Improving EV Energy Forecast Accuracy via ML Residual Correction: The Role of Wind Speed in Data-Driven Predictions Toyota Motor Corporation

Format:

Book

Conference/Event

Author/Creator:

Raghupathy, Vishnu Prasaad, author.

Kim, Shinhoon, author.

Evans, Nic, author.

Niimi, Keisuke, author.

Mochihara, Takahiro, author.

Conference Name:

WCX SAE World Congress Experience (2026-04-14 : Detroit, Michigan, United States)

Language:

English

Subjects (All):

Energy consumption.

Machine learning.

Electric vehicles.

Weather and climate.

Local Subjects:

Energy consumption.

Machine learning.

Electric vehicles.

Weather and climate.

Physical Description:

1 online resource

Place of Publication:

Warrendale, PA SAE International 2026

Summary:

The increasing demand for electrified transportation is leading to accelerated development of highly efficient hybrid and battery electric vehicles. A major concern for customers adapting to battery electric vehicles (BEV) is range anxiety due to low charging speeds, charging infrastructure not matching expectations and unreliable range estimations shown to the customers by their vehicles. Estimating the range more accurately has been difficult due to the sensitivity of vehicle's energy consumption to real-world environmental and driving conditions. This paper aims to find out the effect of true wind in the road load experienced by BEVs in the real-world driving scenarios and how using a highly accurate wind speed measurement improves the energy consumption estimation better. On-road tests were conducted on public roads and in controlled test-track environments to collect reliable wind speed measurements using a dynamic multi-hole pressure probe. Additional coastdown tests were also conducted to find appropriate road load coefficients which provided a slightly better alternative to EPA coefficients to be used in our estimation models. A high-fidelity energy model was developed to estimate energy consumption with greater accuracy than simplified energy models, which are commonly used in the remaining range calculations shown in the information displays in vehicles. Finally, this paper also explores the need for a machine learning correction model which predicts the gap between the high-fidelity energy model estimations and actual energy consumption, thus compensating for dynamic losses which are hard to estimate using physical models. This hybrid approach of a physics-based model complemented by a data-driven residual correction model provides a unique way to increase the accuracy of traditional modeling techniques and also helps to understand the gaps in those techniques better. Results are used as a baseline benchmark for developing fast executing, lower-fidelity models that can be used in production level applications

Notes:

Vendor supplied data

Access Restriction:

Restricted for use by site license