Joint Microservices Caching and Task Offloading Framework in VEC Based on Deep Reinforcement Learning
Dublin Core
Title
Joint Microservices Caching and Task Offloading Framework in VEC Based on Deep Reinforcement Learning
Subject
Mobile Edge Computing (MEC)
Task Offloading
Microservice Caching
Description
Vehicle capacities and intelligence are rapidly increasing, which will likely support a wide range of novel and interesting applications. However, these resources are not effectively utilized. To take advantage of these invaluable capabilities in smart vehicles, they can be used in the cloud environment and can be operated through distributed computing platforms in order to benefit from their combined processing power, storage capacity, and memory resources. Vehicular edge computing (VEC) is a promising field that allows computing tasks to be transferred from cloud servers to vehicular edge servers for processing, allowing data and apps to be placed closer to vehicles (users).
This paper proposes a framework that combines two modules, the first one for managing microservice caching in vehicle-mounted edge networks, such that we use cluster-based caching technique to deal with the case where similar microservices are frequently requested in VEC. The second one integrates the computational capabilities of the edge servers with the capabilities of vehicles to perform task offloading in a collaborative manner.
Our solution addresses the limitations of existing edge computing platforms during peak times by combining microservices caching with computational task offloading to improve overall system performance.
This paper proposes a framework that combines two modules, the first one for managing microservice caching in vehicle-mounted edge networks, such that we use cluster-based caching technique to deal with the case where similar microservices are frequently requested in VEC. The second one integrates the computational capabilities of the edge servers with the capabilities of vehicles to perform task offloading in a collaborative manner.
Our solution addresses the limitations of existing edge computing platforms during peak times by combining microservices caching with computational task offloading to improve overall system performance.
Creator
Ghorab, Ahmed S.
Rasheed, Raed S.
Hamad, Hatem M.
Source
International Journal of Interactive Mobile Technologies (iJIM); Vol. 17 No. 08 (2023); pp. 78-99
1865-7923
Publisher
International Association of Online Engineering (IAOE), Vienna, Austria
Date
2023-04-26
Rights
Copyright (c) 2023 Ahmed S. Ghorab, Hatem Hammad, Raed Rasheed
https://creativecommons.org/licenses/by/4.0
Relation
Format
application/pdf
Language
eng
Type
info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article
Identifier
Citation
Ahmed Ghorab S., Raed Rasheed S. and Hatem Hamad M., Joint Microservices Caching and Task Offloading Framework in VEC Based on Deep Reinforcement Learning, International Association of Online Engineering (IAOE), Vienna, Austria, 2023, accessed November 22, 2024, https://igi.indrastra.com/items/show/2502