The author presents a method of forecasting the hourly load demand on a power system. The forecasting method uses threshold autoregressive models with the stratification rule. With the proposed threshold model algorithm, fewer parameters are required to capture the random component in load dynamics. The techniques employed herein are the determination of an optimum threshold number and the construction of the threshold. The optimum stratification rule attempts not only to remove any judgmental input, but also to render the threshold process entirely mechanistic. Hence, the results demonstrate the proposed method's effectiveness in terms of improving precision and reliability.
References
-
-
1)
-
M.B. Priestely
.
(1988)
Nonlinear and nonstationary time analysis.
-
2)
-
A.D. Papalexopoulos ,
T.C. Hesterberg
.
A regression based approachto short-term system load forecasting.
IEEE Trans. Power Appar. Syst. (USA)
,
4 ,
800 -
811
-
3)
-
W.R. Christiaanse
.
Short-term load forecasting using generalexponential smoothing.
IEEE Trans. Power Appar. Syst. (USA)
,
2 ,
900 -
911
-
4)
-
S. Ranman ,
R. Bhatnager
.
An expert system based algorithm forshort-term load forecasting.
IEEE Trans. Power Appar. Syst. (USA)
,
2 ,
1678 -
1688
-
5)
-
R. Singh
.
Approximately optimum stratification on the auxiliary variable.
J. Am. Stat. Assoc.
,
829 -
833
-
6)
-
D.C. Hill ,
D.G. Infield
.
Modelled operation of the Shetland Islandspower system comparing computational and human operators loadforecasts.
IEE Proc., Gener. Transm. Distrib.
,
6 ,
555 -
559
-
7)
-
M.A. El-Sharkawi ,
D. Niebur
.
(1996)
A tutorial course on artificial neuralnetworks with applications to power systems.
-
8)
-
Lee, K.Y., Cha, Y.T., Park, J.K.: `Short-term load forecasting usingan artificial neural network', 91 WM 199-0 PWRS, IEEE PES winter power meeting, 1991.
-
9)
-
G. Gross ,
F.D. Galiana
.
Short-term load forecasting.
Proc. IEEE
,
12 ,
1558 -
1573
-
10)
-
W.G. Cochran
.
(1997)
Sampling techniques.
-
11)
-
J.F. Chen ,
W.M. Wang ,
C.M. Huang
.
Analysis of an adaptive time-series autoregressive moving-average (ARMA) model for short-term loadforecasting.
Electr. Power Syst. Res. (Switzerland)
,
3 ,
187 -
196
-
12)
-
J. Toyoda ,
M.S. Chen ,
Y. Inouve
.
An application of state estimationto short term load forecasting, Part I and Part II.
IEEE Trans. Power Appar. Syst. (USA)
,
7 ,
1678 -
1688
-
13)
-
H. Tong ,
Lim
.
(1983)
Threshold models in nonlinear time series analysis.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-gtd_19971144
Related content
content/journals/10.1049/ip-gtd_19971144
pub_keyword,iet_inspecKeyword,pub_concept
6
6