Optimal Power Management Based on Q-Learning and Neuro-Dynamic Programming for Plug-in Hybrid Electric Vehicles
dc.contributor.author | Liu, Chang | |
dc.contributor.advisor | Murphey, Yi Lu | |
dc.date.accessioned | 2018-01-18T15:59:33Z | |
dc.date.available | NO_RESTRICTION | en_US |
dc.date.available | 2018-01-18T15:59:33Z | |
dc.date.issued | 2018-04-29 | |
dc.date.submitted | 2017-11-15 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/140754 | |
dc.description.abstract | Energy optimization for plug-in hybrid electric vehicles (PHEVs) is a challenging problem due to its system complexity and various constraints. In this research, we present a Q-learning based in-vehicle model-free solution that can robustly converge to the optimal control. The proposed 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 convergence of those learning algorithms is 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. We will also introduce a new initialization strategy that combines optimal learning with a properly selected penalty function. Such initialization can reduce the learning convergence time by 70%, which has huge impact on in-vehicle implementation. Finally, we develop a neural network (NN) for the battery state-of-charge (SoC) prediction, rendering our power management controller completely model-free. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | Plug-in hybrid electric vehicles | en_US |
dc.subject | Reinforcement learning | en_US |
dc.subject | Q-learning | en_US |
dc.subject | Power management | en_US |
dc.subject | Energy optimization | en_US |
dc.subject | Neuro-dynamic programming | en_US |
dc.subject.other | Information Systems Engineering | en_US |
dc.title | Optimal Power Management Based on Q-Learning and Neuro-Dynamic Programming for Plug-in Hybrid Electric Vehicles | en_US |
dc.type | Thesis | en_US |
dc.description.thesisdegreename | PhD | en_US |
dc.description.thesisdegreediscipline | College of Engineering & Computer Science | en_US |
dc.description.thesisdegreegrantor | University of Michigan-Dearborn | en_US |
dc.contributor.committeemember | Su, Wencong | |
dc.contributor.committeemember | Wang, Shige | |
dc.contributor.committeemember | Yi, Ya Sha | |
dc.identifier.uniqname | 30502938 | en_US |
dc.description.bitstreamurl | https://deepblue.lib.umich.edu/bitstream/2027.42/140754/1/Chang Liu Final Dissertation.pdf | |
dc.identifier.orcid | 0000-0003-4500-143X | en_US |
dc.description.filedescription | Description of Chang Liu Final Dissertation.pdf : Dissertation | |
dc.identifier.name-orcid | Liu, Chang; 0000-0003-4500-143X | en_US |
dc.owningcollname | Dissertations and Theses (Ph.D. and Master's) |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.