Team13_5D_2020_SoCSE_KLETech

In the pre-processing:Observed the dirty data.Interpolated the missing valuesSince after the interpolation many NaN values were left in the dataset so we took out the mean of the consumption data entries for each meter_id and then replace the NaN values with it. Analysis:Observed the trend of the Energy Consumption from the datasetAs observed our data turned out to be stationary and seasonalOur dataset is huge Data Modelling:To model our data we chose the LSTM(Long Short-Term Memory) modelWe also tried using the other modelling methods such as ARIMA and SARIMALSTM works better as we are dealing with huge amount of data and enough training data is available, while ARIMA is better for smaller dataset ARIMA requires a series of parameters (p,q,d) which must be calculated based on data, while LSTM does not require setting such parameters.