Forecasting electricity demand from daily log sheet with correlated variables / Mohamad Syamim Hilmi … [et al.]
Electricity is one of the most important resources and fundamental infrastructure for every nation. Its milestone shows a significant contribution to world development that brought forth new technological breakthroughs throughout the centuries. Electricity demand constantly fluctuates, which affects...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Teknologi MARA Cawangan Pulau Pinang
2020
|
| Subjects: | |
| Online Access: | http://ir.uitm.edu.my/id/eprint/40645/1/40645_.pdf http://ir.uitm.edu.my/id/eprint/40645/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Electricity is one of the most important resources and fundamental infrastructure for every nation. Its milestone shows a significant contribution to world development that brought forth new technological breakthroughs throughout the centuries. Electricity demand constantly fluctuates, which affects the supply. Suppliers need to generate more electrical energy when demand is high, and less when demand is low. It is a common practice in power markets to have a reserve margin for unexpected fluctuation of demand. This research paper investigates regression techniques: multiple linear regression (MLR) and vector autoregression (VAR) to forecast demand with predictors of economic growth, population growth, and climate change as well as the demand itself. Auto-Regressive Integrated Moving Average (Auto-ARIMA) was used in benchmarking the forecasting. The results from MLR and VAR (lag-values=20) and Auto-ARIMA are monitored for five months from June to October of 2019. Using the root mean square error (RMSE) as an indicator for accuracy, Auto-ARIMA has the lowest RMSE for four months except in June 2019. VAR (lag-values=20) shows good forecasting capabilities for all five months, considering it uses the same lag values (20) for each month. Three different techniques have been successfully examined in order to find the best model for the prediction of the demand. |
|---|