摘要
随着人工智能(AI)技术的发展,AI技术正在逐步参与到人们工作和生活的方方面面。但是,AI技术对计算资源和存储资源都有非常高的要求,传统的网络结构已经逐渐不堪重负。MEC边缘计算技术为了缓解传统网络的压力应运而生。文章利用MEC技术,结合无服务器架构(Serverless)这种无状态的事件触发式运行的第三代云计算技术,对传统的网络结构进行了改进,提出了一种新型的计算模型,并以AI计算平台为例,对系统的计算资源和存储资源都有显著的加速效果,进而更好地满足了AI计算平台的需求。
With the development of artifcial intelligence （AI） technology, AI technology is gradually participating in all aspects of people＇s work and life. However, AI technology has very high requirements for computing and storage resources, and the traditional network structure has gradually become overwhelmed. MEC edge computing technology came into being in order to alleviate the pressure of traditional networks. This paper uses MEC technology, combining with the third-generation cloud computing technology of stateless event-triggered operation such as serverless, improves the traditional network structure, and proposes a new computing model with AI. As an example, the computing platform has a signifcant acceleration effect on the computing resources and storage resources of the system, and thus better meets the needs of the AI computing platform.
作者
刘畅
毋涛
徐雷
Liu Chang;Wu Tao;Xu Lei(China Unicom Research Institute,Beijing 100176,China)
出处
《信息通信技术》
2018年第5期45-49,共5页
Information and communications Technologies
关键词
无服务器
边缘计算
人工智能
Serverless
Edge Computing
Artifcial Intelligence
