Using Machine Learning to Guide Simulations Over Unique Samples from Trip Profiles 2018-01-1202
Electric vehicles are highly sensitive to variations in environmental factors (like temperature, drive style, grade, etc.). The distribution of real-world range of electric vehicles due to these environmental factors is an important consideration in target setting. This distribution can be obtained by running several simulations of an electric vehicle for a number of high-frequency velocity, grade, and temperature real-world trip profiles. However, in order to speed up simulation time, a unique set of drive profiles that represent the entire real-world data set needs to be developed.
In this study, we consider 40,000 unique velocity and grade profiles from various real-world applications in EU. We generate metadata that describes these profiles using trip descriptor variables. Due to the large number of descriptor variables when considering second order effects, we normalize each descriptor and use principal component analysis to reduce the dimensions of our dataset to six components. This is based on achieving a high explained variance ratio. Clustering is then performed on this dataset using the k-means algorithm implemented in Scikit-learn. We select sample representative trips by optimizing between the inertia obtained from the k-means algorithm and the explained variance ratio of principal component analysis. The number of representative trips selected is also driven by the performance of simulations for real-world range calculations. Range simulations can now be performed on these select representative trips to obtain a distribution of expected real-world range.