Performance Analysis of Bagging Feed-Forward Neural Network for Forecasting Building Energy Demand

Zarate-Perez, Eliseo; Palumbo, Mariana; Motta, Ana

doi:10.9734/cjast/2018/44836

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…En otras palabras, la medida de desempeño se calculó considerando los documentos asociados a cada clúster o grupo. El índice H se calculó a partir de las citas de los artículos correspondientes a cada tema [29], [30].…”

Section: Cuadrante 3 (Q3)unclassified

Artificial Neural Networks in Forecasting Wind Energy: A Bibliometric Approach from 2007 to 2021

Zarate-Perez¹,

Grados²,

Rubiños³

et al. 2022

Proceedings of the 20th LACCEI International Multi-Conference for Engineering, Education and Technology: “Education, Research A

View full text Add to dashboard Cite

The main objective of this study was to develop an evolutionary analysis of artificial neural networks (ANN) in the forecast of wind energy for the period from 2007 to 2021. T he SciMat software tool was used to identify the performance and impact measures of the main research topics. For this, 250 research articles were retrieved from the Scopus and Web of Science databases. For the first evaluated period (2007-2011), there is a greater use of ANN models for the forecasting of wind energy. In the second period (2012-2016), the forecast interval approa ches based on ANNs are used. Finally, in the third period (2017-2021 ) , hybrid approaches are proposed for forecasting wind energy using ANN models and other approaches. Therefore, the results indicate that this field of research is constantly evolving, without yet reaching its stage of scientific maturity. Furthermore, results show that renewable energy source is the basic and transversal cluster of the application of forecasting wind models.Keywords--Energy forecast; artificial neural networks (ANN); wind energy; bibliometric analysis; SciMat.

show abstract

Section: Cuadrante 3 (Q3)unclassified

Artificial Neural Networks in Forecasting Wind Energy: A Bibliometric Approach from 2007 to 2021

Zarate-Perez¹,

Grados²,

Rubiños³

et al. 2022

Proceedings of the 20th LACCEI International Multi-Conference for Engineering, Education and Technology: “Education, Research A

View full text Add to dashboard Cite

show abstract

“…Los indicadores de desempeño como el RMSE (Raíz del error cuadrático medio) y el MAE (error absoluto medio) midieron la magnitud de los errores, donde un mejor modelo dará un valor menor [13]. Del mismo modo, el sesgo se medirá con el p-value, en el cual un mejor modelo dará un valor cercano a 0.…”

Section: A Selección Del Conjunto De Datosunclassified

Trends and Perspectives of Renewable Energy Based on Microgrids: A Bibliometric Approach

Zarate-Perez¹,

Azpilcueta-Vasquez²,

Santos-Mejía³

et al. 2022

Proceedings of the 2nd LACCEI International Multiconference on Entrepreneurship, Innovation and Regional Development (LEIRD 202

View full text Add to dashboard Cite

The use of renewable energy sources in microgrids is broad and fragmented owing to the contributions of various approaches and disciplines. A bibliometric review contributes to a critical and comprehensive understanding of this field. The SciMAT software was used to determine the evolution of this important field of research. To achieve this, 842 research articles were collected from the Scopus database for 2001-2021. Recently, the thematic interest of researchers has focused on the concepts of life-cycle analyses of solar and wind energy systems and the efficiency of photovoltaic systems as a method of evaluating renewable energy sources. The results illustrate the relevance of renewable energy sources with a gradual increase in the number of studies published in international journals since 2010. The period overlay plots present several new and transient topics between sub-periods; it is a research field that undergoes constant evolution and has not yet reached a stage of scientific maturity.

show abstract

“…The use of smart meters is not significant in some countries in developing state due their installation cost [1,2]. That is why, this research paper has treated the consumed energy forecasting goal to enhance the reliability of forecasted energy and the dynamic forecasting algorithms robustness, by the implementation of the necessary algorithms responsible for the energy forecasting [3][4] [5][6] [7]. Many works have treated the implementation of the forecasting algorithms for energy prediction and PV generation forecasting [10] [11][12] [13].…”

Section: Introductionmentioning

confidence: 99%

Novel Training Methods Based ANN for the Consumed Energy Forecasting

Farhat¹,

Cherif²

2022

Advances in Intelligent Systems Research

View full text Add to dashboard Cite

Artificial Neural Networks have demonstrated best effectiveness and excellent scheduling capabilities in realizing many purposes like recognition, clustering, classification, management and even prediction. For this reason, we have used RBF based Artificial NN for the dynamic forecasting of load and Photovoltaic production using many operations like forecasting, training and validation of the data accuracy. For the validation, the Mean Absolute Percent Error is calculated in function of the most three relevant input parameters, which are previous load and Photovoltaic production measurements, seasonability and temperature or solar radiation data. This work has used real-time measurements of load and Photovoltaic production for their comparison with the predicted load data using RBFNN algorithms for the calculation of MAE and MAPE, to deduce the performance of forecasting algorithms including the accuracy of the forecasted data. This research paper has treated 2 goals. The first is the short-term energy and Photovoltaic production forecasting including training operations. The 2nd goal is the calculation of Mean Absolute Error and Mean Absolute Percent Error via the comparison between the forecasted data and real-time measurements to evaluate the reliability of forecasted data and the performance of the forecasting algorithms. By this way, the dynamic prediction algorithms were implemented, the predicted data were compared to the same time-series measurements and forecasted energy MAPE was calculated.

show abstract

Performance Analysis of Bagging Feed-Forward Neural Network for Forecasting Building Energy Demand

Cited by 5 publications

References 12 publications

Artificial Neural Networks in Forecasting Wind Energy: A Bibliometric Approach from 2007 to 2021

Artificial Neural Networks in Forecasting Wind Energy: A Bibliometric Approach from 2007 to 2021

Trends and Perspectives of Renewable Energy Based on Microgrids: A Bibliometric Approach

Novel Training Methods Based ANN for the Consumed Energy Forecasting

Contact Info

Product

Resources

About