Mobile Edge Cloud (MEC) has emerged as a promising paradigm shift from the centralized mobile cloud due to the explosive growth of edge devices and traffic volumes. Network Function Virtualization (NFV) is a key technology for managing and orchestrating the virtualized instances in MEC. However, it is challenging to perform efficient resource allocation in distributed NFV with MEC due to the multiple existence of NFV Management and Orchestration (MANO) systems in distributed NFV. In this work, we propose a blockchain-enabled NFV framework to reach consensus among multiple MANO systems for complex MEC scenarios. Moreover, we take both the latency of services and operational cost into consideration to achieve better resource allocation. Then, we formulate the efficient resource allocation for services in blockchain-enabled NFV with MEC as a multi-objective optimization problem. Due to the fact that it is difficult to solve this multi-objective optimization problem by traditional methods, we propose a dueling deep reinforcement learning approach. Simulation results are presented to show the effectiveness of our proposed scheme.

2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019
Department of Systems and Computer Engineering

Fu, X. (Xiaoyuan), Yu, F.R, Wang, J. (Jingyu), Qi, Q. (Qi), & Liao, J. (Jianxin). (2019). Resource Allocation for Blockchain-Enabled Distributed Network Function Virtualization (NFV) with Mobile Edge Cloud (MEC). In INFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019.