Electricity price and demand forecasting under smart grid environment

Masri, Dina; Zeineldin, H. H.; Woon, Wei Lee

doi:10.1109/eeeic.2015.7165472

Cited by 2 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both over production and under production of electricity would cause financial loss to the operators [6]. One solution to overcome this problem is forecasting the load, which helps in predicting the amount of power required to meet the demand in the city [7], [8]. Weather parameters, peak/off-peak hours in a day, weekdays/weekend days, customer types, historical load data etc.…”

Section: Introductionmentioning

confidence: 99%

Multivariate Regression for Electricity Load Forecasting in Power Systems

Joy,

Bansal,

Ghenai

et al. 2024

Preprint

View full text Add to dashboard Cite

The development of smart grids in power system necessitates the need for forecasting the electricity load for the safe and economic functioning of electricity markets. A case study has been carried out considering a city's electricity load data using Multivariate Regression model. An input database of the model is generated taking into account of peak and off-peak hours based on maximum and minimum load data obtained from the utility operator. The characteristics of the electricity load over the whole year have been primarily analyzed to obtain a better intuition on the load behavior. In this context, the information in the form of temperature, days, different time duration i.e., peak and off-peak hours and past load data have been given as input to the regression model. The accuracy of the method has been evaluated using Root Mean Square Error (RMSE). The results of the adapted model have been compared with Neural Network, Ensemble and Kernel methods.

show abstract

Section: Introductionmentioning

confidence: 99%