Cloud of Things (CoT): Cloud-Fog-IoT Task Offloading for Sustainable Internet of Things

Abstract

With a high rise in the popularity of Internet of Things (IoT), mobile computing, and wearable devices, a huge amount of data is being generated. Running complex tasks such as that are machine learning-based with minimum energy consumption is a challenge. It requires complex algorithms to run locally such as on middleware fog within the proximity of the devices generating data, or globally in a cloud to analyze the acquired data and create robust and smart applications. However, it depends on the type of task execution policy applied at each level; local or global, to decide on energy and performance efficiency, since certain tasks are high in complexity. Hence, task execution will be hierarchically distributed among the IoT nodes, fog, and cloud. Given that, we present in this paper a three-tier IoT-fog-cloud model. We argue that with distributed task execution, we can achieve high scalability of IoT services, and manage the global energy consumption as well. As a proof-of-concept, we evaluate our three-tier architecture by taking into account computational tasks for various applications in IoT related to medical, multimedia, location-based, and text. We evaluate using real datasets, based on three scenarios: fog-only, cloud-only, and fog-cloud collaborative. Task execution policy (at fog/cloud) play a key role in efficiently processing a task (especially large tasks, such as in deep learning). Therefore, we take that into account and elaborate what types of policies suit what type of offloading environment (fog-only, cloud-only, or fog-cloud collaborative).