Electric vehicles (EVs) are an attractive alternative to conventional vehicles powered by internal combustion engines due to their low carbon footprint, low running cost, and higher energy efficiency. However, currently, they suffer from a lower range than conventional vehicles, which induces range anxiety for consumers. This work explores the EV parameters that strongly impact range using data-driven techniques. A detailed dataset of the technical specifications of commercial EV models manufactured from 2008 to 2021 was collected through web mining. Strong correlations were observed between range and battery capacity, top speed, curb weight, and acceleration (with Pearson coefficients of 0.90, 0.79, 0.70, and −0.84, respectively). Furthermore, regression algorithms were trained and tested on this dataset, with the lowest root-mean-squared error (RMSE) of 31.4 km obtained from support vector machine regression. With a mean EV range in the test set of 364.5 km, an RMSE of 31.4 km equates to around 8.6% accuracy. Additionally, simple linear relationships between EV range and EV model, battery, and performance parameters were determined that may be useful to EV consumers in calculating range.

With the global rise in consumer electronics, electric vehicles, and renewable energy, the demand for lithium-ion batteries (LIBs) is expected to grow. LIBs present a significant challenge for state estimations due to their complex non-linear electrochemical behavior. Currently, commercial battery management systems (BMSs) commonly use easier-to-implement and faster equivalent circuit models (ECMs) than their counterpart continuum-scale physics-based models (PBMs). However, despite processing more mathematical and computational complexity, PBMs are attractive due to their higher accuracy, higher fidelity, and ease of integration with thermal and degradation models. Various reduced-order PBM battery models and their computationally efficient numerical schemes have been proposed in the literature. However, there is limited data on the performance and feasibility of these models in practical embedded and cloud systems using standard programming languages. This study compares the computational performance of a single particle model (SPM), an enhanced single particle model (ESPM), and a reduced-order pseudo-two-dimensional (ROM-P2D) model under various battery cycles on embedded and cloud systems using Python and C++. The results show that reduced-order solvers can achieve a 100-fold reduction in solution times compared to full-order models, while ESPM with electrolyte dynamics is about 1.5 times slower than SPM. Adding thermal models and Kalman filters increases solution times by approximately 20% and 100%, respectively. C++ provides at least a 10-fold speed increase over Python, varying by cycle steps. Although embedded systems take longer than cloud and personal computers, they can still run reduced-order models effectively in Python, making them suitable for embedded applications.