- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Data-driven power estimation of electric buses using...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Data-driven power estimation of electric buses using deep LSTM neural networks and symbolic aggregate approximation filtering Zarei, Pegah
Abstract
This thesis proposes a deep learning framework for estimating the power use of electric vehicle drivetrains, using an artificial recurrent neural network architecture (long short-term memory), and techniques for data curation and analysis. Power samples of battery-electric buses operating in Victoria, B.C. were deployed to train, validate, and test the model. Microtrips were extracted from the dataset by taking out proportions of time spent at standstill. Anomalous trends of the dataset components were detected, marked as outliers, and excluded from the model input using Symbolic Aggregate approXimation (SAX) transformation filtering algorithm. A systematic optimization process is adopted to achieve the best hyperparameter configuration for this estimation task. The resulting fine-tuned deep LSTM model is then created, evaluated, and tested. More effort has been devoted to enhancing the efficacy of the model through investigating alternative model configurations and formulations. Among the several configurations tested, the best power consumption modeling approach yielded an error of about 5% (the RMSE of 0.05747) and a squared correlation coefficient of beyond 90% (R² of 0.92502). [This thesis was revised on October 25, 2021.]
Item Metadata
| Title |
Data-driven power estimation of electric buses using deep LSTM neural networks and symbolic aggregate approximation filtering
|
| Creator | |
| Publisher |
University of British Columbia
|
| Date Issued |
2020
|
| Description |
This thesis proposes a deep learning framework for estimating the power use of electric vehicle drivetrains, using an artificial recurrent neural network architecture (long short-term memory), and techniques for data curation and analysis. Power samples of battery-electric buses operating in Victoria, B.C. were deployed to train, validate, and test the model. Microtrips were extracted from the dataset by taking out proportions of time spent at standstill. Anomalous trends of the dataset components were detected, marked as outliers, and excluded from the model input using Symbolic Aggregate approXimation (SAX) transformation filtering algorithm. A systematic optimization process is adopted to achieve the best hyperparameter configuration for this estimation task. The resulting fine-tuned deep LSTM model is then created, evaluated, and tested. More effort has been devoted to enhancing the efficacy of the model through investigating alternative model configurations and formulations. Among the several configurations tested, the best power consumption modeling approach yielded an error of about 5% (the RMSE of 0.05747) and a squared correlation coefficient of beyond 90% (R² of 0.92502). [This thesis was revised on October 25, 2021.]
|
| Genre | |
| Type | |
| Language |
eng
|
| Date Available |
2022-01-31
|
| Provider |
Vancouver : University of British Columbia Library
|
| Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
| DOI |
10.14288/1.0395392
|
| URI | |
| Degree | |
| Program | |
| Affiliation | |
| Degree Grantor |
University of British Columbia
|
| Graduation Date |
2021-05
|
| Campus | |
| Scholarly Level |
Graduate
|
| Rights URI | |
| Aggregated Source Repository |
DSpace
|
Item Media
Loading media...
Item Citations and Data
Permanent URL (DOI):
Copied to clipboard.Rights
Attribution-NonCommercial-NoDerivatives 4.0 International