Intelligent Energy Demand Estimation
Mentor: Abraham Duarte Muñoz
Phone: (+34) 916655073
University: Universidad Rey Juan Carlos
Partner Host Institution: ATOS
Keywords: Energy demand estimation, Metaheuristics, Neural Networks, Socio-economic predictive variables

Intelligent Energy Demand Estimation

Energy demand prediction is a relevant problem whose solution is evaluated by policy makers in order to take key decisions affecting the economy of a country. A number of previous approaches to improve the quality of this estimation have been proposed in the last decade, the majority of them applying different machine learning techniques. In this project, we will investigate the performance of a robust hybrid approach, composed of a metaheuristic procedure and a neural network. On the one hand, the metaheuristic approach is focused on obtaining the most relevant features among the set of initial ones. We will explore how different models (linear, exponential, etc.) are suitable for this problem. On the other hand, neural networks will be designed to obtain the final energy demand prediction.
While previous approaches consider that the number of macroeconomic variables used for prediction is a parameter of the algorithm (i.e., it is fixed a priori), the proposed approach will optimize both, the number of variables and the best ones.
We have some preliminary results in the real case of energy demand estimation in Spain, which shows the excellent performance of the proposed approach. In particular, the whole method obtains an estimation of the energy demand with an error lower than 2%, even when considering the crisis years, which are a real challenge.

Departament: Computing Science, Computer Architecture, Programming Languages and Systems and Statistics and Operative Investigation
Research Group: Group for Research in Algorithms For Optimization (GRAFO)
More Information:
Relevants projects on the area:
Relevants publications on the area: 1.- Sánchez-Oro, J., A. Duarte, and S. Salcedo-Sanz, "Robust total energy demand estimation with a hybrid Variable Neighborhood Search – Extreme Learning Machine algorithm", Energy Conversion and Management, vol. 123, pp. 445-452, 2016
2.- Sánchez-Oro, J., A. Duarte, and S. Salcedo-Sanz, "Estimating the Spanish Energy Demand Using Variable Neighborhood Search", Advances in Artificial Intelligence: Lecture Notes in Artificial Intelligence, pp. 341–350, 2016