Value‐aware cache replacement in edge networks for Internet of Things

AbstractAbstractWith the development of Internet of Things (IoT), massive amounts of data will be brought. By offloading caching from the cloud to the edge, edge caching technology represents a promising solution in the era of IoT to meet the delay requirements of IoT applications. An efficient cache decision and replacement strategy on edge caching devices is a key factor in ensuring the cache hit ratio. The existing cache replacement policies do not comprehensively consider the characteristics of cache files and are likely to result in cache pollution problems. In order to cache data reasonably, to improve the cache hit ratio, and to reduce the user request delay, we propose a concept of file cache value and a file cache value‐aware cache replacement (FCVACR) algorithm of the edge cache system in this article. File cache value is associated with three aspects of cache file: the file size, the file popularity, and the time of requests. The proposed FCVACR algorithm adopts the file cache value method, improves the utilization of edge caching space, and reduces the content transmission delay. Experimental results show that the proposed FCVACR algorithm has a higher cache hit ratio and lower user request delay than the classical cache replacement algorithms.We develop a new model of the network edge caching system that explores the impact of the user request behavior, file popularity, and file size on the edge caching system and user request latency. We propose a network edge cache decision strategy based on the characteristics of file size, study the cache replacement strategy to minimize the average latency and maximize the cache hit ratio by introducing file cache value, and propose a cache replacement algorithm based on file cache value‐aware. View Figure