An approach based on the Hopfield neural network is proposed for short-term hydro-scheduling. The purpose of short-term hydro-scheduling is to determine the optimal amounts of generated powers for the hydro-units in the system for the next N (N = 24 in this work) hours in the future. The proposed approach is basically a two-stage solution method. In the first stage, a Hopfield neural network is developed to reach a preliminary generation schedule for the hydro-units. Since some practical constraints may be violated in the preliminary schedule, a heuristic rule based search algorithm is developed in the second stage to reach a feasible suboptimal schedule which satisfies all practical constraints. The proposed approach is applied to hydroelectric generation scheduling of the Taiwan power system. It is concluded from the results that the proposed approach is very effective in reaching proper hydro-generation schedules.
References
-
-
1)
-
Y.Y. Hsu ,
C.C. Yang
.
Design of artificial neural networks for short-term loadforecasting, Parts I and II.
IEE Proc. C
,
407 -
418
-
2)
-
Sandell, N.R., Bertsekas, D.P., Shaw, J.J., Gully, S.W., Gendron, R.: `Optimal scheduling of large-scale hydrothermal power systems', Proceedings of the IEEE international Large-scale systemssymposium, 1982, p. 141–147.
-
3)
-
D. Neibur ,
A.J. Germond
.
Power system static security assessment using theKohonen neural network classifier.
IEEE Trans.
,
865 -
872
-
4)
-
H. Sasaki ,
M. Watanabe ,
R. Yokoyama
.
A solution method ofunit commitment by artificial neural networks.
IEEE Trans.
,
974 -
981
-
5)
-
D.J. Sobajic ,
Y.H. Pao
.
Artificial neural-net based dynamic securityassessment for electric power systems.
IEEE Trans.
,
220 -
228
-
6)
-
H. Mori ,
Y. Tamaru ,
S. Tsuzuki
.
An artificial neural-net based technique forpower system dynamic stability with the Kohonen model.
IEEE Trans.
,
856 -
864
-
7)
-
Z. Ouyang ,
S.M. Shahidehpour
.
A hybrid artificial neural network-dynamicprogramming approach to unit commitment.
IEEE Trans.
,
236 -
246
-
8)
-
C.F. Gerald ,
P.O. Wheatley
.
(2006)
Applied numerical analysis.
-
9)
-
E.B. Heinsson
.
Optimal short-term operation of a purely hydroelectric system.
IEEE Trans.
,
1072 -
1077
-
10)
-
D.W. Tank ,
J.J. Hopfield
.
Simple neural optimisation networks: an A/Dconverter, signal decision circuit, and a linear programming circuit.
IEEE Trans.
,
533 -
541
-
11)
-
M.F. Carvalho ,
S. Soares
.
An efficient hydrothermal scheduling algorithm.
IEEE Trans.
,
537 -
542
-
12)
-
Y.Y. Hsu ,
L.H. Jeng
.
Analysis of torsional osciliations using an artificial neuralnetwork.
IEEE Trans.
,
684 -
690
-
13)
-
R.H. Liang ,
Y.Y. Hsu
.
Fuzzy linear programming: an application to hydroelectricgeneration scheduling.
IEE Proc., Gener. Transm. Distrib.
,
6 ,
568 -
574
-
14)
-
A.J. Wood ,
B.F. Wollenberg
.
(1996)
Power generation, operation and control.
-
15)
-
Z. Ouyang ,
S.M. Shahidehpour
.
A multi-stage intelligent systemfor unit commitment.
IEEE Trans.
,
639 -
645
-
16)
-
S.J. Yakowitz
.
Dynamic programming applications in water resources.
Water Resour. Res.
,
673 -
696
-
17)
-
S.M. Amado ,
C.C. Ribeiro
.
Short-term generation scheduling of hydraulicmulti-reservoir multi-area interconnected systems.
IEEE Trans.
,
758 -
763
-
18)
-
H. Habibollazadeh ,
J.A. Bubenko
.
Application of decompositiontechniques to short-term operation planning of hydro-thermal power system.
IEEE Trans.
,
44 -
47
-
19)
-
Liang, R.H., Hsu, Y.Y.: `Hydroelectric generation scheduling using a quadraticprogramming based neural network', Proceedings of the International Power EngineeringConference, 1995, Singapore, p. 684–689.
-
20)
-
Y.Y. Hsu ,
C.R. Chen
.
Tuning of power system stabilisers using an artificialneural network.
IEEE Trans.
,
612 -
619
-
21)
-
N.I. Santoso ,
O.T. Tan
.
Neural-net based real-time control of capacitorsinstalled on distribution systems.
IEEE Trans.
,
266 -
272
-
22)
-
J.J. Hopfield ,
D.W. Tank
.
Neural computation of decisions in optimization problems.
Biol. Cybern.
,
141 -
152
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-gtd_19960350
Related content
content/journals/10.1049/ip-gtd_19960350
pub_keyword,iet_inspecKeyword,pub_concept
6
6