#Berlin5GWeek: “Edge Intelligence” ─ Decentral networks for the Internet of Things
News from Oct. 17, 2017
The International Electrotechnical Commission (IEC) has brought out the White Paper “Edge Intelligence” (EI) in cooperation with Fraunhofer FOKUS and industrial partners. “Edge Intelligence” exploits the advancements in hardware, software and networking for taking decisions faster and cost-attractive to the benefit of multiple industries.
Most applications in the areas like Industry 4.0, Virtual Reality and Smart Cities are data intensive or time sensitive and depend on a lot of data from sensors and devices being processed almost in real time. Furthermore, depending on the application, information must be extracted from the data and transmitted securely. This is possible through “Edge Intelligence”, a combination of Edge Computing, sophisticated Application Function and Network Infrastructure management powered by Machine Learning. “Edge Intelligence” uses the evermore efficient devices and sensors on site for storage and analysis of the data. Having solutions coupled with the new 5G network infrastructure, which provides the right software-based network for each application, in future, a central cloud will be obsolete for verticals with the need for robust and secure communication and low latency.
The White Paper explains the technology, describes the application scenarios and their technological gaps that can be closed with Edge Intelligence (EI) and gives recommendations for a vertical-specific deployment. The authors draw following conclusions:
- Containerization is required but no specific standards exist yet. Containerization means that the businesses will be provided with a box with various EI functions, which they can use flexibly and across industry sectors based on the application.
- “Edge Intelligence” common data models are required so that the various heterogeneous data can be combined.
- Instead of a central cloud, microdata centers will become increasingly important.
- A 5G network infrastructure enables such decentral data centers. 5G networks will enable local data centers “at the edge” and, depending on the location, industry-specific ore networks. Core technologies for this purpose are virtualization, software-based networks and even failure detection through machine learning methods.
- Machine learning and artificial intelligence support customers in making quick and well-founded decisions. Current systems are so complex that simply presenting the gathered data becomes superfluous for timely decisions to be made, autonomous systems can identify and rectify errors in complex IT-Systems independently.
You want to know more about 5G and Edge Intelligence and directly interact with experts? Then visit the #Berlin5GWeek