透過您的圖書館登入
IP:18.188.196.223
  • 期刊

Research on Resource Allocation Under Edge Intelligence

摘要


In recent years, the marginalization of computing infrastructure has gradually become a new trend in the development of computing architecture technology. Under the influence of this trend, the perception and computing mode based on edge computing has been promoted. Therefore, edge computing is also considered as the key technology of the next generation Internet. Compared with the traditional cloud center computing mode, the edge computing mode hands over some computing tasks to edge devices with computing power for processing, which not only reduces the computing pressure and IO pressure of the cloud center server, but also improves the system response speed, enabling users to get better Quality of Experience (QoE). At the same time, edge computing also brings new challenges to network architecture, data transmission, resource allocation, model deployment, data security, etc. In this paper, we study the resource allocation problem in the edge network, and propose an adaptive bandwidth allocation algorithm based on reinforcement learning, which better solves the network resource allocation problem of multiple devices in the edge network.

參考文獻


Cao K, Liu Y, Meng G, et al. An overview on edge computing research[J]. IEEE access, 2020, 8: 85714-85728.
Mao Y, You C, Zhang J, et al. A survey on mobile edge computing: The communication perspective[J]. IEEE communications surveys & tutorials, 2017, 19(4): 2322-2358.
Shi W, Cao J, Zhang Q, et al. Edge computing: Vision and challenges[J]. IEEE internet of things journal, 2016, 3(5): 637-646.
Khan W Z, Ahmed E, Hakak S, et al. Edge computing: A survey[J]. Future Generation Computer Systems, 2019, 97: 219-235.
Abbas N, Zhang Y, Taherkordi A, et al. Mobile edge computing: A survey[J]. IEEE Internet of Things Journal, 2017, 5(1): 450-465.

延伸閱讀