eduzhai > Applied Sciences > Engineering >

Predicting Electric Energy Consumption for a Jerky Enterprise

  • Peter
  • (0) Download
  • 20210302
  • Save

... pages left unread,continue reading

Document pages: 11 pages

Abstract: Wholesaleand retail markets for electricity and power require consumers to forecastelectricity consumption at different time intervals. The study aims to increase economic efficiency of the enterprisethrough the introduction of algorithm for forecasting electric energyconsumption unchanged in technological process. Qualitative forecast allows youto essentially reduce costs of electrical energy, because power cannotbe stockpiled. Therefore, when buying excess electrical power, costs canincrease either by selling it on the balancing energy market or by maintaining reserve capacity. If the purchased power isinsufficient, the costs increase is due to the purchase of additional capacity.This paper illustrates three methods of forecasting electric energyconsumption: autoregressive integrated moving average method, artificial neuralnetworks and classification and regression trees. Actual data from consuming ofelectrical energy was used to make day, week and month ahead prediction.The prediction effect of predictionmodel was proved in Statistica simulation environment. Analysis of estimationof the economic efficiency of prediction methods demonstrated that the use ofthe artificial neural networks method for short-term forecast allowed reducing the cost of electricity moreefficiently. However, for mid- range predictions, the classification and regressiontree was the most efficient method for a Jerky Enterprise. The results indicatethat calculation error reduction allows decreases expenses for the purchase ofelectric energy.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...