Compression algorithm of road traffic data in time series based on temporal correlation

Abstract

The numerous applications of urban traffic detection technology in road traffic data acquisition bring new challenges for transportation and storage of road traffic big data. The travel demand and travel time of travel participants present certain specific regularity; thus, a compression algorithm for road traffic data in time series based on temporal correlation was proposed in this study. First, the temporal correlation of the road traffic data in time series was analysed. Second, the reference sequences of road traffic characteristics were constructed to acquire the base data under different modes. Third, the training data under the same mode were extracted to acquire the difference data between training and base data. Then the optimal threshold of the difference data was trained. Fourth, the optimal threshold was introduced into the difference data between real-time and base data in time series, combining with Lempel-Ziv-Welch (LZW) encoding to achieve the compression of difference data. Finally, the reconstruction of real-time road traffic data in time series was accomplished based on LZW decoding technology. Six typical road segments in Beijing were adopted for case studies. The final results prove the feasibility of the algorithm, and that the reconstructed data can achieve high accuracy.