A cluster-based vehicular cloud architecture with learning-based resource management

Arkian, Hamid Reza; Atani, Reza Ebrahimi; Diyanat, Abolfazl; Pourkhalili, Atefe

doi:10.1007/s11227-014-1370-z

Cited by 71 publications

(33 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Arkian et al [51] tackle resource issues in vehicular clouds by considering all three resource types. Elsewhere, crowdsensing is tackled with the same resource considerations [60].…”

Section: Computation Communication and Storagementioning

confidence: 99%

“…From their evaluation with respect to energy consumption and delay, they conclude that maintaining the cluster consumes extra energy, especially if the devices are very mobile. Arkian et al [51] also present a solution using clusters and an algorithm for selecting the cluster head, i.e. the vehicle which will be responsible for maintaining the vehicular cloud resources.…”

Section: Resource Discoverymentioning

confidence: 99%

“…This can extend to the edge domain (clustering edge servers) or remain at end devices. The latter is investigated by Skarlat et al in so-called fog colonies [50], by Arkian et al within vehicular clusters [51], or by Bianzino et al [81] for uploading data streams in presence of mobility.…”

Section: Resource Sharingmentioning

confidence: 99%

“…In the offline case, Wang et al [77] show that their problem is equivalent to the shortest-path problem and solve it by using dynamic programming. Meng et al [46] solve Bellman equations recursively, Rodrigues et al [70] use integration techniques, and Arkian et al [51] consider fuzzy logic and Q-learning.…”

Section: Resource Optimizationmentioning

confidence: 99%

See 3 more Smart Citations

A Taxonomy for Management and Optimization of Multiple Resources in Edge Computing

Toczé

Nadjm‐Tehrani

2018

Wireless Communications and Mobile Computing

101

View full text Add to dashboard Cite

Edge computing is promoted to meet increasing performance needs of data-driven services using computational and storage resources close to the end devices at the edge of the current network. To achieve higher performance in this new paradigm, one has to consider how to combine the efficiency of resource usage at all three layers of architecture: end devices, edge devices, and the cloud. While cloud capacity is elastically extendable, end devices and edge devices are to various degrees resource-constrained. Hence, an efficient resource management is essential to make edge computing a reality. In this work, we first present terminology and architectures to characterize current works within the field of edge computing. Then, we review a wide range of recent articles and categorize relevant aspects in terms of 4 perspectives: resource type, resource management objective, resource location, and resource use. This taxonomy and the ensuing analysis are used to identify some gaps in the existing research. Among several research gaps, we found that research is less prevalent on data, storage, and energy as a resource and less extensive towards the estimation, discovery, and sharing objectives. As for resource types, the most well-studied resources are computation and communication resources. Our analysis shows that resource management at the edge requires a deeper understanding of how methods applied at different levels and geared towards different resource types interact. Specifically, the impact of mobility and collaboration schemes requiring incentives are expected to be different in edge architectures compared to the classic cloud solutions. Finally, we find that fewer works are dedicated to the study of nonfunctional properties or to quantifying the footprint of resource management techniques, including edge-specific means of migrating data and services.

show abstract

Section: Computation Communication and Storagementioning

confidence: 99%

Section: Resource Discoverymentioning

confidence: 99%

Section: Resource Sharingmentioning

confidence: 99%

Section: Resource Optimizationmentioning

confidence: 99%

See 2 more Smart Citations

A Taxonomy for Management and Optimization of Multiple Resources in Edge Computing

Toczé

Nadjm‐Tehrani

2018

Wireless Communications and Mobile Computing

101

View full text Add to dashboard Cite

show abstract

“…On the other hand, Arkian et al [14] use MDP with Q-learning for selecting the best candidate node for delivering services in a cluster in the vehicular cloud. This selection problem can be abstracted as resource allocation, if vehicle(s) in the cluster are considered as resources.…”

Section: B Resource Provisioning For Vms In Vehicular Cloudsmentioning

confidence: 99%

Reinforcement learning for resource provisioning in the vehicular cloud

Salahuddin

Al-Fuqaha

Guizani

2016

IEEE Wireless Commun.

View full text Add to dashboard Cite

This article presents a concise view of vehicular clouds that incorporates various vehicular cloud models, which have been proposed, to date. Essentially, they all extend the traditional cloud and its utility computing functionalities across the entities in the vehicular ad hoc network (VANET). These entities include fixed road-side units (RSUs), on-board units (OBUs) embedded in the vehicle and personal smart devices of the driver and passengers. Cumulatively, these entities yield abundant processing, storage, sensing and communication resources. However, vehicular clouds require novel resource provisioning techniques, which can address the intrinsic challenges of (i) dynamic demands for the resources and (ii) stringent QoS requirements. In this article, we show the benefits of reinforcement learning based techniques for resource provisioning in the vehicular cloud. The learning techniques can perceive long term benefits and are ideal for minimizing the overhead of resource provisioning for vehicular clouds.

show abstract

A novel clustering and optimal resource scheduling in vehicular cloud networks using MKMA and the CM‐CSO algorithm

Kouser

Manikandan²

2023

Int J Communication

View full text Add to dashboard Cite

Summary Various opportunities aimed at the employment of delay‐sensitive applications in the vehicular environment are presented by the vehicular cloud (VC). Contrary to diverse wireless networks, VC networks possess exceptional features among others, namely, shorter transmission time along with a higher dynamic topology. Although integration with the cloud offers higher storage along with computation capabilities, it as well entails restricted resource availability. The restrictions on the number of resources serve as a challenge in servicing the applications with their necessary quality of service (QoS) guarantees as the number of service requests for applications keeps on augmenting with diverse circumstances. Thus, the need for an effective scheduling methodology arises to decide the sequence of servicing application requests and successful utilization of a broadcast medium, along with data transmission. To do efficient resource scheduling on VC networks, an optimization algorithm, namely, the crossover and mutation (CM)‐centered chicken swarm optimization (CSO) is proposed and implemented with the help of a publicly available dataset. Initially, the VC infrastructure is initialized and some vehicle information is extracted as features. Next, the Brownian motion‐centered bacteria foraging optimization (BM‐BFO) algorithm chooses the essential features. Centered on the chosen features, the vehicles are clustered using the modified K‐means algorithm. Next, as for the cloud server's virtual machines (VMs), the resource information is extracted. Lastly, the CM‐CSO algorithm carries out the optimal scheduling in the VC by means of the clustered features of vehicles and features of the VM. The proposed techniques' findings are scrutinized and analogized to the other prevailing methodologies to confirm that the proposed work performs effectively and gives optimal resource allocation (RA) to the VC.

show abstract

A cluster-based vehicular cloud architecture with learning-based resource management

Cited by 71 publications

References 36 publications

A Taxonomy for Management and Optimization of Multiple Resources in Edge Computing

A Taxonomy for Management and Optimization of Multiple Resources in Edge Computing

Reinforcement learning for resource provisioning in the vehicular cloud

A novel clustering and optimal resource scheduling in vehicular cloud networks using MKMA and the CM‐CSO algorithm

Contact Info

Product

Resources

About