Data-Driven Prediction and Optimization of Energy Use for Transit Fleets of Electric and ICE Vehicles

Ayman, Afiya; Sivagnanam, Amutheezan; Wilbur, Michael; Pugliese, Philip; Dubey, Abhishek; Laszka, Aron

doi:10.1145/3433992

Title: Data-Driven Prediction and Optimization of Energy Use for Transit Fleets of Electric and ICE Vehicles

Journal Article · Mon Feb 28 00:00:00 EST 2022 · ACM transactions on Internet technology (Online)

DOI:https://doi.org/10.1145/3433992· OSTI ID:1824214

Ayman, Afiya ^[1]; Sivagnanam, Amutheezan ^[1]; Wilbur, Michael ^[2]; Pugliese, Philip ^[3]; Dubey, Abhishek ^[2]; Laszka, Aron ^[1]

Univ. of Houston, TX (United States)
Vanderbilt Univ., Nashville, TN (United States)
Chattanooga Area Regional Transportation Authority, Chattanooga, TN (United States)

Due to the high upfront cost of electric vehicles, many public transit agencies can afford only mixed fleets of internal combustion and electric vehicles. Optimizing the operation of such mixed fleets is challenging because it requires accurate trip-level predictions of electricity and fuel use as well as efficient algorithms for assigning vehicles to transit routes. We present a novel framework for the data-driven prediction of trip-level energy use for mixed-vehicle transit fleets and for the optimization of vehicle assignments, which we evaluate using data collected from the bus fleet of CARTA, the public transit agency of Chattanooga, TN. We first introduce a data collection, storage, and processing framework for system-level and high-frequency vehicle-level transit data, including domain-specific data cleansing methods. We train and evaluate machine learning models for energy prediction, demonstrating that deep neural networks attain the highest accuracy. Based on these predictions, we formulate the problem of minimizing energy use through assigning vehicles to fixed-route transit trips. We propose an optimal integer program as well as efficient heuristic and meta-heuristic algorithms, demonstrating the scalability and performance of these algorithms numerically using the transit network of CARTA.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Vanderbilt Univ., Nashville, TN (United States); University of Houston; Chattanooga Area Regional Transportation Authority, Chattanooga, TN (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE)

Grant/Contract Number:: EE0008467

OSTI ID:: 1824214

Journal Information:: ACM transactions on Internet technology (Online), Vol. 22, Issue 1; ISSN 1557-6051

Publisher:: Association for Computing MachineryCopyright Statement

Country of Publication:: United States

Language:: English

References (25)

OpenStreetMap: User-Generated Street Maps Haklay, M.; Weber, P. IEEE Pervasive Computing, Vol. 7, Issue 4 https://doi.org/10.1109/MPRV.2008.80	journal	October 2008
Optimal Routing and Charging of an Electric Vehicle Fleet for High-Efficiency Dynamic Transit Systems Chen, Tao; Zhang, Bowen; Pourbabak, Hajir IEEE Transactions on Smart Grid, Vol. 9, Issue 4 https://doi.org/10.1109/TSG.2016.2635025	journal	July 2018
Accurate and efficient map matching for challenging environments Mohamed, Reham; Aly, Heba; Youssef, Moustafa SIGSPATIAL '14: 22nd SIGSPATIAL International Conference on Advances in Geographic Information Systems, Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems https://doi.org/10.1145/2666310.2666429	conference	November 2014
Hidden Markov map matching through noise and sparseness Newson, Paul; Krumm, John Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems - GIS '09 https://doi.org/10.1145/1653771.1653818	conference	January 2009
Online map-matching based on Hidden Markov model for real-time traffic sensing applications Goh, C. Y.; Dauwels, J.; Mitrovic, N. 2012 15th International IEEE Conference on Intelligent Transportation Systems https://doi.org/10.1109/ITSC.2012.6338627	conference	September 2012
Big Data Analysis: Apache Storm Perspective [English] Hussain Iqbal, Muhammad; Rahim Soomro, Tariq International Journal of Computer Trends and Technology, Vol. 19, Issue 1 https://doi.org/10.14445/22312803/IJCTT-V19P103	journal	January 2015
Mixed bus fleet scheduling under range and refueling constraints Li, Lu; Lo, Hong K.; Xiao, Feng Transportation Research Part C: Emerging Technologies, Vol. 104 https://doi.org/10.1016/j.trc.2019.05.009	journal	July 2019
An Adaptive Learning-Based Approach for Nearly Optimal Dynamic Charging of Electric Vehicle Fleets Korkas, Christos D.; Baldi, Simone; Yuan, Shuai IEEE Transactions on Intelligent Transportation Systems, Vol. 19, Issue 7 https://doi.org/10.1109/TITS.2017.2737477	journal	July 2018
Collaborative Optimization of Vehicle and Charging Scheduling for a Bus Fleet Mixed With Electric and Traditional Buses Zhou, Guang-Jing; Xie, Dong-Fan; Zhao, Xiao-Mei IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2964391	journal	January 2020
Data-Driven Prediction of Route-Level Energy Use for Mixed-Vehicle Transit Fleets Ayman, Afiya; Wilbur, Michael; Sivagnanam, Amutheezan 2020 IEEE International Conference on Smart Computing (SMARTCOMP) https://doi.org/10.1109/SMARTCOMP50058.2020.00026	conference	September 2020
Vehicle positioning system with multi‐hypothesis map matching and robust feedback Zhang, Kai; Liu, Shaojun; Dong, Yuhan IET Intelligent Transport Systems, Vol. 11, Issue 10 https://doi.org/10.1049/iet-its.2017.0072	journal	July 2017
Improving Energy Efficiency of Public Transport Bus Services by Using Multiple Vehicle Types Hassold, Stephan; Ceder, Avishai (Avi) Transportation Research Record: Journal of the Transportation Research Board, Vol. 2415, Issue 1 https://doi.org/10.3141/2415-07	journal	January 2014
A scenario-based map-matching algorithm for complex urban road network Kong, Xiangfu; Yang, Jiawen Journal of Intelligent Transportation Systems, Vol. 23, Issue 6 https://doi.org/10.1080/15472450.2019.1586543	journal	March 2019
A Data-Driven and Optimal Bus Scheduling Model With Time-Dependent Traffic and Demand Wang, Yuan; Zhang, Dongxiang; Hu, Lu IEEE Transactions on Intelligent Transportation Systems, Vol. 18, Issue 9 https://doi.org/10.1109/TITS.2016.2644725	journal	September 2017
Charging cost optimization for EV buses using neural network based energy predictor Nageshrao, Subramanya P.; Jacob, Jubin; Wilkins, Steven IFAC-PapersOnLine, Vol. 50, Issue 1 https://doi.org/10.1016/j.ifacol.2017.08.1493	journal	July 2017
Fuel consumption prediction of fleet vehicles using Machine Learning: A comparative study Wickramanayake, Sandareka; Dilum Bandara, H. M. N. 2016 Moratuwa Engineering Research Conference (MERCon) https://doi.org/10.1109/MERCon.2016.7480121	conference	April 2016
A time–space network based exact optimization model for multi-depot bus scheduling Kliewer, Natalia; Mellouli, Taïeb; Suhl, Leena European Journal of Operational Research, Vol. 175, Issue 3 https://doi.org/10.1016/j.ejor.2005.02.030	journal	December 2006
Operation and charging scheduling of electric buses in a city bus route network Paul, Topon; Yamada, Hisashi 17th International IEEE Conference on Intelligent Transportation Systems (ITSC) https://doi.org/10.1109/ITSC.2014.6958135	conference	October 2014
A Data-Driven Method for Energy Consumption Prediction and Energy-Efficient Routing of Electric Vehicles in Real-World Conditions De Cauwer, Cedric; Verbeke, Wouter; Coosemans, Thierry Energies, Vol. 10, Issue 5 https://doi.org/10.3390/en10050608	journal	May 2017
Transit Bus Scheduling with Limited Energy Li, Jing-Quan Transportation Science, Vol. 48, Issue 4 https://doi.org/10.1287/trsc.2013.0468	journal	November 2014
Apache Spark: a unified engine for big data processing Zaharia, Matei; Franklin, Michael J.; Ghodsi, Ali Communications of the ACM, Vol. 59, Issue 11 https://doi.org/10.1145/2934664	journal	October 2016
A weight-based map-matching algorithm for vehicle navigation in complex urban networks Hashemi, Mahdi; Karimi, Hassan A. Journal of Intelligent Transportation Systems, Vol. 20, Issue 6 https://doi.org/10.1080/15472450.2016.1166058	journal	May 2016
Feature Selection Li, Jundong; Cheng, Kewei; Wang, Suhang ACM Computing Surveys, Vol. 50, Issue 6 https://doi.org/10.1145/3136625	journal	December 2017
An Electric Bus Power Consumption Model and Optimization of Charging Scheduling Concerning Multi-External Factors Gao, Yajing; Guo, Shixiao; Ren, Jiafeng Energies, Vol. 11, Issue 8 https://doi.org/10.3390/en11082060	journal	August 2018
bCharge: Data-Driven Real-Time Charging Scheduling for Large-Scale Electric Bus Fleets Wang, Guang; Xie, Xiaoyang; Zhang, Fan 2018 IEEE Real-Time Systems Symposium (RTSS) https://doi.org/10.1109/RTSS.2018.00015	conference	December 2018

Similar Records

Minimizing Energy Use of Mixed-Fleet Public Transit for Fixed-Route Service

Journal Article · Tue May 18 00:00:00 EDT 2021 · Proceedings of the AAAI Conference on Artificial Intelligence · OSTI ID:1824214

Sivagnanam, Amutheezan; Ayman, Afiya; Wilbur, Michael; +3 more

High-dimensional Data-driven Energy optimization for Multi-Modal Transit Agencies (HD-EMMA) (Final Technical Report)

Technical Report · Wed Sep 01 00:00:00 EDT 2021 · OSTI ID:1824214

Pugliese, Philip; Dubey, Abhishek; Laszka, Aron; +5 more

Energy and Emission Prediction for Mixed-Vehicle Transit Fleets Using Multi-task and Inductive Transfer Learning

Other · Fri Sep 10 00:00:00 EDT 2021 · Lecture Notes in Computer Science · OSTI ID:1824214

Wilbur, Michael; Mukhopadhyay, Ayan; Vazirizade, Sayyed; +3 more

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
33 ADVANCED PROPULSION SYSTEMS

Title: Data-Driven Prediction and Optimization of Energy Use for Transit Fleets of Electric and ICE Vehicles

Citation Formats

References (25)

Similar Records

Related Subjects