TY - GEN
T1 - Day-Ahead Electricity Price Forecasting Using an Adaptive Combination Method in the Japanese Spot Market
AU - Omura, Manaka
AU - Fujimoto, Yu
AU - Ishii, Hideo
AU - Hayashi, Yasuhiro
AU - Sawa, Toshiyuki
AU - Sasaki, Hiroto
AU - Fukuyama, Naoto
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/9
Y1 - 2020/9
N2 - Forecasting the electricity spot market price (i.e., the price of electricity traded for the next day) is important in planning efficient power generation and demand schedules. This research aims to discuss the following two points in the forecasting task: an explicit scheme for estimating high and low-price situations and an effective weighted integration of given multiple forecast products depending on the estimated situations. The authors propose an adaptive method of combining market price forecasts (ADAPTIVE) to utilize several types of given forecast results efficiently and improve forecasting accuracy. The method aims to capture the features of the component models' results considering high- and low-prices situations. To evaluate the effectiveness of the proposed ADAPTIVE, numerical experiments were conducted on electricity spot market prices in the Japan Electric Power Exchange. The results indicate that the proposed method is a promising way to improve the accuracy of the conventional method of combining forecasts.
AB - Forecasting the electricity spot market price (i.e., the price of electricity traded for the next day) is important in planning efficient power generation and demand schedules. This research aims to discuss the following two points in the forecasting task: an explicit scheme for estimating high and low-price situations and an effective weighted integration of given multiple forecast products depending on the estimated situations. The authors propose an adaptive method of combining market price forecasts (ADAPTIVE) to utilize several types of given forecast results efficiently and improve forecasting accuracy. The method aims to capture the features of the component models' results considering high- and low-prices situations. To evaluate the effectiveness of the proposed ADAPTIVE, numerical experiments were conducted on electricity spot market prices in the Japan Electric Power Exchange. The results indicate that the proposed method is a promising way to improve the accuracy of the conventional method of combining forecasts.
KW - Japan Electric Power Exchange
KW - combining forecasts
KW - eXtreme gradient boosting
KW - electricity price forecast
KW - spot market
UR - http://www.scopus.com/inward/record.url?scp=85094844840&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094844840&partnerID=8YFLogxK
U2 - 10.1109/EEM49802.2020.9221894
DO - 10.1109/EEM49802.2020.9221894
M3 - Conference contribution
AN - SCOPUS:85094844840
T3 - International Conference on the European Energy Market, EEM
BT - 2020 17th International Conference on the European Energy Market, EEM 2020
PB - IEEE Computer Society
T2 - 17th International Conference on the European Energy Market, EEM 2020
Y2 - 16 September 2020 through 18 September 2020
ER -