22
Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Embed Size (px)

Citation preview

Page 1: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Faegheh JavadiElham Seifossadat

Fall 2010

Artificial Bee Colony Algorithm

Page 2: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

ContentsIntelligent Swarm-Based

Optimisation Algorithms (SOAs)Bees in NatureArtificial Bee Colony AlgorithmConclusionReferences

2

Page 3: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Intelligent Swarm-Based Optimisation Algorithms (SOAs)Definition: Swarm-based optimisation

algorithms (SOAs) mimic nature’s methods to drive a search towards the optimal solution.

The difference between SOAs and direct search algorithms is that SOAs use a population of solution for every iteration.

Examples: bee colony, ant colony, particle swarm optimization, artificial immune system,…

3

Page 4: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Swarm IntelligentSwarm Intelligent has two fundamental concepts:

1- self organizing: Positive feedback Negative feedback Fluctuations

Multiple interactions

2- division of labour: Simultaneous task performance by cooperating

specialized individuals Enables the swarm to respond to changed

conditions in the search space.

4

Page 5: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Bees in NatureFood Sources:

Proximity to the nest Richness Ease of extracting

Employed Bees: Associated with a particular food source Carry and share information about it

Unemployed Bees: Looking for a food source to exploit Scouts Onlookers

5

Page 6: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Bees in Nature

6

A colony of honey bees can extend itself over long distances in multiple directions.

10 Km

A C

B

Hive

Page 7: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Bees in Nature

7

Scout bees search for food randomly from one flower patch to another.

A C

B

Hive

Page 8: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Bees in Nature

8

The exchange of information among bees is the most important occurrence in the formation of the collective knowledge.

Communication among bees related to the quality of food sources occurs in the dancing area.

The related dance is called waggle dance.The bees evaluate the different patches according to:

The quality of the foodThe amount of energy usage

Page 9: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Bees in Nature

9

Bees communicate through a waggle dance which contains information about:

1. The direction of flower patches (Angle between the sun and patch)

2. The distance from the hive (Duration of the dance)

3. The quality rating (Frequency of the dance)

Page 10: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

An Example:

10

S – Scout R- OnlookerUF-Uncommitted FollowerEF1-Sharing informationEF2- Continue work alone

Page 11: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Artificial Bee Colony(ABC) Algorithm

11

Proposed by Karaboga – 2005ABC is developed based on

inspecting the behaviors of real bees on finding nectar and sharing the information of food sources to the bees in the hive.

Solving multidimensional and multimodal optimisation problems.

Page 12: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Artificial Bee Colony(ABC)

12

Contains three groups of bees:o The Employed Bee(50%):

It stays on a food source and provides the neighborhood of the source in its memory.

o The Onlooker Bee (50%):It gets the information of food sources from the employed bees in the hive and select one of the food source to gathers the nectar.

o The Scout (5-10%):It is responsible for finding new food, the new nectar, sources.

Page 13: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Artificial Bee Colony(ABC)

13

The employed bee whose food source has been exhausted by the bees, becomes a scout.

Scouts are the colony’s explorers.The number of employed bees = the

number of food sourceFood source position = possible solution

to the problemThe amount of nectar of a food

source=quality of the solution

Page 14: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Artificial Bee Colony(ABC)

14

The main steps of the algorithm are given below:

Page 15: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Movement of the Onlookers

15

Probability of Selecting a nectar source:

(1)

Pi : The probability of selecting the ith employed bee

S : The number of employed beesθi : The position of the ith employed bee

: The fitness value

S

kk

ii

F

FP

1

iF

Page 16: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Movement of the Onlookers (2)

16

Calculation of the new position:(2)

: The position of the onlooker bee.t : The iteration numberk : The randomly chosen employed bee.j : The dimension of the solution : A series of random variable in the range

.

txtxtxtx kjijijij 1

1 1,-

ix

Page 17: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Movement of the Scouts

17

The movement of the scout bees follows equation (3).

(3)

r : A random number

minmaxmin

jjjij xxrx x

Page 18: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

18

Artificial Bee Colony (ABC) (3)

The Employed Bee The Onlooker Bee The Scout

S

kk

ii

F

FP

1

Record the best solution found so

far

ttttx kjijijij 1

minmaxmin jjjij r

Page 19: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Different selection process in ABC

19

1. A global probabilistic selection process used by the onlooker bees.

2. A local probabilistic selection process carried out in a region by the employed bees and the onlookers.

3. A local selection called greedy selection process carried out by onlooker and employed bees.

4. A random selection process carried out by scouts

Page 20: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Conclusion

20

Population-based algorithm.Robust search process: exploration

and exploitation processes must be carried out together.

Solving multi-dimensional and multimodal numeric problems.

Page 21: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

References

21

D. Karaboga, B. Basturk, “on the performance of artificial bee colony (ABC) algorithm”, journal of Applied Soft Computing 8 (2008) 687–697.

D. Karaboga, “An idea based on honey bee swarm for numerical optimization”, Technical Report, October 2005.

D. Karaboga, B. Basturk, “A powerful and efficient algorithm for numerical function optimization: Artificial bee Colony (ABC) algorithm”, J Glob Optim (2007) 39:459-471.

D. Karaboga, B. Akay, “Artificial Bee Colony (ABC), Harmony Search and Bees Algorithms on Numerical Optimization”, Erciyes University, The Dept. of Computer Engineering, 38039, Melikgazi, Kayseri, Turkiye

Page 22: Faegheh Javadi Elham Seifossadat Fall 2010 Artificial Bee Colony Algorithm

Thanks For Your Attention

Questions/Comments

22