IoT systems can be regarded as distributed systems that are composed of heterogeneous smart devices with different performances and functionalities. Many IoT applications with various resources and real-time requirements will run concurrently in an IoT system. In addition, non-functional properties such as power consumption and device lifetime are considered important. Since the IoT services can be added or removed anytime and the device status may change at runtime, the system configuration is unprecedentedly dynamic, which brings up a challenging scheduling problem of IoT services onto the devices. We assume that an IoT application is specified by a directed graph, called service graph, where nodes represent services while the directed edges represent the dependencies between them. To tackle this problem, we propose a novel adaptive approach that consists of two scheduling techniques, incremental and global. The incremental heuristic method is proposed to provide fast responsiveness to the dynamically changing configuration while satisfying the real-time constraints. During steady state operation, GA-based global rescheduling is periodically applied. We use the acceptance ratio of new services and energy consumption as two performance metrics of the proposed scheduling method. The viability of the proposed approach is verified by extensive simulations with random IoT service graphs.

物联网系统可以看作是由具有不同性能和功能的异构智能设备组成的分布式系统。许多具有各种资源和实时要求的物联网应用程序将在物联网系统中同时运行。此外，功耗和设备寿命等非功能特性也很重要。由于物联网服务可以随时添加或删除，并且设备状态可能会在运行时发生变化，系统配置是前所未有的动态，这给设备带来了具有挑战性的物联网服务调度问题。我们假设 IoT 应用程序由一个称为服务图的有向图指定，其中节点表示服务，而有向边表示它们之间的依赖关系。为了解决这个问题，我们提出了一种新颖的自适应方法，它包含两种调度技术，增量和全局。提出了增量启发式方法，以在满足实时约束的同时对动态变化的配置提供快速响应。在稳态运行期间，会定期应用基于 GA 的全局重新调度。我们使用新服务的接受率和能源消耗作为所提出的调度方法的两个性能指标。通过使用随机物联网服务图的广泛模拟验证了所提出方法的可行性。定期应用基于 GA 的全局重新调度。我们使用新服务的接受率和能源消耗作为所提出的调度方法的两个性能指标。通过使用随机物联网服务图的广泛模拟验证了所提出方法的可行性。定期应用基于 GA 的全局重新调度。我们使用新服务的接受率和能源消耗作为所提出的调度方法的两个性能指标。通过使用随机物联网服务图的广泛模拟验证了所提出方法的可行性。