Characterizing the electric energy curve can improve the energy efficiency of existing buildings without any structural change and is the basis for controlling and optimizing building performance. Artificial Intelligence (AI) techniques show much potential due to their accuracy and malleability in the field of pattern recognition, and using these models it is possible to adjust the building services in real time. Thus, the objective of this paper is to determine the AI technique that best forecasts electrical loads. The suggested techniques are random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), multilayer perceptron (MLP), long short-term memory (LSTM), and temporal convolutional network (Conv-1D). The conducted research applies a methodology that considers the bias and variance of the models, enhancing the robustness of the most suitable AI techniques for modeling and forecasting the electricity consumption in buildings. These techniques are evaluated in a single-family dwelling located in the United States. The performance comparison is obtained by analyzing their bias and variance by using a 10-fold cross-validation technique. By means of the evaluation of the models in different sets, i.e., validation and test sets, their capacity to reproduce the results and the ability to properly forecast on future occasions is also evaluated. The results show that the model with less dispersion, both in the validation set and test set, is LSTM. It presents errors of −0.02% of nMBE and 2.76% of nRMSE in the validation set and −0.54% of nMBE and 4.74% of nRMSE in the test set.

The increasing trend in energy demand is higher than the one from renewable generation, in the coming years. One of the greatest sources of consumption are buildings. The energy management of a building by means of the production of photovoltaic energy in situ is a common alternative to improve sustainability in this sector. An efficient trade-off of the photovoltaic source in the fields of Zero Energy Buildings (ZEB), nearly Zero Energy Buildings (nZEB) or MicroGrids (MG) requires an accurate forecast of photovoltaic production. These systems constantly generate data that are not used. Artificial Intelligence methods can take advantage of this missing information and provide accurate forecasts in real time. Thus, in this manuscript a comparative analysis is carried out to determine the most appropriate Artificial Intelligence methods to forecast photovoltaic production in buildings. On the one hand, the Machine Learning methods considered are Random Forest (RF), Extreme Gradient Boost (XGBoost), and Support Vector Regressor (SVR). On the other hand, Deep Learning techniques used are Standard Neural Network (SNN), Recurrent Neural Network (RNN), and Convolutional Neural Network (CNN). The models are checked with data from a real building. The models are validated using normalized Mean Bias Error (nMBE), normalized Root Mean Squared Error (nRMSE), and the coefficient of variation (R²). Standard deviation is also used in conjunction with these metrics. The results show that the models forecast the test set with errors of less than 2.00% (nMBE) and 7.50% (nRMSE) in the case of considering nights, and 4.00% (nMBE) and 11.50% (nRMSE) if nights are not considered. In both situations, the R² is greater than 0.85 in all models.

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.

Nowadays, common electrical household appliances are mostly being powered by means of alternate current (AC), although there are cases where direct current (DC) is used instead. In all cases, internal devices are supplied with DC, and this fact involves there are losses due to the need for AC/DC converters. At the same time, most electrical home consumption takes place during peak hours when electricity is more expensive in many electricity markets. The addition of a battery in these installations permits storing electrical energy during certain periods of the day with the aim of supplying it during other ones—when this operation is more efficient or convenient—simultaneously reducing costs and greenhouse gas emissions. In this paper, a comparison is proposed between three possible home consumption scenarios, i.e., one consisting of a current AC system, one consisting of an AC system with a battery, and a third consisting of a hybrid AC/DC system with a battery.

Nowadays, there is a growing trend to incorporate renewables in electrical power systems and, in particular, wind energy, which has become an important primary source in the electricity mix of many countries, where wind farms have been proliferating in recent years. This circumstance makes it particularly interesting to understand wind behavior because generated power depends on it. In this paper, a method is proposed to synthetically generate sequences of wind speed values satisfying two important constraints. The first consists of fitting the given statistical distributions, as the generally accepted fact is assumed that the measured wind speed in a location follows a certain distribution. The second consists of imposing spatial and temporal correlations among the simulated wind speed sequences. The method was successfully checked under different scenarios, depending on variables, such as the number of locations, the duration of the data collection period or the size of the simulated series, and the results were of high accuracy.