摘要：The reduced service cost offered by Sensing and Actuation as a Service paradigm, particularly in Internet of Things (IoT) era, has encouraged many establishments to start without worrying about having their own infrastructure. Such a paradigm is typically managed by a centralized cloud service provider. Fog paradigm has emerged as a mini-cloud that if designed with care to assist the cloud, together will achieve better performance. This article introduces a layered fog architecture called Sensors and Actuator Layered Fog Services Delivery (SALFSD) for IoT ecosystems. The significance of SALFSD is being fault resistant; it dynamically reassigns tasks of the failed node to the nearest active node to maintain the network connection. Besides, SALFSD monitors end users pre-specified cases closer to the physical devices hired by end users to fasten generating the actuation commands. Such node may offload its monitoring responsibility to its parent node in case it is overloaded. SALFSD is evaluated using Yet Another Fog Simulator in different scenarios (numbers of users, sensors, actuators, and areas). A comparison was made for Sensing and Actuating as a Service (SAaaS) with/without layered fog, and layered fog with/without (failure reassignment, pre-specified cases in fog nodes, and offloading). The comparison was conducted in terms of computing/communication latencies and the number of missed messages for both observations and actuation commands. Results show that failure reassignment prevented losing messages and maintained network connectivity. Also, wisely selecting the monitoring fog node per end user pre-specified cases and the offloading scheme decreased actuation latency.
