Machine learning models and techniques for VANET based traffic management: Implementation issues and challenges
- PDF / 2,348,278 Bytes
- 28 Pages / 595.224 x 790.955 pts Page_size
- 95 Downloads / 163 Views
Machine learning models and techniques for VANET based traffic management: Implementation issues and challenges Sahil Khatri1 · Hrishikesh Vachhani1 · Shalin Shah1 · Jitendra Bhatia1 · Manish Chaturvedi2 · Sudeep Tanwar3 · Neeraj Kumar4 Received: 22 February 2020 / Accepted: 26 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Low latency in communication among the vehicles and RSUs, smooth traffic flow, and road safety are the major concerns of the Intelligent Transportation Systems. Vehicular Ad hoc Network (VANET) has gained attention from various research communities for such a matters. These systems need constant monitoring for proper functioning, opening the doors to apply Machine Learning algorithms on enormous data generated from different applications in VANET (for example, crowdsourcing, pollution control, environment monitoring, etc.). Machine Learning is an approach where the system automatically learns and improves itself based on previously processed data. These algorithms provide efficient supervised and unsupervised learning of these collected data, which effectively implements VANET’s objective. We highlighted the safety, communication, and traffic-related issues in VANET systems and their implementation in-feasibility and explored how machine learning algorithms can overcome these issues. Finally, we discussed future direction and challenges, along with a case study depicting a VANET based scenario. Keywords VANET · Machine learning · Safety · Communication · Traffic
1 Introduction With the commencement of the smart city, the need for intelligent mobility increases. Traffic flow monitoring and congestion management are some of the main aspects of a smart city. An increase in the number of incidents of traffic congestion and inefficient wireless communication system for traffic management leads to the concept of Intelligent Transportation Systems (ITS). The primary objectives of ITS, such as traffic congestion control, road safety, and efficient infrastructure usage, can be implemented using VANET. There is an increasing demand for research in the field of VANET, which includes vehicles equipped with OnBoard Units such as global positioning system (GPS), This article belongs to the Topical Collection: Special Issue on P2P Computing for Deep Learning Guest Editors: Ying Li, R.K. Shyamasundar, Yuyu Yin, Mohammad S. Obaidat Neeraj Kumar
[email protected]
Extended author information available on the last page of the article.
mobile phone sensors, and other wireless equipment to support V2V and V2I communication. The vehicles in VANET have high mobility, leading to network congestion, connection instability among the components of VANET, and communication failure. Authentication mechanisms for communication in VANET must have low computational overhead for robustness and scalability [1]. The malicious nodes or links affect the authenticity and decision making of V2X receivers [2]. Nowadays, VANET also comprehends the 5G networkbased Software Defined Net
Data Loading...
