Web Enabled Things Computing System
-
摘要: 近年来兴起的边缘计算试图将部分计算从云端移到设备端，从而减少云端计算负载和网络传输负载.物端计算系统是边缘计算系统中面向物理世界的终端设备组成的计算系统.由于物端设备具有多样性，设计一个统一的体系结构来支持物端智能应用十分具有挑战.现代Web系统的体系结构是解决多样性的有效方案之一，但由于大部分物端设备的资源受限的特性，应用Web体系结构十分困难.1)阐述了现代Web系统、边缘计算系统和物端计算系统的概念，从组成物端计算系统的设备多样性和资源受限特性出发分析其面临的挑战；2)针对这些问题和挑战调研了一些基于REST的用于边缘计算系统的应用层协议；3)详细调研和评估了4个Web系统代表性脚本语言，总结了一些试图将这些语言应用于物端设备的工作；4)调研了传统嵌入式系统的调试技术.通过调研得出结论：目前的物端计算系统虽然市场规模巨大，但是仍未形成高效的、统一的体系结构来支撑人工智能应用的大量部署;5)列出了物端计算系统的一些重要研究方向，包括统一的体系结构、高能效Web、支持物端智能和物端调试技术.Abstract: The rising edge computing paradigm tries to shift some computing tasks from cloud to devices recently, which reduces the computing load of cloud and traffic load of the Internet. The things computing system consists of the devices which are physical world oriented with physical functionalities. It is a great challenge to design a unified system architecture for things computing system because of the system diversity. The architecture of the modern Web system is an efficient solution for the diversity issue. However，due to the resource-constrained feature extending the Web architecture to the things computing system is also very difficult. In this paper, we first introduce the concept of edge computing system and things computing system, and summarize the challenges brought by diversity and resource-constrained features of things computing system. Then, a detailed study of the state-of-the-art technologies, including REST principle, script languages and debugging technique for extending the Web to things computing system, is presented. Most of the related work tried to modify the “Uniform Interface” principle to adapt to edge system. We conclude from the examined literature that things computing system is a massive market, but there is still no unified system architecture which supports both the Web and intelligence. Finally, we present some future research directions for things computing system including the unified system architecture, efficient Web technologies, supporting intelligence and debugging techniques.
-
-
期刊类型引用(6)
1. 王璐璐. 基于混合注意力机制的时间旋转知识图谱补全. 网络安全与数据治理. 2024(10): 42-48 . 
百度学术
2. 何鹏，周刚，陈静，章梦礼，宁原隆. 类型增强的时态知识图谱表示学习模型. 计算机研究与发展. 2023(04): 916-929 . 本站查看
3. 陈小英，熊盛武，王盛，张士伟. 基于上下文时序关联的时序知识图谱嵌入方法. 武汉大学学报(理学版). 2023(02): 249-257 . 百度学术
4. 周丽华，王家龙，王丽珍，陈红梅，孔兵. 异质信息网络表征学习综述. 计算机学报. 2022(01): 160-189 . 百度学术
5. 杨大伟，周刚，卢记仓，宁原隆. 基于知识表示学习的知识图谱补全研究综述. 信息工程大学学报. 2021(05): 558-565 . 百度学术
6. 王红，卢林燕，王童. 航空安全事件知识图谱补全方法. 西南大学学报(自然科学版). 2020(11): 31-42 . 百度学术
其他类型引用(3)
计量
- 文章访问数: 1840
- HTML全文浏览量: 2
- PDF下载量: 909
- 被引次数: 9
下载:
