The management of large-scale events poses significant resilience challenges to urban traffic systems, where classical computational methods often prove inadequate for the resulting complex, dynamic optimization problems. This paper introduces a quantum-enhanced hybrid high-performance computing framework designed to improve traffic resilience during such events. The framework leverages a Quantum Annealing (QA) algorithm to solve a Quadratic Unconstrained Binary Optimization (QUBO) model of key traffic optimization tasks, integrated with classical computing for data processing and workflow control. Using the traffic management for a major concert at Hefei Luogang Park as a case study, we focus on modeling and applying this framework to two core resilience problems: Dynamic Evacuation Route Optimization (DERO) and Emergency Resource Allocation (ERA). Our simulation results provide empirical validation of the framework's effectiveness, demonstrating that the proposed quantumenhanced approach reduces total evacuation time by 20.0 % and average emergency response time by 32.2 % compared to welldefined greedy heuristics. These findings highlight the potential of quantum computing as an emerging high-performance computing paradigm for addressing the intricate challenges of traffic resilience.

The proliferation of Unmanned Aerial Vehicles (UAVs) for urban public safety is critically hindered by operational risks inherent in complex environments. To address these challenges, this paper introduces a “UAV-as-a-Service” (UaaS) paradigm, an application paradigm innovation that leverages the core infrastructure of telecom operators. Our primary contribution is a closed-loop intelligent method, representing an algorithmic innovation, centered on a 3D Dynamic Risk Map (DRM). The DRM is generated in real-time by a Dynamic Bayesian Network (DBN) and explicitly informs both a risk-aware Multi-Agent Reinforcement Learning (MARL) dispatcher and a hybrid Rapidly-exploring Random Tree Star (RRT*)-Model Predictive Control (MPC) path planner. This tight coupling ensures that tactical decisions are grounded in a holistic understanding of risk. Simulation results demonstrate that the proposed UaaS model substantially enhances operational outcomes, reducing the time to achieve critical situational awareness by over 75 % and decreasing firefighter risk exposure by$\mathbf{7 8 \%}$. These technical advancements validate a novel and viable Business-to-Government (B2G) service model, demonstrating significant technologycommercial synergy.

The escalating adoption of electric vehicles (EVs) presents a critical challenge for urban planning: the strategic placement of charging infrastructure, especially when integrating intermittent renewable energy. Existing approaches to this problem often rely on time-series models that neglect spatial dependencies, or they employ simplistic weighted-sum optimizations that fail to resolve the conflicting interests of diverse stakeholders. To overcome these limitations, we introduce a novel Hierarchical Spatio-Temporal Graph Neural Network (H-STGNN) framework. This framework integrates two core components: (1) a Spatio-Temporal Graph Neural Network (ST-GNN) that leverages fine-grained mobile operator data to accurately forecast charging demand by capturing complex spatio-temporal correlations across a city-wide graph. (2) a hierarchical multi-objective optimization model, solved by the NSGA-II algorithm, to generate Pareto-optimal placement strategies. Our model prioritizes maximizing renewable energy consumption and grid stability at a strategic level, while optimizing user convenience and operator profitability at an operational level. Experiments on a large-scale, real-world dataset from Hefei, China, show that our ST-GNN reduces prediction error (MAE) by over 25% compared to state-of-theart baselines. The resulting placement strategies increase renewable energy utilization by over 18% and reduce user generalized costs by 12%, offering a robust and scalable solution for green urban transportation planning.