An increasing number of vehicles are now equipped with GPS devices to facilitate fleet management and send their GPS locations continuously, generating a huge volume of trajectorydata. Sending and storing such vehicl...
详细信息
An increasing number of vehicles are now equipped with GPS devices to facilitate fleet management and send their GPS locations continuously, generating a huge volume of trajectorydata. Sending and storing such vehicle trajectorydata cause sustainable communication and storage overheads. trajectory data compression becomes a promising way to alleviate overhead issues. However, previous solutions are commonly carried out at the side of the data center after data having been received, thus saving the storage cost only. Here, we bring the idea of mobile edge computing and transfer the computation-intensive datacompression task to the mobile devices of drivers. As a result, the trajectorydata is reduced at the side of data generators before being sent out;thus, it can lower data communication and storage costs simultaneously. We propose DAVT, an error-bounded trajectorydata representation, and a compression framework. Specifically, the trajectorydata is reformatted into three parts (i.e., Distance, Acceleration & Velocity, and Time), and three compressors are wisely devised to compress each part. For D and AV parts, a similar Huffman tree-forest structure is exploited to encode data elements effectively, but with quite different rationales. For the T part, the large absolute timestamps are transformed to small time intervals firstly, and different encoding techniques are adopted based on the data quality. We evaluate our proposed system using a large-scale taxi trajectorydataset collected from the city of Beijing, China. Our results show that our compressors outperform other baselines.
This paper proposes a methodology combining Long-Short-Term-Memory (LSTM)-assisted kinematic motion prediction with a hybrid coding algorithm for compressing the trajectorydata of Connected Autonomous Vehicles (CAVs)...
详细信息
This paper proposes a methodology combining Long-Short-Term-Memory (LSTM)-assisted kinematic motion prediction with a hybrid coding algorithm for compressing the trajectorydata of Connected Autonomous Vehicles (CAVs). The vehicle locations after the first two time steps are predicted based on the vehicle positions at the first two time steps and the kinematic equation. The vehicle velocities and accelerations are predicted based on the vehicle locations and LSTM. The hybrid coding algorithm integrates differential coding, Binary Coded Decimal (BCD) coding and arithmetic coding. Differential coding converts the original data into the difference between the original data and the predicted data. Since the length of the original data is large but the difference between it and predicted data is small, the required space for storing the data can be greatly reduced. BCD coding converts subsequences of different lengths to the subsequences with the same length so that the original information can be correctly reproduced after decompression. Arithmetic coding expresses the information in small space by converting the character sequence into a decimal between 0 and 1. The proposed algorithm is evaluated on the Next Generation Simulation trajectorydataset. The experiment results show that the compression ratio and compression rate obtained by the proposed algorithm are respectively higher and lower than those obtained by the baseline algorithms. Also, the sum of compression time, decompression time and transmission time associated with the proposed algorithm is less than that associated with most baseline algorithms and transmission without compression.
暂无评论