To address the challenges of characterizing subway passenger flow fluctuations and overcoming the slow convergence and significant errors of existing intelligent optimization algorithms in tuning deep learning parameters for flow prediction, this study proposes a novel subway passenger flow fluctuation interval prediction model based on a Symmetry-Enhanced FIG-ICPO-XGBoost model. The core innovation is an Improved Cheetah Optimization Algorithm (ICPO), which incorporates enhancements including Circle mapping for population initialization, a hybrid strategy of dimension-by-dimension pinhole imaging opposition-based learning and Cauchy mutation to escape local optima, and adaptive variable spiral search with inertia weight to balance exploration and exploitation. The construction of this methodology embodies the concept of symmetry in algorithm design. For instance, Circle mapping achieves uniformity and ergodicity in the initial distribution of the population within the solution space, reflecting the symmetric principle of spatial coverage. Dimension-by-dimension pinhole imaging opposition-based learning generates opposite solutions through the principle of mirror symmetry, effectively expanding the search space. The adaptive variable spiral search strategy dynamically adjusts the spiral shape, simulating the symmetric relationship of dynamic balance between exploration and exploitation. Utilizing fuzzy-granulated passenger flow data (LOW, R, UP) from Harbin, the ICPO was employed to optimize XGBoost hyperparameters. Experimental results demonstrate the superior performance of the ICPO on 12 benchmark functions. The ICPO-XGBoost model achieves mean MAE, RMSE, and MAPE values of 10,291, 10,612, and 5.8%, respectively, for the predictions of the LOW, R, and UP datasets. Compared to existing models such as CPO-XGBoost, PSO-BiLSTM, GA-BP, and CNN-LSTM, these values represent improvements ranging from 4541 to 13,161 for MAE, 5258 to 14,613 for RMSE, and 2.6% to 7.2% for MAPE. The proposed model provides a reliable theoretical and data-driven foundation for optimizing subway train schedules and station passenger flow management.

Coordinated control across multiple signalized intersections is essential for mitigating congestion propagation in urban road networks. However, existing DQN-based approaches often suffer from unstable action switching, limited interpretability, and insufficient capability to model spatial spillback between adjacent intersections. To address these limitations, this study proposes a Policy-Regulated and Aligned Deep Q-Network (PRA-DQN) for cooperative multi-intersection signal control. A differentiable policy function is introduced and explicitly trained to align with the optimal Q-value-derived target distribution, yielding more stable and interpretable policy behavior. In addition, a cooperative reward structure integrating local delay, movement pressure, and upstream–downstream interactions enables agents to simultaneously optimize local efficiency and regional coordination. A parameter-sharing multi-agent framework further enhances scalability and learning consistency across intersections. Simulation experiments conducted on a 2 × 2 SUMO grid show that PRA-DQN consistently outperforms fixed-time, classical DQN, distributed DQN, and pressure/wave-based baselines. Compared with fixed-time control, PRA-DQN reduces maximum queue length by 21.17%, average queue length by 18.75%, and average waiting time by 17.71%. Moreover, relative to classical DQN coordination, PRA-DQN achieves an additional 7.53% reduction in average waiting time. These results confirm the effectiveness and superiority of the proposed method in suppressing congestion propagation and improving network-level traffic performance. The proposed PRA-DQN provides a practical and scalable basis for real-time deployment of coordinated signal control and can be readily extended to larger networks and time-varying demand conditions.