Service cost-based resource optimization and load balancing for edge and cloud environment
- PDF / 2,971,984 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 87 Downloads / 171 Views
Service cost-based resource optimization and load balancing for edge and cloud environment Chunlin Li1,2 · Jianhang Tang1 · Youlong Luo1 Received: 17 December 2018 / Accepted: 3 July 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract The application of edge clouds is becoming more and more widespread. The resource optimization is one of the important research contents of edge cloud. Generally, the edge cloud has limited computing resources and energy. Resource optimization can make tasks perform efficiently and reduce costs. Therefore, achieving high energy efficiency while ensuring a satisfying user experience is critical. This paper proposes the resource optimization and load balancing model. By considering factors such as user preferences, SLA and cost, the algorithm of resource optimization determines the resources scheme of edge cloud. The data movement after resource optimization is achieved through migration strategies. The load balancing of the edge cloud environment can be ensured. The results of the experiment prove that our proposed algorithm can better control costs. Keywords Service cost · Resource optimization · Load balancing
1 Introduction At present, the data are exponentially increasing, the types of terminal devices are increasing, and service scenarios are diversified. For the purpose of meeting the high bandwidth and low delay demands required for high-speed data growth, edge computing provides intelligent services for devices on the edge of the network near the source of device data, reducing the network bandwidth problem and real-time demand brought by data transmission to cloud computing center [1]. The edge cloud technology can achieve cloud–edge collaboration and enhance user service quality experience. The edge cloud architecture is shown in Fig. 1. For example, edge cloud computing plays an important role in interactive live scenarios [2, 3]. The live broadcast platform has a high pursuit of video live broadcast technology to meet users’ requirements for Blu-ray quality, low latency, stability and real-time interaction. The service of live broadcast has the features of long sessions, low latency and good QoS. Live
B
Chunlin Li [email protected]
1
Department of Computer Science, Wuhan University of Technology, Wuhan 430063, People’s Republic of China
2
National Engineering Research Center for Agro-Ecological Big Data Analysis and Application, Anhui University, Hefei 230601, People’s Republic of China
123
C. Li et al.
Edge Cloud Computing Server Cluster Management Server
Central Cloud
Server Cluster Database
Database
Management Server
WLAN
End Device
Server Cluster
Edge Cloud Database
Database
Management Server
WLAN
End Device
Fig. 1 The architecture of edge cloud computing
broadcast service systems based on live broadcast clouds often need to deploy sub-clouds in the edge area to meet the above requirements. Thus, edge cloud computing is introduced to deal with the problem. When the edge computing service is used for live streaming, the n
Data Loading...
