RLbR: A reinforcement learning based V2V routing framework for offloading 5G cellular IoT

Abstract

5G cellular IoT has several advantages compared to other access technologies, enabling operators to serve a wider area and more IoT devices. However, in the urban transportation system, a massive number of vehicles exhaust the available resources in the cell, resulting in excessive load in the 5G cellular network. This article proposes a novel reinforcement learning based V2V routing (RLbR) framework, which offloads non-realtime traffic into the V2V network and significantly relieves the load of 5G cellular network. Meanwhile, we propose a V2V routing algorithm. Specifically, the Q-values of neighbouring vehicles are firstly calculated according to the cache factor CF and energy factor EF and evaluate the quality of neighbouring vehicles. Then, the position factor PF is calculated, based on which, the vehicle forwards the data packet. In addition, an environment model is designed to accelerate the convergence of Q-table. The results show that the RLbR framework brings the highest offload rate compared to the other three frameworks, and simultaneously, the proposed algorithm improves the lifetime of the V2V network and performs well in terms of delivery ratio and average delay.

Multi-User Computation Offloading and Resource Allocation Algorithm in a Vehicular Edge Network

“…V2V links are used to offload tasks to SeVs [9,10]. Platooning vehicles are considered in work [9], where platoon members can only communicate with the platoon leader and use the resources via V2V communication links.…”

“…Platooning vehicles are considered in work [9], where platoon members can only communicate with the platoon leader and use the resources via V2V communication links. More factors are considered in [10] when SeVs are selected, such as the caching factor, energy factor, and location factor of vehicles to offload non-real-time traffic to V2V networks.…”

“…As seen in Table 1, this literature is based on the three execution modes, M 1 , M 2 , and M 3 , which all involve the local execution mode M 0 . Most of the research in the M 1 and M 2 modes adopts the partial offloading mode [9,10,[14][15][16]25,29], and most of the research in the M 3 mode adopts the 0-1 offloading mode [19,20,23,31,32]. Furthermore, we have studied the use of V2V and V2I links to extend the system's computing resources [33,34].…”

“…To verify the effectiveness of our scheme, three baseline schemes are compared with our scheme; namely, Offloading in Loc + Sev mode (OLSM) [10], Offloading in Loc + Edge mode (OLEM) [14], and Offloading in Random Mode (ORM). Simulation results show that compared with the existing schemes, the proposed scheme can significantly reduce the delay of computation offloading and resource allocation.…”

An efficient and reliable service customized routing mechanism based on deep learning in IPv6 network

“…With the rapid development of IPv6 networks, various scenarios such as the Internet of Things (IoT), 5G vehicle internet [15], Software Defined IPv6 network (SoDIP6), Low‐power and Lossy Networks (LLNs) were gradually formed. Traditional routing methods were gradually unable to meet the QoS and QoE (Quality of Experience) requirements of services.…”