Configuring the Evolutionary Optimization (EVOL) Algorithm

The Evolutionary Optimization Algorithm (Evol) is an evolution strategy that mutates designs by adding a normally distributed random value to each design variable. The mutation strength (standard deviation of the normal distribution) is self-adaptive and changes during the optimization loop.

See Also
Evolutionary Optimization Algorithm (Evol)
  1. From the Optimize view in the Predict page, select Optimization Settings .
  2. From the Optimization Technique options, select Evolutionary Optimization Algorithm.
  3. Enter or select the following:
    OptionDescription
    Max Evaluations The maximum number of evaluations. The default is 100.
    Convergence Tolerance Control the termination criteria of the algorithm. When the absolute value of the difference in the ObjectiveAndPenalty parameter between two consecutive design points is below this parameter, the algorithm stops. The default is 0.01. Other possible values are 0 ⁢   <   ×   ≤   1.0 .
    Minimum Discrete Step The Evolutionary Optimization Algorithm varies input parameters such that the relative change in parameter value, expressed as a percentage of the total range of the variable, is always a multiple of the Minimum Discrete Step. The default value is 0.02 (2% of the total variable range). Other possible values are > 0 and < 1.0 (0 to 100% of the total variable range).
    Consecutive Variable Search Force the Evolutionary Optimization Algorithm to vary only one variable at a time when performing the search. The default value is false (all variables are varied at the same time). The other possible value is true (only one variable at a time is varied).
    Parallel Batch Size The batch size that the Evolutionary Optimization Algorithm submits for parallel execution. The actual number of parallel simulation process flow executions may be further limited by the number of available stations. If the Enable parallel execution option is not selected, the Parallel Batch Size value has no effect. The default value is 1.0 (no parallel execution). Other possible values are > 1 .
    Penalty Base The Evolutionary Optimization Algorithm evaluates the quality of a design point using the combined value of the objective function and penalty function. When calculating the penalty function of the design, the penalty base can be used for all designs that violate at least one constraint. This allows the technique to better differentiate feasible designs with a slightly higher objective function from infeasible designs with a slightly lower objective function.

    The total penalty function is calculated as follows:

    P e n a l t y = P e n a l t y ⁢ B a s e ⁢ +   P e n a l t y ⁢ M u l t i p l i e r × ⁢ S u m ⁢ ( V i o l a t i o n i × W i / S i ) ∧ P e n a l t y ⁢ E x p o n e n t

    where V i o l a t i o n i is the i ⁢ −   t h constraint violation value, W i is the corresponding weight factor, and S i is the corresponding scale factor. The penalty base is set to zero if no constraints are violated. The default value is 0.0.
    Penalty Multiplier Increase or decrease the effect of the total constraint violations on the measure of the design quality. The default value is 1000.0.
    Penalty Exponent Increase or decrease the nonlinearity of the effect of the total constraint violations on the penalty function value. The value type is integer. The default value is 2.
    Max Failed Runs Set the maximum number of failed subflow evaluations that can be tolerated by the optimization technique. If the number of failed runs exceeds this value, the optimization adapter will terminate execution. To disable this feature, set this option to any negative value (for example, –1). When this option is set to a negative value, the optimization will continue execution despite any number of failed subflow runs.
    Failed Run Penalty Value The value of the Penalty parameter that is used for all failed subflow runs. The default value is 1 ⁢   ×   ⁢ 10 30 .
    Failed Run Objective Value The value of the Objective parameter that is used for all failed subflow runs. The default value is 1 ⁢   ×   ⁢ 10 30 .
    Use fixed random seed If this option is selected, the random number generator used by the optimization algorithm is seeded using the Random seed value.

    If this option is not selected, the random number generator is seeded by using the clock time at the moment of execution.
    Random seed value All executions of the Optimization adapter will use the same sequence of random numbers and, therefore, will produce the same design points. This arrangement is useful for debugging the optimization process when it is necessary to reproduce the same sequence of design points.
  4. Click Ok to save your changes and to close the Optimization Editor.