TY - GEN
T1 - Intelligent and adaptive fleet energy management strategy for hybrid electric buses
AU - Lopez-Ibarra, Jon Ander
AU - Goitia-Zabaleta, Nerea
AU - Camblong, Haritza
AU - Milo, Aitor
AU - Gaztanaga, Haizea
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - Learning based energy management strategies are promising methods, due to the high adaptability and the capability to learn from historical data. Widening the scope to a whole fleet, allows to learn from a more extend data-base and wider range of operating conditions. This paper aims to develop a methodology for improving the overall energetic efficiency of a fleet. In this regard, the main contribution lyes on the development of an intelligent decision maker, with the goal to design improved and adapted energy management strategies for each bus operating on a predefined route. The intelligent decision maker is driven by an adaptive neuro-fuzzy inference system technique that learns from the optimal operation optimized with dynamic programming. The obtained results in the developed EMS have shown similarities with the dynamic programming operation, reaching close fuel consumptions, 0.01% of difference and improvements up to 16% of fuel consumption against the initial EMS.
AB - Learning based energy management strategies are promising methods, due to the high adaptability and the capability to learn from historical data. Widening the scope to a whole fleet, allows to learn from a more extend data-base and wider range of operating conditions. This paper aims to develop a methodology for improving the overall energetic efficiency of a fleet. In this regard, the main contribution lyes on the development of an intelligent decision maker, with the goal to design improved and adapted energy management strategies for each bus operating on a predefined route. The intelligent decision maker is driven by an adaptive neuro-fuzzy inference system technique that learns from the optimal operation optimized with dynamic programming. The obtained results in the developed EMS have shown similarities with the dynamic programming operation, reaching close fuel consumptions, 0.01% of difference and improvements up to 16% of fuel consumption against the initial EMS.
KW - Dynamic programming
KW - Fleet energy management
KW - Hybrid electric bus
KW - Intelligent decision maker
KW - Neuro-fuzzy
UR - https://www.scopus.com/pages/publications/85078748636
U2 - 10.1109/VPPC46532.2019.8952368
DO - 10.1109/VPPC46532.2019.8952368
M3 - Conference contribution
AN - SCOPUS:85078748636
T3 - 2019 IEEE Vehicle Power and Propulsion Conference, VPPC 2019 - Proceedings
BT - 2019 IEEE Vehicle Power and Propulsion Conference, VPPC 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE Vehicle Power and Propulsion Conference, VPPC 2019
Y2 - 14 October 2019 through 17 October 2019
ER -
