TY - JOUR
T1 - Edge intelligence empowered internet of vehicles
T2 - concept, framework, issues, implementation, and prospect
AU - Jiang, Kai
AU - Cao, Yue
AU - Zhou, Huan
AU - Ren, Xuefeng
AU - Zhu, Yongdong
AU - Lin, Hai
N1 - Publisher Copyright:
© 2023, Beijing Xintong Media Co., Ltd.. All rights reserved.
PY - 2023
Y1 - 2023
N2 - As an emerging inter discipline field, edge intelligence pushes AI to the side close to the traffic data source. Edge intelligence makes use of the computing power, storage resources, and perception ability of edge to provide a more intelligent and efficient resource allocation and processing mechanism while providing a real-time response, intelligent deci-sion-making and network autonomy, realizing the critical leap for internet of vehicles from access “pipelining” to the intelligent enabling platform of information. However, the successful implementation of edge intelligence in internet of vehicles is still in its infancy, and there exists a demand for a comprehensive survey in this young field from a broader perspective. Based on this context of internet of vehicles, the background, concepts and key technologies of edge intelligence were intro-duced. Then, a holistic overview of service types based on internet of vehicles was taken, and the entire processes of model training and inference in edge intelligence were elaborated. Finally, to promote the potential research directions, the key open challenges of edge intelligence in the internet of vehicles were analyzed, and the coping strategies were discussed.
AB - As an emerging inter discipline field, edge intelligence pushes AI to the side close to the traffic data source. Edge intelligence makes use of the computing power, storage resources, and perception ability of edge to provide a more intelligent and efficient resource allocation and processing mechanism while providing a real-time response, intelligent deci-sion-making and network autonomy, realizing the critical leap for internet of vehicles from access “pipelining” to the intelligent enabling platform of information. However, the successful implementation of edge intelligence in internet of vehicles is still in its infancy, and there exists a demand for a comprehensive survey in this young field from a broader perspective. Based on this context of internet of vehicles, the background, concepts and key technologies of edge intelligence were intro-duced. Then, a holistic overview of service types based on internet of vehicles was taken, and the entire processes of model training and inference in edge intelligence were elaborated. Finally, to promote the potential research directions, the key open challenges of edge intelligence in the internet of vehicles were analyzed, and the coping strategies were discussed.
KW - artificial intelligence
KW - edge intelligence
KW - internet of vehicles
UR - http://www.scopus.com/inward/record.url?scp=85152950209&partnerID=8YFLogxK
U2 - 10.11959/j.issn.2096-3750.2023.00320
DO - 10.11959/j.issn.2096-3750.2023.00320
M3 - 文章
AN - SCOPUS:85152950209
SN - 2096-3750
VL - 7
SP - 37
EP - 48
JO - Chinese Journal on Internet of Things
JF - Chinese Journal on Internet of Things
IS - 1
ER -