Optimization of Urban Traffic Signal Control System on Hadoop Platform Based on Privacy Computing

 With the acceleration of urbanization, the number of motor vehicles has surged, and problems such as urban traffic congestion, low traffic efficiency, and resource waste have become increasingly prominent. Traditional traffic signal control systems rely on fixed allocation or simple sensing control, which cannot adapt to the dynamic changes in traffic flow and cannot meet the needs of refined control. This article aims to leverage the Hadoop platform empowered by privacy computing, balance the efficiency of processing massive traffic data with data privacy and security, optimize urban traffic signal control strategies, and enhance traffic operation efficiency and intelligent control level. In terms of methods, firstly, multi-dimensional traffic data such as traffic flow, speed, and queue length are collected through traffic detectors, monitoring devices, etc., and sensitive traffic data is desensitized and encrypted using privacy computing technology. Combining HDFS distributed storage technology on the Hadoop platform to achieve secure data storage and compliant calling, utilizing components such as MapReduce and Spark to perform data cleaning, mining, and analysis under privacy protection, and constructing a traffic flow prediction model. Based on the predicted results, design a dynamic signal timing optimization algorithm to replace the traditional fixed timing mode. The results show that the optimized traffic signal control system can respond to changes in traffic flow in real time, effectively shorten the average queuing time of vehicles by 15% -25%, improve intersection traffic efficiency by about 20%, reduce vehicle idle fuel consumption and exhaust emissions, and achieve the coordinated promotion of traffic data privacy and security and data utilization. The Hadoop platform empowered by privacy computing can efficiently and securely process massive heterogeneous sensitive data in urban transportation, providing reliable data support, privacy protection, and technical support for traffic signal control optimization. The proposed optimization strategy can effectively alleviate traffic congestion and enhance the intelligence and refinement level of urban traffic control.