Quantitative Insights Into Electric Vehicle Registration Dynamics In New York State: A Comparative Time-Series And Machine Learning Forecasting Study
DOI:
https://doi.org/10.29284/s3s2tz86Keywords:
Electric vehicles · Plug-in hybrid electric vehicles · Time-series forecasting · ARIMA · ETS · Spatial analysis · New York State · Registration data · Machine learning · Adoption dynamics.Abstract
The rapid proliferation of electric vehicles (EVs) poses significant challenges for infrastructure planning, energy-grid management, and evidence-based policy design. This study presents a rigorous, data-driven investigation of EV registration dynamics in New York State (NYS) over the period 2011–2022, employing a dataset of 4,067,756 registration records sourced from the New York State Energy Research and Development Authority (NYSERDA). We conduct systematic exploratory analyses of drivetrain composition, vehicle category distribution, manufacturer market share, and spatiotemporal adoption patterns across NYS counties. For predictive modeling, five forecasting frameworks are benchmarked—Autoregressive Integrated Moving Average (ARIMA), Error–Trend–Seasonality (ETS), Linear Regression, Decision Tree, and Random Forest—under a consistent train–test protocol (training: 2011–2021; evaluation: held-out 2022). ARIMA model selection was performed via exhaustive grid search over ARIMA(p,d,q) with p,q ∈ {0,1,2} and d ∈ {0,1,2}, minimizing the Akaike and Bayesian Information Criteria (AIC/BIC), yielding an optimal ARIMA(2,1,2) specification. Stationarity was established via the Augmented Dickey–Fuller (ADF) test following first-order differencing (pre-differencing ADF p-value = 0.879; post-differencing p = 0.000134). Among the benchmarked models, ETS achieved the lowest forecasting error for the 2022 evaluation year (MAPE = 0.17%; MAE = 1,653 vehicles), while ARIMA attained MAPE ≈ 2.0% (MAE = 19,120 vehicles). Machine learning comparators produced substantially larger errors, underscoring the suitability of classical time-series decomposition methods for structured single-channel adoption series. Spatial analysis reveals a pronounced urban–rural divide, with Suffolk and Nassau counties and the New York City metropolitan area accounting for a disproportionate share of cumulative registrations. These findings offer actionable intelligence for grid operators, transportation planners, and policymakers seeking to align EV infrastructure investment with empirically grounded demand forecasts.
References
[1] H. Shahinzadeh, J. Moradi, A. Hafezimagham, G. B. Gharehpetian, M. Benbouzid, and S. M. Muyeen, "Reliable operation of V2G-equipped parking lots based on probabilistic mobility patterns of plug-in hybrid electric vehicles," in Proc. 8th Int. Conf. Technology and Energy Management (ICTEM),Babol, Iran, Feb. 2023, pp. 1–6. https://doi.org/10.1109/ICTEM56862.2023.10084190
[2] B. D. H. Williams and J. B. Anderson, "From low initial interest to electric vehicle adoption: 'EV converts' in New York State's rebate program," Transportation Research Record, vol. 2677, no. 3, pp. 866–882, 2023. https://doi.org/10.1177/03611981221118537
[3] C.-M. Tseng, S. C.-K. Chau, and X. Liu, "Improving viability of electric taxis by taxi service strategy optimization: A big data study of New York City," IEEE Trans. Intelligent Transportation Systems, vol. 20, no. 3, pp. 817–829, Mar. 2019. https://doi.org/10.1109/TITS.2018.2839265
[4] L. Prates, D. Karthe, L. Zhang, et al., "Sustainability for all? The challenges of predicting and managing end-of-life electric vehicles and their batteries in the Global South," Environmental Earth Sciences, vol. 82, p. 143, 2023. https://doi.org/10.1007/s12665-023-10806-5
[5] T. Samak, C. Samak, S. Kandhasamy, V. Krovi, and M. Xie, "AutoDRIVE: A comprehensive, flexible and integrated digital twin ecosystem for autonomous driving research and education," Robotics, vol. 12, no. 3, p. 77, 2023. https://doi.org/10.3390/robotics12030077
[6] K. Chinen, M. Matsumoto, C. Liu, P. Tong, Y. S. Han, and H. Endo, "Expanding electric-vehicle adoption beyond the national border: Insights for developing marketing policies for global EV manufacturers," International Journal of Sustainable Transportation, vol. 17, no. 4, pp. 393–405, 2023. https://doi.org/10.1080/15568318.2022.2045652
[7] T. Gnann, S. Funke, N. Jakobsson, P. Jochem, F. Lund, and A. Bennehag, "Fast charging infrastructure for electric vehicles: Today's situation and future needs," Transportation Research Part D: Transport and Environment, vol. 62, pp. 314–329, Jul. 2018. https://doi.org/10.1016/j.trd.2018.03.004
[8] G. E. P. Box and G. M. Jenkins, Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ, USA: Wiley, 2015.
[9] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne,Australia: OTexts, 2021. [Online]. Available: https://otexts.com/fpp3/
[10] R. J. Hyndman, A. B. Koehler, J. K. Ord, and R. D. Snyder, Forecasting with Exponential Smoothing: The State Space Approach. Berlin, Germany: Springer, 2008. https://doi.org/10.1007/978-3-540- 71918-2
[11] New York State Energy Research and Development Authority (NYSERDA), "Electric Vehicle Registrations by Zip Code," NYS Open Data, 2023. [Online]. Available: https://data.ny.gov/Energy-Environment/Electric-Vehicle-Registrations-by-Zip-Code/w4pj-7re8
[12] Simplemaps, "US ZIP Codes Database," 2023. [Online]. Available: https://simplemaps.com/data/us- zips
[13] P. Slowik and N. Lutsey, "The continued transition to electric vehicles in U.S. cities," International Council on Clean Transportation (ICCT), Working Paper 2018-02, Feb. 2018.
[14] S. Hardman, A. Jenn, G. Tal, et al., "A review of consumer preferences of and interactions with electric vehicle charging infrastructure," Transportation Research Part D: Transport and Environment, vol. 62, pp. 508–523, Jul. 2018. https://doi.org/10.1016/j.trd.2018.04.002
[15] C. Doyle, B. Collier, and P. McFadden, "Forecasting electric vehicle adoption: A comparative analysis of models," Energy Policy, vol. 182, p. 113776, 2023. https://doi.org/10.1016/j.enpol.2023.113776
[16] X. Luo, J. Liu, and Y. Zhang, "Forecasting EV sales using ARIMA and machine learning models: Evidence from China," Sustainability, vol. 14, no. 11, p. 6648, 2022. https://doi.org/10.3390/su14116648
[17] M. Daina, A. Sivakumar, and J. W. Polak, "Electric vehicle charging choices: Modelling and implications for smart charging development," Energy Research & Social Science, vol. 56, p. 101221, Oct. 2019. https://doi.org/10.1016/j.erss.2019.05.011
[18] A. Ziegler, "Individual characteristics and stated preferences for alternative energy sources and propulsion technologies in vehicles: A discrete choice analysis for Germany," Transportation Research Part A: Policy and Practice, vol. 46, no. 8, pp. 1372–1385, 2012. https://doi.org/10.1016/j.tra.2012.05.016
[19] D. Palchak, J. Cochran, V. Desai, et al., "Greening the Grid: Pathways to Integrate 175 Gigawatts of Renewable Energy into India's Electric Grid," National Renewable Energy Laboratory (NREL), Tech. Rep. NREL/TP-6A20-68530, 2017.
[20] D. A. Dickey and W. A. Fuller, "Distribution of the estimators for autoregressive time series with a unit root," Journal of the American Statistical Association, vol. 74, no. 366, pp. 427–431, Jun. 1979. https://doi.org/10.2307/2286348
[21] H. Akaike, "A new look at the statistical model identification," IEEE Transactions on Automatic Control, vol. 19, no. 6, pp. 716–723, Dec. 1974. https://doi.org/10.1109/TAC.1974.1100705
[22] G. Schwarz, "Estimating the dimension of a model," Annals of Statistics, vol. 6, no. 2, pp. 461–464, 1978. https://doi.org/10.1214/aos/1176344136
[23] G. M. Ljung and G. E. P. Box, "On a measure of lack of fit in time series models," Biometrika, vol. 65, no. 2, pp. 297–303, 1978. https://doi.org/10.1093/biomet/65.2.297
[24] P. H. Franses and D. van Dijk, Non-Linear Time Series Models in Empirical Finance. Cambridge, UK: Cambridge University Press, 2000.
[25] U.S. Department of Energy (DOE), "Types of Electric Vehicles," Alternative Fuels Data Center, 2023. [Online]. Available: https://afdc.energy.gov/vehicles/electric
[26] U.S. Environmental Protection Agency (EPA), "Plug-In Hybrid Electric Vehicles," 2023. [Online]. Available: https://www.fueleconomy.gov/feg/powerYou.shtml
[27] Federal Highway Administration (FHWA), "Vehicle Classification," U.S. Department of Transportation, 2016. [Online]. Available: https://www.fhwa.dot.gov/policy/ohpi/vehclass.cfm
[28] C. A. Mersky, F. Sprei, C. Samaras, and Z. S. Qian, "Effectiveness of incentives on electric vehicle adoption in Norway," Transportation Research Part D: Transport and Environment, vol. 46, pp. 56– 68, Jul. 2016. https://doi.org/10.1016/j.trd.2016.03.011
[29] I. Tal, G. Tal, and D. Sperling, "Charging infrastructure and electric vehicle adoption: Insights from US household survey data," UC Davis Institute of Transportation Studies, 2020.
[30] New York State Climate Leadership and Community Protection Act (CLCPA), S.B. 6599, 2019. [Online]. Available: https://climate.ny.gov/
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
