Developing a hybrid time-series artificial intelligence model to forecast energy use in buildings.

The development of a reliable energy use prediction model is still difficult due to the inherent complex pattern of energy use data. There are few studies developing a prediction model for the one-day-ahead energy use prediction in buildings and optimizing the hyperparameters of a prediction model is necessary. This study aimed to propose a hybrid artificial intelligence model for forecasting one-day ahead time-series energy consumption in buildings. The proposed model was developed based on the integration of the Seasonal Autoregressive integrated Moving average, the Firefly-inspired Optimization algorithm, and the support vector Regression (SAMFOR). A large dataset of energy consumption in 30-min intervals, temporal data, and weather data from six real-world buildings in Vietnam was used to train and test the model. Sensitivity analyses were performed to identify appropriate model inputs. Comparison results show that the SAMFOR model was more effective than the others such as the seasonal autoregressive integrated moving average (SARIMA) and support vector regression (SVR), SARIMA-SVR, and random forests (RF) models. Evaluation results on real-world building depicted that the proposed SAMFOR model achieved the highest accuracy with the root-mean-square error (RMSE) of 1.77 kWh in, mean absolute percentage error (MAPE) of 9.56%, and correlation coefficient (R) of 0.914. The comparison results confirmed that the SAMFOR model was effective for forecasting one-day-ahead energy consumption. The study contributes to (1) the knowledge domain by proposing the hybrid SAMFOR model for forecasting energy consumption in buildings; and (2) the state of practice by providing building managers or users with a powerful tool for analyzing and improving building energy performance.

Proposing a hybrid metaheuristic optimization algorithm and machine learning model for energy use forecast in non-residential buildings.

The building sector is the largest energy consumer accounting for 40% of global energy usage. An energy forecast model supports decision-makers to manage electric utility management. Identifying optimal values of hyperparameters of prediction models is challenging. Therefore, this study develops a novel time-series Wolf-Inspired Optimized Support Vector Regression (WIO-SVR) model to predict 48-step-ahead energy consumption in buildings. The proposed model integrates the support vector regression (SVR) and the grey wolf optimizer (GWO) in which the SVR model serves as a prediction engine while the GWO is used to optimize the hyperparameters of the SVR model. The 30-min energy data from various buildings in Vietnam were adopted to validate model performance. Buildings include one commercial building, one hospital building, three authority buildings, three university buildings, and four office buildings. The dataset is divided into the learning data and the test data. The performance of the WIO-SVR was superior to baseline models including the SVR, random forests (RF), M5P, and decision tree learner (REPTree). The WIO-SVR model obtained the highest value of correlation coefficient (R) with 0.90. The average root-mean-square error (RMSE) of the WIO-SVR was 2.02 kWh which was more accurate than those of the SVR model with 10.95 kWh, the RF model with 16.27 kWh, the M5P model with 17.73 kWh, and the REPTree model with 26.44 kWh. The proposed model improved 442.0-1207.9% of the predictive accuracy in RMSE. The reliable WIO-SVR model provides building managers with useful references in efficient energy management.

Forecasting Time-Series Energy Data in Buildings Using an Additive Artificial Intelligence Model for Improving Energy Efficiency.

Building energy efficiency is important because buildings consume a significant energy amount. The study proposed additive artificial neural networks (AANNs) for predicting energy use in residential buildings. A dataset in hourly resolution was used to evaluate the AANNs model, which was collected from a residential building with a solar photovoltaic system. The proposed AANNs model achieved good predictive accuracy with 14.04% in mean absolute percentage error (MAPE) and 111.98 Watt-hour in the mean absolute error (MAE). Compared to the support vector regression (SVR), the AANNs model can significantly improve the accuracy which was 103.75% in MAPE. Compared to the ANNs model, accuracy improvement percentage by the AANNs model was 4.6% in MAPE. The AANNs model was the most effective forecasting model among the investigated models in predicting energy consumption, which provides building managers with a useful tool to improve energy efficiency in buildings.