swarm intelligance (1)

20
Company LOGO Scientific Research Group in Egypt (SRGE) Swarm Intelligence (I) Particle swarm optimization Dr. Ahmed Fouad Ali Suez Canal University, Dept. of Computer Science, Faculty of Computers and informatics Member of the Scientific Research Group in Egypt

Upload: ahmed-fouad

Post on 01-Nov-2014

883 views

Category:

Technology


0 download

DESCRIPTION

 

TRANSCRIPT

Page 1: Swarm intelligance (1)

Company

LOGO

Scientific Research Group in Egypt (SRGE)

Swarm Intelligence (I)Particle swarm optimization

Dr. Ahmed Fouad AliSuez Canal University,

Dept. of Computer Science, Faculty of Computers and informatics

Member of the Scientific Research Group in Egypt

Page 2: Swarm intelligance (1)

Company

LOGO Scientific Research Group in Egyptwww.egyptscience.net

Page 3: Swarm intelligance (1)

Company

LOGO Meta-heuristics techniques

Page 4: Swarm intelligance (1)

Company

LOGO Outline1. Swarm intelligence (Main idea)1. Swarm intelligence (Main idea)

2. History of Particle swarm optimization 2. History of Particle swarm optimization

3. Particle swarm optimization (PSO)3. Particle swarm optimization (PSO)

4. PSO Algorithm 4. PSO Algorithm

5. Advantage / disadvantage5. Advantage / disadvantage

6. Comparison with Genetic algorithm6. Comparison with Genetic algorithm

7. References 7. References

Page 5: Swarm intelligance (1)

Company

LOGO Swarm intelligence (Main Idea)

• Suppose you and a group of friends are on a treasure finding mission. Each one in the group has a metal detector and can communicate the signal and current position to the n nearest neighbors.

• Each person therefore knows whether one of his neighbors is nearer to the treasure than him. If this is the case, you can move closer to that neighbor. In doing so, your chances are improved to find the treasure. Also, the treasure may be found more quickly than if you were on your own.

Page 6: Swarm intelligance (1)

Company

LOGO Swarm intelligence (Main Idea)

• A swarm can be defined as a structured collection of interacting organisms (or agents).

• Within the computational study of swarm intelligence, individual organisms have included ants, bees, wasps, termites, fish (in schools) and birds (in flocks).

Page 7: Swarm intelligance (1)

Company

LOGO Swarm intelligence (Main Idea)

• The global behavior of a swarm of social organisms therefore emerges in a nonlinear manner from the behavior of the individuals in that swarm

• The interaction among individuals plays a vital role in shaping the swarm's behavior.

• Interaction among individuals aids in refining experiential knowledge about the environment, and enhances the progress of the swarm toward optimality.

Page 8: Swarm intelligance (1)

Company

LOGOHistory of particle swarm optimization

•Proposed by James Kennedy &Russell Eberhart in 1995

• Inspired by simulation social behavior Related to bird

flocking, fish schooling and swarming

theory- steer toward the center- match neighbors’ velocity- avoid collisions

• Combines self-experience with social experience

• Population-based optimization

Page 9: Swarm intelligance (1)

Company

LOGO Particle swarm optimization (concepts)

• Set of agents (particles) that

constitute a swarm moving around

in the search space looking for the

best solution

• Each particle in search space adjusts

its “flying” according to its own

flying experience as well as the flying

experience of other particles

Page 10: Swarm intelligance (1)

Company

LOGO Particle swarm optimization (concepts)

• Movement towards a promising

area

to get the global optimum

• Each particle keeps track:

• Its best solution, personal best,

pbest

• The best value of any particle,

global best, gbest

Page 11: Swarm intelligance (1)

Company

LOGO Particle swarm optimization (concepts)

• Each particle modifies its

position according to:

• its current position

• its current velocity

• the distance between its

current position and pbest

• the distance between its

current position and gbest

Page 12: Swarm intelligance (1)

Company

LOGO Particle swarm optimization (concepts)

• Swarm: a set of particles (S)• Particle: a potential solution

• Position, Velocity:

• Each particle maintains• Individual best position (PBest)

• Swarm maintains its global best (GBest)

Page 13: Swarm intelligance (1)

Company

LOGO Particle swarm optimization Algorithm

P = Particle_Initialization();

For i=1 to it_max For each particle p in P do fp = f(p); If fp is better than f(pBest)             pBest = p; end end gBest = best p in P;

For each particle p in P do v = v + c1*rand*(pBest – p) + c2*rand*(gBest – p); p = p + v; endend

Page 14: Swarm intelligance (1)

Company

LOGO Particle swarm optimization Algorithm

vi(t+1) = vi (t)+ c1*rand*(pBest(t) – p(t)) + c2*rand*(gBest(t) – p(t));

Social influence

Personal influencesInertia

Particle’s velocity

Page 15: Swarm intelligance (1)

Company

LOGO PSO Algorithm (parameter setting)

The right way

This way

Or this way

• Number of particles (10—50) are reported as usually sufficient.

• C1 (importance of personal best)

• C2 (importance of neighborhood best)

• Usually C1+C2 = 4.

• Vmax – too low: too slow too high: too unstable.

Page 16: Swarm intelligance (1)

Company

LOGO Advantage / disadvantage

Advantage Disadvantage

Simple implementation

Slow convergence in refined search stage

Few parameters to adjust

Weak local search ability

Efficient in global search

Page 17: Swarm intelligance (1)

Company

LOGOComparison with genetic algorithm (GA)

• Commonalities• PSO and GA are both population based

stochastic optimization

• Both algorithms start with a group of a randomly generated population,

• Both have fitness values to evaluate the population.

• Both update the population and search for the optimium with random techniques.

• Both systems do not guarantee success.

Page 18: Swarm intelligance (1)

Company

LOGOComparison with genetic algorithm (GA)

• Differences

• PSO does not have genetic operators like crossover and mutation. Particles update themselves with the internal velocity.

• Particles do not die.

• The information sharing mechanism in PSO is significantly different

• There is no selection in PSO

Page 19: Swarm intelligance (1)

Company

LOGO References

• Computational Intelligence An IntroductionAndries P. Engelbrecht, University of Pretoria South Africa

• Some slides adapted from a presentation“The Particle Swarm Optimization Algorithm” By Andry Pinto, Hugo Alves, Inês Domingues, Luís RochaSusana Cruz.

Particle Swarm Optimizationhttp://www.particleswarm.info/http://www.swarmintelligence.org

Page 20: Swarm intelligance (1)

Company

LOGO

Thank youThank you

http://www.egyptscience.net

[email protected]