Hybrid Genetic Algorithm Applied to the Determination of the Optimal Operation of Hydrothermal Systems

The Brazilian Southeast Hydrothermal System is a large scale and complex system, with 36 GW of installed capacity system and composed of 35 hydro plants. The definition of a efficient policy to use the available resources minimizing the operation costs is an optimization problem. Traditional optimization techniques have difficulties to deal with problems of this dimension. A Hybrid Genetic Algorithm based on gradient calculus developed for Hydrothermal System Scheduling is described in this paper. The algorithm employs new genetic operators, gradient mutation and gradient directed mutation. This paper evaluates the performance of this algorithm in the determination of hydrothermal systems optimal operation. Experimental results show the potential of this new algorithm, not only because the gain obtained by using the new operators but also for providing a new tool for large scale hydrothermal systems scheduling. The algorithm can be applied not only to the southeast, but to any part of the Brazilian Hydrothermal System.

[1]  C.E. Zoumas,et al.  A genetic algorithm solution approach to the hydrothermal coordination problem , 2004, IEEE Transactions on Power Systems.

[2]  Mitsuo Gen,et al.  Genetic algorithms and engineering design , 1997 .

[3]  Hong-Chan Chang,et al.  Genetic aided scheduling of hydraulically coupled plants in hydro-thermal coordination , 1996 .

[4]  F. Glover,et al.  In Modern Heuristic Techniques for Combinatorial Problems , 1993 .

[5]  Takuji Nishimura,et al.  Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator , 1998, TOMC.

[6]  Jarmo T. Alander,et al.  An Indexed Bibliography of Genetic Algorithms , 1995 .

[7]  Secundino Soares,et al.  A large scale of an optimal deterministic hydrothermal scheduling algorithm , 1990 .

[8]  Vladimiro Miranda,et al.  Evolutionary computation in power systems , 1998 .

[9]  Kit Po Wong,et al.  Combined genetic algorithm/simulated annealing/fuzzy set approach to short-term generation scheduling with take-or-pay fuel contract , 1996 .

[10]  Zbigniew Michalewicz,et al.  Evolutionary algorithms for constrained engineering problems , 1996, Computers & Industrial Engineering.

[11]  P. Leite,et al.  Energetic Operation Planning Using Genetic Algorithms , 2001, IEEE Power Engineering Review.

[12]  Thomas Bäck,et al.  Evolutionary computation: comments on the history and current state , 1997, IEEE Trans. Evol. Comput..

[13]  Randy L. Haupt,et al.  Practical Genetic Algorithms , 1998 .

[14]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .