Optimization of the Electrical Demand of an Existing Building with Storage Management through Machine Learning Techniques

• Published in: Applied sciences 2021-09, Vol.11 (17), p.7991
• Main Authors: Cordeiro-Costas, Moisés, Villanueva, Daniel, Eguía-Oller, Pablo
• Format: Article
• Language: English
• Subjects: Accuracy; Alternative energy sources; battery management system; building performance; Control algorithms; Cost control; Deep learning; demand response; Electric power demand; Electric vehicles; electrical energy storage; Electricity; electricity demand prediction; Emissions; Emissions control; Energy consumption; energy cost; Energy demand; Energy efficiency; Energy resources; Greenhouse effect; Greenhouse gases; Humidity; Learning algorithms; Linear programming; Machine learning; Mathematical models; Multilayer perceptrons; Neural networks; Office buildings; Optimization; Optimization techniques; Power management; Renewable resources; Storage
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app11177991

Accurate prediction from electricity demand models is helpful in controlling and optimizing building energy performance. The application of machine learning techniques to adjust the electrical consumption of buildings has been a growing trend in recent years. Battery management systems through the machine learning models allow a control of the supply, adapting the building demand to the possible changes that take place during the day, increasing the users’ comfort, and ensuring greenhouse gas emission reduction and an economic benefit. Thus, an intelligent system that defines whether the storage system should be charged according to the electrical needs of that moment and the prediction of the subsequent periods of time is defined. Favoring consumption in the building in periods when energy prices are cheaper or the renewable origin is preferable. The aim of this study was to obtain a building electrical energy demand model in order to be combined with storage devices with the purpose of reducing electricity expenses. Specifically, multilayer perceptron neural network models were applied, and the battery usage optimization is obtained through mathematical modelling. This approach was applied to a public office building located in Bangkok, Thailand.