33
| Date post: | 16-Jan-2016 |
| Category: |
Documents |
| Upload: | whitney-watts |
| View: | 213 times |
| Download: | 0 times |
What is Swarm Intelligence (SI)? “The emergent collective intelligence of groups of simple agents.”
Swarm intelligence (SI) as defined by Bonabeau, Dorigo and Theraulaz is “any attempt to design algorithms or distributed problem-solving devices inspired by the collective behavior of social insect colonies and other animal societies”
Swarms build colonies and work in a coordinated manner — yet no single member of the swarm is in control.
Flocks of birds coordinate to move without collision.
Ants manage to find food sources quickly and efficiently.
Termites build giant structures.Schools of fish fend off predators and
move as one body
ExamplesExamples
The computer revolution changed human societies:
Communication & Transportation Industrial production Administration, writing and
bookkeeping Technological advances Entertainment
However, some problems cannot be tackled with traditional hardware and software!
Why do we need new Why do we need new computing techniques?computing techniques?
Computing tasks have to be :-
Well-definedFairly predictableComputable in reasonable time
with serial computers.
Drawbacks of traditional Drawbacks of traditional techniquestechniques
WorkingWorking
Why Social Colony is a Why Social Colony is a source of inspiration?source of inspiration?
•Flexible: the colony can respond to internal perturbations and external challenges• Robust: tasks are completed even if some individuals fail• Decentralized: there is no central control(ler) in the colony• Self-organized: paths to solutions are emergent rather than predefined
AntsAntsWhy are ants interesting?
◦ants solve complex tasks by simple local means◦ant productivity is better than the sum of their
single activities◦ants are ‘grand masters’ in search and
exploitation
Which mechanisms are important?◦cooperation and division of labour◦adaptive task allocation◦work stimulation by cultivation◦pheromones
Ant Colony Optimization (ACO)
Is inspired by the behavior of ant colonies .
Ability of Optimization in finding shortest path.
Ants leave a chemical pheromone trail.Pheromone trails enables them to find
shortest paths between their nest and food sources
Ants find the shorter path in an experimental setup
A bridge leads from a nest to a foraging area, (a) 4 minutes after bridge placement, (b) 8 minutes after bridge placement
Ant ForagingAnt ForagingCooperative search by pheromone trails
1. The natural behavior of these ants and be programmed into an ant algorithm, which we can use to find the shortest path within graphs.
2. As ants move they leave behind a chemical substance called pheromone, which other ants can smell and identify that an ant has been there before.
ACO algorithm
Main steps of the ACO algorithm are given below:
Pheromone trail initializationSolution construction using pheromone trailEach ant constructs a complete solution to
the problem according to a probabilisticState transition rule. The state transition rule
depends mainly on the state of the pheromone .
Pheromone trail update.
1 : repeat2 : if antCount < maxAnts then3 : create a new ant4 : set initial state5 : end if6 : for all ants do7 : determine all feasible neighbor states {considering the ant's visited states}8 : if solution found V no feasible neighbor state then9 : kill ant10: if we use delayed pheromone update then11: evaluate solution12: deposit pheromone on all used edges13: end if14: else
algorithm
15: stochastically select a feasible neighbor state
{directed by the ants memory, the pheromone concentration on the
edges and local heuristics}16: if we use step-by-step pheromone update then17: deposit pheromone on the used edge18: end if19: end if20: end for21: evaporate pheromone until termination criterion
satisfied {e.g., found a satisfying solution}
Applications of Ant Colony Applications of Ant Colony OptimizationOptimizationTraffic on telecommunications systems, the internet, roads, rail, and sea would all benefit from the reduction in congestion that efficient routing algorithms could provide.
Modern airlines are actually putting the ant colony research to work, with impressive payback
Telecommunication System Airlines
Particle Swarm Optimization Particle Swarm Optimization (PSO)(PSO)
Idea: Used to optimize continuous functions
Function is evaluated at each time step for the agent’s current position
Each agent “remembers” personal best value of the function (pbest)
Globally best personal value is known (gbest)Both points are attracting the agent
Formula for one agent in one dimension:vx = vx + 2.rand().(pbestx - presentx)+2.rand().(gbestx - presentx) ----(a)Where 0 ≤ rand() ≤ 1presentx= presentx+vx ----(b)
The pseudo code of the procedure is as follows
For each particle Initialize particleENDDo For each particle Calculate fitness value If the fitness value is better than the best fitness value (pBest) in history set current value as the new pBest End Choose the particle with the best fitness value of all the particles as the gBest For each particle Calculate particle velocity according equation (a) Update particle position according equation (b) End While maximum iterations or minimum error criteria is not attained
Solving some of the NP-Solving some of the NP-Hard Problems using Hard Problems using Swarm IntelligenceSwarm Intelligence
Hard ProblemsHard Problems
Well-defined, but computational hard problems•NP hard problems (Travelling Salesman Problem)•Action-response planning (Chess playing)
Hard ProblemsHard Problems
Fuzzy problems•intelligent human-machine interaction•natural language understanding
Hard ProblemsHard Problems
Hardly predictable and dynamic problems•real-world autonomous robots•management and business planning
Complex NP complete problems.
Vehicle routing.Network maintenance.The traveling salesperson.Computing the shortest route between two points.
ProblemsProblems
1. Visit cities in order to make sales.
2. Save on travel costs.3. Visit each city once
(Hamiltonian circuit).
Travelling Salesman Travelling Salesman ProblemProblem
If there are N cities, then the number of different paths among them is 1.2……(N-1).
Time to examine single path = N.
Total time to perform the search = (N-1)!
For 10 cities, time reqd. = 10! = 3,268,800.
Combinatorial Explosion Combinatorial Explosion in Travelling Salesman in Travelling Salesman
ProblemProblem
Use of agents for TSP problem.They sense and dispense pheromone.Memory to back step through the graph. Each agent starts at a random starting
city.Once agent finishes a tour, it
determines the size of the tour.Then pheromone is added to the tour,
the shorter the tour, the higher the pheromone level.
Solution of TSP by Swarm Solution of TSP by Swarm IntelligenceIntelligence
It is a 3-step process.1.Identification of analogies: in swarm
biology and IT systems.2.Understanding: computer modeling of
realistic swarm biology.3.Engineering: model simplification and
tuning for IT applications.
How do we design Swarm How do we design Swarm Intelligence Systems?Intelligence Systems?
Bad News , Good NewsBad News , Good NewsBad news• Difficult to predict collective behaviour from individual rules.• Interrogate one of the participants, it won’t tell you anythingabout the function of the group.• Small changes in rules lead to different group-level behaviour.• Individual behaviour looks like noise: how do you detectthreats? Good news• Possible to efficiently control organization ormanipulate groups using simple rules.• Possible to predict group-level outcome using bottomsimulation.
Applications of SI
Swarm/crowd simulation programmingComputer Networks: Adaptive RoutingRobotics/Artificial IntelligenceProcess optimization /Staff Scheduling
Scientists are realizing SI’s potential.
The use of ant algorithms within computing systems has helped to solidify swarm intelligence’s place in the computing world.
Already researchers are observing
other social animals, such as bees and schools of fish in order to utilize it in future applications and algorithms.
ConclusionConclusion
Any Questions?Any Questions?
