Abstract
The Internet of Things (IoTs) is attracting the attention of scientists worldwide. With its explosive growth along with applications that require real-time computing power, a new technology called edge computing has emerged. As a result, edge computing has changed the way data are processed and handled back and forth for millions of devices worldwide, such as autonomous vehicles and electric cars. The confinement of cloud computing technology, such as a content delivery network (CDN), contributed significantly to edge computing development. Currently, this technology can meet the demands of ever-growing mobile devices and the IoTs. This paper describes a novel secure framework consisting of a hybrid storage architecture consisting of CDN, edge computing, and centralized storage. Centralized storage consists of multilevel storage systems that comprise solid-state drivers (SSDs) and hard disk drivers (HDDs), which provide optimal data storage solution for a wide variety of real-time data processing applications. Transforming the data back and forth between SSDs and HDDs is crucial for achieving high performance while meeting the edge device request deadline. Additionally, a new dynamic solid-state disk partitioning mechanism is introduced to optimize security for the proposed framework among hard disk drives. A partition from the solid-state disks to hard disk drives is assigned based on hard disk drive workloads.
Highlights
Cloud computing infrastructure generally provides various services, such as networking, storage, and computation for individual organizations, reducing the burden of edge devices
The proposed architecture consists of an array of hard disk drivers (HDDs), an array of solid-state disks (SSDs), a parallel system server, and a data handler request transmitter and receiver that are directly connected to the edge devices
To make a significant decision to predict content popularity based on end-user expectations and decide which contents should be stored in the solid-state drivers (SSDs) and HDDs, deep learning models are trained as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory recurrent neural networks (LSTM RNNs)
Summary
Cloud computing infrastructure generally provides various services, such as networking, storage, and computation for individual organizations, reducing the burden of edge devices. With edge computing [2], data are processed at the source level, which provide real-time insights, and it is not sent to the cloud. This creates an environment that acts as a public cloud. A hybrid storage framework that integrates several storage devices is proposed, i.e., CDN, edge server connected with the CDN, and an array of solid-state disks. This paper proposes a hybrid storage framework that integrates several storage devices, i.e., CDNs, edge servers that is connected with CDNs, and an array of solid-state disks. The proposed framework uses security control protocols that can be adjusted to encounter security change necessities and workload environments; providing a high level of security for all edge device requests.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
