TY - JOUR
T1 - Agent grouping recommendation method in edge computing
AU - Jakhon, Kayumiy Shokh
AU - Guo, Haitao
AU - Cho, Kyungeun
N1 - Publisher Copyright:
© 2020, Springer-Verlag GmbH Germany, part of Springer Nature.
PY - 2022/3
Y1 - 2022/3
N2 - In edge computing, diverse kinds of data are handled in real-time. An increasing number of researches have been carried out to improve the performance of data handling for agent-based data control technology. An important application for edge computing is to control the distributed agents in real-time strategy (RTS) games. One of the key approaches for agent control is the grouping of agents; however, it is difficult to group them in a reasonable cluster. This paper proposes a recommendation method for the best grouping of agents and edge computing devices to reduce the time of handling data and obtaining optimal results for RTS game agent selecting. The proposed method used K-means, influence mapping, and Bayesian probability, and was evaluated by utilizing a game environment in which the performance of handling data is easily evaluated. The comparison result between the recommendation and random modes shows that our method has ability to increase 47% of the percentage the wins.
AB - In edge computing, diverse kinds of data are handled in real-time. An increasing number of researches have been carried out to improve the performance of data handling for agent-based data control technology. An important application for edge computing is to control the distributed agents in real-time strategy (RTS) games. One of the key approaches for agent control is the grouping of agents; however, it is difficult to group them in a reasonable cluster. This paper proposes a recommendation method for the best grouping of agents and edge computing devices to reduce the time of handling data and obtaining optimal results for RTS game agent selecting. The proposed method used K-means, influence mapping, and Bayesian probability, and was evaluated by utilizing a game environment in which the performance of handling data is easily evaluated. The comparison result between the recommendation and random modes shows that our method has ability to increase 47% of the percentage the wins.
KW - Bayesian probability
KW - Edge computing
KW - Grouping recommendation
KW - Influence map
KW - K-means algorithm
UR - http://www.scopus.com/inward/record.url?scp=85077553703&partnerID=8YFLogxK
U2 - 10.1007/s12652-019-01658-8
DO - 10.1007/s12652-019-01658-8
M3 - Article
AN - SCOPUS:85077553703
SN - 1868-5137
VL - 13
SP - 1641
EP - 1651
JO - Journal of Ambient Intelligence and Humanized Computing
JF - Journal of Ambient Intelligence and Humanized Computing
IS - 3
ER -