Prediction of Electric Buses Energy Consumption from Trip Parameters Using Deep Learning

Teresa Pamuła,Danuta Pamuła

doi:10.3390/en15051747

Abstract

The energy demand of electric buses (EBs) is a very important parameter that should be considered by transport companies when introducing electric buses into the urban bus fleet. This article proposes a novel deep-learning-based model for predicting energy consumption of an electric bus traveling in an urban area. The model addresses two important issues: accuracy and cost of prediction. The aim of the research was to develop the deep-learning-based prediction model, which requires only the data readily available to bus fleet operators, such as location of the bus stops (coordinates, altitude), route traveled, schedule, travel time between stops, and to find the most suitable type and configuration of neural network to evaluate the model. The developed prediction model was assessed with different types of deep neural networks using real data collected for several bus lines in a medium-sized city in Poland. Conducted research has shown that the deep learning network with autoencoders (DLNA) neural network allows for the most accurate energy consumption estimation of 93%. The proposed model can be used by public transport companies to plan driving schedules and energy management when introducing electric buses.

Highlights

Public transport is critical to the operation of urban systems
We propose a novel, original deep learning model for predicting energy consumption of a battery electric bus that uses readily available parameters: travel time between stops, the difference in altitude between stops, rush hours for a given line, weather conditions, and the distance between bus stops
We have considered various configurations and types of neural networks, such as deep learning networks with an autoencoder layer (DLNA) and a network of long short-term memory (LSTM) type

Summary

Introduction

Public transport is critical to the operation of urban systems. There is still a growing discussion on converting transport to so-called clean transport (using clean fuels) while improving service availability [1]. The popularity of electrification of public urban transport is growing due to the low greenhouse gas emissions and noise reduction compared to buses with conventional drive. The electrification of existing bus fleets requires determining the electric bus range and methods of charging, as well as planning the charging infrastructure and schedule that will not interrupt normal bus operation. Designing an efficient electric bus network requires determining the energy demand and selecting the appropriate battery capacity. The energy demand varies throughout the day under different traffic conditions which makes it difficult to estimate using conventional methods

Objectives

Methods

Results