Bandwidth-efficient multi-task AI inference with dynamic task importance for the Internet of Things in edge computing
文献类型：期刊论文
| 作者 | Zhang, Jianfeng2; Zhang, Wensheng1 ; Xu, Jingdong2
|
| 刊名 | COMPUTER NETWORKS
 |
| 出版日期 | 2022-10-24 |
| 卷号 | 216页码:13 |
| 关键词 | Internet of Things Edge computing Edge intelligence Multi-task learning |
| ISSN号 | 1389-1286 |
| DOI | 10.1016/j.comnet.2022.109262 |
| 通讯作者 | Xu, Jingdong(xujd@nankai.edu.cn) |
| 英文摘要 | Over the past years, artificial intelligence (AI) models have been utilized for the Internet of Things (IoT) in applications such as remote assistance based on augmented reality (AR) in smart factories, as well as powerline inspection and precision agriculture missions performed by unmanned aerial vehicles (UAVs). Due to the limited battery capacity and computing power of these devices (e.g., AR glasses and UAVs), edge computing is recognized as a means to empower the Internet of Things (IoT) with AI. Considering that multiple AI model inference tasks (e.g., point cloud classification and fault detection) are typically performed on the same stream of sensory data (e.g., UAV camera feed), we propose TORC (Tasks-Oriented Edge Computing) to reduce the bandwidth requirement. By incorporating AI into data transmission, the lightweight framework of TORC preserves edge computing servers' ability to reconstruct/restore data into the original form, ensuring the proper coexistence of AI inference tasks and traditional non-AI tasks like human inspection, as well as simultaneous localization and mapping. It encodes and decodes sensory data with neural networks, whose training is driven by the AI inference tasks, in order to reduce bandwidth consumption and latency without impairing the accuracy of the AI inference tasks. Additionally, taking into account the mobility of the IoT and changes in the environment, TORC can adapt to variation in the bandwidth budget, as well as the temporally dynamic importance of AI inference tasks, without the need to train multiple neural networks for each setting. As a demonstration, empirical results conducted on the Cityscapes dataset and tasks related to autonomous driving show that, at the same level of accuracy, TORC reduces the bandwidth consumption by up to 48% and latency by up to 26%. |
| 资助项目 | Technology Research and Development Program of Tianjin[18ZXZNGX00200] ; Technology Research and Development Program of Tianjin[18ZXZNGX00140] |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000889101200011 |
| 出版者 | ELSEVIER |
| 资助机构 | Technology Research and Development Program of Tianjin |
| 源URL | [http://ir.ia.ac.cn/handle/173211/50818]  |
| 专题 | 精密感知与控制研究中心_人工智能与机器学习 |
| 通讯作者 | Xu, Jingdong |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Nankai Univ, Coll Comp Sci, Tianjin, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Jianfeng,Zhang, Wensheng,Xu, Jingdong. Bandwidth-efficient multi-task AI inference with dynamic task importance for the Internet of Things in edge computing[J]. COMPUTER NETWORKS,2022,216:13. |
| APA | Zhang, Jianfeng,Zhang, Wensheng,&Xu, Jingdong.(2022).Bandwidth-efficient multi-task AI inference with dynamic task importance for the Internet of Things in edge computing.COMPUTER NETWORKS,216,13. |
| MLA | Zhang, Jianfeng,et al."Bandwidth-efficient multi-task AI inference with dynamic task importance for the Internet of Things in edge computing".COMPUTER NETWORKS 216(2022):13. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。