TY - GEN
T1 - Day-ahead electricity market forecasting using kernels
AU - Kekatos, Vasileios
AU - Veeramachaneni, Sriharsha
AU - Light, Marc
AU - Giannakis, Georgios B
PY - 2013/5/6
Y1 - 2013/5/6
N2 - Weather and life cycles, fuel markets, reliability rules, scheduled and random outages, renewables and demand response programs, all constitute pieces of the electricity market puzzle. In such a complex environment, forecasting electricity prices is a very challenging task; nonetheless, it is of paramount importance for market participants and system operators. Day-ahead price forecasting is performed in the present paper using a kernel-based method. This machine learning approach offers unique advantages over existing alternatives, especially in systematically exploiting the spatio-temporal nature of 10-cational marginal prices (LMPs), while nonlinear cause-effect relationships can be captured by carefully selected similarities. Beyond conventional time-series data, non-vectorial attributes (e.g., hour of the day, day of the week, balancing authority) are transparently utilized. The novel approach is tested on real data from the Midwest ISO (MISO) day-ahead electricity market over the summer of 2012, during which MISO's load peak record was observed. The resultant day-ahead LMP forecasts outperform price repetition and ordinary linear regression, thus offering a promising inference tool for the electricity market.
AB - Weather and life cycles, fuel markets, reliability rules, scheduled and random outages, renewables and demand response programs, all constitute pieces of the electricity market puzzle. In such a complex environment, forecasting electricity prices is a very challenging task; nonetheless, it is of paramount importance for market participants and system operators. Day-ahead price forecasting is performed in the present paper using a kernel-based method. This machine learning approach offers unique advantages over existing alternatives, especially in systematically exploiting the spatio-temporal nature of 10-cational marginal prices (LMPs), while nonlinear cause-effect relationships can be captured by carefully selected similarities. Beyond conventional time-series data, non-vectorial attributes (e.g., hour of the day, day of the week, balancing authority) are transparently utilized. The novel approach is tested on real data from the Midwest ISO (MISO) day-ahead electricity market over the summer of 2012, during which MISO's load peak record was observed. The resultant day-ahead LMP forecasts outperform price repetition and ordinary linear regression, thus offering a promising inference tool for the electricity market.
KW - Locational marginal prices
KW - kriging filtering
KW - machine learning
KW - wholesale electricity market
UR - http://www.scopus.com/inward/record.url?scp=84876917812&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84876917812&partnerID=8YFLogxK
U2 - 10.1109/ISGT.2013.6497797
DO - 10.1109/ISGT.2013.6497797
M3 - Conference contribution
AN - SCOPUS:84876917812
SN - 9781467348942
T3 - 2013 IEEE PES Innovative Smart Grid Technologies Conference, ISGT 2013
BT - 2013 IEEE PES Innovative Smart Grid Technologies Conference, ISGT 2013
T2 - 2013 IEEE PES Innovative Smart Grid Technologies Conference, ISGT 2013
Y2 - 24 February 2013 through 27 February 2013
ER -