This research aims to address the challenges of tunnel ventilation in high-altitude areas by proposing a novel feedforward ventilation strategy based on the Autoregressive Integrated Moving Average (ARIMA) model. By predicting ventilation needs and integrating real-time air quality monitoring, it optimizes air flow and quality within the tunnel, making it particularly suitable for the low oxygen, extreme climates, and complex geological conditions prevalent in high-altitude areas. The research methods include the construction and adjustment of the ARIMA model, optimizing the operation of the ventilation system through preprocessing of environmental parameter data and time series forecasting. Integrating a smart sensor network, the study achieves high accuracy in data input, thereby enhancing prediction accuracy. The results demonstrate that compared to traditional ventilation methods, this strategy significantly improves ventilation efficiency and reduces energy consumption. Overall, this research offers a new perspective on optimizing ventilation strategies for high-altitude internal combustion traction tunnels and showcases the immense potential of the ARIMA model in practical engineering applications. Through precise prediction of ventilation needs combined with real-time monitoring, the study significantly improves air quality within the tunnel, reduces energy consumption, and enhances the overall performance of the ventilation system.