Future Traffic Conditions Research Articles

Driven traffic flow prediction in smart cities using hunter-prey optimization with hybrid deep learning models

Accurate and timely flow prediction is the most significant element for intelligent traffic management systems. However, developing a robust and potential prediction method is a challenge because of the nonlinear characteristics and inherent randomness of the traffic flow in smart cities. Deep learning can analyze historical traffic data and predict future traffic patterns in traffic flow prediction. This can be done by training deep neural networks on large datasets, such as traffic speed and volume data, to learn the underlying relationships between various factors influencing traffic flow. The resulting models can then be used to predict future traffic conditions, helping optimize traffic management, reduce congestion, and improve safety. This study introduces a Hunter Prey Optimization with Hybrid Deep Learning-Driven Traffic Flow in smart cities Prediction (HPOHDL-TFPM). The HPOHDL-TFPM approach's primary goal is to accurately and rapidly forecast traffic flow. The HPOHDL-TFPM technique uses Z-score normalization to normalize the traffic data to achieve this. In addition, the CBLSTM-AE model, which combines convolutional bidirectional long short-term memory and autoencoder, is utilized in the prediction of traffic flow in smart cities. Moreover, the HPO technique is applied as a hyperparameter optimizer to select the hyperparameter values properly. The experimental validation of the HPOHDL-TFPM approach is tested in several contexts. Numerous comparative studies demonstrated the improved performance of the HPOHDL-TFPM approach over other existing methods.

TSANet: Forecasting traffic congestion patterns from aerial videos using graphs and transformers

Forecasting traffic congestion patterns in lane-less traffic scenarios is a complex task because of the combination of high & irregular vehicle densities, fluctuating speeds, and the presence of environmental obstacles. Existing techniques like vehicle counting and density prediction, which successfully estimate congestion in lane-based traffic, are unsuitable for lane-less traffic scenarios due to the irregular and unpredictable nature of traffic density patterns. To overcome these challenges, we propose traffic states to measure congestion patterns in lane-less traffic scenarios. Each traffic state is characterized by the spatio-temporal distribution of neighbouring road users, including vehicles and motorcyclists. We employ traffic graphs to capture the spatial distribution of neighbouring road users. Also, we propose a novel method for the automated construction of traffic graphs by leveraging the detection and tracking of individual road users in aerial videos. Further, in order to incorporate the temporal distribution, we utilize a transformer model to capture the evolution of spatial traffic graphs over time. This enables us to forecast future spatio-temporal distributions and their associated traffic states. Our proposed model, named Traffic State Anticipation Network (TSANet), can effectively forecast future traffic states by analysing sequences of current traffic graphs, thereby enhancing our understanding of evolving traffic patterns in lane-less scenarios. Also, to address the lack of publicly available lane-less traffic datasets, we introduce EyeonTraffic (EoT), a large-scale lane-less traffic dataset containing three hours of aerial videos captured at three busy intersections in Ahmedabad city, India. Experimental results on the EoT dataset demonstrate the efficacy of our proposed TSANet in effectively anticipating traffic states across diverse spatial regions within an intersection. In addition, we also show that TSANet generalizes well for previously unseen intersections, making it suitable for analysing various traffic scenarios without the need for explicit training, thereby enhancing its practical applicability.

Periodic Transformer Encoder for Multi-Horizon Travel Time Prediction

In the domain of Intelligent Transportation Systems (ITS), ensuring reliable travel time predictions is crucial for enhancing the efficiency of transportation management systems and supporting long-term planning. Recent advancements in deep learning have demonstrated the ability to effectively leverage large datasets for accurate travel time predictions. These innovations are particularly vital as they address both short-term and long-term travel demands, which are essential for effective traffic management and scheduled routing planning. Despite advances in deep learning applications for traffic analysis, the dynamic nature of traffic patterns frequently challenges the forecasting capabilities of existing models, especially when forecasting both immediate and future traffic conditions across various time horizons. Additionally, the area of long-term travel time forecasting still remains not fully explored in current research due to these complexities. In response to these challenges, this study introduces the Periodic Transformer Encoder (PTE). PTE is a Transformer-based model designed to enhance traffic time predictions by effectively capturing temporal dependencies across various horizons. Utilizing attention mechanisms, PTE learns from long-range periodic traffic data for handling both short-term and long-term fluctuations. Furthermore, PTE employs a streamlined encoder-only architecture that eliminates the need for a traditional decoder, thus significantly simplifying the model’s structure and reducing its computational demands. This architecture enhances both the training efficiency and the performance of direct travel time predictions. With these enhancements, PTE effectively tackles the challenges presented by dynamic traffic patterns, significantly improving prediction performance across multiple time horizons. Comprehensive evaluations on an extensive real-world traffic dataset demonstrate PTE’s superior performance in predicting travel times over multiple horizons compared to existing methods. PTE is notably effective in adapting to high-variability road segments and peak traffic hours. These results prove PTE’s effectiveness and robustness across diverse traffic environments, indicating its significant contribution to advancing traffic prediction capabilities within ITS.

Do traffic flow states follow Markov properties? A high-order spatiotemporal traffic state reconstruction approach for traffic prediction and imputation

Assessing traffic states accurately is challenging due to the complex, high-dimensional, and nonlinear nature of traffic systems. This study introduces the innovative High-Order Spatiotemporal Traffic State Reconstruction (HOSTSR) algorithm, designed to track and predict traffic flow dynamics effectively. It combines phase space reconstruction with time delays and high-order neighborhood concepts from graph theory to improve traffic state assessments' accuracy. The algorithm's effectiveness is validated using chi-square tests and the Chapman-Kolmogorov equation to confirm the Markovian properties of traffic flows. A lean autoencoder, informed by prior Markov knowledge of traffic states, is developed for mapping traffic states to real traffic data, proving highly effective for traffic data imputation due to the Markov model's memoryless property. Experimental results from the PeMSD04 and PeMSD08 datasets show that HOSTSR outperforms traditional state reconstruction methods based on delayed coordinate embedding in predicting future traffic flow state based on four key metrics. The autoencoder framework, guided by prior Markov knowledge, shows significant advantages in addressing traffic data gaps in different cases over six baseline models. Gradient sensitivity analysis further evaluates the impact of prior knowledge on improving the autoencoder's interpretability for interpolation efforts.

Dynamic multi-scale spatial–temporal graph convolutional network for traffic flow prediction

As a critical component of Intelligent Transportation Systems (ITS), traffic flow prediction is indispensable for vehicle routing and transportation management. However, traffic prediction is an intractable task due to the complex spatial–temporal dependencies. First, traffic data has multiple spatial dependencies that arise from different contexts and vary with time. Second, multi-scale temporal features naturally exist in the traffic data and have dynamic significance for predicting future traffic states. Insufficiently capturing such spatial and temporal dependencies will lead to the prediction performance degradation. To this end, we propose a dynamic multi-scale spatial–temporal graph convolutional network for traffic flow prediction. Unlike existing methods, we propose a novel attention layer assigning weights to each feature of nodes to augment the dynamic spatial dependence modeling and a dynamic multi-branch temporal network learning temporal features from the time domain and frequency domain complementary to enhance the dynamic multi-scale temporal features learning capability. Extensive experiments on four well-known traffic datasets demonstrate that the proposed model outperforms the best baselines with a ratio of 5.27%, 2.44%, 3.27%, and 7.34% in terms of mean absolute error and also has superior long-term prediction performance than state-of-the-art baselines.

PaSTG: A Parallel Spatio-Temporal GCN Framework for Traffic Forecasting in Smart City

Predicting future traffic conditions from urban sensor data is crucial for smart city applications. Recent traffic forecasting methods are derived from Spatio-Temporal Graph Convolution Networks (STGCNs). Despite their remarkable achievements, these spatio-temporal models have mainly been evaluated on small-scale datasets. In light of the rapid growth of the Internet of Things and urbanization, cities are witnessing an increased deployment of sensors, resulting in the collection of extensive sensor data to provide more accurate insights into citywide traffic dynamics. Spatio-temporal graph modeling on large-scale traffic data is challenging due to the memory constraint of the computing device. For traffic forecasting, subgraph sampling from road networks onto multiple devices is feasible. Many GCN sampling methods have been proposed recently. However, combining these with STGCNs degrades performance. This is primarily due to prediction biases introduced by each sampled subgraph, which analyze traffic states from a regional perspective. Addressing these challenges, we introduce a parallel STGCN framework called PaSTG. PaSTG divides the road network into regions, each processed by an individual STGCN in a device. To mitigate regional biases, Aggregation Blocks in PaSTG merge spatial-temporal features from each STBlock. This collaboration enhances traffic forecasting. Furthermore, PaSTG implements pipeline parallelism and employs a graph partition algorithm for optimized pipeline efficiency. We evaluate PaSTG on various STGCNs using three traffic datasets on multiple GPUs. Results demonstrate that our parallel approach applies widely to diverse STGCN models, surpassing existing GCN samplers by up to 57.4% in prediction accuracy. Additionally, the parallel framework achieves speedups of up to 2.87x and 4.70x in training and inference compared to GCN samplers.

Modified Model Predictive Control for Coordinated Signals along an Arterial under Relaxing Assumptions

This paper proposes modified model predictive control (MMPC) for coordinated signals, aiming to enhance a model’s fidelity to the realistic traffic environment by relaxing typical assumptions. We focus on the arterial, where every intersection is equipped with a dual-ring-barrier signal controller that complies with the standards of the National Electric Manufacturers Association. MMPC employs the store-and-forward model to describe traffic flow, thereby transforming the signal control problem into a model-based rolling-horizon optimization problem, in which the prediction horizon is composed of several future sample intervals, commonly equal to the cycle length. A radar detector is used to collect vehicle data upstream of the stop line at every sampling instant. The optimization problem is solved to minimize the number of vehicles within the prediction horizon, and the next timing plan is determined based on the optimization results. Constraints are added and modified in order to incorporate the typical relaxed assumptions in the optimization process. For this purpose, MMPC introduces a transition-free ring-barrier structure, vehicle distribution ratio, and percent arrival before the end of green. Simulation results indicate that coordination can be maintained by MMPC without the need for transitions, and the estimation of current and future traffic states can be improved with the assistance of modified constraints. Compared with benchmark techniques, MMPC offers superior vehicle progression for coordinated movement and significant improvements in delays, number of stops, and total travel time from a system-wide perspective, with an acceptable small increase in runtime.

An AI-Driven Intelligent Transportation System: Functional Architecture and Implementation

The surge in urbanization and the concomitant growth of the urban population have exacerbated issues such as traffic congestion and air pollution across cities globally. While Intelligent Transportation Systems (ITS) offer promise for im- proving urban mobility, existing solutions predominantly exhibit limitations in scalability and adaptability, thus falling short in delivering city-wide traffic management. This unaddressed gap necessitates the development of a robust, scalable, and adaptive system that can manage the intricacies of urban traffic. Our work introduces CityAI, an automated, AI-driven framework designed to operate on a city-wide scale. The system harvests data from diverse sensing infrastructures, employing machine learning algorithms to predict future traffic states and pat terns. Furthermore, it proposes real-time interventions, including adaptive traffic light control and V2X-based solutions. The architecture and components of CityAI not only incorporate state-of-the-art techniques but are also applied in real-world environments. The CityAI framework was implemented in the city of Pécs, Hungary, as a proof-of-concept ITS system. The framework enables city authorities to implement proactive measures, thus preventing traffic issues before they manifest. The paper focuses on practical development aspects of an ITS system undertaking R&D on new technologies, applications, and techniques which may facilitate future product development.

Evaluation of the impact of exclusive bus lanes on traffic in Tashkent

This study evaluates the impact of exclusive bus lanes on traffic in broader traffic networks over an extended timeframe. Using PTV Vissim to model existing traffic conditions, we introduced exclusive bus lanes and studied future traffic conditions considering a modal shift, as inferred from a binary logistic model developed using Stata. The findings reveal that, while exclusive bus lanes significantly enhance bus performance on designated streets, reducing travel time by 37%, they do not improve bus performance on other roads, as indicated by the unchanged levels of service (LOS) in the broader network. However, a modal shift analysis suggests a positive long-term effect on overall traffic, indicating that approximately 33% of car users may shift to using buses following the introduction of exclusive bus lanes. Origin-destination analysis revealed that exclusive bus lanes reduce intersection permeability, leading to congestion that varies based on the traffic flow direction.

Airspace Congestion, flow Relations, and 4-D fundamental Diagrams for advanced urban air mobility

This paper develops theoretical macroscopic air traffic flow models that relate vehicle density and spacing to traffic flow (throughput) measures under different operational parameters for unstructured airspace in the Advanced Air Mobility (AAM) context. Recognizing the role of conflicts in air traffic flow, we relate vehicle density to the frequency of conflict occurrence in airspace using a gas-kinetic analogy. The number of conflicts is then related to vehicle speeds using an average speed loss per conflict. The effects of the speed reductions are coupled with density to explore the fundamental diagram between flow rate and density. The theoretical models are tested and validated with simulated results for a number of parameter levels. The models can be applied for quick predictions of future traffic flow conditions, which will be especially useful for operators or air traffic flow management systems. The theoretical and simulated findings also provide operational and policy insights for AAM operators, planners, and modelers. Notable insights include the critical role of aircraft density in air traffic flow and the variable impact of that density on traffic flow behavior. AAM operators and planners will need to closely manage the airspace density to avoid large numbers of conflicts simultaneously and maintain acceptable travel times and throughputs. Key operational parameters such as aircraft spacing requirements and maximum aircraft speeds were also found to have significant impacts on traffic flow behavior, and offer policy avenues for managing air traffic.

Feasibility Study of a Motorcycle Lane: Evaluation of Travel Time and Delay Impacts at New Baneshwor Intersection

Like many South Asian countries, Nepal can be identified as a “Motorcycle Dependent Country” as the chief mode of transportation on the urban streets of Nepal compromises of Motorcycles for their daily commute. With inefficient public transportation, haphazard lane discipline, and easy accessibility and mobility of PTW, there is a rising dependence on PTW. The risk of life that comes with this dependence is also increasing in the urban streets of the country. Therefore, this research proposes Motorcycle Lanes as a measure to reduce congestion and create a risk-free riding environment. Three scenarios– a) Considering Dedicated motorcycle lanes b) Excluding right turning traffic into dedicated motorcycle lanes c) Dedicated motorcycle lanes only for two intersection legs Maitighar-Tinkune and Tinkune-Maitighar have been proposed, analyzed and compared with base data to measure the efficiency of motorcycle lanes at the New-Baneshwor intersection. The feasibility of those scenarios was checked based on traffic volume, Q-length, and vehicle delay with base data obtained from simulation in VISSIM. It was observed that difficult turning movements, unpredictable riding behavior and signal phases rendered the lanes unfeasible. A need for a holistic approach to address current and future traffic conditions as PTW are poised to experience a high upswing in foreseeable future is an essence.

Bidirectional Spatial-Temporal Adaptive Transformer for Urban Traffic Flow Forecasting.

Urban traffic forecasting is the cornerstone of the intelligent transportation system (ITS). Existing methods focus on spatial-temporal dependency modeling, while two intrinsic properties of the traffic forecasting problem are overlooked. First, the complexity of diverse forecasting tasks is nonuniformly distributed across various spaces (e.g., suburb versus downtown) and times (e.g., rush hour versus off-peak). Second, the recollection of past traffic conditions is beneficial to the prediction of future traffic conditions. Based on these properties, we propose a bidirectional spatial-temporal adaptive transformer (Bi-STAT) for accurate traffic forecasting. Bi-STAT adopts an encoder-decoder architecture, where both the encoder and the decoder maintain a spatial-adaptive transformer and a temporal-adaptive transformer structure. Inspired by the first property, each transformer is designed to dynamically process the traffic streams according to their task complexities. Specifically, we realize this by the recurrent mechanism with a novel dynamic halting module (DHM). Each transformer performs iterative computation with shared parameters until DHM emits a stopping signal. Motivated by the second property, Bi-STAT utilizes one decoder to perform the present → past recollection task and the other decoder to perform the present → future prediction task. The recollection task supplies complementary information to assist and regularize the prediction task for a better generalization. Through extensive experiments, we show the effectiveness of each module in Bi-STAT and demonstrate the superiority of Bi-STAT over the state-of-the-art baselines on four benchmark datasets. The code is available at https://github.com/chenchl19941118/Bi-STAT.git.

Engineering Traffic Prediction With Online Data Imputation: A Graph-Theoretic Perspective

Accurate and timely prediction about the current and near-term future traffic conditions is one of the effective ways to relieve traffic congestion and improve the operation efficiency of road networks. However, the missing data problem is inevitable when collecting real-time traffic flow information due to lossy communication and detector malfunction, which significantly affects the accuracy of prediction. To address this problem, in this article, we propose an approach to exploit online traffic prediction considering missing data effects. Unlike most existing methods imputing all the missing data before traffic prediction, the proposed strategy takes the spatio-temporal relationships between missing data and observed data into account to optimize data imputation patterns, thereby improving the efficiency of online traffic prediction. Specifically, we first propose an analytical framework for online traffic prediction with missing data by extending the space-time autoregressive integrated moving average model to incorporate missing data effects. Then, based on the combined use of optimal cut and data imputation optimization, a graph-theoretic technique is presented to determine the imputed data with consideration of road network topology and missing data pattern. Finally, experiments are conducted based on two real-world datasets. Experimental results indicate the superiority of the proposed approach in accuracy and efficiency compared with existing strategies of traffic flow prediction with missing data, particularly under the circumstance of high data missing ratios in urban road networks.

Software-Defined Network-Based Proactive Routing Strategy in Smart Power Grids Using Graph Neural Network and Reinforcement Learning

Smart power grid relies on sensors and actuators to provide continuous monitoring and precise control functions. Two types of data and command packets are associated with such field devices, namely, periodic fixed scheduling (FS) and emergency-related event-driven (ED) packets, which require different levels of quality-of-service (QoS) support. However, existing routing strategies in smart power grids are not adaptive to network conditions and cannot guarantee differentiated QoS support. To overcome this limitation, we propose a software-defined network (SDN) proactive routing framework in smart grids that takes into account the current and future state of the network while making the routing decisions. The proposed framework offers the following features: (a) It sets up separate queues for ED and FS packets, with higher priority for the ED queue; (b) It predicts the future traffic condition at each switch within the network (congested or not congested) using a graph-neural-network (GNN) model that provides an accurate prediction of the traffic condition despite the sparsity of the ED events; (c) It adopts a reinforcement learning (RL) strategy that establishes an ideal route and updates the queue service rate for each switch along the route following the network’s current and predicted future congestion condition. The proposed framework is tested on the cyber layers of the IEEE 14-bus and 39-bus test systems, and compared to two benchmarks. Our results indicate the superiority of our proposed framework compared with the benchmarks.

Floating Car Data–Based Short-Term Travel Time Forecasting with Deep Recurrent Neural Networks Incorporating Weather Data

The prediction of future traffic conditions represents a main building block for traffic management. With the advent of multiple traffic and environmental sensors, diverse data for predictions are available and models may incorporate not only traffic data but also additional aspects such as local weather conditions. A review of the state-of-the art methods in short-term traffic forecasting presented in this paper reveals that machine learning (ML) algorithms from the field of deep learning are occasionally used for forecasts based on historical traffic data, but not for traffic predictions including exogenous factors. Weather conditions represent an exogenous factor, which, for example, may affect travel times. This paper investigates how short-term travel time predictions may be improved by applying deep recurrent neural networks that incorporate weather data. Therefore, two hypotheses are formulated. Hypothesis 1 tests the prediction quality of the recurrent neural network (RNN) models, long short-term memory (LSTM), and gated recurrent unit (GRU) compared to the autoregressive moving average (ARMA) prediction method. The respective results indicate that the RNN models using historical traffic data and weather data show significant improvement compared to the ARMA model using only historical traffic data. Hypothesis 2 tests the prediction quality of LSTM and GRU compared to ML-based forecast models already in place in the field of traffic predictions, namely k-nearest neighbor (kNN), support vector regression (SVR), and neural networks (NN). In this context, the LSTM and GRU models using historical traffic data and weather data show significant improvement compared to the models kNN, SVR, and NN that also consider weather data. Despite the results presented in this work, there is still further potential for improvement. Thus, further research focusing on hyperparameter tuning of the RNN algorithms and the optimized selection of (additional) input variables with significant influence on travel times can contribute to further improvements of the forecast quality.

A Collaborative Method on Reversible Lane Clearance and Signal Coordination Control in Associated Intersection

To improve traffic efficiency and utilization of road resources and alleviate traffic congestion caused by imbalance of bidirectional traffic flow, in view of the conversion conditions of reversible lane function, the operating characteristics of associated intersections under dynamic reversible lanes are analysed in terms of capacity, and a reversible lane control model is constructed based on short-term traffic flow prediction. On this basis, the reversible lane segment clearing time and upstream and downstream signal control strategies under different states are studied. The collaborative control model of reversible lane clearing time and signal timing of associated intersections is established to obtain the optimal time for reversible lane function switching. Finally, using Chaoyang Road, Beijing, as an example, the effectiveness of the proposed model is verified by the simulation indexes of average vehicle delay and reversible lane clearing time. The results show that the optimized clearing efficiency exceeds 15% and the optimized average vehicle delay is reduced by more than 10%. Combined with the future traffic state, the traffic capacity and saturation flow are greatly improved, and the intelligent reversible lane control is better achieved.

Traffic demand prediction using a social multiplex networks representation on a multimodal and multisource dataset

In this paper, a meaningful representation of the road network using multiplex networks and a novel feature selection framework that enhances the predictability of future traffic conditions of an entire network are proposed. Using data on traffic volumes and tickets’ validation from the transportation network of Athens, we were able to develop prediction models that not only achieve very good performance but are also trained efficiently, do not introduce high complexity and, thus, are suitable for real-time operation. More specifically, the network’s nodes (loop detectors and subway/metro stations) are organized as a multilayer graph, each layer representing an hour of the day. Nodes with similar structural properties are then classified in communities and are exploited as features to predict the future demand values of nodes belonging to the same community. The results reveal the potential of the proposed method to provide reliable and accurate predictions.

A Dynamic Spatio-Temporal Deep Learning Model for Lane-Level Traffic Prediction

Traffic prediction aims to predict the future traffic state by mining features from history traffic information, and it is a crucial component for the intelligent transportation system. However, most existing traffic prediction methods focus on road segment prediction while ignore the fine-grainedlane-level traffic prediction. From observations, we found that different lanes on the same road segment have similar but not identical patterns of variation. Lane-level traffic prediction can provide more accurate prediction results for humans or autonomous driving systems to make appropriate and efficient decisions. In traffic prediction, the mining of spatial features is an important step and graph-based methods are effective methods. While most existing graph-based methods construct a static adjacent matrix, these methods are difficult to respond to spatio-temporal changes in time. In this paper, we propose a deep learning model for lane-level traffic prediction. Specifically, we take advantage of the graph convolutional network (GCN) with a data-driven adjacent matrix for spatial feature modeling and treat different lanes of the same road segment as different nodes. The data-driven adjacent matrix consists of the fundamental distance-based adjacent matrix and the dynamic lane correlation matrix. The temporal features are extracted with the gated recurrent unit (GRU). Then, we adaptively fuse spatial and temporal features with the gating mechanism to get the final spatio-temporal features for lane-level traffic prediction. Extensive experiments on a real-world dataset validate the effectiveness of our model.

Enhanced road information representation in graph recurrent network for traffic speed prediction

AbstractCorrectly capturing the spatial‐temporal correlation of traffic sequences will benefit to make accurate predictions of the future traffic states. In the paper, the methods of enhancing road spatial and temporal information representation are proposed. Firstly, the parameter matrix of each road is constructed to represent the road‐specific traffic patterns for the graph convolution neural network and the recurrent neural network. Then, the node embedding, and matrix factorization are used to reduce the scale of the parameter matrix. Secondly, the node embedding‐based Data Adaptive Graph Generation model was introduced to infer the indirect relationship of each node, and the gating mechanism is designed to control the weights of the direct spatial information and the indirect spatial information. Thirdly, to enhance the traffic sequence representation, the time tag and peak tag for the sequences are designed at each sampling moment. At last, the Enhanced Road Information Representation in Graph Recurrent Network (En‐GRN) is proposed to predict traffic speed, and the prediction performance is tested on SZ‐taxi and Los‐loop dataset. The experimental results show that the presented works are effective for improving traffic prediction accuracy.

DCENet: A dynamic correlation evolve network for short-term traffic prediction

Graph neural networks (GNNs) have been extensively employed in traffic prediction tasks due to their excellent capturing capabilities of spatial dependence. However, the majority of GNN-based approaches tend to employ static graphs, whereas they evolve over time and vary dynamics in real-world traffic situations. It is challenging to capture the dynamic spatial–temporal evolution characteristics of traffic data. To address this problem, we propose a dynamic correlation evolve network (DCENet) for short-term traffic prediction. To be specific, we develop a dynamic correlation self-attention (DCSA) module, which captures dynamic node associations adaptively. In this way, the model acquires new node embedding features without explicitly constructing a new graph structure. Then, an evolution encoder–decoder (EED) module is built to learn the interactions of dynamic features and output future traffic states. The experiments are conducted on two real-world datasets, and the results show that the DCENet outperformers baseline models for most of the cases.