Multiagent-Based Allocation of Complex Tasks in Social Networks
Multiagent-Based Allocation of Complex Tasks in Social Networks
复制标题
DOI：
10.1109/tetc.2015.2403200
复制
发表时间：
2015-10
影响因子：
5.9
通讯作者：
Wanyuan Wang;Yichuan Jiang
中科院分区：
文献类型：
--
作者：
Wanyuan Wang;Yichuan Jiang
在许多社交网络（SN）中，社交个体通常需要共同努力才能完成复杂的任务（例如软件产品开发）。在SN背景下，由于社会联系的存在，复杂的任务分配必须达到令人满意的社会效果；换句话说，每项复杂的任务都应该分配给社会关系密切的个人，以使他们能够有效地沟通和协作。尽管已经提出了几种方法来解决这种所谓的社会任务分配问题，但它们要么受到中心化的困扰，要么忽视了最大化社会效率的目标。在本文中，我们提出了一种基于分布式多智能体的任务分配模型，通过向每个复杂任务的每个子任务分配一个移动且协作的智能体，该模型也解决了社会效益最大化的目标。就移动性而言，每个智能体都可以将自己传送到具有相关能力的合适个体。在合作性方面，代理人之间可以通过组建团队的方式进行合作，如果合作有利的话，可以共同转移到合适的个体。我们的理论分析为该模型提供了可证明的性能保证。我们还将该模型应用于一组静态和动态网络设置中，以研究其有效性、可扩展性和鲁棒性。通过实验结果，确定我们的模型能够有效提高系统负载平衡和社会效益；该模型在减少计算时间方面具有可扩展性，并且在适应系统动态方面具有鲁棒性。
In many social networks (SNs), social individuals often need to work together to accomplish a complex task (e.g., software product development). In the context of SNs, due to the presence of social connections, complex task allocation must achieve satisfactory social effectiveness; in other words, each complex task should be allocated to socially close individuals to enable them to communicate and collaborate effectively. Although several approaches have been proposed to tackle this so-called social task allocation problem, they either suffer from being centralized or ignore the objective of maximizing the social effectiveness. In this paper, we present a distributed multiagent-based task allocation model by dispatching a mobile and cooperative agent to each subtask of each complex task, which also addresses the objective of social effectiveness maximization. With respect to mobility, each agent can transport itself to a suitable individual that has the relevant capability. With respect to cooperativeness, agents can cooperate with each other by forming teams and moving to a suitable individual jointly if the cooperation is beneficial. Our theoretical analyses provide provable performance guarantees of this model. We also apply this model in a set of static and dynamic network settings to investigate its effectiveness, scalability, and robustness. Through experimental results, our model is determined to be effective in improving the system load balance and social effectiveness; this model is scalable in reducing the computation time and is robust in adapting the system dynamics.