Analysis of artificial neural network architectures for modeling smart lighting systems for energy savings
AuthorsCastillo Sequera, José Luis; Corte Valiente, Antonio del; Gómez Pulido, José Manuel; Garcés Jiménez, Alberto; Patricio Dominguez, Esteban
IdentifiersPermanent link (URI): http://hdl.handle.net/10017/42714
AffiliationUniversidad de Alcalá. Departamento de Automática; Universidad de Alcalá. Departamento de Ciencias de la Computación
A. Garces-Jimenez, J. L. Castillo-Sequera, A. Del Corte-Valiente, J. M. Gómez-Pulido and E. P. D. González-Seco, "Analysis of Artificial Neural Network Architectures for Modeling Smart Lighting Systems for Energy Savings," in IEEE Access, vol. 7, pp. 119881-119891, 2019, doi: 10.1109/ACCESS.2019.2932055.
Public lighting design
Artificial neural networks
Uniformity ratio of luminance
Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
(c) 2019 IEEE
Currently, population growth is global and tends to concentrate in large cities, which increases the demand for illuminating public spaces for safety, visual orientation, aesthetic considerations, and quality of life. The undesirable side effects are increase in energy consumption and light pollution. The current tools used for designing public lighting systems are not suitable for optimizing multiple objectives in addition to energy savings, and these solutions could provide for a more sustainable environment. The application of evolutionary optimization techniques seems to be growing rapidly because of the nonlinearity of the model behavior and the nonproprietary nature of the algorithms, which are considered as black box systems. This paper develops a data model for these types of optimizers, analyzing the ability of different artificial neural network (ANN) architectures to simulate a simple public lighting design by measuring the performance with respect to the fitness function, training speed, and goodness of fit with a dataset generated with different conditions. The architectures selected in this paper are those with multilayer perceptrons (MLPs) with different hidden layer configurations using different numbers of neurons in each layer, which have been analyzed to determine the configuration that best _ts the purpose of this work. The data for training the ANNs were generated with a recognized open-software platform, DIALux. The experiments were repeated and analyzed to determine the variance of the results obtained. In this way, it was possible to identify the most appropriate number of iterations required. The results show that better precision is obtained when using the Levenberg-Marquardt training algorithm, especially when the ANN architecture has fewer neurons in the hidden layer.
Files in this item
- CCOMPUT - Artículos