Automatic Definition and Application of Similarity Measures for Self-operation of Network

Tang, Haitao; Stenberg, Kaj; Apajalahti, Kasper; Niiranen, Juha; Räisänen, Vilho

doi:10.1007/978-3-319-52712-3_15

Cited by 1 publication

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All in all, the combination of technologies provides a flexible platform for future network management use cases. The reduction of traditional programming was demonstrated with an example where Clojure implementation of similarity query [24] was replaced with SPARQL calls. Agent composition, in particular together with microservices paradigm, supports efficient use case driven network management.…”

Section: Discussionmentioning

confidence: 99%

“…We used Capacity and Coverage Optimization (CCO) SON function based on fixed rule set in the test system. Configuration Management (CM) and PM data from simulator are streamed over publish/subscribe bus [23] to information crosslinking functionality [24] which stores resulting information in MongoDB.…”

Section: Test Systemmentioning

confidence: 99%

“…A demonstration of substituting traditional programming with reasoning was already possible with our test system. The original goal was to implement the query phase or selfoperation system [24] as a warm-up exercise, mapping it to agents. It was found that two SPARQL queries from the coordinator were sufficient to achieve the same end result than the previous Clojure software implementation for similarity search.…”

Section: Test Systemmentioning

confidence: 99%

See 2 more Smart Citations

Reasoning in agent-based network management

Räisänen

Bell

Apajalahti

2018

NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium

Self Cite

View full text Add to dashboard Cite

An increasing complexity of mobile networks and use cases is reflected in requirements for network management. Advanced automation is required to address this challenge in an economically feasible manner. We describe a system based on agent mapping as a platform for automation for network management in 5G networks and beyond. We use classical and probabilistic reasoning for composing solutions to complex requests by means of relatively simple software agents. We describe different variants of the approach in terms of capabilities, ranging from triple store only to system with semantic and probabilistic reasoning functionalities. This approach provides flexibility for network functionality evolution and facilitates software reuse and is compatible with the use of task-specific machine learning algorithms in network management agents. We describe test system used for evaluating the concept, as well as use case evaluation obtained with it.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Test Systemmentioning

confidence: 99%

Section: Test Systemmentioning

confidence: 99%

See 1 more Smart Citation