Alfred University Research and Archive (AURA)

Short-term Nodal Load forecasting for SCUC Based on Data Mining methodology

Show simple item record

dc.contributor.author Lu, Dan
dc.contributor.author Bao, Zhen
dc.contributor.author Li, Zuyi
dc.contributor.author Zhao, Dongbo
dc.date.accessioned 2019-05-07T14:16:45Z
dc.date.available 2019-05-07T14:16:45Z
dc.date.issued 2018-10-12
dc.identifier.uri http://hdl.handle.net/10829/23387
dc.description.abstract Our poster introduces an advanced method to predict Short-term Nodal Load data in power system. This method forecasts a set of load profiles for the next day which can cover minor changes. Data Mining (DM) techniques are heavily used to deal with the existing historical data. Least absolute shrinkage and selection operator (LASSO) is employed to reduce the number of features for a single nodal load forecasting. Principal component analysis (PCA) is used to capture the features of the historical load in low dimensional space compared to the original high-dimensional load space, whose feature is hard to describe. Bayesian Ridge Regression (BRR) is employed to form the prediction model which is sophisticated method to decide the parameters in the model from statistical point of view. en_US
dc.language.iso en_US en_US
dc.publisher Alfred University en_US
dc.relation.ispartof Scholes Library en_US
dc.rights http://libguides.alfred.edu/AURA/termsofuse en_US
dc.subject AU Energy Symposium en_US
dc.subject Energy en_US
dc.subject Renewable energy en_US
dc.subject Nodal load forecasting en_US
dc.subject Data mining en_US
dc.title Short-term Nodal Load forecasting for SCUC Based on Data Mining methodology en_US
dc.type Presentation or Speech en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search


Browse

My Account