Giovanni Moura de Holanda

Mr. Giovanni Moura de Holanda

orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 November 2025 in Energies
Verified
Journal Article
Open access
PDF file
Djayr Alves Bispo JuniorDjayr Alves Bispo Junior
Djayr Alves Bispo Junior
Gustavo de Novaes Pires LeiteGustavo de Novaes Pires Leite
Gustavo de Novaes Pires Leite
Enrique DroguettEnrique Droguett
Enrique Droguett
OSOthon Vinicius Cavalcanti de Souza
Othon Vinicius Cavalcanti de Souza
LLLucas Albuquerque Lisboa
Lucas Albuquerque Lisboa
TRTsang Ing Ren
Tsang Ing Ren
Accurate wind power forecasting is essential to optimize wind farm operations and ensure the stable integration of renewable energy into the grid. This study explores Transformer-based architectures to address the challenges of wind variability and temporal dependencies in short-term forecasting. A sensitivity analysis on model architecture is conducted, incorporating Time2Vec—a temporal encoding technique that captures complex temporal patterns. In addition, we replace the standard FullAttention mechanism with ProbSparse Attention, FlowAttention and FlashAttention, resulting in the Informer, Flowformer and Flashformer models, to improve computational efficiency while maintaining predictive accuracy. The novelty of this work lies in applying FlashAttention within the context of wind power forecasting and integrating Time2Vec into the Informer, Flowformer and Flashformer models. We propose four architectures—T2V-Transformer, T2V-Informer, T2V-Flowformer, and T2V-Flashformer—and compare them against benchmark models: Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), and DLinear. Real-world data from a wind farm in the Northeast of Brazil is used under two forecasting scenarios. In Scenario A, T2V-Transformer, T2V-Informer and T2V-Flashformer achieved Improvement over Reference RMSE (IoR-RMSE) scores of 17.73%, 17.59% and 16.67%, respectively. In Scenario B, T2V-Flowformer and T2V-Flashformer reached 27.84% and 27.45%, respectively. These results confirm the effectiveness of the proposed models in advancing short-term wind power forecasting.

1 February 2008 in Telematics and Informatics
Verified
Journal Article
Closed access
Giovanni Moura de HolandaGiovanni Moura de Holanda
Giovanni Moura de Holanda
IÁIsmael M.A. Ávila
Ismael M.A. Ávila
RMRicardo B. Martins
Ricardo B. Martins

15 June 2021
Verified
Book Chapter
Closed access
PDF file
JSJorge M. de Souza
Jorge M. de Souza
Giovanni Moura de HolandaGiovanni Moura de Holanda
Giovanni Moura de Holanda
HHHingmar A. Henriques
Hingmar A. Henriques
RFRafael H. Furukawa
Rafael H. Furukawa

29 May 2019 in Smart Innovation, Systems and Technologies
Verified
Book Chapter
Closed access
PDF file
Giovanni Moura de HolandaGiovanni Moura de Holanda
Giovanni Moura de Holanda
CACristina Y. K. Obata Adorni
Cristina Y. K. Obata Adorni
JSJorge Moreira de Souza
Jorge Moreira de Souza

5 October 2023 in Código 31: revista de informação, comunicação e interfaces
Verified
Journal Article
Open access
PDF file
Giovanni Moura de HolandaGiovanni Moura de Holanda
Giovanni Moura de Holanda
Um roteiro para as reflexões propostas no livro “Sentimento da Inteligência Artificial: novas tecnologias, antigos conceitos”.

1 December 2020 in Rio Oil and Gas Expo and Conference
Verified
Journal Article
Closed access
MVMaria Gorete Valus
Maria Gorete Valus
Giovanni Moura de HolandaGiovanni Moura de Holanda
Giovanni Moura de Holanda
JSJorge M. De Souza
Jorge M. De Souza