Load forecast errors can yield suboptimal unit commitment decisions. The ec
onomic cost of inaccurate forecasts is assessed by a combination of forecas
t simulation, unit commitment optimization, and economic dispatch modeling
for several different generation/load systems. The forecast simulation pres
erves the error distributions and correlations actually experienced by user
s of a neural net-based forecasting system. Underforecasts result in purcha
ses of expensive peaking or spot market power; overforecasts inflate start-
up and fixed costs because too much capacity is committed. The value of imp
roved accuracy is found to depend on load and generator characteristics; fo
r the systems considered here, a reduction of 1% in mean absolute percentag
e error (MAPE) decreases variable generation costs by approximately 0.1%-0.
3% when MAPE is in the range of 3%-5%. These values are broadly consistent
with the results of a survey of 19 utilities, using estimates obtained by s
impler methods. A conservative estimate is that a 1% reduction in forecasti
ng error far a 10,000 MW utility can save up to $1.6 million annually.