David Juan Cerezo Quina

Mr. David Juan Cerezo Quina

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
7 June 2025 in Sensors
Verified
Journal Article
Open access
PDF file
JYJhan Piero Paulo Merma Yucra
Jhan Piero Paulo Merma Yucra
David Juan Cerezo QuinaDavid Juan Cerezo Quina
David Juan Cerezo Quina
GEGerman Alberto Echaiz Espinoza
German Alberto Echaiz Espinoza
MSManuel alejandro valderrama solis
Manuel alejandro valderrama solis
DCDaniel Domingo Yanyachi Aco Cardenas
Daniel Domingo Yanyachi Aco Cardenas
Andres Ortiz SalazarAndres Ortiz Salazar
Andres Ortiz Salazar
The use of recurrent neural networks has proven effective in time series prediction tasks such as weather. However, their use in resource-limited systems such as MCUs presents difficulties in terms of both size and stability with longer prediction windows. In this context, we propose a variant of the LSTM model, which we call SE-LSTM (Single Embedding LSTM), which uses embedding techniques to vectorially represent seasonality and latent patterns through variables such as temperature and humidity. The proposal is systematically compared in two parts: The first compares it against other reference architectures such as CNN-LSTM, TCN, LMU, and TPA-LSTM. The second stage, which includes implementation, compares it against the CNN-LSTM, LSTM, and TCN networks. Metrics such as the MAE and MSE are used along with the network weight, a crucial aspect for MCUs such as an ESP32 or Raspberry Pi Pico. An analysis of the memory usage, energy consumption, and generalization across different regions is also included. The results show that the use of embedding optimizes the network space without sacrificing the performance, which is crucial for edge computing. This research is part of a larger project, which focuses on improving agricultural monitoring systems.

24 October 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
David Juan Cerezo QuinaDavid Juan Cerezo Quina
David Juan Cerezo Quina
TSTadeu Félix Santos
Tadeu Félix Santos
JLJuan Antonio Butron Llamoca
Juan Antonio Butron Llamoca
GEGerman Alberto Echaiz Espinoza
German Alberto Echaiz Espinoza
Andres Ortiz SalazarAndres Ortiz Salazar
Andres Ortiz Salazar
Elmer Rolando Llanos VillarrealElmer Rolando Llanos Villarreal
Elmer Rolando Llanos Villarreal
Microgrids represent small-scale energy generation units with low cost-effectiveness, making use of renewable resources, such as photovoltaic and wind energy. These systems can operate both in connection with and independent from the primary power grid. The widespread adoption and expansion of microgrids are increasingly vital in light of the global shift towards minimizing fossil fuel consumption and promoting cleaner energy sources. Similar to conventional electrical networks, microgrids require Supervisory Control and Data Acquisition (SCADA) systems to ensure sustained and reliable operation. In support of the proliferation and growth of microgrid networks, this paper proposes the implementation of an open-source SCADA system. This system, being platform-independent, significantly reduces the costs associated with microgrid implementation, thus aligning with the principles of social responsibility. The proposed SCADA system will be deployed on a simulated microgrid, featuring both photovoltaic and wind energy sources, and will include a Phase-Locked Loop (PLL) synchronization system for grid connection. The simulation will be carried out using the Matlab-Simulink environment, leveraging the power systems library. The interface between Matlab and SCADA is done using an OPC Server. Additionally, the SCADA system will interface with an SQL database to facilitate the archiving of historical data.