TY - JOUR
T1 - Electricity consumption modeling by a chaotic convolutional radial basis function network
AU - Garcia, Donaldo
AU - Rubio, José de Jesús
AU - Sossa, Humberto
AU - Pacheco, Jaime
AU - Gutierrez, Guadalupe Juliana
AU - Aguilar-Ibañez, Carlos
N1 - Publisher Copyright:
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.
PY - 2024/3
Y1 - 2024/3
N2 - Electricity is an essential energy resource in the industrial, commercial and housing sector, having a very important role in the development of societies. Urbanization and industrialization implies a great demand of energy for developing economies. In the search to be able to know how much electrical energy is consumed, a modeling of the electrical energy demand is carried out. However, the inherent intricacy and nonlinear nature of electricity consumption patterns present a significant obstacle to achieve precise modeling. In this article, a chaos theory approach is carried out to analyze the behavior of the system and to obtain properties of its dynamic system. A network consisting of a convolutional part, a hidden part and an output part is proposed. Convolutional operations are employed for dimensionality reduction in transformed data sets by reconstruction of the phase space. A radial basis function neural is used in the hidden part. The dynamic analysis approach using chaos theory, and the proposed neural network is compared with the radial basis function neural network for the modeling of electrical energy consumption.
AB - Electricity is an essential energy resource in the industrial, commercial and housing sector, having a very important role in the development of societies. Urbanization and industrialization implies a great demand of energy for developing economies. In the search to be able to know how much electrical energy is consumed, a modeling of the electrical energy demand is carried out. However, the inherent intricacy and nonlinear nature of electricity consumption patterns present a significant obstacle to achieve precise modeling. In this article, a chaos theory approach is carried out to analyze the behavior of the system and to obtain properties of its dynamic system. A network consisting of a convolutional part, a hidden part and an output part is proposed. Convolutional operations are employed for dimensionality reduction in transformed data sets by reconstruction of the phase space. A radial basis function neural is used in the hidden part. The dynamic analysis approach using chaos theory, and the proposed neural network is compared with the radial basis function neural network for the modeling of electrical energy consumption.
KW - Chaos theory
KW - Electrical power demand modeling
KW - Phase space reconstruction
KW - Radial basis function neural network
UR - http://www.scopus.com/inward/record.url?scp=85175632356&partnerID=8YFLogxK
U2 - 10.1007/s11227-023-05733-y
DO - 10.1007/s11227-023-05733-y
M3 - Artículo
AN - SCOPUS:85175632356
SN - 0920-8542
VL - 80
SP - 7102
EP - 7119
JO - Journal of Supercomputing
JF - Journal of Supercomputing
IS - 5
ER -