Achieving predictable and low end-to-end latency for a network of smart services

To remain competitive in the field of manufacturing today, companies must constantly improve the automation loops within their production plants. This can be done by augmenting the automation applications with "smart services" such as supervisory-control applications or machine-learning inference algorithms. The downside is that these smart services are often hosted in a cloud infrastructure and the automation applications require a low and predictable end-to-end latency. However, with the 5G technology it will become possible to establish a low-latency connection to the cloud infrastructure and with proper control of the capacity of the smart services, it will become possible to achieve a low and predictable end-to-end latency for the augmented automation applications.

In this work we address the challenge of controlling the capacity of the smart services in a way that achieves a low and predictable end-to-end latency. We do this by deriving a mathematical framework that models a network of smart services that is hosting several automation applications. We propose a generalized AutoSAC (automatic service- and admission controller) that builds on previous work by the authors. In the previous work the system was only capable of handling a single set of smart services, with a single application hosted on top of it. With the contributions of this paper it becomes possible to host multiple applications on top of a larger, more general network of smart services.