Big Data in Urban Traffic Management: Current Applications, Challenges, and Future Directions

Abstract

The integration of big data analytics represents a pivotal paradigm shift, moving urban traffic governance from traditional reactive models to proactive, intelligent systems. Through a comprehensive and systematic review of contemporary research literature, this paper synthesizes the current state of the field. It examines prominent applications, such as adaptive signal control and smart parking, and delineates their transformative benefits in reducing congestion, minimizing vehicle emissions, and enhancing overall urban mobility. The review then critically analyzes the persistent challenges that impede widespread implementation, primarily the foundational issues of data quality and integrity, the operational constraints of partial connectivity, and the critical privacy risks that can erode public trust. The significance of this research lies in its dual contribution: it informs the academic community by structuring existing knowledge and identifying crucial research gaps, while simultaneously providing actionable, data-driven insights for policymakers and urban planners. Conclusively, the paper outlines promising future directions, emphasizing the shift towards deep reinforcement learning for holistic network-wide optimization and the imperative of developing resilient, secure data ecosystems that are both efficient and trustworthy.