Optimizing MDS-coded cache-enable wireless network:a blockchain-based cooperative deep reinforcement learning approach

• Published in: 高技术通讯（英文版） Vol. 27; no. 2; pp. 129 - 138
• Main Authors: Zhang Zheng, Yang Ruizhe, Yu Fei Richard, Zhang Yanhua, Li Meng
• Format: Journal Article
• Language: English
• Published: Faculty of Information Technology,Beijing University of Technology,Beijing 100124,P.R.China%Department of Systems and Computer Engineering,Carleton University,Ottawa K1S5B6,Canada 01.06.2021
• Subjects: deep reinforcement learning(DRL); blockchain; caching technology
• ISSN: 1006-6748
• DOI: 10.3772/j.issn.1006-6748.2021.02.003

Mobile distributed caching(MDC)as an emerging technology has drawn attentions for its abili-ty to shorten the distance between users and data in the wireless network.However,the DC network state in the existing work is always assumed to be either static or real-time updated.To be more real-istic,a periodically updated wireless network using maximum distance separable(MDS)-coded DC is studied,in each period of which the devices may arrive and leave.For the efficient optimization of the system with large scale,this work proposes a blockchain-based cooperative deep reinforcement learning(DRL)approach,which enhances the efficiency of learning by cooperating and guarantees the security in cooperation by the practical Byzantine fault tolerance(PBFT)-based blockchain mechanism.Numerical results are presented,and it illustrates that the proposed scheme can dramat-ically reduce the total file download delay in DC network under the guarantee of security and effi-ciency.