In algorithmic computing, the program follows a predefined set of rules – the algorithm. The analyst/designer of the program analyzes the intended tasks of the program, defines the rules for its expected behaviour and programs the implementation. The creators of algorithmic software must therefore foresee, identify and implement all possible cases for its behaviour in the future application!
However, what if the problem is not fully defined? Or the environment is uncertain? What if situations are too complex to be predicted? Or the environment is changing dynamically? In many such cases algorithmic computing fails.
In such situations, the software needs an additional degree of freedom: Autonomy! Autonomy allows software to adapt to partially defined problems, to uncertain or dynamically changing environments and to situations that are too complex to be predicted. As more and more applications – such as autonomous cars and planes, adaptive power grid management, survivable networks, and many more – fall into this category, a gradual switch from algorithmic computing to autonomic computing takes place.
Autonomic computing has become an important software engineering discipline with a rich literature, an active research community, and a growing number of applications.
| Identifer | oai:union.ndltd.org:DRESDEN/oai:qucosa.de:bsz:14-qucosa-232820 |
| Date | 13 February 2018 |
| Contributors | Technische Universität Dresden, Fakultät Informatik |
| Publisher | Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden |
| Source Sets | Hochschulschriftenserver (HSSS) der SLUB Dresden |
| Language | German, English |
| Detected Language | English |
| Type | doc-type:workingPaper |
| Format | application/pdf |
| Relation | dcterms:isPartOf:Technische Berichte / Technische Universität Dresden, Fakultät Informatik; 2017,03 (TUD-FI17-03-Dezember 2017) |
Page generated in 0.002 seconds