithm is made to dynamically adapt the ant colony and network coding parameters in response to traffic changes.

A Comparison of Neural-Network-Based Intrusion Detection against Signature-Based Detection in IoT Networks

Over the last few years, a plethora of papers presenting machine-learning-based approaches for intrusion detection have been published. However, the majority of those papers do not compare their results with a proper baseline of a signature-based intrusion detection system, thus violating good machine learning practices. In order to evaluate the pros and cons of the machine-learning-based approach, we replicated a research study that uses a deep neural network model for intrusion detection. The results of our replicated research study expose several systematic problems with the used datasets and evaluation methods. In our experiments, a signature-based intrusion detection system with a minimal setup was able to outperform the tested model even under small traffic changes. Testing the replicated neural network on a new dataset recorded in the same environment with the same attacks using the same tools showed that the accuracy of the neural network dropped to 54%. Furthermore, the often-claimed advantage of being able to detect zero-day attacks could not be seen in our experiments.

A Method for 5G–ICN Seamless Mobility Support Based on Router Buffered Data

The 5G core network adopts a Control and User Plane Separation (CUPS) architecture to meet the challenges of low-latency business requirements. In this architecture, a balance between management costs and User Experience (UE) is achieved by moving User Plane Function (UPF) to the edge of the network. However, cross-UPF handover during communication between the UE and the remote server will cause TCP/IP session interruption and affect continuity of delay-sensitive real-time communication continuity. Information-Centric Networks (ICNs) separate identity and location, and their ability to route based on identity can effectively handle mobility. Therefore, based on the 5G-ICN architecture, we propose a seamless mobility support method based on router buffered data (BDMM), making full use of the ICN’s identity-based routing capabilities to solve the problem of UE cross-UPF handover affecting business continuity. BDMM also uses the ICN router data buffering capabilities to reduce packet loss during handovers. We design a dynamic buffer resource allocation strategy (DBRAS) that can adjust the buffer resource allocation results in time according to network traffic changes and business types to solve the problem of unreasonable buffer resource allocation. Finally, experimental results show that our method outperforms other methods in terms of average packet delay, weighted average packet loss rate, and network overhead. In addition, our method also has good performance in average handover delay.

Enlightening the Darknets: Augmenting Darknet Visibility With Active Probes

Darknets collect unsolicited traffic reaching unused address spaces. They provide insights into malicious activities, such as the rise of botnets and DDoS attacks. However, darknets provide a shallow view, as traffic is never responded. Here we quantify how their visibility increases by responding to traffic with interactive responders with increasing levels of interaction. We consider four deployments: Darknets, simple, vertical bound to specific ports, and, a honeypot that responds to all protocols on any port. We contrast these alternatives by analyzing the traffic attracted by each deployment and characterizing how traffic changes throughout the responder lifecycle on the darknet. We show that the deployment of responders increases the value of darknet data by revealing patterns that would otherwise be unobservable. We measure Side-Scan phenomena where once a host starts responding, it attracts traffic to other ports and neighboring addresses. uncovers attacks that darknets and would not observe, e.g. large-scale activity on non-standard ports. And we observe how quickly senders can identify and attack new responders. The “enlightened” part of a darknet brings several benefits and offers opportunities to increase the visibility of sender patterns. This information gain is worth taking advantage of, and we, therefore, recommend that organizations consider this option.

Service Chain Provisioning Model Considering Traffic Changes Due to Virtualized Network Functions

Service Chain Provisioning Model Considering Traffic Changes Due to Virtualized Network Functions

AN AGENT BASED MODEL TO IMPROVE TRAFFIC FLOW AND ASSESS THE IMPACT OF SMART TRAFFIC LIGHT

The Traffic in developing country undergoes severs perturbations due to either a misunderstanding of the physical phenomenon or in bad calibration of equipments such as traffic light. Due to this high complexity, mathematical models fail to well represent different scenario. Those issues are mostly due to the high amount of parameter which should be taken into consideration when dealing with some mathematical model and the drivers behaviors. Since agent-based model is a computational simulation that represents individual entities (called agents) and their interactions within a defined environment. It is a powerful tools used to investigate human behavior impact in a mathematical model. Therefore, this paper proposed a novel agent-based approach framework for effectively making traffic light timing dynamic according to traffic density. Moreover, based on different rules such as lane changing, stop and goat the traffic light, we develop an Agent based model to represent the relationships between the traffic changing and its environment. The use of agent-based models for traffic light time optimization offers a more granular, adaptive, and integrative approach that better capture the complexities of real-world traffic scenarios. Finally, the experimental result is applied on synthetic data and compared to other results in almost the same context for both static and dynamic traffic light. The results show that the travel time distribution is less for dynamic traffic light.

Hidden target recognition method for high-speed network security threats based on attack graph theory

Instantaneous traffic changes in high-speed networks will interfere with abnormal traffic characteristics, making it difficult to accurately identify hidden targets of security threats. This paper designs a high-speed network security threat hidden target recognition method based on attack graph theory. Using the high-speed network traffic reduction method, under the condition that the network topology remains unchanged, the instantaneous input traffic is reduced according to a certain proportion, and after compressing the flow data scale, the abnormal traffic of the high-speed network is identified through the convolutional recurrent neural network, and the information entropy is used to describe the high-speed network. The abnormal traffic characteristics of the network are used as constraints to design an attack graph of hidden targets of high-speed network security threats, and an attack path discovery method based on multi-heuristic information fusion is designed to extract attack paths of high-speed networks, locate attacking hosts, and identify hidden threat targets. In the experiment, the method can accurately identify the hidden targets of high-speed network security threats, and has better identification ability.

Traffic-aware optimal routing in software defined networks by predicting traffic using neural network

Network infrastructure management has been completely transformed by Software-Defined Networking (SDN), allowing for centralized control and programmability. The significant challenge in SDN is to provide optimal routing decisions based on real-time network performance metrics. In this work, it is proposed to have Gated Recurrent Unit (GRU) based traffic prediction to dynamically adjust link weights in SDN. It facilitates real-time adaptation to traffic changes and optimal routing decisions for improved Quality of Service (QoS). This work is to provide optimal routing in SDN by leveraging the capability of GRU to predict future traffic based on network performance metrics sampled at different time sequences. It enables the network to adapt the changing traffic patterns in real-time. The predicted traffic is then used to determine the edge weights between links in the network, which are updated dynamically to reflect changes in the network. When an outbound packet is received, it can be routed optimally by selecting a path with less traffic, thereby reducing latency and improving the QoS of routing the packets. The simulation results reveals that the proposed methodology has the potential to reduce delay up to 9.16% and jitter up to 32.31%, coupled with significant throughput enhancements up to 26.81% compared to the default shortest path. These quantitative findings highlight its effective contribution towards optimizing network performance and QoS.

Hyper-heuristic algorithm for traffic flow-based vehicle routing problem with simultaneous delivery and pickup

Abstract To address the realistic problem of seriously reducing distribution efficiency and increasing distribution cost caused by road traffic congestion, this paper constructs a time-dependent speed describing vehicle travel speed and road traffic flow by simulating the change of urban traffic flow, to establish a vehicle route problem model considering traffic flow with distribution cost and customer satisfaction as optimization objectives. To solve this problem, a hyper-heuristic algorithm based on tabu search is designed in this paper, in which the underlying search operator is selected more efficiently by a high-level heuristic strategy. In addition, the correctness of the model and the effectiveness of the algorithm are verified by conducting simulation experiments on several benchmark sets. Experiment results are shown as the travel speed of the vehicle increases, the average customer satisfaction in lc1-type instances increases to 0.94. And the impact of urban traffic changes on logistics costs and customer satisfaction is further analyzed.

Optimal order-[formula omitted] routing policy for adaptive routing in real road networks

In uncertain traffic networks, adaptive routing mechanism is essential in adapting to dynamic traffic changes and making effective routing decisions. Most previous work on adaptive routing commonly ignores the realistic requirement of drivers to select and enter a right lane before intersections, and this would lead to urgent lane changing at intersections that not only violates traffic rules but even causes traffic accidents. This paper redefines the adaptive routing problem in real road networks as an optimal order-k routing policy problem by proposing a novel order-k routing policy. It is a routing mechanism that selects the next k arcs at each decision intersection and the first m arcs are the same with the last m arcs of the k arcs selected at the last decision intersection, which are defined as an m-arc-constrained order-k link. This routing mechanism gives sufficient preparation time for lane changing. We develop a two-phase methodology to handle this problem. To address complex spatio-temporal correlations in real road networks, instead of using the random sampling method, we use a copula-based scenario generation method to generate high-quality scenarios for improving solution performances. A two-stage algorithm integrating the enumeration of m-arc-constrained order-k links and the construction of the optimal routing policy is developed to find the optimal order-k routing policy based on the scenarios generated. Extensive numerical experiments demonstrate the superiority of the optimal order-k routing policy to simultaneously obtain good performances and meet the realistic requirement of drivers’ lane changing.

Framework for Virtualized Network Functions (VNFs) in Cloud of Things Based on Network Traffic Services

The cloud of things (CoT), which combines the Internet of Things (IoT) and cloud computing, may offer Virtualized Network Functions (VNFs) for IoT devices on a dynamic basis based on service-specific requirements. Although the provisioning of VNFs in CoT is described as an online decision-making problem, most widely used techniques primarily focus on defining the environment using simple models in order to discover the optimum solution. This leads to inefficient and coarse-grained provisioning since the Quality of Service (QoS) requirements for different types of CoT services are not considered, and important historical experience on how to provide for the best long-term benefits is disregarded. This paper suggests a methodology for providing VNFs intelligently in order to schedule adaptive CoT resources in line with the detection of traffic from diverse network services. The system makes decisions based on Deep Reinforcement Learning (DRL) based models that take into account the complexity of network configurations and traffic changes. To obtain stable performance in this model, a special surrogate objective function and a policy gradient DRL method known as Policy Optimisation using Kronecker-Factored Trust Region (POKTR) are utilised. The assertion that our strategy improves CoT QoS through real-time VNF provisioning is supported by experimental results. The POKTR algorithm-based DRL-based model maximises throughput while minimising network congestion compared to earlier DRL algorithms.

Model Development and Simulation for Predicting Proportional Changes in Traffic Volume as a Consequence of Natural Weather Hazards

Abstract This study used a model to calculate the proportional drop for every vehicle class based on 266 climate patterns consisting of seven temperature groups and varied snowfalls. The winter traffic models use weigh-in-motion (WIM) traffic collected on the commuter roadway for 5 years. The marginal impact and combined effect of meteorological conditions on the proportional decrease in winter traffic volume are evaluated. The predicted percentage decrease in traffic for all three vehicle classes increases as temperature decreases and snowfall increases. Mathematical functions are fitted for the decreased patterns for the considered vehicle type. Roadway authorities may utilize traffic percentage decrease to identify weather-related traffic changes when planning winter highway operation and maintenance.