.png){kind=icon}
Return
User preference-aware edge resource cache dynamic deployment
.png){kind=icon}
PRE
AI
DOI：10.1007/s10586-026-06441-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Dynamic deployment of edge resource cache is a critical technology in edge computing, which can effectively optimize resource utilization and improve service response speed. However, current researches still face issues such as unreasonable selection of cache resources and low cache hit rates. Therefore, this paper studies the dynamic deployment technology of user preference-aware edge resource cache. First, a user preference-aware cache resource pre-selection method is proposed, which adopts the Empirical Mode Decomposition (EMD) to obtain the user preference sequence components of edge resources. Meanwhile, the Gate Recurrent Unit (GRU) model is utilized to predict the user preference of edge resources in the next cache cycle, and pre-select cache resources according to the prediction results. Then, a dynamic deployment method of edge resource cache based on improved Particle Swarm Optimization Algorithm (PSO) is proposed, and a dynamic deployment model of edge resource cache is established with minimizing cache energy consumption and delivery delay as the cost function. The improved particle swarm optimization algorithm is utilized to solve the dynamic deployment model of edge resource cache, so as to obtain the optimal dynamic deployment scheme of edge resource cache. Results demonstrate that our method can effectively reduce the cache energy consumption, reduce the delivery delay and improve the cache hit rate.
Keywords:
Dynamic deployment
Edge computing
Particle swarm optimization algorithm
Resource cache
User preferences
Journal
IF:
2.9
Papers:
221
Citations:
1.1K