Service offloading oriented edge server placement in smart farming. (18th June 2020)

• Record Type: Journal Article
• Authors: Zhang, Jie; Li, Xiang; Zhang, Xuyun; Xue, Yuan; Srivastava, Gautam; Dou, Wanchun
• Other Names: Kumar Neeraj guestEditor.; Jindal Anish guestEditor.; Villari Massimo guestEditor.; Srirama Satish Narayana guestEditor.
• Is Part Of: Software, practice & experience. Volume 51:Number 12(2021)
• Page Start: 2540
• Page End: 2557
• Publication Date: 2020-06-18
• Subjects: edge computing -- ESs placement -- IoT -- smart farming; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2847
• Languages: English
• ISSNs: 0038-0644

Abstract

Summary: Currently, smart farming has been established to realize agriculture automation by leveraging sensors to gather the growth and environmental data for crops, and realizing multiple intelligent controls, such as irrigation, fertilization, and so on, to increase the crop yields. To support real‐time intelligent controls, edge computing is introduced to smart farming by endowing computing and storage capacities to edge devices nearby the geographically distributed sensors. However, the farmers are relatively willing to purchase and deploy a small quantity of edge servers (ESs) in the farm from the perspective of expenditure saving, thereby leading to a key challenge to guarantee the performance of the real‐time controls and the overall edge services. In view of this challenge, a service offloading‐oriented ES placement method for supporting smart farming, called SOP, is proposed to optimize the data transmission delay from sensors to ESs and the load balance among ESs. More precisely, the corresponding service range of a certain ES is ascertained according to the specific analysis of the farming service requirements. Subsequently, the layout policies for the trade‐offs of the ES performance and service efficiency are acquired. Then the most balanced policy is determined as the final ES placement strategy. Eventually, we evaluate the performance of the whole ES system and the service execution efficiency with SOP.