Edge_Computing_Forum
Nov. 13, 2018 – Fraunhofer FOKUS, Berlin, Germany

Dr. Klaus Wölfel

CEO, Nexedi GmbH, Germany

Dr. Klaus Wölfel is CEO of Nexedi GmbH, the German branch of Nexedi, the largest Free Software Publisher in Europe. Together with his team in Munich, Klaus currently develops data processing infrastructure for smart sensors in wind energy and civil engineering based on Nexedis Wendelin out-of-core data analytics platform and SlapOS edge computing operating system.

Klaus accomplished his PhD on automation of ERP category configuration with machine learning at the Chair of Information Systems, esp. in Manufacturing and Commerce in the Faculty of Economics of Technische Universität Dresden.

Open Edge Computing for Industry 4.0 

Abstract

SlapOS is an open source general purpose overlay operating system for distributed POSIX infrastructures with a strong focus on service management. SlapOS is probably the first edge computing system that was ever made. It has been deployed commercially for 10 years in industry in Germany, France and Japan in applications that range from senors to on premise gateways to large servers in data centrsr

The core idea of SlapOS is to automatically deploy services using the same "service descriptor language", independent from what kind of service is deployed when where (data center, sensor) and in which context (e.g. hardware architecture, version of operating system). It covers the whole life cycle of a service, from build to monitoring, from order to accounting.

SlapOS uses re6st which was created to fix problems of current Internet through an IPv6 overlay network. In today's Internet, latency is usually sub-optimal and transit provided by telecommunication providers is not always reliable. There are lots of network cuts. DPI systems introduce sometimes data corruption in basic protocols (ex. TCP). Governments add censorship and bogus routing policies, in China for example. There is no way to ensure that two points A and B on the Internet can actually interconnect. The probability of connectivity fault is about 1% in Europe/USA and 10% inside China. It is too much for industrial applications.

Without re6st, an edge computing system cannot work. If one has to deploy 100 orchestrated services over a network of edge nodes with a 1% probability of faulty routes, the overall probability of failure quickly becomes too close to 100%. There is therefore no way to deploy edge without fixing the Internet first.