Distributed Data Processing Optimization Based on Edge Computing in Intelligent Transportation System

With the rapid development of intelligent transportation systems, the amount of data is growing exponentially, which puts higher demands on real-time processing and storage of data. In view of the limitations of the traditional centralized data storage mode, this study introduces consistent hash algorithm and edge computing to conduct distributed processing of ITS data. The results of removing outliers from the data showed that compared to the original data, the cleaned data stream appeared smoother, especially the abnormal fluctuation between 17:00 and 19:00 is effectively suppressed. In the comparative analysis of storage time and rate, when the number of files reached 14, 000, the storage time of the research scheme was only about 30 s, while the HDFS scheme required about 65 s. When the data exceeded 20 MB, the storage rate of the research plan could be maintained above 80 MB/s, while MongoDB maintained above 60 MB/s and HDFS maintained above 40 MB/s. Experiments show that the distributed intelligent transportation system with consistent hash algorithm and edge computing can effectively improve the efficiency of data processing. The research method can also reduce latency, alleviate the burden on central data centers, enhance data security, and provide more accurate and efficient services for urban transportation.