Efficient Road Traffic Estimation for Proactive Beam Allocation in an ISAC Setup

被引:0
作者
Al Amiri, Wesam [1 ]
Guo, Terry N. [2 ]
MacKenzie, Allen B. [1 ]
机构
[1] Tennessee Technol Univ, Dept Elect & Comp Engn, Cookeville, TN 38505 USA
[2] Tennessee Technol Univ, Ctr Mfg Res, Cookeville, TN 38505 USA
基金
美国国家科学基金会;
关键词
Sensors; Estimation; Monitoring; Roads; Resource management; Road traffic; OFDM; Intelligent transportation systems; Integrated sensing and communication; Intelligent transportation system (ITS); traffic estimation; integrated sensing and communication (ISAC); communication signals of opportunity; Jensen-Shannon ([!text type='JS']JS[!/text]) divergence; least-squares estimation (LSE); proactive mmWave beam allocation; ALGORITHM;
D O I
10.1109/ACCESS.2024.3415956
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Building efficient and effective road traffic monitoring systems has become a major challenge in different countries, mainly due to the rapid growth of the metropolis road network and the booming of vehicles. Existing traffic monitoring methods are accurate but typically come with inherent limitations, prompting the exploration of alternative techniques. Integrated sensing and communication (ISAC) offers an effective approach to traffic monitoring by leveraging the synergy between sensing and communication to enhance system efficiency and reduce costs. In this paper, we present a particular ISAC use case tailored for radio-based traffic monitoring. Both traffic density and speed estimations take advantage of communication functionality, involving the reuse of communication waveforms for the sensing purpose. In particular, proactive millimeter-wave (mmWave) beam allocation aided by traffic density estimation is studied to enhance communication coverage of vehicular users in the area of interest for bandwidth-intensive applications. Specifically, we exploit orthogonal frequency division multiplexing (OFDM) communication signals of opportunity reflected from targets (vehicles) to efficiently estimate the road traffic density and speed in a road section. A hybrid scheme combining model-based and data-driven methods is considered to build efficient estimators that require reduced-size training data and are less computationally complex. Simulation and comparison results demonstrate that the proposed traffic estimation techniques can accurately handle a wide range of numbers of vehicles, even with a small-sized dataset. Furthermore, the proactive beam allocation analysis shows that the quality of service (QoS, in terms of outage probability) of the communication system is effectively improved.
引用
收藏
页码:84952 / 84967
页数:16
相关论文
共 53 条
[41]   Integrated Sensing and Communication in 6G: Motivations, Use Cases, Requirements, Challenges and Future Directions [J].
Tan, Danny Kai Pin ;
He, Jia ;
Li, Yanchun ;
Bayesteh, Alireza ;
Chen, Yan ;
Zhu, Peiying ;
Tong, Wen .
2021 1ST IEEE INTERNATIONAL ONLINE SYMPOSIUM ON JOINT COMMUNICATIONS & SENSING (JC&S), 2021,
[42]   Fog Computing for Detecting Vehicular Congestion, an Internet of Vehicles Based Approach: A Review [J].
Thakur, Arnav ;
Malekian, Reza .
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE, 2019, 11 (02) :8-16
[43]  
Tulay H. B., 2020, P IEEE 91 VEH TECHN, P1
[44]   Road State Inference via Channel State Information [J].
Tulay, Halit Bugra ;
Koksal, Can Emre .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2023, 72 (07) :8329-8341
[45]  
Wang J, 2022, IEEE INTERNET THINGS, V9, P23416, DOI [10.1109/JIOT.2022.3190845, 10.1109/jiot.2022.3190845]
[46]   Reliable Traffic Density Estimation in Vehicular Network [J].
Wang, Jian ;
Huang, Yan ;
Feng, Zhiyong ;
Jiang, Chunxiao ;
Zhang, Heijun ;
Leung, Victor C. M. .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2018, 67 (07) :6424-6437
[47]   Development and Application of Artificial Neural Network [J].
Wu, Yu-chen ;
Feng, Jun-wen .
WIRELESS PERSONAL COMMUNICATIONS, 2018, 102 (02) :1645-1656
[48]   Travel Cost Inference from Sparse, Spatio-Temporally Correlated Time Series Using Markov Models [J].
Yang, Bin ;
Guo, Chenjuan ;
Jensen, Christian S. .
PROCEEDINGS OF THE VLDB ENDOWMENT, 2013, 6 (09) :769-780
[49]   Real-Time Traffic Speed Estimation With Graph Convolutional Generative Autoencoder [J].
Yu, Jamen Jian Qiao ;
Gu, Jiatao .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2019, 20 (10) :3940-3951
[50]   Data-Driven Intelligent Transportation Systems: A Survey [J].
Zhang, Junping ;
Wang, Fei-Yue ;
Wang, Kunfeng ;
Lin, Wei-Hua ;
Xu, Xin ;
Chen, Cheng .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2011, 12 (04) :1624-1639