Bus delays significantly affect urban public transportation by reducing operational efficiency and incurring high costs. Understanding the causes of these delays is essential for developing targeted mitigation strategies. While traditional research focuses on correlation-based analysis, it often fails to uncover the underlying causal mechanisms. This study examines various causal graph discovery algorithms combined with structural equation models (SEMs) to infer the causal relationships among factors that affect bus delays. These algorithms generate causal graphs for bus delays, revealing the interrelations and impacts of various operational factors. SEM is used to quantify the causal effects. This study evaluates the performance of these algorithms from the perspectives of both the statistical data fitting and the causal relationships generated. A case study is conducted using General Transit Feed Specification (GTFS) data from frequent bus routes in Stockholm, Sweden. The validation results demonstrate the effectiveness of data-driven causal discovery models in identifying causal links, particularly when combined with domain knowledge. The empirical analysis shows the complexity of factors contributing to bus delays, emphasizing the necessity of integrating causality into bus delay analysis. For example, a high correlation between origin delay and bus arrival delay (coefficient = 0.63) does not indicate direct causation, and a strong causation between dwell time and arrival delay does not imply a higher correlation (coefficient = 0.12). Comparing variable importance with linear regression (LR) reveals notable differences; origin delay, which is often overlooked by previous studies, is significant in the causal graph model (standardized coefficient = 0.601) but ranks much lower in LR (standardized coefficient = 0.003). These insights underscore the importance of automated, data-driven causal discovery in enhancing decision-making processes and improving the efficiency and reliability of transit services.
The growing energy and carbon footprint of large-scale radio access network (RAN) has made green operation an increasingly important infrastructure-level problem. Existing research has advanced downstream energy-saving control, yet comparatively less attention has been paid to upstream decisions on where limited operational resources and energy-saving capabilities should be deployed. A key challenge is that energy, traffic, spatial coverage, and technical--operational features are heterogeneous in form and difficult to compare within a unified cell-level decision space. This paper proposes an interpretable, decision-conditioned operational-value profiling and prioritization framework for upstream green RAN decision support. It transforms heterogeneous historical evidence into comparable cell-level value representations and adapts priority formation to decision contexts and resource constraints. The framework is evaluated using two years of real commercial-network data covering 19,796 cells and 403,602 directed coverage relationships. Seven rolling 90-day out-of-time cycles provide large-scale offline validation across changing network conditions. Relative to the operator rule, the proposed method increases the eligible-cohort deployment rate by 10.2 percentage points and cell-averaged energy saving by 29.8\%, while reducing four operational-risk rates by 1.99--3.37 percentage points. Live deployments in ten preselected high-complexity multi-coverage regions further preserve the expected improvement directions in benefit, risk control, and overall operational value. These results indicate that upstream operational-value prioritization can improve resource allocation and role coordination in complex RAN environments and provide actionable guidance for downstream green control.
12 May 2026 in Transportation Research Part C: Emerging Technologies