The Bees Algorithm

1
The Bees Algorithm
A Novel Tool for Optimisation Problems
The Bees Algorithm is a new population-based
search algorithm. The algorithm mimics the food
foraging behaviour of swarms of honey bees. In
its basic version, the algorithm performs a kind
of neighbourhood search combined with random
search and can be used for optimisation.
- 1 - Scout bees search for food randomly from
one flower patch to another.
- 4 - The dancer bees meet other bees at the
dance floor with high population density.
- 2 - A colony of honey bees can extend itself
over long distances in multiple directions.

• - 3 -
• The bees evaluate the different patches according
  to
• Nectar quality
• Energy usage

- 5 - Communication via Waggle Dance gives 1.
Direction 2. Distance 3. Quality
- 8 - 2. Determine the size of neighbourhood
(patch size)
- 6 - According to the fitness, patches can be
visited by more bees or abandoned
8
- 7 - A Simple Example 1. Initialise a
population of scout bees with random search
- 9 - 3. Recruit bees for selected sites
- 10 - 4. Select the fittest bee from each site
Flowchart of the Bees Algorithm
- 11 - 5. Assign remaining bees to random search

• - 12 -
• Some Applications
• Statistical Quality Control
• Wood Defect Classifier
• Mechanical Design
• Electronic Design
• Clustering
• Job Scheduling
• Robotics
• Travelling Salesman Problem
• Data Mining

Cardiff University Manufacturing Engineering
Centre www.mec.cf.ac.uk E-mail koce_at_cf.ac.uk
The Cardiff Bay Bees Prof. D.T. Pham, E. Koc,
A. Ghanbarzadeh, S. Otri, S. Rahim, M. Zaidi, J.
Phrueksanant, J. Lee, S. Sahran, M. Sholedolu,
M. Ridley, M. Mahmuddin, H. Al-Jabbouli, A. H.
Darwish, A. Soroka, M. Packianather and M.
Castellani