Residential Level Short-Term Demand Forecasting Using ANFIS Model

Forecasting is a process in which future demand is predicted with the help of past and current data. Uncertainty in real-world data makes this forecasting process challenging. Short-term load forecasting for individual electric customers is necessary to forecast future demand at the residential level. It has been observed that many loads forecasting approaches that are good for grid or substation load forecasting don’t fit the residential load forecasting problems. So, it will be implicated on the residential level. Recurrent Neural Network (RNN), Artificial Neural Network (ANN), Adaptive Network-based Fuzzy Interference System (ANFIS), Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) Neural Network are some of the forecasting methods. In this paper, the ANFIS method will forecast the residential level. Weather factor (temperature, pressure, humidity, wind speed, etc.) is considered for better prediction. Forecasting is done for 24 h, and demand at a different time is observed. It is compared with the ANN method.