Grouping-Based Consistency Protocol Design for End-Edge-Cloud Hierarchical Storage System

Abstract

With the increasing of the number of edge-devices and the demand of real-time experience, the end-edge-cloud hierarchical storage system (EECHSS) is emerged recently for reliable caching and fast offloading of massive amounts of data. EECHSS can accommodate various services, save computing power and improve storage capacity, due to transformation from central-cloud to edge-cloud, considerable reducing service delay and communication overhead. One of the main challenges brought by edge-cloud architecture is consistency problem. It is difficult to guarantee that the data from the two distributed clusters is consistent by existing consistency protocols. In addition, as the variety of applications increases, the existing fixed consistency level of classical protocols can no longer satisfy the system dynamic requirements. In this paper, we focus on designing grouping-based consistency protocols with adaptively selecting consistency level in EECHSS. At first, we analyze the internal structure and the workflow of EECHSS, and devise two modified adaptive grouping-based consistency protocols (GM-Paxos and GEPaxos) with efficient grouping algorithms. Then, for the characteristics that data is offloaded frequently, we design two synchronization strategies to ensure the consistency of the data cached in the edge-cloud and the central-cloud, respectively. Experiments show that, our proposed grouping-based consistency protocols of EECHSS can improve the availability as much as possible while ensuring data consistent. INDEX TERMS End-edge-cloud hierarchical storage system, adaptive consistency, grouping algorithm, synchronization strategy.

Enhancing Global Blockchain Privacy via a Digital Mutual Trust Mechanism

“…Although PBFT has Byzantine Fault Tolerance, high efficiency, and low power consumption [18][19][20], it also has shortcomings such as malicious nodes that cannot be eliminated in time and C/S response mode; since the number of nodes in the network cannot be dynamically sensed, the efficiency of consistency will decline when the number of nodes increases. To solve these problems, the PBFT consistency protocol and master node scheduling are optimized based on RPoS, and a dynamic Byzantine consensus algorithm (DPBFT) is proposed.…”

Consistency issue and related trade-offs in distributed replicated systems and databases: a review

“…The second large group of recent research activities (see Table 2) puts forward (i) new data models suitable for efficient distributed across multiple nodes [29-30]; (ii) new consistency models [40-46], (iii) consistency control algorithms and consensus quorum protocols [31][32][33][34][35][36][37][38][39], and (iv) techniques for data replications and strategies for replica placement [47][48][49][50][51][52][53][54][55].…”