Artificial Bee Colony Algorithm Presented By: Asma Sanam Larik.
Bee Colony Algorithm
description
Transcript of Bee Colony Algorithm
History and Biological Analogy
� Bee colony components � Queen, Drones, Workers and Broods
� Bee Communication � The Waggle Dance - Video (4:59)
� Bee Behaviour 1. Foraging behaviour
a. Nest site searching b. Food source searching
2. Marriage behaviour
Computational Implementation
� Foraging behaviour � Nest site searching � Food source
searching � Marriage behaviour
Publications [*]
Foraging behaviour Marriage behaviour
Bee Colony Optimization
� Initialize Repeat Choose partial solutions Expand partial solutions Return to hive Recruit nestmates Until (Stopping criterion)
Bees Algorithm
� Initialize with random sites Repeat Recruit bees for selected sites Select fittest bees from each patch Assign remaining to search randomly Until (Stopping Criterion)
Artificial Bee Colony
� Initial Scout Bees Phase Repeat Employed Bees Phase Onlooker Bees Phase Scout Bees Phase Until (Maximum Cycle/CPU time)
Comparison of the ABC and the BA for PID Controller Tuning [6]
� Complicated fitness function. � minimum overshoot, rise time, steady state
error and settling time in the step response. � Although ABC has less control
parameters, exhibits better tuning performance and convergence time.
Ant Colony Optimization � Ants use pheromones for back tracking
route to food source. Bees instead use Path Integration. Bees are able to compute their present location from past trajectory continuously.
� Bees algorithm is more efficient as it is more scalable and requires lesser number of steps.
� However, Bees algorithm is less adaptive than ACO.
Task Scheduling and ANN training
� Makespace optimization and Job scheduling priorities and resource allocation.
� ANN coefficient training optimization applications
Advantages & Limitations � When compared to GA’s, DE, and alternative
PSO’s for various general assignment problems and scheduling problems [1][3]
� Best for multivariable multimodal function optimization.
� Control parameter optimization. � Spread of population into roles. � Defining size of neighbourhood. � Probabilistic selection vs deterministic.
Other Applications
� Statistical Quality Control � Wood Defect Classifier � Mechanical Design � Electronic Design � Clustering � Job Scheduling � Robotics � Travelling Salesman Problem
References 1. Artificial Bee Colony Algorithm and Its Application to Generalized Assignment
Problem (2007). - Adil Baykasoùlu, Lale Özbakır and Pınar Tapkan, University of Gaziantep, Department of Industrial Engineering.
2. Bee Algorithms, Maw-Sheng Chern. http://chern.ie.nthu.edu.tw/gen/10.pdf 3. Performance evaluation of Particle SwarmOptimization (PSO) and Artificial
Bee Colony (ABC)Algorithm (2011) . Ravi C. Butani, Bhavin D. Gajjar, Electronics and Communication department, L.D. College of Engineering, Gujarat Technological University Ahmedabad, India.
4. Comparison of Ant Colony and Bee Colony Optimization for Spam Host Detection, International Journal of Engineering Research and Development. http://www.ijerd.com/paper/vol4-issue8/E04082632.pdf
5. A comparative study of Artificial Bee Colony algorithm. Applied Mathematics and Computation Volume 214, Issue 1, 1 August 2009, Pages 108–132.
6. Comparison of the Artificial Bee Colony and the Bees Algorithm for PID Controller Tuning. Ozden ERCIN1 and Ramazan COBAN. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5946157
References 1. A Survey On Bee Colony Algorithms. Bitam et. Al (2009). A survey:
algorithms simulating bee swarm intelligence, Dervis Karaboga, Bahriye Akay.
2. Bee Colony Optimization – A Cooperative Learning Approach to Complex Transportation Problems. Dusan Teodorovic, Mauro Orco.
3. The Bees Algorithm – A Novel Tool for Complex Optimisation Problems D.T Pham et. Al (2005)
4. Dervis Karaboga - An Idea Based On Honey Bee Swarm for Numerical Optimization.