4.7 Article

A Novel Data Placement and Retrieval Service for Cooperative Edge Clouds

期刊

IEEE TRANSACTIONS ON CLOUD COMPUTING
卷 11, 期 1, 页码 71-84

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCC.2021.3076229

关键词

Cloud computing; Servers; Edge computing; Routing; Aerospace electronics; Distributed databases; Control systems; Data placement; data retrieval; cooperative edge clouds; mobile edge computing

向作者/读者索取更多资源

Mobile edge computing is a new paradigm that places computing and storage resources at the edge of the Internet. Efficient data placement and retrieval services are crucial for the collaborative edge clouds in mobile edge computing. The existing methods like distributed hash tables (DHTs) are insufficient for efficient data placement and retrieval. This article proposes GRED, a novel data placement and retrieval service that achieves load balance, routing path lengths, and forwarding table sizes efficiently. GRED utilizes programmable switches to support a virtual-space based DHT with only one overlay hop, allowing easy data location implementation and efficient load balancing.
Mobile edge computing is a new paradigm in which the computing and storage resources are placed at the edge of the Internet. Data placement and retrieval are fundamental services of mobile edge computing when a network of edge clouds collaboratively provide data services. These services require short-latency and low-overhead implementation in network and computing devices and load balance on edge clouds. However existing methods such as distributed hash tables (DHTs) are not enough to achieve efficient data placement and retrieval services for cooperative edge clouds. This article presents GRED, a novel data placement and retrieval service for mobile edge computing, which is efficient in not only the load balance but also routing path lengths and forwarding table sizes. GRED utilizes the programmable switches to support a virtual-space based DHT with only one overlay hop. Data location can be easily implemented on top of the GRED by associating a virtual position with each data by hashing, and storing the data at the edge server connected to the switch whose position is the nearest to the position of the data in the virtual space. We implement GRED in a P4 prototype, which provides a simple and efficient solution. Results from theoretical analysis, simulations, and experiments show that GRED can efficiently balance the load of edge clouds, and can fast answer data queries due to its low routing stretch.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据