IIoT services focused on industry-oriented services often require objects run more than one task. IIoT objects poses the challenge of distributing and managing task allocation among them. The fairness of task allocation brings flexible network reconfiguration and maximizes the tasks to be performed. Although existing approaches optimize and manage the dynamics of objects, not all them consider both co-relationship between tasks and object capabilities and the distributed allocation over the cluster service. This paper introduces the ACADIA mechanism for task allocation in IIoT networks in order to distribute task among objects. It relies on relational consensus strategies to allocate tasks and similarity capabilities to determine which objects can play in accomplishing those tasks. Evaluation on NS-3 showed that ACADIA achieved 98% of allocated tasks in an IIoT-Health considering all scenarios, average more than 95% of clusters apt to performed tasks in a low response time, and achieved 50% more effectiveness in task allocation compared to the literature solution CONTASKI.
翻译:以工业为导向的服务为主的IIOT服务往往需要运行不止一项任务。IIOT对象在分配和管理任务分配方面构成挑战。任务分配的公平性带来了灵活的网络重组,使要完成的任务最大化。虽然现有办法优化和管理目标的动态,但并非所有办法都考虑任务与目标能力之间的关系以及集群服务的分配。本文件介绍了ACADIA机制,以便在IIOT网络中分配任务,以便在目标之间分配任务。它依靠相关共识战略分配任务和类似能力,以确定哪些目标可以在完成这些任务中发挥作用。对NS-3的评估表明,考虑到所有情况,ACADIA在IIO-Health中完成了98%的分配任务,平均95%以上的集群能够在低响应时间内完成任务,任务分配效率比COTASKI的文献解决方案高50%。