Institutional Repository
Scientific Publications Repository
Preserve, Disclose and Give Access to Intellectual Production
From Portucalense University
Recent Submissions
Time-series Forecasting of Electricity Prices for Industries in Portugal: A Real-world Internship-based Study
2025-11-25 - Khalid, Naiya
This work presents the development of a short-term electricity price forecasting solution using
machine learning, conducted during the author’s internship at Vanaci Prime, an IT consulting firm
specializing in data-driven solutions. The project was developed for the Portuguese market, in
collaboration with a client from the energy sector, and addresses the critical need for accurate,
real-time, and scalable electricity price forecasts to support strategic planning, cost optimization,
and operational decision-making.
The forecasting system is built upon a unified dataset combining information from three
authoritative sources: OMIE (day-ahead marginal electricity prices for the Iberian market), REN
Datahub (electricity load and renewable generation), and the Copernicus Climate Data Store
(meteorological variables including temperature, solar radiation, and precipitation). The combined
data underwent extensive time-series preprocessing and feature engineering, including lag features,
rolling statistics, calendar-based encodings, interaction terms, and normalized indicators reflecting
load trends and solar activity.
Multiple machine learning models were explored—namely LightGBM, XGBoost, and Extra
Trees—with LightGBM ultimately selected due to its superior performance and generalization
capability.
A complete machine learning pipeline in Python was developed to automate the transformation
of raw input data into model-ready features. To enhance the solution’s practical utility, a consumerfocused component was added to estimate potential monthly savings based on predicted electricity
prices.
The trained model and preprocessing pipeline are serialized and deployed using the FastAPI
web framework to serve real-time predictions via web endpoints.
Overall, the work demonstrates how artificial intelligence techniques can be used to automate
and optimize electricity price forecasting by integrating environmental, market, and load data,
while offering a replicable methodology for similar forecasting challenges in the energy sector.
O Impacto do Investimento Público no Desenvolvimento da Indústria Aeroespacial: O caso da RFA Portugal
2025-11-14 - Lucas, Vasco
A evolução da indústria aeroespacial tem apresentado um conjunto de oportunidades
marcantes para o desenvolvimento deste setor de atividade. Tradicionalmente, esta
indústria encontrava-se relacionada com países que apresentassem níveis de
prosperidade económica notáveis, sendo que o investimento necessário para que este
setor de atividade se desenvolvesse é elevado. No presente relatório será abordado o
papel do estado no setor referido anteriormente para permitir aferir de que forma este
impulsiona e apoia a atividade deste ramo da economia, fazendo ligação entre as
entidades públicas a as empresas privadas pertencentes à indústria aeroespacial. Desta
forma, foram analisados dois programas de cofinanciamento público e também a
internacionalização da empresa acolhedora em Portugal. Também foram abordadas as
atividades praticadas ao longo do estágio curricular de 6 meses realizado na RFA,
principalmente no tema do procurement. Os resultados obtidos demonstram a
dependência do setor do financiamento e apoio públicos, indo de encontro a outras
indústrias que apresentam características parecidas com o ramo aeroespacial.
Práticas de autocuidado e indicadores de saúde mental: Relações com a adaptaçãoi ao Ensino Superior
2025-11-27 - Andrade, Joana Maria Collus Montenegro Soveral
A adaptação ao Ensino Superior (ES) implica a gestão de exigências emocionais, sociais e académicas que podem desencadear stress, sintomatologia ansiosa e depressiva entre os estudantes. [...]