Mobility-Aware Edge Caching and Computing in Vehicle Networks: A Deep Reinforcement Learning

By Le Thanh Tan, Rose Qingyang Hu. IEEE Transactions on Vehicular Technology, 2018

325 citations recorded by the source corpus.

This paper studies the joint communication, caching and computing design problem for achieving the operational excellence and the cost efficiency of the vehicular networks. Moreover, the resource allocation policy is designed by considering the vehicle's mobility and the hard service deadline constraint. These critical challenges have often been either neglected or addressed inadequately in the existing work on the vehicular networks because of their high complexity. We develop a deep reinforcement learning with the multi-timescale framework to tackle these grand challenges in this paper. Furthermore, we propose the mobility-aware reward estimation for the large timescale model to mitigate the complexity due to the large action space. Numerical results are presented to illustrate the theoretical findings developed in the paper and to quantify the performance gains attained.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/162bbb112721b234400cb3d8b540f5f3d8c0adc2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Electrical and Electronic Engineering

Citations in the corpus

A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art (2019, unknown): “Other studies on (deep) RL based caching algorithms can be found in [246], [247].”
Edge Computing with Artificial Intelligence: A Machine Learning Perspective (2022, methodology): “Incontrast, the method of [155] imposes the task of content caching on both roadside units and vehicles.”
Fast Adaptive Task Offloading in Edge Computing Based on Meta Reinforcement Learning (2020, methodology): “[37] proposed a deep Q-learning based offloading method considering constraints of limited resources, vehicle’s mobility and delay.”
Quantum Machine Learning for 6G Communication Networks: State-of-the-Art and Vision for the Future (2019, background): “Moreover, ML-based proactive content caching at the edge node can also be exploited to avoid backhaul congestion and further reduce the service latency [66], [67].”
Vehicular Edge Computing and Networking: A Survey (2019, methodology): “problem. However, the joint consideration of these three factors increase the complexity of the problem. Thus, a deep reinforcement learning method is introduced to solve the optimization problem. In [66], the joint communication, computation cache problem is studied. The resource scheduling is desi”
Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challenges (2019, methodology): “Tan and Hu [135] used DRL in a multi-timescale framework for cache replacement and computing resource management.”
Toward Edge Intelligence: Multiaccess Edge Computing for 5G and Internet of Things (2020, background): “A number of studies have been conducted on the problems of joint 4C (communication, computation, control, and caching) optimization [115], [116], mobile crowdsensing [117], joint big data analytics [118], caching [119], [120], and computation ofﬂoading [121], [122].”
Machine Learning for 5G/B5G Mobile and Wireless Communications: Potential, Limitations, and Future Directions (2019, methodology): “Deep Q-learning has been suggested to determine the sets of possible connecting neighboring vehicles, as well as to configure the parameters of caching placement [94].”
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2019, background): “Besides, Vehicle-to-Vehicle (V2V) communication technology can be taken advantaged to further connect vehicles, either as an edge node or an end device managed by DRL-based control policies [112].”
Mobile Edge Intelligence and Computing for the Internet of Vehicles (2019, methodology): “Focusing on resource allocation in the integrated architecture, two joint optimization models were formulated in [77], [78] to determine the optimal caching and computing decisions, which were then solved by deep reinforcement learning based methods.”