Federated Learning Approach for Multi-Regional Traffic Flow Prediction

FedTT: A Federated Spatio-Temporal Learning Framework for Cross-City Traffic Knowledge Transfer

Traffic prediction aims to forecast future traffic conditions from historical spatio-temporal data. In practice, many cities face limited traffic data due to incomplete sensing infrastructures, making accurate prediction difficult. Federated traffic knowledge transfer offers a promising solution by allowing data-rich source cities to assist data-scarce target cities while keeping local data private. However, existing methods still face key challenges, including cross-city distribution discrepancies, incomplete or noisy observations, and potential privacy leakage from shared gradients or model parameters during federated optimization. To this end, we propose FedTT, a federated spatio-temporal learning framework for cross-city traffic knowledge transfer. FedTT features three co-designed components: (i) a Traffic Domain Adapter (TDA) that explicitly aligns heterogeneous traffic data distributions across cities to improve transfer effectiveness, (ii) a Traffic View Imputation (TVI) module that enhances data quality by completing missing traffic observations through spatio-temporal dependency modeling, and (iii) a lightweight Traffic Secret Aggregation (TSA) protocol that enables attack-resistant knowledge aggregation with formal privacy analysis, without relying on heavy cryptographic primitives. Extensive experiments on four real-world traffic datasets demonstrate that FedTT consistently outperforms 18 state-of-the-art baselines, achieving improved prediction accuracy while maintaining strong empirical resistance to attacks.

Adaptive Parameter-Harmonized Dynamic Hypergraph Spatio-Temporal Prediction for Distributed Traffic Scenarios

Traffic flow prediction is a critical task in Intelligent Transportation Systems (ITS), essential for alleviating traffic congestion and optimizing resource allocation. While graph neural network-based methods have achieved significant success in modeling pairwise relationships between nodes, they often struggle to capture the dynamic, high-order spatio-temporal dependencies inherent in traffic networks. Furthermore, in distributed real-world scenarios, data heterogeneity among different clients often leads to negative transfer in traditional federated learning methods, thereby limiting model performance. To address these challenges, this paper proposes a novel Adaptive Parameter Coordination Dynamic Hypergraph Spatio-Temporal Prediction (ADH-STPC) framework for decentralized learning. This framework centers on the Client-Adaptive Parameter Sharing (CAPS) module, which coordinates decentralized collaboration by quantifying the similarity of global and local feature distributions, ensuring that parameter propagation occurs only between compatible clients, thereby suppressing negative propagation. Additionally, to accurately predict changes in traffic flow, we designed the Dynamic Hypergraph Convolution Architecture (DHCGA), which captures higher-order nonlinear dependencies by adaptively evolving hypergraph structures, thereby uncovering latent relationships among features. CAPS provides the core topology for adaptive collaboration, while DHCGA captures spatio-temporal traffic features, and together they drive the model to achieve optimal performance. Extensive experiments on two large-scale real-world traffic datasets validate the effectiveness of this framework. Compared to existing state-of-the-art baseline models, ADH-STPC demonstrates superior performance: achieving significant reductions across all key metrics on the BJSubway dataset, including a 15.1% decrease in MAE, a 15.2% reduction in RMSE, and a 7.1% improvement in MAPE.

FedTP: A Federated Learning Framework for Traffic Prediction

FedTraffic: A Hierarchical Federated Learning Framework for Traffic Flow Prediction in Intelligent Transportation Systems

The rapid growth of Intelligent Transportation Systems (ITSs) and Internet of Things (IoT) technologies has generated massive volumes of distributed traffic data, creating significant challenges related to privacy, scalability, communication overhead, and heterogeneous traffic patterns. To address these challenges, this paper proposes FedTraffic, a hierarchical federated learning framework for traffic flow forecasting that integrates Edge–Fog–Cloud computing, hybrid deep learning, adaptive federated optimization, and Explainable Artificial Intelligence (XAI). The proposed framework combines a Temporal Convolutional Network–Conditional Variational Autoencoder (TCN–CVAE) with traffic-behavior clustering, adaptive client selection, and hierarchical model aggregation to enable accurate, privacy-preserving, and interpretable traffic prediction under heterogeneous non-IID environments. Extensive experiments demonstrate that FedTraffic achieves a best Mean Absolute Error (MAE) of 2.12, a Root Mean Square Error (RMSE) of 4.28, a Mean Absolute Percentage Error (MAPE) of 5.47%, and an R2 score of 0.966. Compared with the strongest federated baseline, it improves MAE by up to 18.77%, RMSE by 16.41%, and MAPE by more than 22%, while reducing communication overhead through an 8:1 latent representation compression ratio. These results demonstrate the effectiveness of FedTraffic as a scalable, privacy-preserving, and interpretable solution for next-generation intelligent transportation systems.

Intelligent Traffic Path Recommendations Using Machine Learning based Temporal Feature Aggregation and Time Series Based Graph Routing

Urban transportation networks generate massive volumes of spatio-temporal data, and the effective exploitation of such data to enable intelligent route recommendations has become a critical priority in smart city development. Existing systems predominantly rely on static or short-horizon prediction models that fail to capture the complex, non-stationary dynamics characterizing real-world vehicular traffic, particularly under congestion-prone conditions in densely populated urban corridors. The challenges are further compounded by high-dimensional, noisy, and heterogeneous sensor data that makes robust feature extraction and temporal modeling particularly difficult, as traditional approaches exhibit poor generalization across varying prediction horizons and traffic regimes. This research proposes an integrated framework for traffic path recommendation that combines systematic feature extraction, temporal prediction, and dynamic graph-based routing. The methodology begins with the Feature Extraction for Vehicular Traffic Time Series (FEVTTS) algorithm, which applies Mutual Information, Random Forest Regression, and Correlation Coefficient analysis to derive an optimal, low-redundancy feature set from raw sensor data. The refined features are then fed to the Temporal Traffic Feature Aggregation Algorithm (TFTAA), which integrates short-term and long-term traffic patterns using a rolling window mechanism to produce accurate multi-horizon forecasts. Finally, the predicted traffic variables are embedded as dynamic edge weights into a Time Series Based Graph (TSBG), on which Dijkstra's algorithm computes optimal time-dependent routes. The proposed TFTAA algorithm employs a hybrid statistical and ensemble machine learning design, incorporating SARIMAX for seasonal decomposition and gradient-boosted residual correction using XGBoost, augmented by quantile regression for uncertainty quantification. The framework was validated using the London Traffic Dataset (Highways England) and a locally collected Pune city dataset comprising 26,785 and 25,920 samples, respectively, across diverse road types. TFTAA consistently outperformed SARIMAX and XGBoost baselines at all evaluated prediction horizons from 5 to 60 minutes, achieving a Mean Absolute Error (MAE) of 2.1 at the 5-minute horizon and 14.3 at the 60-minute horizon, compared to 25.1 for SARIMAX at the same horizon. The TSBG-based routing reduced average travel time by an average of 18.3% over static Dijkstra across 15 test days on the London dataset. The proposed framework demonstrates that tightly coupling predictive traffic modeling with dynamic graph routing yields measurable improvements in route efficiency over baseline approaches. The research advances the state of the art in intelligent transportation systems by providing a scalable, feature-engineered, and prediction-integrated path recommendation solution applicable to both developed and emerging urban road networks.

Traffic congestion management using attention based federated hybrid deep learning model in Vehicle-to-Everything (V2X) systems