Particle Swarm Optimization - PSO
Download as PPT, PDF10 likes2,920 views
The document discusses Particle Swarm Optimization (PSO), a computational method inspired by natural social behaviors of animals exploring solutions in a search space. It outlines the PSO algorithm, parameters, advantages, and limitations compared to Genetic Algorithms (GA). Key features of PSO include self and social experiences of particles, dynamic adjustments based on these experiences, and the absence of genetic operators like crossover or mutation.
![PSO Algorithm
[x*] = PSO()
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;
end
end](https://image.slidesharecdn.com/psomohamedtalaat-180325192418/85/Particle-Swarm-Optimization-PSO-11-320.jpg)
Particle Swarm Optimization - PSO
- 2. Agenda • What is PSO? • Basic Idea of PSO. • PSO Algorithm. • PSO Parameters. • GA vs PSO • Demo • Advantages of PSO. • Limitations of PSO. 2
- 3. 3 What is PSO? • Inspired from the nature social behavior and dynamic movements with communications of insects, birds and fish. – Steer toward the center – Match neighbors’ velocity – Avoid collisions • Proposed by James Kennedy & Russell Eberhart (1995)
- 4. Neural Networks NN 1 4 Basic Idea Of PSO
- 5. 5 Basic Idea Of PSO • Uses a number 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. Combines self-experiences with social experiences.
- 6. 6 Basic Idea Of PSO • Collection of flying particles (swarm) - Changing solutions • Search area - Possible solutions • 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
- 7. 7 Basic Idea Of PSO • Each particle adjusts its travelling speed dynamically corresponding to the flying experiences of itself and its colleagues. • 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
- 8. PSO Algorithm – Mathematical Model
- 9. PSO Algorithm 1. Create a ‘population’ of agents (particles) uniformly distributed over X 2. Evaluate each particle’s position according to the objective function. 3. If a particle’s current position is better than its previous best position, update it. 4. Determine the best particle (according to the particle’s previous best positions).
- 10. PSO Algorithm 5. Update particles’ velocities: 6. Move particles to their new positions: 7. Go to step 2 until stopping criteria are satisfied
- 11. PSO Algorithm [x*] = PSO() 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; end end
- 12. PSO Parameters • Number of Particles: usually between 10 and 50 • C1: is the importance of personal best value • C2: is the importance of neighborhood best value • Usually C1 + C2 = 4 • If velocity is too low → algorithm too slow • If velocity is too high → algorithm too unstable
- 13. GA vs PSO • 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 optimum with random techniques. • Both systems do not guarantee success. • PSO does not have genetic operators like crossover and mutation. Particles update themselves with the internal velocity.
- 14. GA vs PSO • In GAs, chromosomes share information with each other. So the whole population moves like a one group towards an optimal area. • In PSO, only gBest (or lBest) gives out the information to others. It is a one -way information sharing mechanism. • In GAs, the evolution only looks for the best solution. • In PSO, all the particles tend to converge to the best solution quickly.
- 15. Demo 15
- 16. 16 Advantage/Disadvantages s of PSO • Advantages: • Simple implementation. • Easily parallelized for concurrent processing. • Derivative free. • Very few algorithm parameters. • Very efficient global search algorithm. • Disadvantages: • Memory • Slow convergence.
- 17. Thanks 17