Information and Communication Technologies Area, Ikerlan Technology Research Centre, 20500 Arrasate-Mondragón, Spain.
Department of Communications Engineering, University of Cantabria, 39005 Santander, Spain.
Sensors (Basel). 2019 Apr 8;19(7):1673. doi: 10.3390/s19071673.
The adoption of both Cyber⁻Physical Systems (CPSs) and the Internet-of-Things (IoT) has enabled the evolution towards the so-called Industry 4.0. These technologies, together with cloud computing and artificial intelligence, foster new business opportunities. Besides, several industrial applications need immediate decision making and fog computing is emerging as a promising solution to address such requirement. In order to achieve a cost-efficient system, we propose taking advantage from spot instances, a new service offered by cloud providers, which provide resources at lower prices. The main downside of these instances is that they do not ensure service continuity and they might suffer from interruptions. An architecture that combines fog and multi-cloud deployments along with Network Coding (NC) techniques, guarantees the needed fault-tolerance for the cloud environment, and also reduces the required amount of redundant data to provide reliable services. In this paper we analyze how NC can actually help to reduce the storage cost and improve the resource efficiency for industrial applications, based on a multi-cloud infrastructure. The cost analysis has been carried out using both real AWS EC2 spot instance prices and, to complement them, prices obtained from a model based on a finite Markov chain, derived from real measurements. We have analyzed the overall system cost, depending on different parameters, showing that configurations that seek to minimize the storage yield a higher cost reduction, due to the strong impact of storage cost.
采用 赛博物理系统（CPS）和物联网（IoT）已经推动了向所谓的工业 4.0 的发展。这些技术，再加上云计算和人工智能，催生了新的商业机会。此外，一些工业应用需要即时决策，雾计算作为一种满足这种需求的有前途的解决方案正在出现。为了实现具有成本效益的系统，我们建议利用云提供商提供的新服务——即时实例，以较低的价格提供资源。这些实例的主要缺点是它们不能保证服务的连续性，并且可能会受到中断的影响。一种结合雾计算和多云部署以及网络编码（NC）技术的架构，为云环境提供了所需的容错能力，同时还减少了提供可靠服务所需的冗余数据量。在本文中，我们基于多云基础设施分析了网络编码如何实际帮助降低存储成本并提高工业应用的资源效率。成本分析是使用真实的 AWS EC2 即时实例价格以及基于有限马尔可夫链的模型价格（从实际测量中得出）来完成的。我们分析了不同参数下的整个系统成本，结果表明，由于存储成本的强烈影响，旨在最小化存储的配置会带来更高的成本降低。
