TY - JOUR
T1 - Forecasting electricity market pricing using artificial neural networks
AU - Pao, Hsiao-Tien
PY - 2007/3/1
Y1 - 2007/3/1
N2 - Electricity price forecasting is extremely important for all market players, in particular for generating companies: in the short term, they must set up bids for the spot market; in the medium term, they have to define contract policies; and in the long term, they must define their expansion plans. For forecasting long-term electricity market pricing, in order to avoid excessive round-off and prediction errors, this paper proposes a new artificial neural network (ANN) with single output node structure by using direct forecasting approach. The potentials of ANNs are investigated by employing a rolling cross validation scheme. Out of sample performance evaluated with three criteria across five forecasting horizons shows that the proposed ANNs are a more robust multi-step ahead forecasting method than autoregressive error models. Moreover, ANN predictions are quite accurate even when the length of the forecast horizon is relatively short or long.
AB - Electricity price forecasting is extremely important for all market players, in particular for generating companies: in the short term, they must set up bids for the spot market; in the medium term, they have to define contract policies; and in the long term, they must define their expansion plans. For forecasting long-term electricity market pricing, in order to avoid excessive round-off and prediction errors, this paper proposes a new artificial neural network (ANN) with single output node structure by using direct forecasting approach. The potentials of ANNs are investigated by employing a rolling cross validation scheme. Out of sample performance evaluated with three criteria across five forecasting horizons shows that the proposed ANNs are a more robust multi-step ahead forecasting method than autoregressive error models. Moreover, ANN predictions are quite accurate even when the length of the forecast horizon is relatively short or long.
KW - Artificial neural network
KW - Autoregressive error model
KW - Cross validation scheme
KW - European energy exchange
KW - Long-term forecasts
UR - http://www.scopus.com/inward/record.url?scp=33846266227&partnerID=8YFLogxK
U2 - 10.1016/j.enconman.2006.08.016
DO - 10.1016/j.enconman.2006.08.016
M3 - Article
AN - SCOPUS:33846266227
SN - 0196-8904
VL - 48
SP - 907
EP - 912
JO - Energy Conversion and Management
JF - Energy Conversion and Management
IS - 3
ER -