"Range anxiety" remains one of the major issues of electric vehicles (EVs). Most of the existing range prediction technologies rely on simulated conditions or limited datasets, making it difficult to accurately capture variations caused by regional climate, road conditions, and vehicle types.

In a study published in Applied Energy, a team led by Prof. CHEN Zhongwei and Assoc. Prof. MAO Zhiyu from the Dalian Institute of Chemical Physics of the Chinese Academy of Sciences, and Assoc. Prof. ZHANG Zhaosheng from the Beijing Institute of Technology, developed a comprehensive real-world data–driven framework for EVs range prediction and intelligent management.

The researchers developed an integrated framework for online range estimation and optimization analysis which incorporates the influence including driving behavior, ambient temperature, and battery State of Health. A Random Forest algorithm was used to predict energy consumption per unit distance and the remaining range, which improves prediction accuracy and enhances model interpretability.

Using three years of real-world operational data with a combined driving distance of more than 300,000 kilometers, the researchers validated the framework. They found that the average relative error between the predicted remaining driving range (RDR) and the actual drivable distance is below 5.5%, outperforming traditional methods.

Further analysis showed that the average current which reflects the power intensity of the trip and the average speed are the key determinants of energy consumption. Reasonable adjustments in driving behavior could increase the driving range by more than 30% for passenger cars and more than 10% for buses.

"Our study not only answers the question of how far the vehicle can go, but also provides a quantitative basis for how to go farther," said Prof. CHEN. The study achieves a high-accuracy RDR estimation under diverse, real-world operating conditions, and provides an engineering-ready solution for intelligent EV fleet management.