تجزیه و تحلیل ویژگی های شبکه وسیله نقلیه به کمک کلان داده
Abstract
1- Introduction
2- State-of-the-art
3- Complex Network Feature Verification
4- System Model
5- Scheme Comparison
6- Conclusion
References
Abstract
Vehicular networks play a pivotal role in intelligent transportation system (ITS) and smart city (SC) construction, especially with the coming of 5G. Mobility models are crucial parts of vehicular network, especially for routing policy evaluation as well as traffic flow management. The big data aided vehicle mobility analysis and design attract researchers a lot with the acceleration of big data technology. Besides, complex network theory reveals the intrinsic temporal and spatial characteristics, considering the dynamic feature of vehicular network. In the following content, a big GPS dataset in Beijing, and its complex features verification are introduced. Some novel vehicle and location collaborative mobility schemes are proposed relying on the GPS dataset. We evaluate their performance in terms of complex features, such as duration distribution, interval time distribution and temporal and spatial characteristics. This paper elaborates upon mobility design and graph analysis of vehicular networks.
Introduction
Nowadays, large population and heavy traffic in urban areas lead to traffic congestion and automobile exhaust, reducing people’s travel experience by a large scale [1]. To address these issue, many schemes have been proposed, and vehicular networks are one of them [2]. Furthermore, vehicular networks also play a pivotal role in intelligent transportation system (ITS) and smart city (SC) construction [3], which means a lot in terms of traffic flow management [4], urban planing [5], location based recommendation service [6], etc. The arrival of 5G era provide vast potential for future development for vehicular network. In other words, there will be a greater bandwidth, higher carrier frequency, extreme base station and device densities [7, 8]. Therefore, how to design and optimize vehicular networks has been concerned by many scholars and researchers. Mobility models are of great importance to vehicular network with the consideration that vehicular network is dynamic [9]. Actually, mobility models determine its spatial and temporal characteristics of the network topology. Hence, a practical mobility model is important for assessing relevant algorithms and systems, especially for routing policy evaluation as well as traffic flow management [10]. An inappropriate mobility model may even lead to erroneous conclusions [11]. In fact, we give the way of combining the two classical mobility model construction methods. The classic mobility model is based on math, such as RWP. Pure data driven approach does not have a certain of universality. Our method aims to combine the two methods.