Real-time Traffic Conditions Research Articles

Evaluation of a Probabilistic Framework for Traffic Volume Forecasting Using Deep Learning and Traditional Models

Forecasting is a very important issue in the present times to optimize urban traffic management systems and their proper planning. It is often found that traditional forecasting models cannot fully approximate the non-linear and dynamic nature of traffic patterns. The presented paper proposes a framework that integrates multiple traditional models such as Autoregression (AR), Support Vector Regression (SVR), Exponential Smoothing, Historical Average, Random Walk and Artificial Neural Network (ANN) with deep learning models, especially Stacked Autoencoders, and enhances their predictive efficiency phenomenally. The forecast accuracy is then further enhanced through a dynamic probabilistic model integration strategy that adapts to real-time traffic conditions by dynamically weighting the models based on their performance. It is found that the hybrid framework proposed in the present paper performs much better than the traditional models in predicting traffic volume. Deep learning models with RMSE of 26.9976, AR (RMSE: 22.6679) and SVR (RMSE: 28.2221) provided remarkable prediction accuracy. Based on the results, the authors are confident that the integrated models are useful for real-time traffic management applications. However, they still have great potential for further refinement and optimization.

Pri-DDQN: learning adaptive traffic signal control strategy through a hybrid agent

Adaptive traffic signal control is the core of the intelligent transportation system (ITS), which can effectively reduce the pressure on traffic congestion and improve travel efficiency. Methods based on deep Q-leaning network (DQN) have become the mainstream to solve single-intersection traffic signal control. However, most of them neglect the important difference of samples and the dependence of traffic states, and cannot quickly respond to randomly changing traffic flows. In this paper, we propose a new single-intersection traffic signal control method (Pri-DDQN) based on reinforcement learning and model the traffic environment as a reinforcement learning environment, and the agent chooses the best action to schedule the traffic flow at the intersection based on the real-time traffic states. With the goal of minimizing the waiting time and queue length at intersections, we use double DQN to train the agent, incorporate traffic state and reward into the loss function, and update the target network parameters asynchronously, to improve the agent’s learning ability. We try to use the power function to dynamically change the exploration rate to accelerate convergence. In addition, we introduce a priority-based dynamic experience replay mechanism to increase the sampling rate of important samples. The results show that Pri-DDQN achieves better performance, compared to the best baseline, it reduces the average queue length is reduced by 13.41%, and the average waiting time by 32.33% at the intersection.

Model-enhanced spatial-temporal attention networks for traffic density prediction

Traffic density is a crucial indicator for evaluating the level of service, as it directly reflects the degree of road congestion and driving comfort. However, accurately predicting real-time traffic density has been a significant challenge in Intelligent Transportation Systems (ITS) due to the nonlinear and spatial-temporal dynamic complexity of traffic density. In this paper, we propose a novel Model-enhanced Spatial-Temporal Attention Network (MSTAN), which constructs a spatial-temporal traffic kernel density model using the Kernel Density Estimation (KDE) method to process the spatiotemporal data and calculate the probabilities of various spatiotemporal events. These probabilities are input into the attention mechanism, enabling the model to recognize the inherent connection between dynamic and distant events. Through this fusion, the network can deeply learn and analyze the spatial-temporal properties of traffic features. Furthermore, this paper utilizes the attention mechanism to dynamically model spatial-temporal dependencies, capturing real-time traffic conditions and density, and constructs a spatial-temporal attention module for learning. To validate the performance of the proposed MSTAN model, experiments are conducted on two public datasets of California highways (PeMS04 and PeMS08). The experimental results demonstrate that the MSTAN model outperforms existing state-of-the-art baseline models in terms of prediction accuracy, thus proving the effectiveness of the model both theoretically and practically.

Enhancing Urban Traffic Flow Through Fuzzy Logic-Based Signal Light Control Optimization

Urban traffic congestion is an urgent problem, which is aggravated by the fixed-time urban traffic signal control system. In order to solve this problem, optimization based on fuzzy logic provides flexibility to adapt to real-time traffic conditions. This study discusses the application of fuzzy logic in traffic control and puts forward the optimization scheme of urban traffic light system, including the design of fuzzy controller, the formulation of fuzzy rules, and the system implementation. The results show that compared with the traditional method, the traffic flow and efficiency have been improved, which shows that it has great potential in the real world. By considering the dynamic characteristics of traffic conditions, this method can realize a more flexible and effective control strategy. It is possible to significantly improve the quality of urban transportation system by implementing this method in real scenes.

TPTrans: Vessel Trajectory Prediction Model Based on Transformer Using AIS Data

The analysis of large amounts of vessel trajectory data can facilitate more complex traffic management and route planning, thereby reducing the risk of accidents. The application of deep learning methods in vessel trajectory prediction is becoming more and more widespread; however, due to the complexity of the marine environment, including the influence of geographical environmental factors, weather factors, and real-time traffic conditions, predicting trajectories in less constrained maritime areas is more challenging than in path network conditions. Ship trajectory prediction methods based on kinematic formulas work well in ideal conditions but struggle with real-world complexities. Machine learning methods avoid kinematic formulas but fail to fully leverage complex data due to their simple structure. Deep learning methods, which do not require preset formulas, still face challenges in achieving high-precision and long-term predictions, particularly with complex ship movements and heterogeneous data. This study introduces an innovative model based on the transformer structure to predict the trajectory of a vessel. First, by processing the raw AIS (Automatic Identification System) data, we provide the model with a more efficient input format and data that are both more representative and concise. Secondly, we combine convolutional layers with the transformer structure, using convolutional neural networks to extract local spatiotemporal features in sequences. The encoder and decoder structure of the traditional transformer structure is retained by us. The attention mechanism is used to extract the global spatiotemporal features of sequences. Finally, the model is trained and tested using publicly available AIS data. The prediction results on the field data show that the model can predict trajectories including straight lines and turns under the field data of complex terrain, and in terms of prediction accuracy, our model can reduce the mean squared error by at least 6×10−4 compared with the baseline model.

Traffic Flow Outlier Detection for Smart Mobility Using Gaussian Process Regression Assisted Stochastic Differential Equations

Current methods for detecting outliers in traffic streaming data often struggle to capture real-time dynamic changes in traffic conditions and differentiate between genuine changes and anomalies. This study proposes a novel approach to outlier detection in traffic streaming data that effectively addresses stochasticity and uncertainty in observations. The proposed method utilizes Stochastic Differential Equations (SDEs) and Gaussian Process Regression (GPR). By employing SDEs, we can capture drift and diffusion estimates in traffic streaming data, providing a more comprehensive modeling of the data generation process. Integrating GPR allows precise Bayesian posterior inferences for outlier detection within the SDE framework. To improve practicality, we introduce a flexible threshold-setting mechanism using statistical testing to control the false positive rate. This adaptability helps strike a balance between model fitting and complexity in outlier detection. Compared to traditional SDE-based methods, our SDE-GPR outlier detection method demonstrates enhanced robustness and better adaptability to the complexities of traffic systems. This is evidenced through an empirical study using time series data collected in California, USA. Overall, this study introduces a more advanced and accurate approach to outlier detection in traffic streaming data, paving the way for improved real-time traffic condition monitoring and management.

Traffic signal phase control at urban isolated intersections: an adaptive strategy utilizing the improved D3QN algorithm

Abstract The intelligent control of traffic signals at urban single intersections has emerged as an effective approach to mitigating urban traffic congestion. However, the existing fixed phase control strategy of traffic signal lights lacks capability to dynamically adjust signal phase switching based on real-time traffic conditions leading to traffic congestion. In this paper, an adaptive real-time control method employed by the traffic signal phase at a single intersection is considered based on the improved Double Dueling Deep Q Network (D3QN) algorithm. Firstly, the traffic signal phase control problem is modeled as a Markov decision process, with its state, action, and reward defined. Subsequently, to enhance the convergence speed and learning performance of the D3QN algorithm, attenuation action selection strategy and priority experience playback technology based on tree summation structure are introduced. Then, traffic flow data from various traffic scenarios are utilized to train the traffic signal control model based on the improved D3QN to obtain the optimal signal phase switch strategy. Finally, the effectiveness and optimal performance of the improved D3QN-based traffic signal control strategy are validated across diverse traffic scenarios. The simulation results show that, compared with the control strategy based on AC, DQN, DDQN, D3QN, and C-D3QN algorithms, the cumulative reward of the proposed I-D3QN strategy is increased by at least 6.57%, and the average queue length and average waiting time are reduced by at least 9.64% and 7.61%, which can effectively reduce the congestion at isolated intersections and significantly improve traffic efficiency.

A hierarchical deep reinforcement learning method for solving urban route planning problems under large-scale customers and real-time traffic conditions

As urbanization and economic growth advance, large-scale customers and real-time traffic conditions have become crucial factors in urban route planning. Deep reinforcement learning is considered the most effective method for solving urban route planning problems involving large-scale customers and real-time traffic conditions. Due to memory usage limitations, existing deep reinforcement learning methods cannot identify candidate customers or determine optimal travel routes in large-scale and real-time environments. To tackle these problems, this study introduces a hierarchical deep reinforcement learning method utilizing an improved transformer model (HDRLITF) based on the divide-and-conquer concept. Graph attention networks and gate mechanisms are integrated into the transformer model to capture dynamic features and improve the model’s performance. A two-stage training method, based on the actor-critic algorithm, is proposed to determine the optimal policy function. To evaluate the HDRLITF method, experiments were conducted using datasets from the cities of Shenzhen and Chengdu in China. The experimental results suggest that the HDRLITF method can effectively interact with real-time traffic environments and obtain high-quality solutions compared to other deep reinforcement learning methods. The robustness and reliability of HDRLITF were further validated across multiple traffic scenarios and indicators.

Green commuting within the x-minute city: Towards a systematic evaluation of its feasibility

In cities, carbon emissions associated with commuting transport is large and significant. This study integrates data about the jobs-housing relationship, road network configurations, public transport availability, and real-time traffic conditions during peak hours to evaluate the commuting feasibility and performance of green travel modes (walking, cycling and public transport) and explore the potential determining factors. In the context of the x-minute city, the green travel commuting feasibility (GTCF) indicator measures the percentage of the working population who can commute via green travel modes within specific x-minute thresholds. 15, 30, 45 and 60 min have been considered. In comparison, the car travel commuting feasibility (CTCF) indicator is developed to evaluate the corresponding commuting performance by car. Nanshan district of Shenzhen in China is taken as a case study. Results show that distinct gaps exist between GTCF and CTCF. Public transport performs well only for long-distance (> 8 km) commuting trips, and cycling does well for short (< 3 km) and medium-distance trips. Geographically, areas with large differences of GTCF and CTCF are identified for improving green travel modes with priority. Potential factors influencing GTCF are explored with a regression model and case-based analysis. Smaller street blocks, bus route realignment and better jobs-housing balance should be targeted. Designing cycling short-cuts and public transport routes that avoid traffic jams are also recommended to promote green commuting. The findings demonstrate that real-time trip-planning information is of great value in evaluating the commuting feasibility of multimodal travel and identifying influential factors for achieving the x-minute city.

TariqAmn's Innovative Road Safety Paradigm through Smart Technology

In response to escalating road safety challenges within Algeria, marked by rising traffic volumes and urban development, the "TariqAmn Algeria" initiative emerges as a groundbreaking approach in traffic management. This study delineates the development and deployment of this innovative system, which leverages intelligent traffic signs, LiDAR (Light Detection and Ranging, using laser light to measure distances) radar, and proactive brake control technologies, embedded within a robust traffic management framework. The system's dynamic adaptation to real-time traffic conditions and its enforcement of speed compliance are central to its design. Rigorous evaluations through SUMO (Simulation of Urban Mobility, a traffic simulation software) simulations and field tests in high-risk urban settings affirm its efficacy, demonstrating a 60% reduction in traffic incidents and a 50% reduction in speeding violations. By marrying local cultural insights with cutting-edge technology, "TariqAmn Algeria" not only enhances immediate road safety but also establishes a new paradigm in traffic management systems. The findings illuminate the significant scalability potential of the system, promising broader applications in enhancing road safety and adherence to traffic regulations across various regions, such as densely populated urban areas, high-traffic corridors, and accident-prone black spots. This initiative underscores the critical role of Intelligent Transportation Systems (ITS) in modern road safety strategies and sets a precedent for future technological advancements in the field.

Real-time traffic condition uncertainty quantification using adaptive grey prediction interval model

Uncertainty quantification is important for making reliable transportation decisions. For grey-based uncertainty quantification approaches, the data classification methods for most models cannot yield real-time upper and lower limited data sequence, limiting their application in dynamic transportation systems. Therefore, this paper proposes an adaptive grey prediction interval model to quantify real-time traffic condition uncertainty. To this end, polynomial regression is first used to fit the traffic flow trend function in real time, generating dynamically the upper and lower limited data sequence. Then, upper grey (UG) and lower grey (LG) models are built with parameters optimised using particle swarm optimisation. Finally, based on the real-time upper and lower bounds generated by the UG and LG models, prediction intervals are constructed. Using real-world traffic flow data, the proposed model was shown to be able to generate workable prediction intervals in real time. Future studies are recommended to advance traffic condition uncertainty quantification.

Real-time application of grey system theory in intelligent traffic signal optimization

In order to solve these problems, this paper introduced the grey system theory (GST) method in the real-time application of intelligent traffic signal optimization (ITSO). In this paper, the deep Q-network (DQN) algorithm was used to realize the dynamic signal light setting of real-time traffic conditions, which can improve the overall operating efficiency of the traffic system, and the PPO (Proximal Policy Optimization) algorithm was used to solve the problem of the lack of real-time performance of the traditional traffic signal optimization methods. By comparing the traffic congestion index of S city before and after the application of the GST method, the paper found that the average one week before the application was 60.1%, but it dropped to 26.6% after the application. In the experimental test of average speed comparison, the speed after applying the GST method was generally higher than the value before application, and the overall speed increase was about 20 km/h. This paper emphasizes the importance of evaluating the robustness of the GST method, particularly in its ability to manage unexpected scenarios. The research concentrates on assessing four critical indicators: outlier handling, noise tolerance, handling missing data, and nonlinear coping ability.

Fuzzy adaptive cruise control with model predictive control responding to dynamic traffic conditions for automated driving

Traditional Adaptive Cruise Control (ACC) systems often struggle to dynamically adapt to rapidly changing traffic conditions, resulting in suboptimal performance. Additionally, with fuel consumption emerging as a critical consideration alongside safety, there is a pressing need for more advanced solutions. This paper presents a novel approach to address these challenges by integrating Fuzzy ACC with Model Predictive Control, denoted as FACMPC. This integration aims to enhance both the longitudinal safety of AVs and fuel efficiency by considering real-time traffic conditions. The FACMPC system utilizes fuzzy logic inside the MPC, adaptively generates controller's weighting factors, allowing the system to adapt instantly to varying traffic environments and driving circumstances. The findings show that this adaptation improves the balance between driving safety, efficiency, and comfort. Additionally, three interruption scenarios, Alpha, Beta and Gama, are examined. In Alpha, the study evaluates the sensitivity of the FACMPC to disturbances by applying band-limited white noise to the lead vehicle velocity. In Beta, the AV experiences a loss of the lead vehicle velocity signal for a defined period, prompting safety considerations and assumptions. The Gama scenario includes a sensitivity analysis to account for variations and uncertainties in parameters by considering a range of ±5% around the nominal values for four key parameters: road slope, wind speed, wind direction, and rolling resistance. The findings indicate that the proposed controller's mean fuel consumption is 8.110, only a 3.21% increase over the nominal, compared to a 7.03% increase for the conventional ACC, demonstrating greater robustness against uncertainties.

Leveraging Cooperative Intent and Actuator Constraints for Safe Trajectory Planning of Autonomous Vehicles in Uncertain Traffic Scenarios

This study explores the integration of dynamic vehicle trajectories, vehicle safety factors, static traffic environments, and actuator constraints to improve cooperative intent modeling for autonomous vehicles (AVs) navigating uncertain traffic scenarios. Existing models often focus solely on interactions between dynamic trajectories, limiting their ability to fully interpret the intentions of surrounding vehicles. To address this limitation, we present a more comprehensive approach using the Cooperative Intent Multi-Layer Graph Neural Network (CMGNN) model. The CMGNN analyzes not only the dynamic trajectories but also the lane position relationships, vehicle angle changes, and actuator constraints and performs group interaction analysis. This richer information allows the CMGNN to more accurately capture the cooperative intent and better understand the surrounding vehicle behavior. This study investigated the impact of the CMGNN in the Carla simulator on surrounding vehicle trajectory prediction and AV safe trajectory planning. An innovative mechanism for dynamic trajectory risk assessment is introduced, which takes into account the constraints of the actuators when evaluating trajectory planning metrics. The results show that incorporating cooperative intent and considering the actuator limitations enhanced the CMGNN’s safety and driving efficiency in uncertain scenarios, significantly reducing the probability of AVs colliding. This is achieved as the model dynamically adapts its driving strategy based on the real-time traffic conditions, the perceived intentions of the surrounding vehicles, and the physical constraints of the vehicle actuators.

Development of trust-based autonomous driving framework in New Zealand

PurposeAutonomous vehicles (AVs) have the potential to transform the infrastructure, mobility and social well-being paradigms in New Zealand (NZ) amid its unprecedented population and road safety challenges. But, public acceptance, co-evolution of regulations and AV technology based on interpersonal and institutional trust perspectives pose significant challenges. Previous theories and models need to be more comprehensive to address trust influencing autonomous driving (AD) factors in natural settings. Therefore, this study aims to find key AD factors corresponding to the chain of human-machine interaction (HMI) events happening in real time and formulate a guiding framework for the successful deployment of AVs in NZ.Design/methodology/approachThis study utilized a comprehensive literature review complemented by an AV users’ study with 15 participants. AV driving sprints were conducted on low, medium and high-density roads in Auckland, followed by 15 ideation workshops to gather data about the users’ observations, feelings and attitudes towards the AVs during HMI.FindingsThis research study determined nine essential trust-influencing AD determinants in HMI and legal readiness domains. These AD determinants were analyzed, corresponding to eight AV events in three phases. Subsequently, a guiding framework was developed based on these factors, i.e. human-machine interaction autonomous driving events relationship identification framework (HMI-ADERIF) for the deployment of AVs in New Zealand.Research limitations/implicationsThis study was conducted only in specific Auckland areas.Practical implicationsThis study is significant for advanced design research and provides valuable insights, guidelines and deployment pathways for designers, practitioners and regulators when developing HMI Systems for AD vehicles.Originality/valueThis study is the first-ever AV user study in New Zealand in live traffic conditions. This user study also claimed its novelty due to AV trials in congested and fast-moving traffic on the four-lane motorway in New Zealand. Previously, none of the studies conducted AV user study on SUV BMW vehicle and motorway in real-time traffic conditions; all operations were completely autonomous without any input from the driver. Thus, it explored the essential autonomous driving (AD) trust influencing variables in human factors and legal readiness domains. This research is also unique in identifying critical AD determinants that affect the user trust, acceptance and adoption of AVs in New Zealand by bridging the socio-technical gap with futuristic research insights.

Markov game for CV joint adaptive routing in stochastic traffic networks: A scalable learning approach

This study proposes a learning-based approach to tackle the challenge of joint adaptive routing in stochastic traffic networks with Connected Vehicles (CVs). We introduce a Markov Routing Game (MRG) to model the adaptive routing behavior of all vehicles in such networks, thereby incorporating both competitive route choices and real-time decision-making. We establish the existence of the Nash policy (i.e., optimal joint adaptive routing policy) within the MRG that enables vehicles to adapt optimally to real-time traffic conditions online through efficient communication. To enhance scalability, we innovate with a homogeneity-based mean-field approximation method and, based on that, further develop the Homogeneity-based Mean-Field Deep Reinforcement Learning (HMF-DRL) algorithm to learn the Nash policy within the MRG. Through numerical experiments on the Nguyen–Dupuis network, we demonstrate our algorithm’s ability to efficiently converge and learn the joint adaptive routing policy that significantly enhances traffic network efficiency. Furthermore, our study provides insights into the effects of travel demand, penetration of CVs, and levels of uncertainty on the performance of the joint adaptive routing policy. This paper presents a significant step towards improving network efficiency and reducing the travel time for a majority of vehicles amid uncertain traffic conditions.

A Careful Examination of the Security and Traffic Effects Associated with the Vehicle Ad-hoc Network (VANET)

During recent years, vehicular ad hoc networks, or VANETs, have emerged as one of the most exciting and difficult study fields. VANET is regarded as a subset of MANET, or mobile ad hoc network, which is primarily used on automobiles. With the use of traffic data, VANET hopes to supply an advanced Intelligent Transportation System (ITS) with a wealth of information. Mention how daily traffic data collection helps with transportation planning, particularly with regard to intra-city communication. Two of the main issues with the existing traffic system are jams in traffic and accidents. Around the world, numerous people lose their lives or suffer severe injuries in traffic accidents each year. Human lives on the road are directly impacted by these issues. VANET can help to avert these mishaps and facilitate the efficient operation of daily traffic. Furthermore, VANET offers a plethora of intriguing applications, including real-time traffic condition monitoring, dynamic route scheduling, blind crossing prevention, safety, and more. In addition, there are certain drawbacks in terms of traffic and security. The absence of a centralised infrastructure in VANET is one of the main security issues. One of the most difficult jobs in the resultant decentralised and self- organizing VANETs is the administration of the wireless channel to make an efficient use of its capacity because there is no centralised infrastructure in charge of synchronisation and coordination of transmissions. VANET is primarily used to lower the risk of accidents in urban areas with a high volume and complexity of vehicles. We introduce the VANET Security R&amp;D Ecosystem and examine traffic in this article. The four main components of the R&amp;D ecosystem are end customers, government agencies, automakers, and university research. Every facet of VANET is covered in detail. Our study primarily focuses on the security and traffic within VANETs, including how data is safeguarded from vehicle-to-vehicle (V2V), vehicle-to-roadside infrastructure communications devices (V2I), access points, and other sources.

Exploring Spatiotemporal Patterns of Frequently Congested Urban Road Segments Based on Multi-Source Data: A Case Study of China’s Super-Large Cities

Traffic congestion has emerged as a primary obstacle to sustainable urban development and the livability of life. Seven super-large cities in China were the study area of this paper as the problem tends to be more severe in larger cities. First, frequently congested road segments were defined based on real-time traffic condition data from online maps. Then, the spatiotemporal characteristics of these road segments were explored. Finally, mitigation measures and ways to ease traffic congestion in big cities were discussed against the background of rapid urbanization. The results demonstrate that the proportion of frequently congested road segments takes up between 1.8% and 9.87% of China’s super-large cities. There is a positive correlation between the overall operational efficiency of the urban road network and the ratio of frequently congested road segments. Temporally, commuting patterns during the morning and evening are displayed by these road segments. Spatially, they also demonstrate significant clustering characteristics. The proportion of frequently congested road segments caused by the lack of alternative routes is about 20% in the six cities studied. The data for Chongqing is even higher at 42.94%. Therefore, congestion caused by the lack of alternative routes may be underestimated by existing research. This work could provide theoretical support for transportation planning and management. As cities continue to expand and urbanization accelerates, the significance of this research will increase.

Traffic planning in modern large cities Paris and Istanbul

The enhancement of flexibility, energy efficiency, and environmental friendliness constitutes a widely acknowledged trend in the development of urban infrastructure. The proliferation of various types of transportation vehicles exacerbates the complexity of traffic regulation. Intelligent transportation systems, leveraging real-time traffic status prediction technologies, such as velocity estimation, emerge as viable solutions for the efficacious management and control of urban road networks. The objective of this project is to address the complex task of increasing accuracy in predicting traffic conditions on a big scale using deep learning techniques. To accomplish the objective of the study, the historical traffic data of Paris and Istanbul within a certain timeframe were used, considering the impact of variables such as speed, traffic volume, and direction. Specifically, traffic movie clips based on 2 years of real-world data for the two cities were utilized. The movies were generated with HERE data derived from over 100 billion GPS (Global Positioning System) probe points collected from a substantial fleet of automobiles. The model presented by us, unlike the majority of previous ones, takes into account the cumulative impact of speed, flow, and direction. The developed model showed better results compared to the well-known models, in particular, in comparison with the SR-ResNet model. The pixel-wise MAE (mean absolute error) values for Paris and Istanbul were 4.299 and 3.884 respectively, compared to 4.551 and 3.993 for SR-ResNET. Thus, the created model demonstrated the possibilities for further enhancing the accuracy and efficacy of intelligent transportation systems, particularly in large urban centres, thereby facilitating heightened safety, energy efficiency, and convenience for road users. The obtained results will be useful for local policymakers responsible for infrastructure development planning, as well as for specialists and researchers in the field. Future research should investigate how to incorporate more sources of information, in particular previous information from physical traffic flow models, information about weather conditions, etc. into the deep learning framework, as well as further increasing of the throughput capacity and reducing processing time.

An Integrated DQN and RF Packet Routing Framework for the V2X Network

With the development of artificial intelligence technology, deep reinforcement learning (DRL) has become a major approach to the design of intelligent vehicle-to-everything (V2X) routing protocols for vehicular ad hoc networks (VANETs). However, if the V2X routing protocol does not consider both real-time traffic conditions and historical vehicle trajectory information, the source vehicle may not transfer its packet to the correct relay vehicles and, finally, to the destination. Thus, this kind of routing protocol fails to guarantee successful packet delivery. Using the greater network flexibility and scalability of the software-defined network (SDN) architecture, this study designs a two-phase integrated DQN and RF Packet Routing Framework (IDRF) that combines the deep Q-learning network (DQN) and random forest (RF) approaches. First, the IDRF offline phase corrects the vehicle’s historical trajectory information using the vehicle trajectory continuity algorithm and trains the DQN model. Then, the IDRF real-time phase judges whether vehicles can meet each other and makes a real-time routing decision to select the most appropriate relay vehicle after adding real-time vehicles to the VANET. In this way, the IDRF can obtain the packet transfer path with the shortest end-to-end delay. Compared to two DQN-based approaches, i.e., TDRL-RP and VRDRT, and traditional VANET routing algorithms, the IDRF exhibits significant performance improvements for both sparse and congested periods during intensive simulations of the historical GPS trajectories of 10,357 taxis within Beijing city. Performance improvements in the average packet delivery ratio, end-to-end delay, and overhead ratio of the IDRF over TDRL-RP and VRDRT under different numbers of pairs and transmission ranges are at least 3.56%, 12.73%, and 5.14% and 6.06%, 11.84%, and 7.08%, respectively.