An Evaluation of Optimisation Approaches in Cloud of Things Resource Trading

Abstract

Cloud Computing and Internet of Things (IoT) have evolved to meet the requirements of many real-world applications. Many of these requirements cannot be fulfilled by using either technology separately. In order to fulfil such diverse requirements, the integration of Cloud Computing and IoT is emerging as a new paradigm called Cloud of Things (CoT). CoT is expected to host heterogeneous resources and fulfil complex requirements of resource providers and consumers. This complexity poses a real challenge for resource allocation in CoT. To tackle this challenge, resource allocation is described as a trading optimisation problem and utility functions are used to rank candidate resource allocation assignments. The contributions of this paper are 1) introducing vocabularies needed for trading CoT resources 2) proposing a marketplace system architecture to enable efficient trading of CoT resources 3) examining the use of different utility functions to rank candidate resource assignments 4) performing simulations to validate the effectiveness of the proposed approach using three optimisation algorithms.