TY - JOUR
T1 - Fine-grained RNN with Transfer Learning for Energy Consumption Estimation on EVs
AU - Hua, Yining
AU - Sevegnani, Michele
AU - Yi, Dewei
AU - Birnie, Andrew
AU - Mcaslan, Steve
N1 - This work is supported by the Engineering and Physical Sciences Research Council, under PETRAS SRF grant MAGIC (EP/S035362/1) and the University of Glasgow Impact Acceleration Account.
PY - 2022
Y1 - 2022
N2 - Electric vehicles (EVs) are increasingly becoming an environmentally-friendly option in current transportation systems thanks to reduced fossil fuel consumption and carbon emission. However, the more widespread adoption of EVs has been hampered by two factors: the lack of charging infrastructure and the limited cruising range. Energy consumption estimation is crucial to address these challenges as it provides the foundations to enhance charging-station deployment, improve eco-driving behaviour, and extend the EV cruising range. We propose an EV energy consumption estimation method capable of achieving accurate estimation despite insufficient EV data and ragged driving trajectories. It consists of three distinct features: knowledge transfer from Internal Combustion Engine/Hybrid Electric Vehicles (ICE/HEV) to EVs, segmentation-aided trajectory granularity, time-series estimation based on bidirectional recurrent neural network. Experimental evaluation shows our method outperforms other machine learning benchmark methods in estimating energy consumption on a real-world vehicle energy dataset.
AB - Electric vehicles (EVs) are increasingly becoming an environmentally-friendly option in current transportation systems thanks to reduced fossil fuel consumption and carbon emission. However, the more widespread adoption of EVs has been hampered by two factors: the lack of charging infrastructure and the limited cruising range. Energy consumption estimation is crucial to address these challenges as it provides the foundations to enhance charging-station deployment, improve eco-driving behaviour, and extend the EV cruising range. We propose an EV energy consumption estimation method capable of achieving accurate estimation despite insufficient EV data and ragged driving trajectories. It consists of three distinct features: knowledge transfer from Internal Combustion Engine/Hybrid Electric Vehicles (ICE/HEV) to EVs, segmentation-aided trajectory granularity, time-series estimation based on bidirectional recurrent neural network. Experimental evaluation shows our method outperforms other machine learning benchmark methods in estimating energy consumption on a real-world vehicle energy dataset.
KW - electric vehicle
KW - energy consumption estimation
KW - trajectory segmentation
KW - transfer learning
KW - recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=85123371675&partnerID=8YFLogxK
U2 - 10.1109/TII.2022.3143155
DO - 10.1109/TII.2022.3143155
M3 - Article
AN - SCOPUS:85123371675
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
SN - 1551-3203
ER -