DOIONLINE 
DOIONLINE Publish In |
International Journal of Industrial Electronics and Electrical Engineering (IJIEEE)-IJIEEE |
 Journal Home Volume Issue |
||||||||
Issue |
Volume-7,Issue-10 ( Oct, 2019 ) | |||||||||
Paper Title |
Peak Demand Forecasting of Zone Substations | |||||||||
Author Name |
Jiaming Li, Omid Motlagh | |||||||||
Affilition |
CSIRO-DATA61,CORNER VIMIERA& PEMBROKE RDS, MARSFIELD, NSW, AUSTRALIA CSIRO-ENERGY, 10 MURRAY DWYER CCT, MAYFIELD WEST, NSW, AUSTRALIA | |||||||||
Pages |
22-26 | |||||||||
Abstract |
Electricity peak demand forecasting has been a real challenge for power system scheduling in different levels of energy sectors. The supply industry requires forecasts with lead times that range from the short term (a few minutes, hours, or days ahead) to the long term (up to 20 years ahead). Short-term forecasts have become increasingly important since the rise of the competitive energy markets. Being a mid-point in the electricity supply chain, the forecasts of zone substation load is a key component in both top-down and bottom-up analyses of electricity demand. This paper presents a support vector regression (SVR) based method for forecasting tomorrow's peak half-hourly power demand for a zone substation. Keywords - Short-term Peak Demand Forecasting, Support Vector Machine, Support Vector Regression, Machine Learning. | |||||||||
| View Paper | ||||||||||
