Michael Wilbur, Ayan Mukhopadhyay, Sayyed Vazirizade, Philip Pugliese, Aron Laszka, Abhishek Dubey
Joint European Conference on Machine Learning and Knowledge Discovery in Databases 2021
Accurately predicting energy consumption across heterogeneous transit fleets is essential for operational planning and environmental impact assessment, but limited data for each vehicle type makes this challenging. This work is significant because it leverages transfer learning to improve prediction accuracy when some vehicle types have insufficient training data. The multi-task learning approach captures generalizable patterns across vehicle classes.
This paper proposes energy and emission prediction for mixed-vehicle transit fleets using multi-task learning and inductive transfer learning approaches. The framework addresses the challenge of predicting energy consumption for diverse vehicle types by leveraging shared representations across vehicle classes. The approach develops a unified prediction model that can handle variations in vehicle specifications and operating conditions.
The multi-task learning approach significantly outperformed vehicle-specific baseline models, particularly for vehicle classes with limited data. The inductive transfer learning successfully improved predictive accuracy for classes with insufficient training samples. The evaluation on real transit data demonstrated that the proposed approach achieves better generalization and handles new vehicle types more effectively than traditional methods.
@inproceedings{ecml2021,
author = {Wilbur, Michael and Mukhopadhyay, Ayan and Vazirizade, Sayyed and Pugliese, Philip and Laszka, Aron and Dubey, Abhishek},
booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases},
title = {Energy and Emission Prediction for Mixed-Vehicle Transit Fleets Using Multi-Task and Inductive Transfer Learning},
year = {2021},
acceptance = {29},
abstract = {Public transit agencies are focused on making their fixed-line bus systems more energy efficient by introducing electric (EV) and hybrid (HV) vehicles to their eets. However, because of the high upfront cost of these vehicles, most agencies are tasked with managing a mixed-fleet of internal combustion vehicles (ICEVs), EVs, and HVs. In managing mixed-fleets, agencies require accurate predictions of energy use for optimizing the assignment of vehicles to transit routes, scheduling charging, and ensuring that emission standards are met. The current state-of-the-art is to develop separate neural network models to predict energy consumption for each vehicle class. Although different vehicle classes' energy consumption depends on a varied set of covariates, we hypothesize that there are broader generalizable patterns that govern energy consumption and emissions. In this paper, we seek to extract these patterns to aid learning to address two problems faced by transit agencies. First, in the case of a transit agency which operates many ICEVs, HVs, and EVs, we use multi-task learning (MTL) to improve accuracy of forecasting energy consumption. Second, in the case where there is a significant variation in vehicles in each category, we use inductive transfer learning (ITL) to improve predictive accuracy for vehicle class models with insufficient data. As this work is to be deployed by our partner agency, we also provide an online pipeline for joining the various sensor streams for fixed-line transit energy prediction. We find that our approach outperforms vehicle-specific baselines in both the MTL and ITL settings.},
contribution = {lead},
tag = {ai4cps,transit},
keywords = {energy prediction, transit systems, multi-task learning, transfer learning, emissions, vehicle fleets}
}