iHorizon-Enabled Energy Management for Electrified Vehicles

iHorizon-Enabled Energy Management for Electrified Vehicles proposes a realistic solution that assumes only scarce information is available prior to the start of a journey and limited computational capability can be allocated for energy management.

The framework exploits the available resources and closely emulates optimal results, as generated with an offline global optimal algorithm. This is achieved by exploring the application of machine learning to vehicle control, a theory well-known in other research areas, but infrequently applied to vehicle control.

The authors also consider the present and future of the automotive industry and it’s move towards increasing levels of automation. Driver vehicle-infrastructure is integrated here for the first time, not only to address the high level of interdependence of hybrid powertrains but also to comply with connected vehicle infrastructure. Our approach is therefore holistic and adaptive to increasing connectivity capabilities so as to accept future infrastructure developments and consists of the iHorizon and Neural Network-based energy management.

This book targets upper-division undergraduate students and graduate students interested in control applied to the automotive sector, including electrified powertrains, ADAS features, and vehicle automation.

1. Introduction
2. Integrated energy management for electrified vehicles
3. The driver in the loop
4. iHorizon in cycle-length windows
5. iHorizon in short-term windows
6. iHorizon driver energy management for PHEV real-time control
7. iHorizon extension for vehicle applications
8. Conclusions, discussion and future direction for research