| 引用本文: | 谢小瑜,周俊煌,张勇军.深度学习在泛在电力物联网中的应用与挑战[J].电力自动化设备,2020,40(4): |
| XIE Xiaoyu,ZHOU Junhuang,ZHANG Yongjun.Application and challenge of deep learning in Ubiquitous Power Internet of Things[J].Electric Power Automation Equipment,2020,40(4): |
|
| 摘要: |
| 泛在电力物联网是智能电网发展的高级应用形态，对电网的数据处理能力和计算能力提出了更高的要求。近年来，深度学习技术取得了突破性的进展，为泛在电力物联网的实现与发展提供了强大的支撑。基于此，总结了现有深度学习模型的主要组成及技术特点；从泛在电力物联网应用的技术需求出发，综述了深度学习在数据处理、边缘计算以及态势感知方面的技术特点与应用场合；基于泛在电力物联网应用的典型场景，深入分析了深度学习在泛在电力物联网中的具体应用，为泛在电力物联网的建设与研究提供参考。 |
| 关键词: 深度学习 泛在电力物联网 态势感知 边缘计算 数据处理 智能电网 |
| DOI：10.16081/j.epae.202002008 |
| 分类号:TP391.44;TN929.5;TM76 |
| 基金项目:国家自然科学基金资助项目(51777077) |
|
| Application and challenge of deep learning in Ubiquitous Power Internet of Things |
|
XIE Xiaoyu1, ZHOU Junhuang2, ZHANG Yongjun1
|
|
1.School of Electric Power, South China University of Technology, Guangzhou 510641, China;2.Guangzhou Power Electrical Technology Co.,Ltd.,Guangzhou 510700, China
|
| Abstract: |
| UPIoT(Ubiquitous Power Internet of Things) is an advanced application form of smart grid development, which requires higher data processing and computing ability of the power grid. In recent years, the deep learning technology has made a breakthrough, providing a strong support for the realization and development of UPIoT. Based on this, the main components and technical characteristics of the existing deep learning models are summarized. Based on the technical requirements of UPIoT application, the technical characteristics and application scenarios of deep learning in data processing, edge calculation and situation awareness are reviewed. Based on the typical application scenarios of UPIoT, the specific application of deep learning in UPIoT is deeply analyzed, providing reference for the construction and research of UPIoT. |
| Key words: deep learning UPIoT situation awareness edge calculation data processing smart grid |
