This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Smart OTA Scheduling for Connected Vehicles using Prescriptive Analytics and Deep Reinforcement Learning
ISSN: 0148-7191, e-ISSN: 2688-3627
Published August 30, 2022 by SAE International in United States
Annotation ability available
OTA (over the air) updates help automotive manufacturers to reduce vehicle warranty and recall costs. Vehicle recall is expensive, and many automotive manufacturers have implemented OTA updates. Updating parameters for connected vehicles can be challenging when dealing with thousands of vehicles across different regions. For example, how does the manufacturer prioritise which vehicles need updating? Environmental and geographical factors affect degradation rates and vehicles in hotter regions or congested cities may degrade faster.
For EVs, updating the BMS (battery management system) parameters requires careful analysis prior to the update being deployed, to maximise impact and reduce the likelihood of adverse behaviour being introduced. The analysis overhead increases with the number of vehicles. This is because it requires simulation and optimisation of the fleet BMS calibration in a digital twin environment. A targeted approach is the best option to prioritise vehicles for software updates.
Smart OTA scheduling makes use of predictive analytics for battery health prediction together with prescriptive analytics in a smart decision engine. The smart scheduling system uses a deep reinforcement learning (DRL) agent in a digital twin environment. The DRL agent can learn and simulate different scenarios and identify the best update sequence depending on monthly temperature profile, traffic congestion, and many other factors to slow down the degradation of fleet health. Whenever there is an update, the DRL agent assesses the situation and recommends the appropriate action to minimise vehicle failures and maintain fleet health. In a large-scale simulation, this approach improved average fleet battery life by 8 to 13% and increased average vehicle range by 2%.
CitationMohd Azmin, F. and Mustafa, K., "Smart OTA Scheduling for Connected Vehicles using Prescriptive Analytics and Deep Reinforcement Learning," SAE Technical Paper 2022-01-1045, 2022, https://doi.org/10.4271/2022-01-1045.
- Ng , A. July 29, 2021 https://hbr.org/2021/07/ai-doesnt-have-to-be-too-complicated-or-expensive-for-your-business
- WEC October, 2020 https://www3.weforum.org/docs/WEF_Future_of_Jobs_2020.pdf
- Wang , L. , Pan , Z. , and Wang , J. A Review of Reinforcement Learning Based Intelligent Optimization for Manufacturing Scheduling Complex System Modeling and Simulation 1 4 December 2021 257 270 10.23919/CSMS.2021.0027
- Lewandowski , R. and Olszewska , J.I. Automated Task Scheduling for Automotive Industry IEEE 24th International Conference on Intelligent Engineering Systems (INES) 2020 159 164
- Wright , J. , Stafford-Fraser , Q. , Mahmoud , M. , Robinson , P. et al. Intelligent Scheduling for In-Car Notifications IEEE 3rd International Forum on Research and Technologies for Society and Industry (RTSI) 2017 1 6 10.1109/RTSI.2017.8065957