Open data - Download the Knowledge base
You are free to download the data of this Knowledge base.
To do this you must be an authenticated user: log in or sign in now.
All the data are licensed as Creative Common CC-BY 4.0.
Edge Intelligence EI
A Whitepaper from Fraunhofer FOKUS and several cooperation partners developed an ingenious future technology, for Improvement of the 5G Net-Infrastructure through networks which are capable to learn. Thanks to this it will be possible soon to provide a 5G Network without any latencies. In conclusion it means, that the cloud system will be obsolete for big companies faster or sooner. The Article explains the technology behind it and the possibilities
Type of content:
Assets
Type of asset:
Model
Big data potential
Yes
Policy domains:
Environment & Energy
Phase in the policy cycle:
Policy Design and Analysis
TRL
7
Implementation/customisation cost
Low
Open license availability
Yes
Ease of use
High
Tags:
Machine learning
Strategic planning
Addresses:
| SWOT Analysis for Edge Intelligence EI |
||
|---|---|---|
| Helpful | Harmful | |
Internal |
Strengths• Taking decisions more quickly and efficiently by placing machine learning (ML) algorithms on the edge devices and reducing the frequency of contact with cloud servers, thus steadily reducing the effect of the roundtrip delay on decision-making; • Reaching decisions according to local identity management and access control policies specific to the running applications, securing the data close to its source and following local regulations • Lowering communication costs by reducing communication over public wide area networks, using caching or local algorithms to pre-process the data so that only decisions or alarms can be forwarded to the cloud servers, rather than raw data; • Load-balance the user, application or network requests based on changes in the edge or core infrastructure, adapting to temporary failures or maintenance procedures • Taking decisions based on the alarms or pre-processed information exchange between the edge devices, i.e. east/west (E/W) communication between two peers on the edge. |
Weaknesses• 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. • Required data volume and available bandwidth • Need for intermittent connectivity • Credibility and (decentralised) trust • Self-organisation, self-configuration, and self-discovery • East/west communication between multiple Edge Computing Nodes (ECN) • Implementation of algorithms for Machine Learning • Definition of basic functionality of ECNs • Semantic interoperability • Fault detection Standards • Embedded system containerisation for application programming interface (API), and execution level capability and tenancy |
External |
Opportunities• Take decisions more quickly and efficiently, as the roundtrip delay in contacting the cloud is removed; • Reach decisions according to local identity management and access control policies, securing the data close to its source; |
Threats• Credibility and (decentralised) trust • Self-organisation, self-configuration, and self-discovery • East/west communication between multiple Edge Computing Nodes(ECN) |
