Published Paper Details:

For effective energy management and resource planning, accurate electricity demand forecasts are essential. Time series forecasting methods like Exponential Smoothing (ES) and ARIMA models have grown popular recently because of their capacity to identify complex seasonal trends in data. This study aims to compare the performance of different wavelet families in conjunction with ES and ARIMA models for electricity demand forecasting and we are able to observe the reverse effect of wavelet. The results are compared to assess the accuracy and effectiveness of different wavelets in improving the forecasting performance of ES and ARIMA models. The findings of this study contribute to a better understanding of the applicability of wavelet-based approaches for electricity demand forecasting. However, it's important to note that the choice between ARIMA and Exponential Smoothing ultimately depends on the specific characteristics of the time series data and the forecasting objectives. For complex and noisy data, ARIMA with wavelets emerges as a robust and effective forecasting method, demonstrating superior performance in our analysis.