Mobile Energy Resources in Grids of Electricity

Publications

Islanding operation of active distribution grids using an agent-based architecture

Publication . Issicaba, D.; Gil, N. J.; Lopes, J. A. Peças

This paper presents a decentralized architecture for the islanding operation of distribution grids with large volume of distributed generation. This architecture involves the definition of network blocks which share the responsibility of frequency control. The control block abstraction was particularly designed to support the transition from regular grids to smart grids. In addition, the control schemes were developed using an agentbased paradigm. Hence, an agent-based simulation platform was implemented using libraries from the Java Agent Development Framework (JADE). The control schemes were evaluated using a test system with different sorts of distributed energy resources and modeled in the EUROSTAG environment. Simulation results show the effectiveness of the control architecture when different failure events are applied to the test system.

2010-10Conference paper

Restricted access

Publication . Mena, Jose Daniel Luna; Malheiro, Ricardo Manuel da Silva

This project presents an efficient approach to chorus recognition in English song lyrics that achieves state-of-the-art performance with significantly fewer resources than existing methods. We developed a Bidirectional Long Short-Term Memory (BiLSTM) model with localized attention mechanisms, trained on only 780 songs compared to the 25,000+ songs typically used in Music Information Retrieval research. Our approach addresses class imbalance through comprehensive stabilization techniques and leverages nine feature views capturing structural, semantic, and rhythmic patterns via selfsimilarity matrices. Through systematic experimentation, we demonstrate that chorus detection relies primarily on local contextual patterns rather than global structural awareness, with head self-similarity features (line beginnings) proving most critical for segmentation. The BiLSTM + Attention model achieves 78.2% Macro F1 at the line level, matching Watanabe & Goto's (2020) performance with 100,000+ songs and significantly exceeding Fell et al.'s (2018) 67.4% F1 with 25,000 songs. For boundary detection, the model achieves 59.6% F1 for exact boundaries and 74.7% F1 with ±2 tolerance. The research demonstrates that strategic data curation, comprehensive feature engineering, and targeted optimization can compete effectively with resource-intensive approaches, showing that local pattern recognition outperforms complex global modeling strategies in specialized domains like lyric analysis.

2025-11-25Master thesis

Open access