计算机科学
分布式计算
云计算
可扩展性
移动边缘计算
服务质量
虚拟网络
虚拟化
软件定义的网络
GSM演进的增强数据速率
编配
计算机网络
操作系统
人工智能
艺术
音乐剧
视觉艺术
作者
Hongsheng Xu,Ganglong Fan,Libo Sun,W. Li,Guofang Kuang,Bin Fan,Gholamreza Ahmadi
标识
DOI:10.1016/j.jksuci.2023.101577
摘要
Mobile Edge Computing (MEC) is a well-known network architecture that extends cloud computing to the network edge. Compared with cloud computing, Network Function Virtualization (NFV) can provide flexible services in MEC for mobile users. Virtual Network Functions (VNFs) have emerged as software-based hardware middleboxes by NFV technology to host real-time applications. Basically, the combination of multiple VNF instances is defined as a Service Function Chain (SFC), which can provide dynamic service requirements in the MEC. Despite the rapid growth of MEC and the widespread support of service providers for SFC, many issues are still challenging and need to be addressed. In MEC scenarios with limited resources, the effective placement of SFCs with the aim of resource efficiency remains a challenging problem. Motivated by the scalability shortcomings of existing schemes to solve dynamic placement of SFCs, we propose Deep Reinforcement Learning (DRL)-based approaches to solve this problem, i.e., Asynchronous Advantage Actor-Critic (A3C). The proposed scheme is based on the reuse of initialized VNFs to improve the Quality of Service (QoS), which is developed with the aim of maximizing the long-term cumulative reward. In addition, a parallel processing approach of SFCs is included in the proposed scheme, which can split the traffic in each flow into sub-flows. This shares the processing load by instantiating duplicate instances of each VNF type in the SFC. The simulation results guarantee the efficiency of the proposed scheme and improves the average performance between 6% and 24% compared to the state-of-the-art clustering methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI