Dynamic cooperative caching strategy for delay-sensitive applications in edge computing environment
- PDF / 1,602,753 Bytes
- 25 Pages / 439.37 x 666.142 pts Page_size
- 25 Downloads / 183 Views
Dynamic cooperative caching strategy for delay‑sensitive applications in edge computing environment Li Chunlin1,2,3 · Jing Zhang2,3
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In the context of the interconnection of everything, the edge data are experiencing explosive growth, and the bandwidth and computing resources of cloud computing cannot be efficiently processed. Edge computing, with its low latency, high throughput and low network pressure, has become a very effective mode to deal with massive data. Due to the increasing number of end users, a large number of data are generated on the edge of the network, and the timeliness of users’ service requirements is constantly improving, so further reducing the delay of cloud service network is still a major challenge. Cache is an effective solution to this problem. In order to make full use of the limited edge device space, a dynamic cache replacement algorithm is proposed based on edge popularity and node heat, which caches popular content in the core node and non-popular content in the secondary node, so as to improve the hit rate of the whole network and reduce the server load. In order to meet the increasing demand of data content access in the network, a cooperative caching algorithm is proposed. The idea of this algorithm is to put the cache object in the proper node, so that the user’s request can get timely response. Thus, the availability of the object is improved and the network delay is reduced. In the edge computing environment of campus network, dynamic cache replacement algorithm and cooperative cache algorithm are evaluated. The experimental results show that the dynamic cache replacement algorithm proposed in this paper is better than the benchmark replacement algorithm in cache hit rate, server load, average delay and average hops, and the cooperative cache algorithm is better than the benchmark cooperative cache algorithm in node hit rate and average hops.
* Li Chunlin [email protected] 1
Chongqing Engineering and Technology Research Center for Big Data of Public Transportation Operation, Chongqing Jiaotong University, Chongqing, People’s Republic of China
2
Anhui Province Key Laboratory of Big Data Analysis and Application, Hefei, People’s Republic of China
3
Department of Computer Science, Wuhan University of Technology, Wuhan 430063, People’s Republic of China
13
Vol.:(0123456789)
L. Chunlin, J. Zhang
Keywords Edge computing · Cache replacement · Collaborative cache
1 Introduction With the popularity of intelligent terminal devices and rich cloud services, many data are generated on the edge of the network, which puts forward higher requirements for the data transmission bandwidth and data processing capacity in the traditional cloud computing model. Although it is an efficient data processing method to transmit all data to the cloud for processing, more and more real-time data generated by edge devices need to be processed in time, and the data processing performance based on cloud computi
Data Loading...
