DATA REDUCTION VERSUS FEATURE SELECTION IN APPLICATION OF DAILY MAXIMUM POWER LOAD FORECASTING

Abstract

Load forecasting task of small energetic region is a difficult problem due to high variability of power consumption. The accurate forecast of the power in the next hours is very important from the economic point of view. The most important problems in prediction are the choice of predictor and selection of features. Two methods of features selection was presented – simple selection using of genetic algorithm and dimensionality reduction methods for creating new features from many available measured data. As a predictor the Support Vector Machine working in regression mode (SVR) was chosen. The load forecasting results with SVR are presented and discussed.

Authors and Affiliations

Krzysztof Siwek

Keywords

Related Articles

SPRZĘTOWO-PROGRAMOWA REALIZACJA SYSTEMU TRANSMISJI INFORMACJI AUDIO Z SZYFROWANIEM CHAOTYCZNYMI SEKWENCJAMI

W artykule opisano system transmisji informacji audio z szyfrowaniem chaotycznymi sekwencjami generowanymi na podstawie jednowymiarowych dyskretnych chaotycznych odwzorowań. Pracę systemu rozpatruje się na przykładzie tr...

POWER SYSTEM MODELING BASED ON THE CIM STANDARD IEC61970

The article describes general power system modeling rules based on international standard IEC61970. Discussion has been divided on three stages. In the first case the genesis of standard has been shown. The second descri...

SPALANIE WĘGLI I PALIW ALTERNATYWNYCH W ATMOSFERZE TLENOWEJ

Artykuł przedstawia wyniki badań uzyskane w czasie realizacji procesu spalania w atmosferze oxy-fuel. Prezentowane wyniki skupiająsię na określeniu takich własności jak zapłon, parametry wybuchowości, emisję zanieczyszcz...

E-LABS – ADVANCED E-LEARNING

The aim of this article is to describe the development of distance learning techniques which opened the possibilities of conducting laboratory activities. In effect there emerged e-labs used for practical activities in t...

DISTORTIONLESS SIGNALS TRANSFER THROUGH A WIRE MEDIA METASTRUCTURE

In the paper the development of the components of communication means is considered based on the wire metastructures. This approach is novel and quite promising due to the metamaterials provides new opportunities for the...

Download PDF file
  • EP ID EP59442
  • DOI -
  • Views 113
  • Downloads 0

How To Cite

Krzysztof Siwek (2013). DATA REDUCTION VERSUS FEATURE SELECTION IN APPLICATION OF DAILY MAXIMUM POWER LOAD FORECASTING . Informatyka Automatyka Pomiary w Gospodarce i Ochronie Środowiska, 3(2), 9-12. https://europub.co.uk/articles/-A-59442