文献类型：期刊文献

英文题名：A New Approach for Resource Recommendation in the Fog-Based IoT Using a Hybrid Algorithm

作者：Xu, Zhiwang[1,2];Qin, Huibin[2];Yang, Shengying[2];Arefzadeh, Seyedeh Maryam[3]

机构：[1]Shaoxing Univ, Yuanpei Coll, Shaoxing 312000, Zhejiang, Peoples R China;[2]Hangzhou Dianzi Univ, Inst Electron Device & Applicat, Hangzhou 310018, Zhejiang, Peoples R China;[3]Islamic Azad Univ, Bushehr Branch, Dept Control Engn, Bushehr 7515895496, Iran

年份：0

外文期刊名：COMPUTER JOURNAL

收录：SCI-EXPANDED(收录号：WOS:000789353000001)、、EI(收录号：20241816013022)、Scopus(收录号：2-s2.0-85191613246)、WOS

语种：英文

外文关键词：recommender system; fog computing; Particle Swarm Optimization; Genetic Algorithm

外文摘要：Internet of things (IoT) is an architecture of connected physical objects; these objects can communicate with each other and transmit and receive data. Also, fog-based IoT is a distributed platform that provides reliable access to virtualized resources based on various technologies such as high-performance computing and service-oriented design. A fog recommender system is an intelligent engine that suggests suitable services for fog users with less answer time and more accuracy. With the rapid growth of files and information sharing, fog recommender systems' importance is also increased. Besides, the resource management problem appears challenging in fog-based IoT because of the fog's unpredictable and highly variable environment. However, many current methods suffer from the low accuracy of fog recommendations. Due to this problem's Non-deterministic Polynomial-time (NP)-hard nature, a new approach is presented for resource recommendation in the fog-based IoT using a hybrid optimization algorithm. To simulate the suggested method, the CloudSim simulation environment is used. The experimental results show that the accuracy is optimized by about 1-8% compared with the Cooperative Filtering method utilizing Smoothing and Fusing and Artificial Bee Colony algorithm. The outcomes of the present paper are notable for scholars, and they supply insights into subsequent study domains in this field.