Bee algorithm
-
Upload
njoud-omar -
Category
Technology
-
view
2.685 -
download
1
description
Transcript of Bee algorithm
29/04/1434
1
Bee Algorithm
Direct Bee Colony Algorithm
29/04/1434
2
Njoud Maitah and Lila Bdour
Copyright ©
29/04/1434
3
The Goal
• We will present an optimization algorithm that inspired by decision-making process of honey bees .
29/04/1434
4
Bee Algorithm
Presented by : Njoud Maitah and Lila bdour
29/04/1434
5
Outline •Introduction
•Bee in nature
•Bee algorithm
•Example
•Applications
29/04/1434
6
• Honeybee search for the best nest site between many sites with taking care of both speed and accuracy .
• This analogues to finding the optimal solution (optimality) in an optimization process.
Introduction
29/04/1434
7
Bee in nature
• The group decision making process used by bees for searching out the best food resources among various solutions is a robust example of swarm-based decision method.
• This group decision-making process can be mimicked for finding out solutions of optimization problems.
29/04/1434
8
Bee in nature cont..
• Bee use a waggle dance to communicate
• What is the waggle dance ?!
It is a dance that performed by scout bees to inform other foraging bees about nectar site.
• What are the scout and foraging ?!
Scout bee : the navigator
Forging bee : the collector of food from
29/04/1434
9
Bee in nature cont..
• The waggle dance is showed in the following video .
29/04/1434
10
A moment of thinking ?? بـســـم هللا الـرحـمـــن الـرحـيــــم
خذي من الجبال بيوتا ومن " حل أن ات ك إلى الن وأوحى رب
ا يعرشون جر ومم مرات فاسلكي ( 68)الش ثم كلي من كل الث
ك ذلال يخرج من بطونها شراب مختلف ألوانه فيه سبل رب
رون اس إن في ذلك آلية لقوم يتفك ”( 69)شفاء للن
29/04/1434
11
Bee in nature >>
• Waggle dance is a communication method used by bees to inform other bees about food resources and location of nest site .
• Figure-eight running 8 .
• Number of runs represents the distance .
• The angle of run indicates the direction.
29/04/1434
12
Bee in nature >>
• Waggle dance in decision-making
• Waggle dance gives precise information about quality ,distance and direction of flower patch.
29/04/1434
13
Bee in nature >>
• Decision 1 : Quiescent bees evaluate the patch and decide to recruit or explore for other patches. “decision”
If the patch still good ,increase the number of foraging bees.
29/04/1434
14
Bee in nature >>
• Decision 2 : decide the number of bees recruited to the patch based on the quality.
29/04/1434
15
Bee in nature >>
• Decision 3 : Nest-site selection.
Two activity to reach to the decision :
• Consensus : agreement among the group of quiescent.
• Quorum : threshold value.
29/04/1434
16
Bee Algorithm (BA)
• The Bees Algorithm is an optimisation
algorithm inspired by the natural foraging
behaviour of honey bees to find the
optimal solution.
29/04/1434
17
Bee Algorithm (BA)
1. Initialise population with random solutions.
2. Evaluate fitness of the population.
3. While (stopping criterion not met)
//Forming new population.
4. Select sites for neighbourhood search.
5. Recruit bees for selected sites (more bees for best e sites) and evaluate fitnesses.
6. Select the fittest bee from each patch.
7. Assign remaining bees to search randomly
and evaluate their fitnesses.
8. End While.
29/04/1434
18
Evaluate the Fitness of the Population
Determine the Size of Neighbourhood
(Patch Size ngh)
Recruit Bees for Selected Sites (more Bees for the Best e Sites)
Select the Fittest Bee from Each Site
Assign the (n–m) Remaining Bees to Random Search
New Population of Scout Bees
Select m Sites for Neighbourhood Search
Nei
gh
bo
urh
oo
d S
earc
h
Flowchart of the Basic BA
Initialise a Population of n Scout Bees
29/04/1434
19
Simple Example: Function Optimisation
• Here are a simple example about how Bee algorithm works
• The example explains the use of bee algorithm to get the best value representing a mathematical function (functional optimal)
29/04/1434
20
Simple Example
• The following figure shows the mathematical function
29/04/1434
21
Simple Example
• 1- The first step is to initiate the population with any 10 scout bees with random search and evaluate the fitness. (n=10)
29/04/1434
22
Graph 1. Initialise a Population of (n=10) Scout Bees with random Search and evaluate the fitness.
x
y
*
*
*
*
*
* * * * *
Simple Example
29/04/1434
23
2- Population evaluation fitness:
• An array of 10 values is constructed and ordered in ascending way from the highest value of y to the lowest value of y depending on the previous mathematical function
29/04/1434
24
3- The best m site is chosen ( the best evaluation to m scout bee) from n
m=5, e=2, m-e=3
29/04/1434
25
Graph 2. Select best (m=5) Sites for Neighbourhood Search: (e=2) elite bees “▪” and (m-e=3) other selected bees“▫”
x
y
▪ ▫
▪
▫
▫
* * * * *
m e
29/04/1434
26
4- Select a neighborhood search site upon ngh size:
x
y
▪ ▫
▪
▫
▫
Graph 3. Determine the Size of Neighbourhood (Patch Size ngh)
29/04/1434
27
• 5- recruits bees to the selected sites and evaluate the fitness to the sites:
– Sending bees to e sites (rich sites) and m-e sites (poor sites).
– More bees will be sent to the e site.
• n2 = 4 (rich)
• n1 = 2 (poor)
29/04/1434
28
x
y
▪ ▫
▪
▫
▫
*
* *
*
Graph 4. Recruit Bees for Selected Sites (more Bees for the e=2 Elite Sites)
*
*
*
*
* *
* * *
*
* *
* * * *
29/04/1434
29
6- Select the best bee from each location (higher fitness) to form the new bees population.
Choosing the best bee from every m site as follow:
29/04/1434
30
30
x
y
▪ ▫
▪
▫
▫
*
* *
*
Graph 5. Select the Fittest Bee * from Each Site
*
* *
*
* *
* * *
*
Simple Example
29/04/1434
31
31
Simple Example
7- initializes a new population:
Taking the old values (5) and assigning random values (5) to the remaining values n-m
29/04/1434
32
32
x
y
*
Graph 6. Assign the (n–m) Remaining Bees to Random Search
*
* *
o *
o
o
o
o
m
e
Simple Example
29/04/1434
33
33
Simple Example
8- the loop counter will be reduced and the steps from two to seven will be repeated until reaching the stopping condition (ending the number of repetitions imax)
• At the end we reach the best solution as shown in the following figure
• This best value (best bees from m) will represent the optimum answer to the mathematical function
29/04/1434
34
x
y *
Graph 7. Find The Global Best point
*
* *
*
Simple Example
29/04/1434
35
BA- Applications
Function Optimisation
BA for TSP
Training NN classifiers like MLP, LVQ, RBF and
SNNs
Control Chart Pattern Recognitions
Wood Defect Classification
ECG Classification
Electronic Design
29/04/1434
36
Honeybee foraging algorithm for load balancing in cloud computing
• Servers are bees
• Web applications are flower patches
• And an advert board is used to simulate a waggle dance.
• Each server is either a forager or a scout
• The advert board is where servers, successfully fulfilling a request or may place adverts
29/04/1434
37
Flow chart of Honeybee Foraging Algorithm in load balancing for cloud computing