Real-time map matching method based on GPU and Spark hybrid parallel computing architecture
A map matching and parallel computing technology, applied in the field of digital navigation, to improve efficiency, improve performance, and reduce matching delays
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0043] Such as Figure 1 to Figure 2 As shown, a real-time map matching method based on GPU and Spark hybrid parallel computing architecture is provided in this embodiment,
[0044] S1. Divide the road network into grids, and superimpose the roads in the road network into each grid, intercept the road segments in each grid, and calculate the distance from each road segment to the original road starting and ending points; Road segments in the same grid are summarized into the same set of data structures as candidate roads;
[0045] S2. Calculate the shortest network distance between each road in the road network and other adjacent roads, and summarize it into a network distance table;
[0046] S3. Input a batch of GPS points to be matched, obtain its corresponding grid number according to the batch of GPS points to be matched, merge the batch of GPS points to be matched with the corresponding grid number, and call CUDA program;
[0047] S4. Calculate and output the matching ...
Embodiment 2
[0086] The present invention is deployed on three ecs.gn5-c8g1.2xlarge servers of Alibaba Cloud. This type of cloud server contains 1 NVIDIA P100 GPU core. At the same time, on these three servers, a Spark Standalone cluster was built for program operation. The road network data uses the road data of Haidian District, Beijing. The road network data includes roads of various levels, such as expressways, urban expressways, urban ordinary roads, etc. Since the taxi data has trajectories on all roads, the road Road grades are not differentiated, but treated uniformly. Using taxi GPS points for map matching, the calculation efficiency reaches 7570 points / second. In contrast, using Storm for performance analysis of streaming map matching, the report system processing performance is only 100-150 points / second.
[0087] By adopting the above-mentioned technical scheme disclosed by the present invention, the following beneficial effects are obtained:
[0088] The present invention p...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


