traffic engineering

Calibrating traffic flow models for large-scale metropolitan highway networks remains challenging due to sparse, low-resolution sensor data and computational intractability of conventional black-box optimization methods. Method: This paper proposes a path-level travel time–driven demand calibration framework tailored for high-resolution stochastic traffic microsimulators. Unlike traditional link-based approaches relying on sparse detector data, our method employs an interpretable, sample-efficient, path-oriented calibration strategy that avoids heuristic black-box optimizers (e.g., SPSA). Contribution/Results: We demonstrate the first systematic, scalable calibration across six metropolitan networks and 54 diverse scenarios. The framework significantly improves cross-network generalizability and achieves an average 43.5% gain in fitting accuracy over SPSA (up to 80.0%), while drastically reducing simulator evaluations. This establishes a novel paradigm for real-time, large-scale dynamic network calibration.

This study addresses the limitation of conventional microsimulation in faithfully reproducing transient traffic wave dynamics. We propose a data-driven co-simulation framework integrating CARLA with high-fidelity trajectory data from the I-24 MOTION dataset. Our method introduces a boundary-condition-driven mechanism—leveraging ghost cells, autonomous vehicle generation, and configurable vehicle dynamics models—to reconstruct spatiotemporal traffic states end-to-end. To our knowledge, this is the first implementation of measurement-based, boundary-driven simulation within CARLA, overcoming the constraints of localized car-following models and enabling microscale emergence of macroscopic traffic phenomena. Experiments successfully replicate the formation, propagation, and dissipation of traffic waves under both high- and low-density conditions, achieving significantly improved spatiotemporal fidelity. The framework provides a high-fidelity simulation environment for evaluating traffic control strategies and validating autonomous vehicle perception systems.

This study addresses the challenge of holistically evaluating urban traffic control policies, where direct effects—such as changes in traffic flow and emissions—are intricately intertwined with indirect effects, including behavioral responses and shifts in economic accessibility. To this end, the authors propose a multilayer urban mobility simulation framework that integrates a physical layer (modeling traffic dynamics and emissions) with a social layer (capturing user behavioral responses). The framework leverages real-world data to instantiate scenarios, encode policy parameters, and formalize behavioral assumptions, thereby enabling systematic comparison and forward-looking assessment of diverse “what-if” policy scenarios. Applied to vehicle restriction policies, the approach effectively uncovers the interactive mechanisms between policy design and user feedback, offering actionable insights for developing more anticipatory and coordinated transportation policies.

Traffic assignment is computationally expensive and impractical for real-time applications, especially on large-scale road networks. To address this, we propose an interpretable meta-model based on Message Passing Neural Networks (MPNNs), the first to align Graph Neural Network (GNN) architecture with the logic of Stochastic User Equilibrium (SUE) solving—directly mapping origin-destination (OD) demands to equilibrium flows without iterative simulation. The model takes a traffic graph as input and explicitly encodes path-choice behavior and flow allocation mechanisms, substantially improving out-of-distribution generalization. Experiments demonstrate that our approach reduces computational time by over 90% while preserving prediction accuracy, enabling real-time analysis on large-scale networks. Moreover, it exhibits strong robustness across distributionally shifted scenarios, overcoming the limited extrapolation capability typical of purely data-driven models.

This study addresses energy efficiency optimization in communication networks during low-traffic periods by jointly optimizing network topology design and shortest-path routing. The approach ensures that all traffic demands can be satisfied within the activated subnetwork through dynamically adapted shortest paths. The authors propose, for the first time, a capacitated integer linear programming model that precisely captures dynamic shortest-path routing, complemented by provably effective strengthening constraints to accelerate solution convergence. A tailored column generation algorithm is developed to efficiently handle large-scale instances. Experimental results demonstrate that a simplified strategy—fixing routes and deactivating redundant links—achieves near-optimal performance, while the traffic-oblivious method TOCA exhibits superior efficacy in multi-demand scenarios.

This study addresses the accuracy limitations of network simulation in research on the Differentiated Services (DiffServ) architecture by proposing a hybrid validation methodology that integrates real-world experimentation with simulation. The authors deploy representative scenarios in a physical testbed and replicate identical configurations in a re-engineered simulation environment, enabling systematic comparison of key performance metrics. To enhance fidelity, they substantially refactor the DiffServ modules of widely used network simulators, significantly improving their modeling capabilities. Their findings demonstrate that uncalibrated simulations can yield misleading conclusions in advanced networking studies. The proposed approach not only exposes critical shortcomings in current simulation practices but also offers a practical, actionable pathway toward higher simulation accuracy for DiffServ-based research.

To address insufficient traffic simulation fidelity and ambiguous requirement specifications in driving simulators, this paper proposes a systematic traffic simulation requirement analysis method based on sub-goal decomposition. The experimental objective is hierarchically decomposed into verifiable sub-goals—including microscopic traffic modeling, agent behavioral modeling, and visual rendering—thereby establishing a structured, traceable mapping from research objectives to simulation configuration. This method establishes, for the first time, an explicit linkage between traffic simulation design and underlying experimental goals, significantly enhancing simulation fidelity, experimental validity, and participant immersion. Empirical evaluation demonstrates that the proposed framework supports high-fidelity development and human–autonomy interaction testing of autonomous driving systems.

This work addresses the design of potential flow networks—a class of optimization problems that are significantly harder than classical network flow due to their inherent nonlinearity. The paper presents the first effective approximation algorithm framework for this problem by introducing a refined reduction to well-studied combinatorial optimization problems such as constrained shortest paths, thereby enabling efficient solutions through existing algorithmic techniques. The study establishes matching complexity lower bounds that precisely delineate the approximability frontier of the problem and further demonstrates the NP-hardness and inapproximability of several key variants. Collectively, these results provide a comprehensive characterization of the computational complexity and algorithmic tractability of potential flow network design.

To address the challenge of high-fidelity, flexible environment simulation in mobile network planning and optimization, this paper proposes the first generative world model tailored for mobile wireless networks. Built upon a diffusion-based architecture, the model jointly encodes heterogeneous multi-source data (e.g., base stations, user equipment, sensors) and multimodal inputs (time-series and image modalities), while incorporating spatiotemporal context, user behavior patterns, and optimization policies as conditional factors—enabling controllable generation of both network-element-level and system-level performance metrics. Compared to conventional approaches, our model exhibits superior generalization capability and policy controllability. In cooperative energy-saving scenarios, it significantly improves the efficiency of base station sleep scheduling and user offloading decisions, achieving a measured 18.7% reduction in energy consumption. This demonstrates its effectiveness and practicality for low-cost, high-fidelity network simulation.

Urban Air Mobility (UAM) faces significant scalability challenges due to high infrastructure costs and complex air-ground coordination. To address this, this paper proposes an air-ground integrated UAM network modeling and optimization framework leveraging existing regional airports. We develop LPSim—a large-scale parallel simulation platform—that uniquely integrates multi-GPU acceleration, demand-balancing search algorithms, dynamic scheduling of heterogeneous electric vertical take-off and landing (eVTOL) fleets, and coupled ground shuttle systems. By jointly optimizing demand forecasting, fleet composition, and multimodal connectivity, the approach substantially lowers deployment barriers. Empirical evaluation in the San Francisco Bay Area demonstrates an average travel time reduction of 20.7 minutes across 230,000 trips, validating the “light-infrastructure, strong-coordination” paradigm. This work provides a scalable methodology and technical foundation for transitioning UAM from conceptual exploration to practical, operationally viable deployment.