Optimal path strategy for the web computing under deep reinforcement learning. Issue 5 (30th October 2020)

• Record Type: Journal Article
• Authors: Shengdong, Mu; Fengyu, Wang; Zhengxian, Xiong; Xiao, Zhuang; Lunfeng, Zhang
• Is Part Of: International journal of web information systems. Volume 16:Issue 5(2020)
• Page Start: 529
• Page End: 544
• Publication Date: 2020-10-30
• Subjects: Deep reinforcement learning -- Optimal path -- Web computing; World Wide Web -- Periodicals; Internet -- Periodicals; Information storage and retrieval systems -- Periodicals; 004.678
• DOI: 10.1108/IJWIS-08-2020-0055
• Languages: English
• ISSNs: 1744-0084

Abstract

Abstract : Purpose: With the advent of the web computing era, the transmission mode of the Internet of Everything has caused an explosion in data volume, which has brought severe challenges to traditional routing protocols. The limitations of the existing routing protocols under the condition of rapid data growth are elaborated, and the routing problem is remodeled as a Markov decision process. this paper aims to solve the problem of high blocking probability due to the increase in data volume by combining deep reinforcement learning. Finally, the correctness of the proposed algorithm in this paper is verified by simulation. Design/methodology/approach: The limitations of the existing routing protocols under the condition of rapid data growth are elaborated and the routing problem is remodeled as a Markov decision process. Based on this, a deep reinforcement learning method is used to select the next-hop router for each data transmission task, thereby minimizing the length of the data transmission path while avoiding data congestion. Findings: Simulation results show that the proposed method can significantly reduce the probability of data congestion and increase network throughput. Originality/value: This paper proposes an intelligent routing algorithm for the network congestion caused by the explosive growth of data volume in the future of the big data era. With the help of deep reinforcement learning, it is possible to dynamically select the transmission jump router according to the current network state, thereby reducing the probability of congestion and improving network throughput.