Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

Improving of the power consumption short-range forecasting accuracy by taking into consideration the seasonality factor dynamics

Dulesov A.   (The Khakas State University by N.F. Katanov, Abakan)

Shilov A.   (The Khakas State University by N.F. Katanov, Abakan)

The short-range forecast power consumption forecasting problem with considering of «Day status» (workday or day off) factor (attribute) and seasonality associated with temperature changes is shown. The detailed analysis of outside air temperature factor influence on the process of power consumption is given and 3 seasons depending on the enabled/disabled building heating system: season without heating; heating season; off-season. The clustering procedure based on above-mentioned partition is made. The values obtained in the hourly power consumption) forecasting in the Republic of Khakassia (from the zero to the twenty-third hour) both in general and with a focus on the trends turning points: 8-9; 12-13; 17-18 hours with using of linear regression, moving averages and neural network methods are analyzed. Conclusions about the accuracy improving of the forecast values with applying of clustering procedure based on the «Season depending on heating» factor are made.

Keywords:short-range forecast; forecast error; clustering; season; linear regression; moving averages; neural networks.
 

Read the full article …

Citation link:
Dulesov A. , Shilov A. Improving of the power consumption short-range forecasting accuracy by taking into consideration the seasonality factor dynamics // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2016. -№04. -С. 31-34
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences