Information Technology Reference
In-Depth Information
The improvement of the production cost for the model based on fuzzy approach
depends on the number of fuzzy rules taken in the resolution. However, increasing
this number leads to increase the horizon of solutions research which implies the
increase of the execution time. Furthermore, the optimization of the production cost
through genetic algorithm requires a proper selection of the GA parameters which
vary from one system to another. Thus, it is dif
cult to reduce for both the exe-
cution time and the production cost for the mentioned methods. As regards to
production cost, the proposed strategy based on Gradient-genetic algorithm method
is more promising; Indeed, it leads to a better combination of the production units
operating states leading to an optimal production cost While as regards to con-
vergence speed and execution time, the approach based on fuzzy logic has pre-
sented high performances. The founded results show the advantage of the proposed
strategies. In addition, the adopted approach was promising both in terms of con-
vergence to get the best optimal solutions to minimize the cost production and for
an ef
cient unit commitment scheduling for the different units production.
6 Conclusion
For the present chapter, we analyzed the resolution of the Unit Commitment
problem through the combination of genetic algorithm and gradient method in one
side and through a fuzzy logic approach in the other side. The simulations done
under the Matlab environment on an electrical network having
five production
units, have proved the effectiveness of these methods as well execution time as
production cost. Besides, throughout a comparative study between these two
strategies, results showed that in terms of execution time and convergence effec-
tiveness, the resolution through fuzzy logic approach is reliable despite the pro-
duction cost is relatively minimal but didn
t present the best production cost. Yet,
the Gradient-genetic algorithm method has presented high performances in opti-
mizing the production cost and capability of convergence to a global optimum. In
addition, it is noted that the adopted strategies lead to signi
'
cant reduction in the
number of decision variables and therefore a reduction of the optimization problem
size. In addition, they have the potential to reach a global solution of UC problem
since they have ensured an optimized unit commitment scheduling of the On/Off
unit states which proves their potential to solve problems related to high power
electric networks system.
Due to
flexibility in Gradient-Genetic Algorithm and Fuzzy logic several other
practical constraints can also be easily considered. For future work, the above
problem can be solved with arti
fl
cial intelligence technique like evolutionary pro-
gramming and arti
cial neural network. The Unit Commitment problem could be
solved if the system complexity increases either by increasing the number of units
or adding other constraints.
Search WWH ::
Custom Search