![](bg6.png)
5 DISCUSSION
5.1 Very Large Scale Cases
The interest of a feasible initial population has been
shown in previous results. In this paper, this feasible
population is computed by an ant algorithm. The ant
colony algorithm can be seen as a stochastic
dynamic programming algorithm. The size of the
state space is 2
K
. This is the main limiting point of
the proposed method. Thus, for high values of K, the
computation times of the ant colony algorithm grows
very quickly. Thus, one of the main points is the
application of ant colony to very large scale cases.
5.2 Global Optimization and
Cooperation
Ant colony algorithm and genetic algorithm are two
global optimization techniques and it may be
astonishing to use them as a cooperative method.
The goal of this hybridising was to couple the
feasibility properties of ant colony algorithm and the
intensive exploration of genetic algorithm. The
cooperation is a sequential procedure, and a more
alternated procedure could be profitable. For
instance, results of genetic algorithms can be used to
define the attractiveness parameters in a new
iteration of ant colony algorithms. Furthermore, it
will be interesting to couple the method with a local
search.
6 CONCLUSIONS
In this paper, an optimization strategy has been
defined and applied to solve the Unit Commitment.
The main idea is to use an ant algorithm as a feasible
solutions generator. These feasible solutions are
brought together in an initial population for a genetic
algorithm. To guarantee the feasibility of the final
solution, a special criterion is computed from the
results of the ant algorithm. To increase the
efficiency of the classical genetic algorithm, a
knowledge-based operator is defined (selective
mutation). Finally, the proposed method leads to
high quality solution, with guarantees of feasibility
and with low computation times. The main limiting
point appears to be the computation times of ant
colony algorithm for very large scale cases.
However, the use of feasible solutions in the initial
population of a genetic algorithm is an interesting
way to decrease the number of iterations required to
find near optimal solutions. Forthcoming works deal
with the use of such algorithm for predictive control
of non linear hybrid systems.
REFERENCES
Chen C.-L, Wang S.-C., 1993. Branch and Bound
scheduling for thermal generating units. In: IEEE
Transactions on Energy Conversion, 8(2), 184-189.
Dorigo M., Maniezzo V., Colorni A., 1996. The Ant
System: Optimization by a Colony of Cooperating
Agents. In: IEEE Transactions on Systems, Man and
Cybernetics-Part B, 26(1), 1-13.
Dorigo M., Gambardella, L. M., 1997. Ant Colony
System : a Cooperative Learning Approach to the
Traveling Salesman Problem. In: IEEE Transactions
on Evolutionary Computation, 1, 53-66.
Ouyang Z., Shahidehpour S. M., 1991. An intelligent
dynamic programming for unit commitment
application. In: IEEE Transactions on Power Systems,
6(3), 1203-1209.
Rajan C. C. A, Mohan M. R., 2004. An evolutionary
programming-based tabu search method for solving
the unit commitment problem. In: IEEE Transactions
on Power Systems, 19(1), 577-585.
Sandou, G., Font, S., Tebbani, S., Hiret, A., Mondon, C.,
2007. Enhanced genetic algorithm with guarantee of
feasibility for the Unit Commitment problem. In:
Proceeding of the 8
th
International Conference on
Artificial Evolution, Tours, France.
Sen S., Kothari D. P., 1998. Optimal Thermal Generating
Unit Commitment: a Review. In: Electrical Power &
Energy Systems, 20(7), 443-451.
Senjyu T., Shimabukuro, K., Uezato K. and Funabashi T.,
2004. A fast technique for Unit Commitment problem
by extended priority list. In: IEEE Transactions on
Power Systems, 19(4), 2119-2120.
Stützle T., Hoos, H. H., 2000. MAX-MIN Ant System, In:
Future Generation Computer Systems, 16, 889-914.
Swarup K., Yamashiro, S., 2002. Unit commitment
solution methodology using genetic algorithm. In:
IEEE Transactions on Power Systems, 17(1), 87-91.
Yin Wa Wong S., 1998. An Enhanced Simulated
Annealing Approach to Unit Commitment. In:
Electrical Power & Energy Systems, 20(5), 359-368.
Zhai Q; Guan X., 2002. Unit Commitment with identical
units: successive subproblems solving method based
on Lagrangian relaxation. In: IEEE Transactions on
Power Systems, 17(4), 1250-1257.
ICINCO 2008 - International Conference on Informatics in Control, Automation and Robotics
168