Comparison of Forecasting Methods of House Electricity Consumption for Honda Smart Home

The electricity consumption of buildings composes a major part the city’s energy consumption. Electricity forecasting enables development home management systems, resulting in future design more sustainable houses and decrease total Energy performance is influenced by many factors, like ambient temperature, humidity, variety electrical devices. Therefore, multivariate prediction methods are preferred rather than univariate. Honda Smart Home US data set was selected to compare three for minimizing errors, MAE RMSE: Artificial Neural Networks (ANN), Support Vector Regression (SVR), Fuzzy RuleBased Systems (FRBS) constructing models each method on different time-terms. comparison shows that SVR superior over alternatives.