Description of the project
The project consists of the application of artificial intelligence technologies on energy consumption data both in the domestic sphere and in the industrial sector with the aim of finding consumption patterns and creating models that allow improving efficiency and reduce energy consumption.
In a first phase, the experimental data will be obtained and treated so that they can be subsequently analyzed. The first contributions are expected to be made in the field of signal processing and data pre-processing. Afterwards, work will be done on "feature selection" algorithms for the search for better predictors of energy consumption and generation. From the selection of patterns, the different techniques for data modeling will be introduced, both in "machine learning" and in "deep learning" (neural networks, convolutional neural networks, recurrent neural networks), regressions.
Techniques such as anomaly or novelty algorithms will be assessed for the analysis of operation and diagnosis. Likewise, regression models will also be used as an indicator of malfunction.
The "clustering" of data will be valued as a pre-processing technique and "ensemble learning" to obtain indicators that can be easily interpreted by non-expert users.
The objective is to obtain patterns of consumption and disaggregation of consumption and electricity generation from the application of these techniques, to be able to detect what the energy consumption habits of consumers are and to be able to control and promote effective flexibility strategies.
The direct application of all this study is energy saving. The objective will be to have aggregated and disaggregated models of electricity consumption, renewable generation and state of charge available in batteries that allow the optimization of flexibility services. Work will be done on the basis of load availability prediction to finally optimize flexibility services.
