Feature selection in short-term load forecasting

Feature selection in short-term load forecasting

This paper investigates correlation between energy consumption 24 hours ahead and features used for predicting energy consumption. The features originate from three categories: weather, time and previous energy. The correlations are calculated using Pearson correlation and mutual information. This r...

Full description

Bibliographic Details
Main Authors: Söderberg, Max Joel, Meurling, Axel
Format: Others
Language:English
Published: KTH, Skolan för elektroteknik och datavetenskap (EECS) 2019
Subjects:
Short-term load forecasting
energy consumption forecasting
Linear regression
SVR
Random Forest
machine learning
regression
feature selection
attribute selection
Pearson correlation
Mutual information
correlation matrix
Two-way ANOVA
Tukey’s HSD test.
Kortsiktig lastprognos
Energiförbrukningsprognos
Linjär regression
Random forest
Maskininlärning
Attributval
Pearson-korrelation
Ömsesidig information
Korrelationsmatris
Tvåvägs ANOVA
Tukey’s HSD-test.
Computer and Information Sciences
Data- och informationsvetenskap
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259692

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259692

Similar Items