Energy Estimation of Last Mile Electric Vehicle Routes

TL;DR

This paper introduces deep learning models, including a novel Transformer-based approach, to accurately predict energy consumption of electric vehicles on last-mile delivery routes, surpassing traditional methods.

Contribution

It proposes a range of deep learning solutions, notably the Route Energy Transformer (RET), for energy prediction in EV routing, achieving significant accuracy improvements over existing models.

Findings

RET improves MAPE by 217 bps over NN

Deep learning models outperform physics-based approaches

Energy prediction enables better EV route planning

Abstract

Last-mile carriers increasingly incorporate electric vehicles (EVs) into their delivery fleet to achieve sustainability goals. This goal presents many challenges across multiple planning spaces including but not limited to how to plan EV routes. In this paper, we address the problem of predicting energy consumption of EVs for Last-Mile delivery routes using deep learning. We demonstrate the need to move away from thinking about range and we propose using energy as the basic unit of analysis. We share a range of deep learning solutions, beginning with a Feed Forward Neural Network (NN) and Recurrent Neural Network (RNN) and demonstrate significant accuracy improvements relative to pure physics-based and distance-based approaches. Finally, we present Route Energy Transformer (RET) a decoder-only Transformer model sized according to Chinchilla scaling laws. RET yields a +217 Basis Points (bps) improvement in Mean Absolute Percentage Error (MAPE) relative to the Feed Forward NN and a +105 bps improvement relative to the RNN.