Loading [a11y]/accessibility-menu.js
Content Caching Optimization Based on Improved Bandit Learning Algorithm | IEEE Conference Publication | IEEE Xplore

Content Caching Optimization Based on Improved Bandit Learning Algorithm


Abstract:

The combination of MEC and artificial intelligence technology effectively solves the problems of network congestion, high network latency, and high local computing energy...Show More

Abstract:

The combination of MEC and artificial intelligence technology effectively solves the problems of network congestion, high network latency, and high local computing energy consumption of users. The basis for solving these problems is to solve the problem of low caching hit rate. In large-scale Internet of Things, utilizing caching solutions can effectively improve the caching hit rate of edge nodes, thereby enhancing the user experience. This chapter establishes a large-scale collaborative mobile edge computing architecture supported by 6G. In this architecture, a fine-grained context based caching optimization problem is established with the goal of achieving the hit rate of all user requests in the system. To solve this optimization problem, this article uses a caching optimization algorithm based on Lin UCB to solve the optimization algorithm. Finally, this article uses simulation experiments to verify the superiority of the cache optimization scheme and the rationality of the experiments.
Date of Conference: 29-31 July 2024
Date Added to IEEE Xplore: 22 August 2024
ISBN Information:

ISSN Information:

Conference Location: Kailua-Kona, HI, USA

Funding Agency:


References

References is not available for this document.