The search of an optimal solution to the unit commitment problem in an electric power system is vital, since it could be translated into major annual savings in generation costs. This article shows the methodology followed to solve the unit commitment problem implementing a computer program using genetic algorithms. The algorithm approach does not only include the basic genetic operators (i.e., crossover and mutation), but also implements five particular genetic operators that proved to be very useful in order to obtain faster and more accurate solutions lowering the possibility of reaching local optimums. Results obtained showed the importance of using those particular operators, and some relevant differences between methodologies employed. Among the concluding remarks are the need to generate repair algorithms and penalizing functions capable of improving the convergence mechanism, which were also included in the methodology described in this paper.
[1]
Ross Baldick,et al.
The generalized unit commitment problem
,
1995
.
[2]
Hong-Tzer Yang,et al.
A parallel genetic algorithm approach to solving the unit commitment problem: implementation on the transputer networks
,
1997
.
[3]
Gerald B. Sheblé,et al.
Genetic-based unit commitment algorithm
,
1996
.
[4]
Anastasios G. Bakirtzis,et al.
A genetic algorithm solution to the unit commitment problem
,
1996
.
[5]
Ching-Lien Huang,et al.
Application of genetic-based neural networks to thermal unit commitment
,
1997
.