Back to Search
Start Over
Energy consumption forecasting based on Elman neural networks with evolutive optimization
- Source :
- Expert Systems with Applications. 92:380-389
- Publication Year :
- 2018
- Publisher :
- Elsevier BV, 2018.
-
Abstract
- One new method is proposed based on recurrent neural networks.The method addresses the problem of energy consumption forecasting.The method is evaluated using data form public buildings of University of Granada. Buildings are an essential part of our social life. People spend a substantial fraction of their time and spend a high amount of energy in them. There is a grand variety of systems and services related to buildings, in order to better control and monitoring. The prompt taking of decisions may prevent costs and contamination. This paper proposes a method for energy consumption forecasting in public buildings, and thus, achieve energy savings, in order to improve the energy efficiency, without affecting the comfort and wellness. The prediction of the energy consumption is indispensable for the intelligent systems operations and planning. We propose an Elman neural network for forecasting such consumption and we use a genetic algorithm to optimize the weight of the models. This paper concludes that the proposed method optimizes the energy consumption forecasting and improves results attained in previous studies.
- Subjects :
- Consumption (economics)
Artificial neural network
Operations research
Computer science
business.industry
020209 energy
General Engineering
Evolutionary algorithm
Intelligent decision support system
02 engineering and technology
Energy consumption
Computer Science Applications
Artificial Intelligence
Genetic algorithm
0202 electrical engineering, electronic engineering, information engineering
Artificial intelligence
business
Efficient energy use
Subjects
Details
- ISSN :
- 09574174
- Volume :
- 92
- Database :
- OpenAIRE
- Journal :
- Expert Systems with Applications
- Accession number :
- edsair.doi...........d7aff39c8ffeace8dd12ca7d094933a5