Computational Technology Resources - CCC

B. Jamil¹, A. Rodríguez², L. Serrano-Luján^1,3, J.M. Ruperez², C.P. Rodríguez² and J.M. Sanz²

¹Department of Computer Science, Universidad Rey Juan Carlos, Mostoles (Madrid), Spain
²Department of Models for System Operation, Red Eléctrica de Espana, Alcobendas (Madrid), Spain
³Departamento de Electrónica, Tecnología de Computadoras y Proyectos, Universidad Politécnica de Cartagena, Campus Muralla del Mar (Cartagena), Spain

doi:10.4203/ccc.2.17.1

B. Jamil, A. Rodríguez, L. Serrano-Luján, J.M. Ruperez, C.P. Rodríguez, J.M. Sanz, "Application of metaheuristics methods for prediction of electrical energy demand in peninsular Spain", in B.H.V. Topping, P. Iványi, (Editors), "Proceedings of the Eleventh International Conference on Engineering Computational Technology", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 2, Paper 17.1, 2022, doi:10.4203/ccc.2.17.1

Keywords: electrical energy, demand prediction, metaheuristic algorithms, error analysis, Spain.

Abstract

In this paper, a year-ahead electrical energy demand prediction has been performed for the Peninsular region of Spain. Data for electrical energy demand and three other demographic and economic parameters were obtained from the historical records (1990-2021) of Red Eléctrica de Espana (Madrid). For the prediction of future energy demand, metaheuristic algorithms were proposed which utilize data from previous years to predict the electrical energy demand for the coming year. Particularly, the ensemble of Grammatical Evolution (GE) and Differential Evolution (DE) algorithms were used, where GE develops the model form for the equation while DE optimizes the coefficient of the model. Three cases were then studied under the present work where the data from one previous year, three previous years, and five previous years (resulting in three, nine, and fifteen inputs respectively) were used to train the algorithms. For each case, the data were bifurcated into training and test datasets. The accuracy of the algorithmic methods was realized in terms of the objective function (Root Mean Square Error, RMSE). Further, the predicted electrical energy demand and actual data were also compared with the help of RMSE and other statistical errors. It was found that the least value of RMSE=3.4052 resulted in Case 2 where the inputs for three previous years were used. Further, it was concluded that the ensemble of GEDE can effectively be used to produce highly accurate electrical energy demand predictions.

download the full-text of this paper (PDF, 8 pages, 755 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 2 PROCEEDINGS OF THE ELEVENTH INTERNATIONAL CONFERENCE ON ENGINEERING COMPUTATIONAL TECHNOLOGY Edited by: B.H.V. Topping and P. Iványi Paper 17.1 Application of metaheuristics methods for prediction of electrical energy demand in peninsular Spain B. Jamil¹, A. Rodríguez², L. Serrano-Luján^1,3, J.M. Ruperez², C.P. Rodríguez² and J.M. Sanz² ¹Department of Computer Science, Universidad Rey Juan Carlos, Mostoles (Madrid), Spain ²Department of Models for System Operation, Red Eléctrica de Espana, Alcobendas (Madrid), Spain ³Departamento de Electrónica, Tecnología de Computadoras y Proyectos, Universidad Politécnica de Cartagena, Campus Muralla del Mar (Cartagena), Spain doi:10.4203/ccc.2.17.1 Full Bibliographic Reference for this paper B. Jamil, A. Rodríguez, L. Serrano-Luján, J.M. Ruperez, C.P. Rodríguez, J.M. Sanz, "Application of metaheuristics methods for prediction of electrical energy demand in peninsular Spain", in B.H.V. Topping, P. Iványi, (Editors), "Proceedings of the Eleventh International Conference on Engineering Computational Technology", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 2, Paper 17.1, 2022, doi:10.4203/ccc.2.17.1 Keywords: electrical energy, demand prediction, metaheuristic algorithms, error analysis, Spain. Abstract In this paper, a year-ahead electrical energy demand prediction has been performed for the Peninsular region of Spain. Data for electrical energy demand and three other demographic and economic parameters were obtained from the historical records (1990-2021) of Red Eléctrica de Espana (Madrid). For the prediction of future energy demand, metaheuristic algorithms were proposed which utilize data from previous years to predict the electrical energy demand for the coming year. Particularly, the ensemble of Grammatical Evolution (GE) and Differential Evolution (DE) algorithms were used, where GE develops the model form for the equation while DE optimizes the coefficient of the model. Three cases were then studied under the present work where the data from one previous year, three previous years, and five previous years (resulting in three, nine, and fifteen inputs respectively) were used to train the algorithms. For each case, the data were bifurcated into training and test datasets. The accuracy of the algorithmic methods was realized in terms of the objective function (Root Mean Square Error, RMSE). Further, the predicted electrical energy demand and actual data were also compared with the help of RMSE and other statistical errors. It was found that the least value of RMSE=3.4052 resulted in Case 2 where the inputs for three previous years were used. Further, it was concluded that the ensemble of GEDE can effectively be used to produce highly accurate electrical energy demand predictions. download the full-text of this paper (PDF, 8 pages, 755 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions