Formula-E race strategy development using artificial neural networks and Monte Carlo tree search
- PDF / 3,054,004 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 68 Downloads / 184 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
Formula-E race strategy development using artificial neural networks and Monte Carlo tree search Xuze Liu1 • Abbas Fotouhi1 Received: 13 March 2019 / Accepted: 19 March 2020 The Author(s) 2020
Abstract Energy management has been one of the most important parts in electric race strategies since the Fe´de´ration Internationale de l’Automobile Formula-E championships were launched in 2014. Since that time, a number of unfavorable race finishes have been witnessed due to poor energy management. Previous researches have been focused on managing the power flow between different energy sources or different energy consumers based on a fixed cycle. However, there is no published work in the literature about energy management of a full electric racing car on repeated course but with changeable settings and driving styles. Different from traditional energy management problems, the electric race strategy is more of a multistage decision-making problem which has a very large scale. Meanwhile, this is a time-critical task in motorsport where fast prediction tools are needed and decisions have to be made in seconds to benefit the final outcome of the race. In this study, the use of artificial neural networks (ANN) and tree search techniques is investigated as an approach to solve such a large-scale problem. ANN prediction models are developed to replace the traditional lap time simulation as a much faster performance prediction tool. Implementation of Monte Carlo tree search based on the proposed ANN fast prediction models has provided decent capability to generate decision-making solution for both pre-race planning and in-race reaction to unexpected scenarios. Keywords Formula-E race strategy Energy management Machine learning Artificial neural networks
1 Introduction 1.1 Formula-E racing The first worldwide electric motorsport event, the Fe´de´ration Internationale de l’Automobile (FIA) Formula-E (FE) championship, was originally conceived as a single-seater electric motor racing championship in 2011 and launched its first ePrix in September 2014 [1]. Since then, several electric racing series have been developed such as I-PACE Trophy, Electric GT. So far in any of these series, teams have been running very similar cars fitted with the same rechargeable energy storage system (RESS). It has always been a problem for engineers and drivers to properly & Abbas Fotouhi [email protected] 1
Advanced Vehicle Engineering Centre, School of Aerospace, Transport and Manufacturing (SATM), Cranfield University, Cranfield, Bedfordshire MK43 0AL, UK
manage the battery energy during the race. For example, a flat battery or an over-heated battery will lead to a Did Not Finish (DNF) before crossing the finished line. Among all the series, the current fifth FIA FE season 2018/2019 has raised the problem of energy management to a completely different level. The new FE Gen 2 cars have to last for the entire 45 min plus one-lap race, and a new power mode called the ‘A
Data Loading...
