Hybrid Cooperative Caching Based IoT Network Considering the Data Cold Start
Xinxin Yang, Heli Zhang, Hong Ji, Xi Li · 2021
With the rapid development of the Internet of Things(IoT), the amount of data on the IoT is overgrowing, and how to improve the performance of the network is crucial. In this article, we propose the common cold start problem of IoT data. Based on this, we design a novel hybrid caching strategy. We divide the cache space into two parts for proactive caching and reactive caching. Proactive caching uses deep learning methods to predict data popularity, while reactive caching uses an improved LRU-K algorithm. The combination of the two can not only ensure performance but also solve the problem of data cold start. Through the cellular IoT structure, we implement a cooperative caching strategy in small base stations and macro base stations, increasing the cache hit rate and reducing user access delay. We conducted extensive simulations to prove that our proposed solution can solve the cold start problem well and is better than existing solutions.