IEEE VIC CIS Talk on Optimal Power Management

#PowerManagement #DynamicProgramming #HybridElectricVehicles #optimisation #patternrecognition

Prof Yi Lu Murphey (IEEE Fellow) will deliver a talk on Optimal Power Management.

This is a part of the IEEE Victorian Computational Intelligence Society (CIS) series of talks. The online delivery is kindly hosted by IEEE Victorian Section and will take place 5.00 - 6.00 pm (AEST).

Join Zoom Meeting (Friday 9th December 2022, 12.00 – 1.00 pm (AEST)

Meeting ID: TBA
Password: TBA

  Date and Time




  • Date: 09 Dec 2022
  • Time: 12:00 PM to 01:00 PM
  • All times are (UTC+11:00) Canberra
  • Add_To_Calendar_icon Add Event to Calendar
If you are not a robot, please complete the ReCAPTCHA to display virtual attendance info.
  • Contact Event Hosts
  • Co-sponsored by IEEE VIC CIS Chapter; IEEE VIC Section
  • Starts 10 September 2022 06:30 PM
  • Ends 09 December 2022 11:30 AM
  • All times are (UTC+11:00) Canberra
  • No Admission Charge


Prof Yi Lu Murphey of University of Michigan-Dearborn


Optimal Power Management based on Q-Learning and Neuro-Dynamic Programming for Plug-in Hybrid Electric Vehicles

Energy optimization for Plug-in Hybrid Electric Vehicles (PHEVs) is a challenging problem due to the system complexity and many physical and operational constraints in PHEVs. In this lecture, we present a Q-learning based in-vehicle learning system that is free of physical- models, and can robustly converge to an optimal energy control solution. The proposed machine learning algorithms combine Neuro-Dynamic Programming (NDP) with future trip information to effectively estimate the expected future energy cost (expected cost-to-go) for a given vehicle state and control actions. The convergences of those learning algorithms were demonstrated on both fixed and randomly selected drive cycles. Based on the characteristics of these learning algorithms, we propose a two-stage deployment solution for PHEV power management applications. Furthermore, we introduce a new initialization strategy, which combines the optimal learning with a properly selected penalty function. This initialization scheme can reduce the learning convergence time by 70%, which is a significant improvement in in-vehicle implementation efficiency. Finally, we present a Neural Network (NN) for predicting battery –State-of-Charge (SoC), rendering the proposed power management controller completely free of physical models.


Dr. Yi Lu Murphey is a Professor of the ECE(Electrical and Computer Engineering) department and the director of the Intelligent Systems Lab at the University of Michigan-Dearborn. She received a M.S. degree in computer science from Wayne State University, Detroit, Michigan, in 1983, and a Ph.D degree with a major in Computer Engineering and a minor in Control Engineering from the University of Michigan, Ann Arbor, Michigan, in 1989. During 2007 ~ 2020, Professor Murphey served as the Chair of the ECE department, Associate Dean for Graduate Education and Research, and the Vice Provost for Research at the University of Michigan-Dearborn. Her current research interests are in the areas of machine learning, pattern recognition, computer vision and intelligent systems with applications to engineering diagnostics and prognostics, optimal vehicle power management, data analytics, and robotic vision systems. She has authored over 290 publications in refereed journals and conference proceedings. She is an editor for the Journal of Pattern Recognition. She has served on technical committees and session chairs for many conferences, and organized symposiums and special sessions for various conferences sponsored by the IEEE Society. Her research has been funded by the National Science Foundation (NSF), National Institute of Health (NIH), Department of Energy (DoE), US Army TARDEC, State of Michigan, Ford Motor Company, TRW, Nissan, and many others. She is a fellow of IEEE and a senior life member of AAAI. She is a Distinguished Lecturer for both IEEE Vehicular Society and IEEE Computational Intelligence Society, and the recipient of 2019 SAE Ralph H. Isbrandt Automotive Safety Engineering Award.

Address:Michigan, United States