Research Article
Edge Server Deployment Approach Based on Uniformity and Centrality
@INPROCEEDINGS{10.1007/978-3-031-54521-4_6, author={Xinghong Jiang and Yong Ma and Yunni Xia and Qilin Xie and Wenxin Jian}, title={Edge Server Deployment Approach Based on Uniformity and Centrality}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 19th EAI International Conference, CollaborateCom 2023, Corfu Island, Greece, October 4-6, 2023, Proceedings, Part I}, proceedings_a={COLLABORATECOM}, year={2024}, month={2}, keywords={Edge computing Service scope expansion Deployment Intersection centrality}, doi={10.1007/978-3-031-54521-4_6} }- Xinghong Jiang
Yong Ma
Yunni Xia
Qilin Xie
Wenxin Jian
Year: 2024
Edge Server Deployment Approach Based on Uniformity and Centrality
COLLABORATECOM
Springer
DOI: 10.1007/978-3-031-54521-4_6
Abstract
In mobile Internet applications that support edge computing, the deployment scheme of edge servers affects the business operation state. Traditional edge servers are deployed on base stations, which do not fully extend the service range of edge servers, resulting in difficult access to edge services. Therefore, this paper proposes the Edge Server Deployment Approach Based on Uniformity and Centrality (ESDA-UC). ESDA-UC considers intersections as candidate deployment locations for edge servers, taking into account traffic density and road network structure. Connection centrality, between centrality, base station centrality, and traffic density are used as the main factors. The intersection centrality of each intersection is calculated as the selection criteria for the deployment location. To avoid concentrating the coverage of edge servers in developed regions of the city, we allocate the number of edge servers according to regional importance. Finally, the improved greedy algorithm is utilized to generate a deployment plan for edge servers. Experiments show that ESDA-UC has higher base station coverage, vehicle coverage, and vehicle coverage time ratios compared to the baseline method.
