A Deep Learning Approach for Macroscopic Energy Consumption Prediction with Microscopic Quality for Electric Vehicles. Moawad, A., Gurumurthy, K. M., Verbas, O., Li, Z., Islam, E., Freyermuth, V., & Rousseau, A. arXiv:2111.12861 [cs], November, 2021. arXiv: 2111.12861
Paper abstract bibtex This paper presents a machine learning approach to model the electric consumption of electric vehicles at macroscopic level, i.e., in the absence of a speed profile, while preserving microscopic level accuracy. For this work, we leveraged a high-performance, agent-based transportation tool to model trips that occur in the Greater Chicago region under various scenario changes, along with physics-based modeling and simulation tools to provide high-fidelity energy consumption values. The generated results constitute a very large dataset of vehicle-route energy outcomes that capture variability in vehicle and routing setting, and in which high-fidelity time series of vehicle speed dynamics is masked. We show that although all internal dynamics that affect energy consumption are masked, it is possible to learn aggregate-level energy consumption values quite accurately with a deep learning approach. When large-scale data is available, and with carefully tailored feature engineering, a well-designed model can overcome and retrieve latent information. This model has been deployed and integrated within POLARIS Transportation System Simulation Tool to support real-time behavioral transportation models for individual charging decision-making, and rerouting of electric vehicles.
@article{moawad_deep_2021,
title = {A {Deep} {Learning} {Approach} for {Macroscopic} {Energy} {Consumption} {Prediction} with {Microscopic} {Quality} for {Electric} {Vehicles}},
url = {https://anl.box.com/s/fsexy08ee86c5r5l4pv9fglxt0dignjc},
abstract = {This paper presents a machine learning approach to model the electric consumption of electric vehicles at macroscopic level, i.e., in the absence of a speed profile, while preserving microscopic level accuracy. For this work, we leveraged a high-performance, agent-based transportation tool to model trips that occur in the Greater Chicago region under various scenario changes, along with physics-based modeling and simulation tools to provide high-fidelity energy consumption values. The generated results constitute a very large dataset of vehicle-route energy outcomes that capture variability in vehicle and routing setting, and in which high-fidelity time series of vehicle speed dynamics is masked. We show that although all internal dynamics that affect energy consumption are masked, it is possible to learn aggregate-level energy consumption values quite accurately with a deep learning approach. When large-scale data is available, and with carefully tailored feature engineering, a well-designed model can overcome and retrieve latent information. This model has been deployed and integrated within POLARIS Transportation System Simulation Tool to support real-time behavioral transportation models for individual charging decision-making, and rerouting of electric vehicles.},
urldate = {2021-12-10},
journal = {arXiv:2111.12861 [cs]},
author = {Moawad, Ayman and Gurumurthy, Krishna Murthy and Verbas, Omer and Li, Zhijian and Islam, Ehsan and Freyermuth, Vincent and Rousseau, Aymeric},
month = nov,
year = {2021},
note = {arXiv: 2111.12861},
keywords = {AI, Autonomie, DOE SMART, Transportation systems},
}
Downloads: 0
{"_id":"QoQeMHrEgqmNyHSAT","bibbaseid":"moawad-gurumurthy-verbas-li-islam-freyermuth-rousseau-adeeplearningapproachformacroscopicenergyconsumptionpredictionwithmicroscopicqualityforelectricvehicles-2021","author_short":["Moawad, A.","Gurumurthy, K. M.","Verbas, O.","Li, Z.","Islam, E.","Freyermuth, V.","Rousseau, A."],"bibdata":{"bibtype":"article","type":"article","title":"A Deep Learning Approach for Macroscopic Energy Consumption Prediction with Microscopic Quality for Electric Vehicles","url":"https://anl.box.com/s/fsexy08ee86c5r5l4pv9fglxt0dignjc","abstract":"This paper presents a machine learning approach to model the electric consumption of electric vehicles at macroscopic level, i.e., in the absence of a speed profile, while preserving microscopic level accuracy. For this work, we leveraged a high-performance, agent-based transportation tool to model trips that occur in the Greater Chicago region under various scenario changes, along with physics-based modeling and simulation tools to provide high-fidelity energy consumption values. The generated results constitute a very large dataset of vehicle-route energy outcomes that capture variability in vehicle and routing setting, and in which high-fidelity time series of vehicle speed dynamics is masked. We show that although all internal dynamics that affect energy consumption are masked, it is possible to learn aggregate-level energy consumption values quite accurately with a deep learning approach. When large-scale data is available, and with carefully tailored feature engineering, a well-designed model can overcome and retrieve latent information. This model has been deployed and integrated within POLARIS Transportation System Simulation Tool to support real-time behavioral transportation models for individual charging decision-making, and rerouting of electric vehicles.","urldate":"2021-12-10","journal":"arXiv:2111.12861 [cs]","author":[{"propositions":[],"lastnames":["Moawad"],"firstnames":["Ayman"],"suffixes":[]},{"propositions":[],"lastnames":["Gurumurthy"],"firstnames":["Krishna","Murthy"],"suffixes":[]},{"propositions":[],"lastnames":["Verbas"],"firstnames":["Omer"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Zhijian"],"suffixes":[]},{"propositions":[],"lastnames":["Islam"],"firstnames":["Ehsan"],"suffixes":[]},{"propositions":[],"lastnames":["Freyermuth"],"firstnames":["Vincent"],"suffixes":[]},{"propositions":[],"lastnames":["Rousseau"],"firstnames":["Aymeric"],"suffixes":[]}],"month":"November","year":"2021","note":"arXiv: 2111.12861","keywords":"AI, Autonomie, DOE SMART, Transportation systems","bibtex":"@article{moawad_deep_2021,\n\ttitle = {A {Deep} {Learning} {Approach} for {Macroscopic} {Energy} {Consumption} {Prediction} with {Microscopic} {Quality} for {Electric} {Vehicles}},\n\turl = {https://anl.box.com/s/fsexy08ee86c5r5l4pv9fglxt0dignjc},\n\tabstract = {This paper presents a machine learning approach to model the electric consumption of electric vehicles at macroscopic level, i.e., in the absence of a speed profile, while preserving microscopic level accuracy. For this work, we leveraged a high-performance, agent-based transportation tool to model trips that occur in the Greater Chicago region under various scenario changes, along with physics-based modeling and simulation tools to provide high-fidelity energy consumption values. The generated results constitute a very large dataset of vehicle-route energy outcomes that capture variability in vehicle and routing setting, and in which high-fidelity time series of vehicle speed dynamics is masked. We show that although all internal dynamics that affect energy consumption are masked, it is possible to learn aggregate-level energy consumption values quite accurately with a deep learning approach. When large-scale data is available, and with carefully tailored feature engineering, a well-designed model can overcome and retrieve latent information. This model has been deployed and integrated within POLARIS Transportation System Simulation Tool to support real-time behavioral transportation models for individual charging decision-making, and rerouting of electric vehicles.},\n\turldate = {2021-12-10},\n\tjournal = {arXiv:2111.12861 [cs]},\n\tauthor = {Moawad, Ayman and Gurumurthy, Krishna Murthy and Verbas, Omer and Li, Zhijian and Islam, Ehsan and Freyermuth, Vincent and Rousseau, Aymeric},\n\tmonth = nov,\n\tyear = {2021},\n\tnote = {arXiv: 2111.12861},\n\tkeywords = {AI, Autonomie, DOE SMART, Transportation systems},\n}\n\n","author_short":["Moawad, A.","Gurumurthy, K. M.","Verbas, O.","Li, Z.","Islam, E.","Freyermuth, V.","Rousseau, A."],"key":"moawad_deep_2021","id":"moawad_deep_2021","bibbaseid":"moawad-gurumurthy-verbas-li-islam-freyermuth-rousseau-adeeplearningapproachformacroscopicenergyconsumptionpredictionwithmicroscopicqualityforelectricvehicles-2021","role":"author","urls":{"Paper":"https://anl.box.com/s/fsexy08ee86c5r5l4pv9fglxt0dignjc"},"keyword":["AI","Autonomie","DOE SMART","Transportation systems"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://api.zotero.org/groups/2254223/items?key=Bbol5AZSx3A5fDcmq91mfOKd&format=bibtex&limit=100","dataSources":["rY8uL8LFtJi4FqTy8","qc6TuRNtLYeLyawhB","cGgmoLgbNTEZGWgPE","YAe24F3YNSozTyd4w","3DafxWjHsFsQwSZ2s","hrgMhj9JTHdmk3x5P"],"keywords":["ai","autonomie","doe smart","transportation systems"],"search_terms":["deep","learning","approach","macroscopic","energy","consumption","prediction","microscopic","quality","electric","vehicles","moawad","gurumurthy","verbas","li","islam","freyermuth","rousseau"],"title":"A Deep Learning Approach for Macroscopic Energy Consumption Prediction with Microscopic Quality for Electric Vehicles","year":2021,"downloads":1}