Alana Kelly Xavier Santos
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Alana Kelly Xavier Santos has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Allan Martins
Departamento de Física Teórica e Experimental, Universidade Federal do Rio Grande do Norte, Campus Universitário, Natal, RN 59072-970, Brazil
1 shared publication - Carlos Henrique Torres de Andrade
Computing Institute, A. C. Simões Campus, Federal University of Alagoas—UFAL, Maceió 57072-970, Brazil
1 shared publication - Damásio Fernandes Júnior
Department of Electrical Engineering, Federal University of Campina Grande (UFCG), Campina Grande 58429-900, Brazil
1 shared publication - Davi Bibiano Brito
UFAL
1 shared publication - Felipe B. Dantas
Department of Electrical Engineering, Federal University of Campina Grande, Campina Grande, Brazil
1 shared publication - Flavio Bezerra Costa
Department of Electrical and Computer Engineering, Michigan Technological University, Houghton, MI, USA
1 shared publication
Latest Publications
- Open Access
- 3 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 123961-123976
Optimal Inverter-Based Resource Installation to Minimize Technical Energy Losses in Distribution Systems
This paper proposes an algorithm for the optimal installation of inverter-based resources (IBR) composed of wind energy conversion systems, photovoltaic systems, and battery energy storage systems in distribution systems using genetic algorithm (GA) and the cuckoo search (CS) as optimization techniques. The OpenDSS software is used to calculate the power flow in the distribution system with different penetration levels of IBRs. It is used a standard load shape of the IEEE 123 bus system programmed in OpenDSS and irradiance, temperature, and wind speed curves from Brazil. The proposed algorithm, using a genetic algorithm and cuckoo search, was able to define the quantity and the location of hybrid renewable generation arrangements reducing electrical energy losses. Case studies were carried out for maximum penetration from 20% to 60%, totaling 5 cases, where each simulation was performed for a period of 24 hours. It is simple, fast and efficient, achieving satisfactory results and being able to be applied to larger systems. The proposed method stands out for the possibility of using IBR in conjunction with energy storage, in addition to having a customizable hybrid array and being able to carry out case studies with high penetration while optimally locating and sizing the hybrid array configured accordingly with the needs of each problem, reducing losses and maintaining the quality of the system’s electrical voltage.
- 3 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 123961-123976
Open AccessOptimal Inverter-Based Resource Installation to Minimize Technical Energy Losses in Distribution Systems
This paper proposes an algorithm for the optimal installation of inverter-based resources (IBR) composed of wind energy conversion systems, photovoltaic systems, and battery energy storage systems in distribution systems using genetic algorithm (GA) and the cuckoo search (CS) as optimization techniques. The OpenDSS software is used to calculate the power flow in the distribution system with different penetration levels of IBRs. It is used a standard load shape of the IEEE 123 bus system programmed in OpenDSS and irradiance, temperature, and wind speed curves from Brazil. The proposed algorithm, using a genetic algorithm and cuckoo search, was able to define the quantity and the location of hybrid renewable generation arrangements reducing electrical energy losses. Case studies were carried out for maximum penetration from 20% to 60%, totaling 5 cases, where each simulation was performed for a period of 24 hours. It is simple, fast and efficient, achieving satisfactory results and being able to be applied to larger systems. The proposed method stands out for the possibility of using IBR in conjunction with energy storage, in addition to having a customizable hybrid array and being able to carry out case studies with high penetration while optimally locating and sizing the hybrid array configured accordingly with the needs of each problem, reducing losses and maintaining the quality of the system’s electrical voltage.
- Open Access
How Does Neural Network Model Capacity Affect Photovoltaic Power Prediction? A Study Case
The use of models capable of forecasting the production of photovoltaic (PV) energy is essential to guarantee the best possible integration of this energy source into traditional distribution grids. Long Short-Term Memory networks (LSTMs) are commonly used for this purpose, but their use may not be the better option due to their great computational complexity and slower inference and training time. Thus, in this work, we seek to evaluate the use of neural networks MLPs (Multilayer Perceptron), Recurrent Neural Networks (RNNs), and LSTMs, for the forecast of 5 min of photovoltaic energy production. Each iteration of the predictions uses the last 120 min of data collected from the PV system (power, irradiation, and PV cell temperature), measured from 2019 to mid-2022 in Maceió (Brazil). In addition, Bayesian hyperparameters optimization was used to obtain the best of each model and compare them on an equal footing. Results showed that the MLP performs satisfactorily, requiring much less time to train and forecast, indicating that they can be a better option when dealing with a very short-term forecast in specific contexts, for example, in systems with little computational resources.
Open AccessHow Does Neural Network Model Capacity Affect Photovoltaic Power Prediction? A Study Case
The use of models capable of forecasting the production of photovoltaic (PV) energy is essential to guarantee the best possible integration of this energy source into traditional distribution grids. Long Short-Term Memory networks (LSTMs) are commonly used for this purpose, but their use may not be the better option due to their great computational complexity and slower inference and training time. Thus, in this work, we seek to evaluate the use of neural networks MLPs (Multilayer Perceptron), Recurrent Neural Networks (RNNs), and LSTMs, for the forecast of 5 min of photovoltaic energy production. Each iteration of the predictions uses the last 120 min of data collected from the PV system (power, irradiation, and PV cell temperature), measured from 2019 to mid-2022 in Maceió (Brazil). In addition, Bayesian hyperparameters optimization was used to obtain the best of each model and compare them on an equal footing. Results showed that the MLP performs satisfactorily, requiring much less time to train and forecast, indicating that they can be a better option when dealing with a very short-term forecast in specific contexts, for example, in systems with little computational resources.