Asynchronous federated and reinforcement learning for mobility-aware edge caching in IoVs

Jiang, Kai, Cao, Yue, Song, Yujie, Zhou, Huan, Wan, Shaohua and Zhang, Xu ORCID: https://orcid.org/0000-0001-6557-6607 (2024) Asynchronous federated and reinforcement learning for mobility-aware edge caching in IoVs. IEEE Internet of Things Journal. ISSN 2327-4662

[thumbnail of Asynchronous_Federated_and_Reinforcement_Learning_for_Mobility-Aware_Edge_Caching_in_IoVs]
Preview
PDF (Asynchronous_Federated_and_Reinforcement_Learning_for_Mobility-Aware_Edge_Caching_in_IoVs) - Accepted Version
Download (3MB) | Preview

Abstract

Edge caching is a promising technology to reduce backhaul strain and content access delay in Internet-of-Vehicles (IoVs). It pre-caches frequently-used contents close to vehicles through intermediate roadside units. Previous edge caching works often assume that content popularity is known in advance or obeys simplified models. However, such assumptions are unrealistic, as content popularity varies with uncertain spatial-temporal traffic demands in IoVs. Federated learning (FL) enables vehicles to predict popular content with distributed training. It preserves the training data remain local, thereby addressing privacy concerns and communication resource shortages. This paper investigates a mobility-aware edge caching strategy by exploiting asynchronous FL and Deep Reinforcement Learning (DRL). We first implement a novel asynchronous FL framework for local updates and global aggregation of Stacked AutoEncoder (SAE) models. Then, utilizing the latent features extracted by the trained SAE model, we adopt a hybrid filtering model for predicting and recommending popular content. Furthermore, we explore intelligent caching decisions after content prediction. Based on the formulated Markov Decision Process (MDP) problem, we propose a DRL-based solution, and adopt neural network-based parameter approximations for the curse of dimensionality in RL. Extensive simulations are conducted based on real-world data trajectory. Especially, our proposed method outperforms FedAvg, LRU, and NoDRL, and the edge hit rate is improved by roughly 6%, 21%, and 15%, respectively, when the cache capacity reaches 350 MB.

Item Type: Article
Uncontrolled Keywords: computational modeling,content prediction,data models,deep reinforcement learning,delays,edge caching,feature extraction,federated learning,optimization,predictive models,stacked autoencoder,training,signal processing,information systems,hardware and architecture,computer science applications,computer networks and communications ,/dk/atira/pure/subjectarea/asjc/1700/1711
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 02 Feb 2024 02:18
Last Modified: 02 Feb 2024 02:19
URI: https://ueaeprints.uea.ac.uk/id/eprint/94351
DOI: 10.1109/JIOT.2023.3349255

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item