Scribd
Upload
8 views8 pages

Chapter Three

The document discusses optimization as a process of finding the best solution based on an objective function, highlighting the use of nature-inspired optimization algorithms like Particle Swarm Optimization (PSO). PSO mimics social behaviors to guide particles in a search space towards optimal solutions, though it faces challenges like local minima and parameter sensitivity. An example is provided to illustrate the application of PSO in finding the global minimum of a benchmark function.

Uploaded by

abbas aqeel
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views8 pages

Chapter Three

The document discusses optimization as a process of finding the best solution based on an objective function, highlighting the use of nature-inspired optimization algorithms like Particle Swarm Optimization (PSO). PSO mimics social behaviors to guide particles in a search space towards optimal solutions, though it faces challenges like local minima and parameter sensitivity. An example is provided to illustrate the application of PSO in finding the global minimum of a benchmark function.

Uploaded by

abbas aqeel
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Lecture Three

Nature-inspired Optimization Algorithms


1. What is the optimization?
Optimization is a process of finding the best solution. Solutions are labeled good or bad after
determining the objective function that states the relations between system parameters and
constraints. The objective function is often formulated based on application, and it can be in the
form of fabrication cost, process efficiency, and so on.
Recently, Computational Intelligence Optimization Algorithms have been extensively used to
solve complex optimization problems in various domains, including science, commerce, and
engineering.
The optimization algorithms are used to:
• solve a problem more quickly
• or to find an approximate solution when classical methods fail to find the solution,
especially with multimodal optimization problems.
Finding optimum solution for such problems using classical optimization techniques becomes
complicated as the size of the search space increases with the dimension of the optimization
problem (Kanzow et al. 2004). Therefore, nature-inspired optimization techniques are considered.
2. Particle Swarm Optimization (PSO)
Particle swarm optimization (PSO) is a population based heuristic optimization technique
developed by Eberhart et al. (1995). It mimics the social behavior of bird flock or fish schooling
during their movement (Eberhart et al. 1995). The principle of the PSO work is basic variant by
having the swarms (populations) of the particles (candidate solutions). The particles are moving
in the search space to find the optimal solution. The searches of the particles are guided by local
best position (Pbest) in the search space as well as the global best position (Gbest). PSO can solve
complex multimodal optimization problem.
However, PSO has some control parameters in which the selection of these parameters
significantly influences the final solution. Furthermore, trap in local minimum is very common
problem of PSO (Park et al. 2010).
Individual particles (1 and 2) are accelerated toward the location of the global best solution (Gbest)
and the location of their own personal best (Pbest) in the n-dimensional space.
Start

PSO Specification

Generate initial population (Z)

j>N Yes
Reach Maximum population?
j =j + 1 No

Calculate objective function

i>Titeration Yes
Reach Maximum Iteration?
No

Update the velocity of the populations

Update the position of the populations

i=i+1 j>N Yes


Reach Maximum population?
j =j + 1 No
Calculate objective function

Objective function evaluation

Output the optimal parameters

Start
Example 1: Find the global minimum for the following benchmark function using PSO algorithm:
𝑛

𝑓 (𝑥 ) = ∑ 𝑥𝑖2
𝑖=1

Where n is the dimension of the problem.


Number of swarm = 4
Number of iteration = 1
Cognitive coefficient C1 = 2
Social coefficient C2 = 2
Inertia weight W1 = 0.5
Dimension of problem (n) = 2
L1 = L2 = 0
U1 = U2 = 10.

solution:
Homework 1: Find the global minimum for the following benchmark function using PSO
algorithm:

You might also like