A New Hybrid Model Based on Data Preprocessing and an Intelligent Optimization Algorithm for Electrical Power System Forecasting

Algorithm 2

Pseudocode of MFA.

Input:

 The initial random value of weight and threshold of BP artificial neural network.

Output:

 The global optimal extreme point and the best individual value

Parameters:

 —the number of population of the particle swarm.

 —the cognitive and social weight of PSO algorithm. In usual, .

 —the maximum iteration.

(1) Initialize the population ;

(2) update the light intensity after evaluating new solution;

(3) ;

(4) While    do

(5)  for : all fireflies do

(6)   for : all fireflies do

(7)    if   then

(8)     Move firefly towards using uniform distribution;

(9)    end if

(10)   end for

(11)   Evaluate new solutions and update light intensity;

    ;  

(12) end for

(13) Rank fireflies and find the best individual;

(14) end while