Novel Online Sequential Learning-Based Adaptive Routing for Edge Software-Defined Vehicular Networks

Abstract

To provide efficient networking services at the edge of Internet-of-Vehicles (IoV), Software-Defined Vehicular Network (SDVN) has been a promising technology to enable intelligent data exchange without giving additional duties to the resource constrained vehicles. Compared with conventional centralized SDVNs, hybrid SDVNs combine the centralized control of SDVNs and self-organized distributed routing of Vehicular Ad-hoc NETworks (VANETs) to mitigate the burden on the central controller caused by the frequent uplink and downlink transmissions. Although a wide variety of routing protocols have been developed, existing protocols are designed for specific scenarios without considering flexibility and adaptivity in dynamic vehicular networks. To address this problem, we propose an efficient online sequential learning-based adaptive routing scheme, namely, Penicillium reproduction-based Online Learning Adaptive Routing scheme (POLAR) for hybrid SDVNs. By utilizing the computational power of edge servers, this scheme can dynamically select a routing strategy for a specific traffic scenario by learning the pattern from network traffic. Firstly, this paper applies Geohash to divide the large geographical area into multiple grids, which facilitates the collection and processing of real-time traffic data for regional management in controller. Secondly, a new Penicillium Reproduction Algorithm (PRA) with outstanding optimization capabilities is designed to improve the learning effectiveness of Online Sequential Extreme Learning Machine (OS-ELM). Finally, POLAR is deployed in control plane to generate decision-making model (i.e., routing policy). Based on the real-time featured data, this scheme can choose the optimal routing strategy for a specific area. Extensive simulation results show that POLAR is superior to a single traditional routing protocol in terms of packet delivery ratio and latency.

A Survey of VANET/V2X Routing From the Perspective of Non-Learning- and Learning-Based Approaches

“…Multi-hop routing is combined with Huffman and arithmetic coding to compress data packet payloads. The work in [157] addresses communication proficiency and routing in VANETs by using a support vector machine (SVM)-based ML scheme to study and process data Item Contributions [152] Designs a Q-learning-based proactive network link status extraction mechanism using periodic HELLO packets [153] The proposed routing approach resolves the network congestion difficulty in VANETs [154] Proposes a Q-learning-based routing protocol for handling microscopic as well as macroscopic issues while taking a routing decision [155] Proposes a ML-based approach to detect local and global invasions in VANETs [156] Handles data forwarding using location on roadsides with the help of k-shortest course routing [157] Designs a SVM-based study of the analysis and process of using probes to collect car data [158] Learning automata improves multipath routing with the help of leapfrog method with Particle Swarm Optimization [159] Reinforcement learning-based routing mechanism adaptively chooses the optimal path for charging data delivery in large-scale dynamic VANET environments [160] Predicts a routing strategy to control traffic congestion in VANETs using Geographic Information System [161] The proposed clustering-based mechanism reduces traffic congestion and significantly increases throughput [162] The learning-based routing scheme has the ability to select routing strategies dynamically using edge server computational power [50] Detects network loads and timely adjusts the routing decision such that the network congestion can be prevented [53] Predicts the vehicle movement patterns based on past traces such that the transmission performance can be increased [163] Addresses the issue of the inefficient data dissemination in V2X communications, and accordingly designs a cluster-based solution collected from cars.…”

Matching Learning-Based Relay Selection for Substation Power Internet of Things

“…It has the advantages of fast convergence and strong adaptability. [31,32], the source nodes and the relay nodes are modeled as players and arms, respectively. In the tth slot, s i selects r j to transmit data, and the performance of r j can only be observed afterwards.…”

Short‐Term IoT Data Forecast of Urban Public Bicycle Based on the DBSCAN‐TCN Model for Social Governance

“…The input content of the causal convolution is shown in Equation (3). The computation process of the causal convolution is shown in Equations ( 4), (5), and (6).…”

“…In this sense, smart cities present themselves as a viable solution to aggregate public resources, human capital, social capital and information, and communication technologies, to promote sustainable development [4]. For instance, the information gathered by the advancements of the intelligent transportation systems are progressively intricate and are portrayed by heterogeneous devices, huge volume, mistakes in spatial and transient procedures, and continuous necessities of real-time processing [5,6]. Various countries throughout the world have started their efforts in designing and implementing smart cities [7].…”