Information Technology Reference
In-Depth Information
Trial
Flatten
Table
If
Cr
Random
,
Population
i, 2, j
,
1
i, j
,
i, NP
,
j, Dim
&
Noisy
,1
442.422,
560.034
,
194.845,
354.393
,
127.976, 99.3825
,
718.466, 244.138
,
236.027,
128.204
,
335.943, 355.91
,
317.752,
402.607
,
119.503, 163.852
,
507.525, 502.251
,
160.401,
149.99
Fig. 7.19.
Trial Vector
BoundaryChecking
Flatten
MapIndexed
CheckInterval
1,
2
&,
1
,1
&
Trial
442.422,
2.47524
,
194.845,
354.393
,
127.976, 99.3825
,
300.954, 244.138
,
236.027,
128.204
,
335.943, 355.91
,
317.752,
402.607
,
119.503, 163.852
,
507.525, 502.251
,
160.401,
149.99
Fig. 7.20.
Boundary Checking
In[44]:=
IndividualsCostValue
CostFunction
1
,
1
&
BoundaryChecking
364.224,
442.422,
2.47524
,
200.331,
194.845,
354.393
,
70.135,
127.976, 99.3825
,
279.978,
300.954, 244.138
,
41.6243,
236.027,
128.204
,
161.461,
335.943, 355.91
,
106.047,
317.752,
402.607
,
157.266,
119.503, 163.852
,
464.407,
507.525, 502.251
,
62.8734,
160.401,
149.99
Out[44]=
Fig. 7.21.
Individual Cost Value
NewPopulation
MapThread
If
1
1
2
1
,
1,
2
&,
Population,
IndividualsCostValue
364.224,
442.422,
2.47524
,
200.331,
194.845,
354.393
,
70.135,
127.976, 99.3825
,
208.07,
214.324, 244.138
,
41.6243,
236.027,
128.204
,
161.461,
335.943, 355.91
,
106.047,
317.752,
402.607
,
157.266,
119.503, 163.852
,
464.407,
507.525, 502.251
,
62.8734,
160.401,
149.99
Fig. 7.22.
Next Population Selection
avoid setting of local or global variables for the trial vector list, the
Table
command
is used instead of
Fo r
.
Trial
vectors are returned in the list given in Fig 7.19, which is
created automatically.
All the
Trial
vectors are created at once. Before the fitness is calculated, the popula-
tion of the trial individuals are checked for boundary conditions. If some parameter is
out of the allowed boundary, then it is
randomly
returned back. The function is given in
Fig 7.20.
Now, there exists a repaired set of trial vectors, which is evaluated by the cost func-
tion. It is done by the function
CostFunction
applied by
/
@onthe
BoundaryChecking
set. Note that the body of each individual in Fig 7.21 is enlarged by the function
Indi-
vidualsCostValue
.
The better individual of both
parent
and
child
is selected into the new population by
means of the
MapThread
function.
Search WWH ::
Custom Search