ML-Based Energy Optimization in Android Infotainment for Electric Vehicles

Authors: Ronak Indrasinh Kosamia

DOI: https://doi.org/10.37082/IJIRMPS.v11.i3.232418

Short DOI: https://doi.org/g9gqqf

Country: USA

Full-text Research PDF File:   View   |   Download

Abstract: Electric Vehicles (EVs) increasingly rely on advanced infotainment systems that offer navigation, media play back, connectivity, and occupant-centric applications, often powered by Android or Android Automotive. However, these information units can consume a substantial amount of battery energy, thereby reducing the overall driving range of EVs. This paper proposes a Machine Learning (ML)-based energy optimization framework for Android infotainment. By monitoring user interaction patterns, trip context, and system-level metrics, our ML model forecasts upcoming load demands and dynamically scales computational resources, display usage, or service scheduling. Preliminary results from a prototype testbed indicate that this adaptive approach can yield up to 15–20% power savings over traditional static operation, without sacrificing occupant experience. Key technical considerations, such as real time responsiveness, occupant concurrency, privacy constraints, and integration with Android Automotive power management APIs, are also discussed. This Abstract and the subsequent Introduction section lay the foundation for a broader exploration of how ML can intelligently manage infotainment resources in EV ecosystems, thus extending vehicle range and enhancing user satisfaction.

Keywords: Android Automotive, Electric Vehicles, Infotainment, Energy Optimization, Machine Learning, Battery Efficiency

Paper Id: 232418

Published On: 2023-06-08

Published In: Volume 11, Issue 3, May-June 2023

Share this