A New Fuzzy Logic Based Method For Residential Loads Forecasting

The load forecasting is crucial for energy management to maintain stability, power quality and reliability of the building's power system. This work proposes a new two input based fuzzy logic controller method for residential load forecasting. The proposed fuzzy system considers the temperature and a new variable calculated based on occupancy and week/special days for predicting the building's energy consumption. For the comparison purpose, the predicted energies by new fuzzy system and by artificial neural network are analyzed against actual energy consumption data in an apartment building located in Memphis city of USA. The efficacy of the proposed new fuzzy logic based prediction system over the conventional neural network approach is validated by MATLAB simulations and the performance indices.