IoT systems are becoming an essential part of our environment. Smart cities, smart manufacturing, augmented reality, and self-driving cars are just some examples of the wide range of domains, where the applicability of such systems has been increasing rapidly. These IoT use cases often require simultaneous access to geographically distributed arrays of sensors, and heterogeneous remote, local as well as multi-cloud computational resources. This gives birth to the extended Cloud-to-Things computing paradigm. The emergence of this new paradigm raised the quintessential need to extend the orchestration requirements i.e., the automated deployment and run-time management) of applications from the centralised cloud-only environment to the entire spectrum of resources in the Cloud-to-Things continuum. In order to cope with this requirement, in the last few years, there has been a lot of attention to the development of orchestration systems in both industry and academic environments. This paper is an attempt to gather the research conducted in the orchestration for the Cloud-to-Things continuum landscape and to propose a detailed taxonomy, which is then used to critically review the landscape of existing research work. We finally discuss the key challenges that require further attention and also present a conceptual framework based on the conducted analysis.

翻译：物联网系统正成为我们环境中不可或缺的一部分。智慧城市、智能制造、增强现实和自动驾驶汽车只是众多领域中此类系统应用迅速增长的几个例子。这些物联网用例通常需要同时访问地理分布式的传感器阵列以及异构的远程、本地和多云计算资源。这催生了扩展的云到物计算范式。这一新范式的出现引发了对编排需求（即应用程序的自动部署和运行时管理）的扩展，从集中的纯云环境扩展到云到物连续体中的全部资源范围。为了应对这一需求，近年来，工业界和学术界对编排系统的开发给予了大量关注。本文旨在收集云到物连续体编排领域的研究，并提出一个详细的分类法，进而利用该分类法对现有研究工作进行批判性审视。最后，我们讨论了需要进一步关注的关键挑战，并基于分析提出了一个概念性框架。