Alexandre Lucas

Abstract
The application of Artificial Intelligence (AI) in the energy sector offers new opportunities for developing flexible, efficient, and sustainable infrastructures. Nevertheless, real-world deployment is still constrained by the lack of large-scale, integrated environments that can evaluate advanced algorithms under realistic operating conditions while ensuring regulatory compliance. This paper presents EnerTEF (which stands for Energy Testing and Experimentation Facility), a federated platform for testing and experimentation in the energy sector designed to address this gap. We introduce a unified TEF architecture that enables full-stack evaluation of intelligent systems, including predictive modeling, optimization, learning under data distribution shifts and federated learning across geographically distributed sites. The framework integrates high-fidelity digital twins, a privacy-preserving data exchange framework and regulatory sandboxing to support transparent, explainable and robust AI development. EnerTEF demonstrates how such a framework can be deployed in critical energy domains through three real-world scenarios including short-term hydropower generation forecasting, coordination between distribution network operators and distributed energy resources and real-time optimization of self-consumption for municipal buildings. Results show that EnerTEF effectively enables the development of novel AI models, improves cross-context generalizability and supports innovation for complex energy infrastructures, ultimately creating a practical, scalable path for addressing different energy-related problems and heterogeneous data. © 2025 The Authors.

Abstract
The business models (BM) for renewable energy communities (REC) are often based on their promoters being the sole or primary investors in energy assets, such as photovoltaic panels (PV) and battery energy storage systems (BESS), operating these assets centrally, and selling the locally produced energy to the REC members. This research addresses the computation of fixed local energy prices that the REC developer may apply under the optimal operation of the energy assets to maximize its revenues, while guaranteeing that all REC members benefit from belonging to the REC. We do this from two perspectives, depending on who operates the storage systems: i) maximizing the investor's benefits and ii) minimizing the REC cost by maximizing its self-consumption, ensuring maximization of the energy sold by the REC promoter/investor. The optimization framework includes energy production and demand balance constraints, peak load limitations, and constraints coming from the Portuguese regulatory framework. It also considers the opportunity costs of the members for buying the energy deficit from the grid or selling the energy surplus to the grid.

Abstract

Abstract
The rapid rise of Renewable Energy Communities (REC) offers unique opportunities for decentralizing and decarbonizing energy systems but also brings challenges in designing fair mechanisms for distributing the benefits of collective self-consumption. This paper evaluates three approaches for benefit-sharing based on the Shapley value, direct marginal contributions, and system marginal cost. A case study compares these methodologies in terms of practicality, fairness, and impact on financial returns. Additionally, this paper proves that settling local transactions using system marginal costs ensures that all REC participants incur equal or lower costs compared to operating independently.

Abstract
Accurately imputing missing data is critical in time series analysis. The present work compares Foundation Model Chronos against Linear Interpolation, K-Nearest Neighbor Imputer, and Gaussian Mixture Model Imputer with three types of missing data patterns: random, short sequential chunks, and a long sequential chunk. These results confirm that for random missing values, KNN and interpolation yield the highest performance, while Chronos outperforms these on sequences. Indeed, however, for longer sequences of missing values, Chronos starts suffering from cascading errors which eventually allow the simpler imputation methods to outrank it. Another test with limited quantities of training data showed different tradeoffs for the different methods. Unlike KNN and interpolation, which smooth out the gaps, Chronos generates variable synthetic data. This can be beneficial in tasks which require control or simulation. The results highlight the strengths and weaknesses of the imputers and, therefore, offer practical insights into trade-offs between computational complexities, accuracy, and suitability for time series imputation scenarios.