The Definitions Of Energy Remand And Energy Demands

Decent Essays
In the 6am in the morning, the energy consumption starts to rise. Then energy surges around noon. Around 6pm, energy demand increases again (Figure 1). The relationship between all the variables with the energy consumption of appliances in the training set. Correlation equals to 1 is total positive correlation, -1 is total negative correlation, and 0 represents no correlation. It also gives the measurement of the linear dependence between two variables, shown in scatter plot below the diagonal, histogram plot along the diagonal and the Pearson correlation above the diagonal (Figure 2). The high correlations exist between T1 and T2(0.84), T2 and T3 (0.74), T4 and T5 (0.87), T5 and T6 (0.63), T7 and T8 (0.88), and T8 with T9 (0.86). The…show more content…
Lights as the second most important predictor pick by the RF and SVM-radial model. For GBM model, the second most important predictor is the atmospheric pressure. The data from the wireless sensor network was ranked highly in the GBM model, especially with information from the living room (RH2), the kitchen (RH1), the laundry room (T3), and bathroom (RH5) in the top position. Conclusion This study presents the data-driven predictive models for the energy use of appliances. the data set include the measurements of temperature and humidity sensor from a wireless network, weather from a nearby airport station and recorded energy use of lighting fixtures. We test the relationship between the appliances energy consumption and different predictors testing by four models (linear regression, support vector machines, random forest and gradient boosting machines) to predict energy consumption. Finding the best model by computing root mean squared error (RMSE), R-squared, and the mean absolute error (MAE). GBM and RF models give best prediction on RSME and R2 compared with SVM-radial and multiple linear regression. The best model GBM explain 97% of the variance (R2) in the training set and with 57% in the testing set with all the predictors. For all the models, the time information (NSM) is ranked as the most important predictor in appliances’ consumption. The data from the wireless sensor network is ranked highly in the GBM model, especially with information
Get Access