Research Article
A Co-caching Strategy for Edges Based on Federated Learning and Regional Prevalence
@INPROCEEDINGS{10.1007/978-3-031-28990-3_20, author={Zhirong Zhu and Yiwen Liu and Yanxia Gao and Wenkan Wen and Yuanquan Shi and Xiaoning Peng}, title={A Co-caching Strategy for Edges Based on Federated Learning and Regional Prevalence}, proceedings={Edge Computing and IoT: Systems, Management and Security. Third EAI International Conference, ICECI 2022, Virtual Event, December 13-14, 2022, Proceedings}, proceedings_a={ICECI}, year={2023}, month={3}, keywords={Data Storage Computing IoT Technology Edge Computing Cache Hit Rate}, doi={10.1007/978-3-031-28990-3_20} }- Zhirong Zhu
Yiwen Liu
Yanxia Gao
Wenkan Wen
Yuanquan Shi
Xiaoning Peng
Year: 2023
A Co-caching Strategy for Edges Based on Federated Learning and Regional Prevalence
ICECI
Springer
DOI: 10.1007/978-3-031-28990-3_20
Abstract
With the rise of data storage computing and IoT technology. The increase in data volume and user demand, the accurate delivery of data and low latency during transmission become important factors that affect the end-user experience. To address this issue, previous authors have proposed the concept of edge computings. In the general environment of edge computing, reasonable scheduling of edge caches can largely achieve low latency and high efficiency, thus improving user experience. In this paper, based on existing research, we propose a combination of a joint learning framework for cache prediction based on region popularity and an edge collaborative cache value optimization method to further improve cache hit rate and cache utilization efficiency. The method obtains excellent expected results through simulation experiments.
