Abstract
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.
- OpenStreetMap Foundation. 2018. Traffic Message Channel. https://wiki.openstreetmap.org/wiki/TMC.Google Scholar
- Apache Software Foundation. 2019. Apache BookKeeper – A scalable, fault-tolerant, and low-latency storage service optimized for real-time workloads. https://bookkeeper.apache.org/.Google Scholar
- Apache Software Foundation. 2019. Apache Pulsar – An open-source distributed pub-sub messaging system. https://pulsar.apache.org/.Google Scholar
- Apache Software Foundation. 2019. Apache ZooKeeper. https://zookeeper.apache.org/.Google Scholar
- MongoDB, Inc. 2019. MongoDB – The database for modern applications. https://www.mongodb.com/.Google Scholar
- Google LLC. 2020. Google Cloud Platform. https://cloud.google.com/.Google Scholar
- VMware, Inc. 2020. VMware. https://www.vmware.com/.Google Scholar
- Afiya Ayman, Michael Wilbur, Amutheezan Sivagnanam, Philip Pugliese, Abhishek Dubey, and Aron Laszka. 2020. Data-driven prediction of route-level energy use for mixed-vehicle transit fleets. In Proceedings of the 6th IEEE International Conference on Smart Computing (SMARTCOMP’20).Google Scholar
Cross Ref
- Tao Chen, Bowen Zhang, Hajir Pourbabak, Abdollah Kavousi-Fard, and Wencong Su. 2016. Optimal routing and charging of an electric vehicle fleet for high-efficiency dynamic transit systems. IEEE Transactions on Smart Grid 9, 4 (2016), 3563–3572.Google Scholar
Cross Ref
- François Chollet et al. 2015. Keras. https://keras.io.Google Scholar
- Dark Sky. 2019. API Documentation. https://darksky.net/dev/docs.Google Scholar
- Cedric De Cauwer, Wouter Verbeke, Thierry Coosemans, Saphir Faid, and Joeri Van Mierlo. 2017. A data-driven method for energy consumption prediction and energy-efficient routing of electric vehicles in real-world conditions. Energies 10, 5 (2017), 608.Google Scholar
Cross Ref
- EIA. 2018. U.S. Energy Information Administration: Use of energy explained – Energy use for transportation.Retrieved May 31, 2020, from https://www.eia.gov/energyexplained/use-of-energ y/transportation.php.Google Scholar
- Yajing Gao, Shixiao Guo, Jiafeng Ren, Zheng Zhao, Ali Ehsan, and Yanan Zheng. 2018. An electric bus power consumption model and optimization of charging scheduling concerning multi-external factors. Energies 11, 8 (2018), 2060.Google Scholar
Cross Ref
- Chong Yang Goh, Justin Dauwels, Nikola Mitrovic, Muhammad Tayyab Asif, Ali Oran, and Patrick Jaillet. 2012. Online map-matching based on hidden Markov model for real-time traffic sensing applications. In 2012 15th International IEEE Conference on Intelligent Transportation Systems. IEEE, 776–781.Google Scholar
Cross Ref
- Mordechai Haklay and Patrick Weber. 2008. OpenStreetMap: User-generated street maps. IEEE Pervasive Computing 7, 4 (2008), 12–18. Google Scholar
Digital Library
- Mahdi Hashemi and Hassan A. Karimi. 2016. A machine learning approach to improve the accuracy of GPS-based map-matching algorithms. In 2016 IEEE 17th International Conference on Information Reuse and Integration (IRI’16). IEEE, 77–86.Google Scholar
- Mahdi Hashemi and Hassan A. Karimi. 2016. A weight-based map-matching algorithm for vehicle navigation in complex urban networks. Journal of Intelligent Transportation Systems 20, 6 (2016), 573–590.Google Scholar
Cross Ref
- Stephan Hassold and Avishai Ceder. 2014. Improving energy efficiency of public transport bus services by using multiple vehicle types. Transportation Research Record 2415, 1 (2014), 65–71.Google Scholar
Cross Ref
- HERE. 2020. HERE Maps API. Retrieved May 31, 2020, from https://developer.here.com/.Google Scholar
- Selin Hulagu and Hilmi Berk Celikoglu. 2020. An electric vehicle routing problem with intermediate nodes for shuttle fleets. IEEE Transactions on Intelligent Transportation Systems. https://ieeexplore.ieee.org/abstract/document/9204749.Google Scholar
- Muhammad Hussain Iqbal and Tariq Rahim Soomro. 2015. Big data analysis: Apache storm perspective. International Journal of Computer Trends and Technology 19, 1 (2015), 9–14.Google Scholar
Cross Ref
- Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Natalia Kliewer, Vitali Gintner, and Leena Suhl. 2008. Line change considerations within a time-space network based multi-depot bus scheduling model. In Computer-Aided Systems in Public Transport. Springer, 57–70.Google Scholar
- Natalia Kliewer, Taieb Mellouli, and Leena Suhl. 2006. A time–space network based exact optimization model for multi-depot bus scheduling. European Journal of Operational Research 175, 3 (2006), 1616–1627.Google Scholar
Cross Ref
- Xiangfu Kong and Jiawen Yang. 2019. A scenario-based map-matching algorithm for complex urban road network. Journal of Intelligent Transportation Systems 23, 6 (2019), 617–631.Google Scholar
Cross Ref
- Christos D. Korkas, Simone Baldi, Shuai Yuan, and Elias B. Kosmatopoulos. 2017. An adaptive learning-based approach for nearly optimal dynamic charging of electric vehicle fleets. IEEE Transactions on Intelligent Transportation Systems 19, 7 (2017), 2066–2075.Google Scholar
Cross Ref
- Jundong Li, Kewei Cheng, Suhang Wang, Fred Morstatter, Robert P. Trevino, Jiliang Tang, and Huan Liu. 2017. Feature selection: A data perspective. Computing Surveys 50, 6 (2017), 1–45. Google Scholar
Digital Library
- Jing-Quan Li. 2014. Transit bus scheduling with limited energy. Transportation Science 48, 4 (2014), 521–539. Google Scholar
Digital Library
- Lu Li, Hong K. Lo, and Feng Xiao. 2019. Mixed bus fleet scheduling under range and refueling constraints. Transportation Research Part C: Emerging Technologies 104 (2019), 443–462.Google Scholar
Cross Ref
- Reham Mohamed, Heba Aly, and Moustafa Youssef. 2014. Accurate and efficient map matching for challenging environments. In Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 401–404. Google Scholar
Digital Library
- Yi Lu Murphey, Jungme Park, Zhihang Chen, Ming L. Kuang, M. Abul Masrur, and Anthony M. Phillips. 2012. Intelligent hybrid vehicle power control–Part I: Machine learning of optimal vehicle power. IEEE Transactions on Vehicular Technology 61, 8 (2012), 3519–3530.Google Scholar
Cross Ref
- Subramanya P. Nageshrao, Jubin Jacob, and Steven Wilkins. 2017. Charging cost optimization for EV buses using neural network based energy predictor. IFAC-PapersOnLine 50, 1 (2017), 5947–5952.Google Scholar
Cross Ref
- Paul Newson and John Krumm. 2009. Hidden Markov map matching through noise and sparseness. In Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 336–343. Google Scholar
Digital Library
- Office of Transportation and Air Quality. 2019. Fast Facts: U.S. Transportation Sector Greenhouse Gas Emissions 1990–2017. Technical Report EPA-420-F-19-047. https://nepis.epa.gov/Exe/ZyPDF.cgi?Dockey=P100WUHR.pdf.Google Scholar
- Aleksandra O’Donovan, James Frith Analyst, and Colin McKerracher. 2018. Electric Buses in Cities: Driving Towards Cleaner Air and Lower CO2. Bloomberg New Energy Finance. https://data.bloomberglp.com/professional/sites/24/2018/05/Electric-Bus es-in-Cities-Report-BNEF-C40-Citi.pdf.Google Scholar
- Topon Paul and Hisashi Yamada. 2014. Operation and charging scheduling of electric buses in a city bus route network. In 17th International IEEE Conference on Intelligent Transportation Systems (ITSC’14). IEEE, 2780–2786.Google Scholar
Cross Ref
- Federico Perrotta, Tony Parry, and Luis C. Neves. 2017. Application of machine learning for fuel consumption modelling of trucks. In 2017 IEEE International Conference on Big Data (Big Data’17). IEEE, 3810–3815.Google Scholar
- Diogo Santos, Zafeiris Kokkinogenis, Jorge Freire de Sousa, Deborah Perrotta, and Rosaldo J. F. Rossetti. 2016. Towards the integration of electric buses in conventional bus fleets. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC’16). IEEE, 88–93.Google Scholar
- Scikit-learn Developers. Sklearn.Tree.DecisionTreeRegressor. Retrieved May 31, 2020, from https://scikit-learn.org/stable/modules/generate d/sklearn.tree.DecisionTreeRegressor.html.Google Scholar
- Tennessee Department of Finance and Administration. 2019. Elevation Data. https://www.tn.gov/finance/sts-gis/gis/data.html.Google Scholar
- USGS. 2019. The National Map. https://pubs.er.usgs.gov/publication/fs20193032.Google Scholar
- Guang Wang, Xiaoyang Xie, Fan Zhang, Yunhuai Liu, and Desheng Zhang. 2018. bCharge: Data-driven real-time charging scheduling for large-scale electric bus fleets. In 2018 IEEE Real-Time Systems Symposium (RTSS’18). 45–55.Google Scholar
Cross Ref
- Yuan Wang, Dongxiang Zhang, Lu Hu, Yang Yang, and Loo Hay Lee. 2017. A data-driven and optimal bus scheduling model with time-dependent traffic and demand. IEEE Transactions on Intelligent Transportation Systems 18, 9 (2017), 2443–2452.Google Scholar
Digital Library
- Sandareka Wickramanayake and H. M. N. Dilum Bandara. 2016. Fuel consumption prediction of fleet vehicles using machine learning: A comparative study. In 2016 Moratuwa Engineering Research Conference (MERCon’16). IEEE, 90–95.Google Scholar
Cross Ref
- Matei Zaharia, Reynold S. Xin, Patrick Wendell, Tathagata Das, Michael Armbrust, Ankur Dave, Xiangrui Meng, Josh Rosen, Shivaram Venkataraman, Michael J. Franklin, et al. 2016. Apache Spark: A unified engine for big data processing. Communications of the ACM 59, 11 (2016), 56–65. Google Scholar
Digital Library
- Kai Zhang, Shaojun Liu, Yuhan Dong, Daoshun Wang, Yi Zhang, and Lixin Miao. 2017. Vehicle positioning system with multi-hypothesis map matching and robust feedback. IET Intelligent Transport Systems 11, 10 (2017), 649–658.Google Scholar
Cross Ref
- Guang-Jing Zhou, Dong-Fan Xie, Xiao-Mei Zhao, and Chaoru Lu. 2020. Collaborative optimization of vehicle and charging scheduling for a bus fleet mixed with electric and traditional buses. IEEE Access 8 (2020), 8056–8072.Google Scholar
Cross Ref
Index Terms
Data-Driven Prediction and Optimization of Energy Use for Transit Fleets of Electric and ICE Vehicles
Recommendations
Community Energy Management with Electric Vehicles for Effective Use of Solar Energy
ICAIET '14: Proceedings of the 2014 4th International Conference on Artificial Intelligence with Applications in Engineering and TechnologyPhotovoltaic generation (PV) output varies depending on the time, weather, and season. In these days, batteries equipped in electric vehicles (EVs) can be utilized as substitutes for the storage systems, and are expected to use output of PV generation ...
Hybrid energy storage systems and battery management for electric vehicles
DAC '13: Proceedings of the 50th Annual Design Automation ConferenceElectric vehicles (EV) are considered as a strong alternative of internal combustion engine vehicles expecting lower carbon emission. However, their actual benefits are not yet clearly verified while the energy efficiency can be improved in many ways. ...
Electric Vehicle Optimized Charge and Drive Management
Electric vehicles (EVs) have been considered as a solution to the environmental issues caused by transportation, such as air pollution and greenhouse gas emission. However, limited energy capacity, scarce EV supercharging stations, and long recharging ...






Comments