AN EFFICIENT MODEL BASED ON EXTREME LEARNING MACHINES FOR SHORT-TERM ELECTRIC LOAD FORECASTING

T. Venkat Narayana Rao, Rithik .

Abstract


Short-Term Load Forecasting (STLF) is an extremely important kit for many power generating energy companies so that they can organize and plan their daily power generation schedules and transmissions. There are many number of techniques that have been reported in literature and used for STLF forecasting model. Among these models the Artificial Neural Network (ANN) forecasting model are proven the most assuring techniques. This paper proposes an extreme learning machine (ELM) based model for a short term electric load forecast in power generating companies. The real historical data of energy company is used in the action of process for 30 minutes ahead load prediction with a prominence given to data analysis. Correlation analysis is used for identifying and nominating the utmost significant and dominant input parameters for the model. The simulation results obtained from this experiment are presented and compared with other standard ANN based models like NN-GA, NN-ABC and NN-PSO etc. The acceptable accuracy of our proposed model concludes its applicability in forecasting and that it can also be used by the electricity generating power companies for better demand and response features.



Full Text:

PDF

Refbacks

  • There are currently no refbacks.


© 2017 International Journal of Global Research in Computer Science (JGRCS)
Copyright Agreement & Authorship Responsibility