Plethora of customer applications & services require guarantees which should never be affected by the state of the substrate network and of its computing resources. Indeed, the commercial potential of many promising 6G concepts will only come to life if the network itself is capable of automatically deciding and enforcing at runtime the most suitable intelligent, data driven actions.
Lamda Networks already delivers as a consulting company custom AI/ML solutions for 5G operators and system integrators, optimally operators’ exact hardware and software requirements.
Our mature, TRL-7 codebase, StreamAnalyzer is 5G ready, having being tested and validated in carrier-grade 5G infrastructures. We are currently building new functionalities fitting the 6G commercial roadmap and are actively pursuing to commercialize StreamAnalyzer to the 6G market. Drop us an email should you be interested in StreamAnalyzer.
AI insights and ML analytics for the 5G Core
Many features of StreamAnalyzer to enable intelligent decision in 5G making have been developed and validated over state of the art 5G substrates within the scope EU projects. For example the predictive autoscaling in StreamAnalyzer, which outperforms Kubernetes autoscaling, especially the scale-out performance (liner in K8s but following the real load decrease non-linear function in our software) and which leads to energy savings for the telco cloud, has been supported by SoftFIRE, Fed4FIRE+ and 5GinFIRE (solution validated in Telefonica’s 5GTONIC OpenStack running Open Source MANO.
Lamda Networks is a member of ETSI OSM.
StreamAnalyzer implements AI models tested and validated for their suitability in intelligent 5G Slicing. In 6G-XR H2030 project where StreamAnalyzer was integrated with Cumucore which is the commercial 5G Core of UOULU 5GTN. Our code’s performance was validated to outperform 5G’s standard behavior on ML slicing on UOULU’ 5GTN 5G mobile private network. Part of the open-source code is available at our GitHub here.
Near-real time Spark-based ML analytics to detect privacy vulnerabilities of Network Applications were provided by StreamAnalyzer to the ICT-41 5GASP project.
AI insights and ML analytics for the 5G Radio Access Network
Selected 3GPP TS29.520 Rel. 18 NWDAF ML-based functionalities to predict RAN KPIs using Telemetry data from Amarisoft’s Web Socket API were developed and validated at the NCRSD 5G RAN within the scope of our Open Call project with 6G-SANDBOX H2030 project.
Lamda Networks is a member of the 6G Smart Networks and Services Industry Association (6G-IA).