Publicação
Charging Towards 2030: Forecasting Electric Vehicle Charging Station in Braga by 2030: A Data-Driven Approach Aligned with Portugal’s National Roadmap for Carbon Neutrality
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | pt_PT |
| dc.contributor.advisor | Naranjo-Zolotov, Mijail Juanovich | |
| dc.contributor.author | Castro, Francisco Rodrigues de Carvalho Garcia de | |
| dc.date.accessioned | 2025-11-12T11:46:11Z | |
| dc.date.available | 2025-11-12T11:46:11Z | |
| dc.date.issued | 2025-10-29 | |
| dc.description | Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics | pt_PT |
| dc.description.abstract | Portugal aims to achieve carbon neutrality by 2050. To meet this goal, it is imperative to reduce greenhouse gas emissions from the transport sector, as it is one of the main sources of emissions. One way to reduce this pollution is through the electrification of transport, but this approach faces several challenges. Electric vehicles have shorter driving ranges and take more time to charge than a fossil fuel vehicle, therefore require an optimized network of charging stations. Without such infrastructure, adoption of these vehicles may be limited. This project aimed to predict the necessary number of charging stations in the municipalities of the Braga district by 2030 to help design a pathway toward achieving carbon neutrality by 2050. The approach can also be applied to other districts. Data on charging stations in Portugal was sourced from a state-owned enterprise that act as the Electric Mobility Network Managing Entity, while demographic, socioeconomic, territorial, and transport data were obtained from public sources such as the Instituto Nacional de Estatística, Instituto da Mobilidade e dos Transportes, and Direção-Geral do Território. The CRISP-DM methodology was followed. This project addressed both regression and classification problems. Tree-based models were evaluated, with Random Forest classifier proving the best option for the prediction, showing the second-best validation results while producing less overfitting. The study found that the Braga district will need a minimum of 470 and a maximum of 837 charging stations by 2030. This range combines the lower and upper estimates from the different charging station models. Such number of charging stations by 2030 suggests that Braga is on a good path toward achieving carbon neutrality. | pt_PT |
| dc.identifier.tid | 204073200 | |
| dc.identifier.uri | http://hdl.handle.net/10362/190579 | |
| dc.language.iso | eng | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Electric vehicles | pt_PT |
| dc.subject | Charging stations | pt_PT |
| dc.subject | Machine Learning | pt_PT |
| dc.subject | Prediction | pt_PT |
| dc.subject | Random Forest | pt_PT |
| dc.subject | SDG 9 - Industry, innovation and infrastructure | pt_PT |
| dc.subject | SDG 13 - Climate action | pt_PT |
| dc.title | Charging Towards 2030: Forecasting Electric Vehicle Charging Station in Braga by 2030: A Data-Driven Approach Aligned with Portugal’s National Roadmap for Carbon Neutrality | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | Mestrado em Ciência de Dados e Métodos Analíticos Avançados, especialização em Business Analytics | pt_PT |