A Danger-Theory-Based Immune Network Optimization Algorithm

Algorithm 1

The description of opt-aiNet.

(1) Initialize. Randomly generate the initial network population;

(2) While (termination conditions are not meet) do

Begin

 (2.1) While (changes of the average fitness of the population compared with that of the last generation is greater than

 the specified value) do

 Begin

  (2.1.1) Compute the fitness of every individual in the population;

  (2.1.2) Clone the same number for every individual, and get clone groups;

  (2.1.3) Mutate the clone groups, and get mutated groups;

  (2.1.4) Compute the fitness of every clone in the mutated groups;

  (2.1.5) Select the clone with highest fitness in every mutated group, and form a new population;

  (2.1.6) Compute the average fitness of the population;

 End;

 (2.2) Compute the distance between any two individuals; if the distance is less than the threshold, retain one;

 (2.3) Randomly generate a certain number of antibodies;

End;