试验台
服务器
边缘计算
计算机科学
调度(生产过程)
分布式计算
高效能源利用
能源消耗
云计算
绿色计算
GSM演进的增强数据速率
人工智能
计算机网络
操作系统
工程类
电气工程
运营管理
作者
Sha Zhu,Kaoru Ota,Mianxiong Dong
出处
期刊:IEEE transactions on green communications and networking
[Institute of Electrical and Electronics Engineers]
日期:2022-03-01
卷期号:6 (1): 79-88
被引量:46
标识
DOI:10.1109/tgcn.2021.3100622
摘要
Artificial Intelligence (AI) technology is a huge opportunity for the Industrial Internet of Things (IIoT) in the fourth industrial revolution (Industry 4.0). However, most AI-driven applications need high-end servers to process complex AI tasks, bringing high energy consumption to IIoT environments. In this article, we introduce intelligent edge computing, emerging technology to reduce energy consumption in processing AI tasks, to build green AI computing for IIoT applications. We first propose an intelligent edge computing framework with a heterogeneous architecture to offload most AI tasks from servers. To enhance the energy efficiency of various computing resources, we propose a novel algorithm to optimize the scheduling for different AI tasks. In the performance evaluation, we build a small testbed to show the AI-driven IIoT applications’ energy efficiency with intelligent edge computing. Meanwhile, extensive simulation results show that the proposed online scheduling strategy consumes less than 80% energy of the static scheduling and 70% of the first-in, first-out (FIFO) strategy in most settings.
科研通智能强力驱动
Strongly Powered by AbleSci AI