Case Study Of Genetic Algorithm

1840 Words 8 Pages
ABSTRACT: Genetic Algorithm is one of the global optimization schemes that have gained popularity as a means to attain water resources optimization. It is an optimization technique, based on the principle of natural selection, derived from the theory of evolution, is used for solving optimization problems. In the present study Genetic Algorithm (GA) has been used to develop a policy for optimizing the release of water for the purpose of irrigation. The study area is Sukhi Reservoir project in Gujarat, India. The months taken for the case study are June, July, August and September for three years from year 2004 to 2006. The fitness function used is to minimize the squared difference between the monthly reservoir release and irrigation demand …show more content…
St = Storage at the beginning of the period t.
Qt = Inflow during the period t.
Rt = Release for irrigation in period t.
Ao = Reservoir water surface area corresponding to the dead storage volume.
Et = Evaporation rate for the period t.

C. Reservoir storage capacity constraints
The reservoir storage in any period should not exceed its active storage capacity (Smax) of the reservoir.

St ≤ Smax t = 1, 2, 3, 4
St ≥ Smin t = 1, 2, 3, 4
Smax = Active storage capacity of reservoir in MCM. Smin = Dead Storage of the reservoir in MCM.


The important input variables in present GA model study are the monthly inflow in to the reservoir system and monthly irrigation demands for the month of June, July, August and September from year 2004 to 2006. After applying GA to the above model the following results are generated which gives the releases by GA and that we consider as optimum releases for the year 2004 to 2006.

Table 1: Demand, Actual Release and Obtained Release by GA for the year 2004 to 2006

Actual Release, MCM
Release by GA, MCM
…show more content…
The releases developed by Genetic algorithm satisfy completely the irrigation demands for all the four months i.e. June, July, August and September from the year 2004 to 2006 respectively. The amount of water saved in the months of June, July and August for year 2004 to 2006 is 318.25 MCM, 1319.6 MCM and 897.78 respectively. Thus, almost in nine out of twelve months the optimal releases obtained by genetic algorithm, are less than the actual releases, which leads to considerable amount in saving of

Related Documents