Please use this identifier to cite or link to this item: https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4585
Title: Forecast Electricity Sales in Industrial Sector in Sri Lanka Using Predictive Analytics
Authors: Chandrasena, A. U. B.
Issue Date: 23-May-2022
Abstract: Electricity has turned in to a significant type of end-use energy in the today’s advanced society. The impact of electricity is enormous and has been perceived as a fundamental day today need of human. Forecasting of Electricity sales is significant and critical for a utility to decide on the correct selection relating to future power generation stations and organizational strengthening. During the last decade, several techniques are being used to forecast electricity sales. This study attempts to review the time series, Autoregressive Moving-Average (ARMA) and Linear Regression methods and choose the most suitable forecasting method for long-term electricity sales forecast using annual data from 1969 to 2018. The two models were created and fine-tuned using recorded industrial electricity sales of Sri Lanka, andtARIMAt(0,2,1)twas observed astthetbest fittmodeltfor forecasting annual industrial electricity sales of the Sri Lanka power system with the lowest RMSE of 176.553 GWH, MAPE of 15.42% and R2 88%.
URI: https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4585
Appears in Collections:2021

Files in This Item:
File Description SizeFormat 
2018 BA 007.pdf1.45 MBAdobe PDFView/Open


Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.