Journal of System Simulation
Abstract
Abstract: Three K-means clustering algorithms are proposed to prevent chaos in the formation of a multi-agent system (MAS) with multiple leaders. The algorithm divides the cluster into communities with the same number of leaders, and the agents within the community will follow the same leader. Among the three proposed algorithms, algorithm #1 is suitable for scenarios with widely distributed agents wherein rapid consensus can be achieved in the shortest time; algorithm #2 is suitable for scenarios with a sparse agent distribution and effectively prevented agent collisions; and algorithm #3 exhibits rapid convergence and considerably reduces the MAS control cost, but will sacrifice the convergence speed of the system.. Unlike the traditional method in which the agents are numbered and the leader-follower relationship is fixed, the proposed clustering methods can shorten the MAS convergence time and effectively adapt to task changes by rapidly assigning new suitable tasks to agents.
Recommended Citation
Yuan, Guodong; He, Ming; Ma, Ziyu; Zhang, Weishi; Liu, Xueda; and Li, Wei
(2023)
"Multiagent Following Multileader Algorithm Based on K-means Clustering,"
Journal of System Simulation: Vol. 35:
Iss.
3, Article 15.
DOI: 10.16182/j.issn1004731x.joss.21-1158
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol35/iss3/15
First Page
616
Revised Date
2022-01-21
DOI Link
https://doi.org/10.16182/j.issn1004731x.joss.21-1158
Last Page
622
CLC
TP391.9
Recommended Citation
Guodong Yuan, Ming He, Ziyu Ma, Weishi Zhang, Xueda Liu, Wei Li. Multiagent Following Multileader Algorithm Based on K-means Clustering[J]. Journal of System Simulation, 2023, 35(3): 616-622.
DOI
10.16182/j.issn1004731x.joss.21-1158
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons