TY - GEN
T1 - Decentralized Learning-based Scenario Identification Method for Intelligent Vehicular Communications
AU - Zhou, Yaru
AU - Wangt, Yu
AU - Liu, Pengfei
AU - Yang, Jie
AU - Ohtsuki, Tomoaki
AU - Sari, Hikmet
N1 - Funding Information:
This work was sponsored by NUPTSF (Grant No. NY221012).
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Scenario identification (SCI) is one of key techniques for intelligent vehicular communications (IVC) to maintain an effective and reliable operating state. Based on the deep learning (DL), it is a hotspot to identify scenarios of wireless communication using the characteristic quantity inherent in wireless channels. This paper proposes a decentralized learning-based SCI (DecentSCI) for IVC, relying on the algorithm of lightweight and model aggregation. By improving training efficiency and meanwhile reducing model complexity, the proposed method achieves low computing and communication, which is applicable for vehicular devices. Simulation results show that the training efficiency is upgraded by 97.15% and the model complexity is decreased by 90.25% at the cost of slight performance loss, i.e., 0.15%.
AB - Scenario identification (SCI) is one of key techniques for intelligent vehicular communications (IVC) to maintain an effective and reliable operating state. Based on the deep learning (DL), it is a hotspot to identify scenarios of wireless communication using the characteristic quantity inherent in wireless channels. This paper proposes a decentralized learning-based SCI (DecentSCI) for IVC, relying on the algorithm of lightweight and model aggregation. By improving training efficiency and meanwhile reducing model complexity, the proposed method achieves low computing and communication, which is applicable for vehicular devices. Simulation results show that the training efficiency is upgraded by 97.15% and the model complexity is decreased by 90.25% at the cost of slight performance loss, i.e., 0.15%.
KW - Scenario identification
KW - decentralized learning
KW - lightweight convolutional neural network
KW - model aggregation
UR - http://www.scopus.com/inward/record.url?scp=85122984695&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122984695&partnerID=8YFLogxK
U2 - 10.1109/VTC2021-Fall52928.2021.9625563
DO - 10.1109/VTC2021-Fall52928.2021.9625563
M3 - Conference contribution
AN - SCOPUS:85122984695
T3 - IEEE Vehicular Technology Conference
BT - 2021 IEEE 94th Vehicular Technology Conference, VTC 2021-Fall - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 94th IEEE Vehicular Technology Conference, VTC 2021-Fall
Y2 - 27 September 2021 through 30 September 2021
ER -