This research addresses the challenge of forecasting electric vehicle (EV) demand in Thailand and its influence on the development of charging infrastructure. To improve predictive capability in environments with restricted historical data, we employed the grey model (GM) and genetic algorithms (GA) both independently and in combination. Using EV registration records from 2019 to 2023 obtained from the Automotive Information Center of Thailand, the optimized GM-GA hybrid model achieved markedly superior accuracy, with a mean absolute error (MAE) of 0.0016 and root mean squared error (RMSE) of 0.0031. These results demonstrate the model’s capacity to deliver precise forecasts despite data limitations, making it a valuable decision-making tool for charging station planning and deployment. The outcomes underscore the importance of forward-looking infrastructure strategies to support the growth of Thailand’s EV market and its transition toward sustainable mobility.
Collaboration network of the authors
7 authors ·
15 co-authorship links
· 8 across different organisations
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
King Mongkut's University of Technology North Bangkok
Chiang Mai University
Future University in Egypt
Different organisations
Same organisation
Affiliation unknown
Thicker line = more joint articles · bigger circle = more articles
King Mongkut's University of Technology North Bangkok
1
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.