[Paper Review] A Compressive Sensing Approach for Connected Vehicle Data Capture and Recovery and its Impact on Travel Time Estimation

Lei Lin, Weizi Li+1 more|arXiv (Cornell University)|Jun 26, 2018

Sparse and Compressive Sensing Techniques18 references3 citations

TL;DR

This paper proposes a compressive sensing (CS) framework for real-time compression and accurate recovery of connected vehicle (CV) data, enabling efficient storage and communication while maintaining high fidelity for travel time estimation. It achieves up to 65% reduction in travel time estimation error and sub-0.05 root-mean-squared error in speed data recovery, even at low compression ratios, reducing OBU hardware costs.

ABSTRACT

Connected vehicles (CVs) can capture and transmit detailed data such as vehicle position and speed through vehicle-to-vehicle and vehicle-to-infrastructure communications. The wealth of CV data provides new opportunities to improve safety and mobility of transportation systems. However, it is likely to overburden storage and communication systems. To mitigate this issue, we propose a compressive sensing (CS) approach that allows CVs to capture and compress data in real-time and later recover the original data accurately and efficiently. The approach is evaluated using two case studies. In the first study, we use this approach to recapture 10 million CV Basic Safety Message (BSM) speed samples. It can recover the original speed data with root-mean-squared error as low as 0.05. We also explore recovery performance for other BSM variables. In the second study, a freeway traffic simulation model is built to evaluate the impact of this approach on travel time estimation. Multiple scenarios with various CV market penetration rates, On-board Unit (OBU) capacities, compression ratios, arrival rate patterns, and data capture rates are simulated. The results show that the approach provides more accurate estimation than conventional data collection methods, through up to 65% relative reduction in travel time estimation error. Even when the compression ratio is low, the approach can provide accurate estimation, thereby reducing OBU hardware costs. Further, it can improve accuracy of travel time estimation when CVs are in traffic congestion as it provides a broader spatial-temporal coverage of traffic conditions and can accurately and efficiently recover the original CV data.

Motivation & Objective

• To address the data overload challenge in connected vehicle systems due to high-volume, real-time data from CVs.
• To develop a real-time data compression and recovery method that preserves data fidelity for transportation applications.
• To evaluate the impact of CS-based CV data handling on travel time estimation accuracy under varying market penetration and system constraints.
• To reduce OBU hardware costs by enabling effective data compression without sacrificing estimation performance.

Proposed method

• The study employs compressive sensing (CS) to sample and compress CV data, such as Basic Safety Messages (BSMs), at a sub-Nyquist rate.
• A sparse representation of CV data is assumed, leveraging temporal and spatial correlation in vehicle speed and position for efficient compression.
• Orthogonal matching pursuit (OMP) is used as the reconstruction algorithm to recover original data from compressed measurements.
• The framework is validated using real BSM data from 10 million samples and a freeway traffic simulation model with variable market penetration and OBU capacity.
• Compression ratios are varied to assess trade-offs between data reduction and estimation accuracy.
• Travel time estimation is performed using recovered data, and results are compared against conventional data collection methods.

Experimental results

Research questions

• RQ1 How accurately can compressive sensing recover original CV data, particularly speed, from compressed measurements?
• RQ2 What is the impact of varying compression ratios on travel time estimation accuracy in real-world traffic scenarios?
• RQ3 How does the proposed CS approach compare to conventional data collection in terms of estimation error reduction?
• RQ4 To what extent does the method maintain accuracy under low CV market penetration and limited OBU storage capacity?
• RQ5 Can the CS framework reduce OBU hardware costs while preserving data fidelity for traffic monitoring applications?

Key findings

• The CS approach recovers CV speed data with a root-mean-squared error as low as 0.05, demonstrating high fidelity even at high compression rates.
• Travel time estimation error is reduced by up to 65% compared to conventional data collection methods when using the CS framework.
• Accurate travel time estimation is maintained even at low compression ratios, enabling cost-effective OBU deployment with reduced hardware requirements.
• The method improves estimation accuracy during traffic congestion by providing broader spatial-temporal coverage of traffic conditions.
• Recovery performance is robust across different BSM variables, indicating generalizability beyond speed data.
• The framework enables efficient data capture and recovery, making it suitable for real-time transportation monitoring systems.