Use of AI in Telecom’s is not a new topic . However what has enabled with 5G and Edge is a Open and Flexible Infrastructure that helps to deliver AI as a standard platform and capabilities .
As an example the SON , NSP and other type of platforms are a tailored or closed systems but that definitely delivers an outcome and value , but the same can not be extended towards other domains . That is exactly what AI based operations in new era will be able to solve .
AI based Operations for 5G and Edge
AI for Telecom has gained industry interests recently primarily driven by both wide deployments of 5G platforms which generates 4X more data compared to early generations alongside other global events like Covid-19 which necessitates a close loop operation avoiding the human. This initiative require not only orchestration but infact intelligent policy generation based on real time use and customer behaviors and will enable a SLA based offering for each 5G business tenant.
The use of ML/AI is still in initial phases of standardization, to ensure realization of a successful autonomous networks so the ML/AI should address following domains
- Analysis
- Intelligence
- Automation and Policy
There is not just the technical side of ML/AI use in Telecom but a business side also. As we are well aware that many of NFV/SDN products in the market today that comes with native ML/AI functionality which are enabled not only in intent driven software level but also in chipset level one such example is Intel Atom , Intel 3rd gen Xeon processors with built in bfloat16 support that reduces data required to build training models . However still Telco’s in 5G are trying to find sweet spot that will make business case of 5G positive. This is a fact that to build same coverage as 4G we need to pump 4 times more sites which means use of ML/AI for automated managed and use cases to optimize infrastructure is mandatory. In this context we also need to evaluate new business models for 5G to see “If 5G data can be monetized than Service can Free. From Infra view to Managed services view to vertical industry offering view”
Use cases for AIOPS
In this context in 2022+ Telco’s need to evaluate and commercialize following key cases for 5G ML/AI to speed up the deployment
- Life Cycle Managmeent of Infrastructure
- Automating Application and Infra Dependency
- Automatic output rule to Optimize NW specially RAN and Transport
- Advanced AI e.g build New Network Topology ,
- Work load placement , SLA analysis in case of PoP migration
The Telco operators should take active interest in following industry efforts to successfully use ML/AI in 5G Cloud Infrastructure
- ITU-T Focus group on ML for future NW (FM ML5G)
- ETSI enhanced network intelligence (ENI)
- O-RAN alliance for RIC (RAN intelligent controller)
Below is the summary of Use cases and architectures delivered in TMF AIOPS framework and this is a great start point to start your AI journey in the OSS/BSS and Network Domains .
Security of Networks for AI era
Cloud infrastructures by its nature becomes more secure than black boxes over time however till their maturity there is a increasing risk of security vulnerabilities primarily due to increased attack surface and ease to access and use API’s once a security hole is concealed by hackers. It is clear that the existing Security solutions are not tailored to handle such architectures. The future security solutions in the Cloud must consider
- Real time monitoring
- API discovery
- Policy management
- Distributed security
- Software based security frameworks
Service mesh is the futuristic technology that is required to protect the future 5G infrastructures. Delivering security as a service is a definite requirement for Telco’s and it is very important, we deliver security enhancement in a software manner to cover
- Advanced Cluster management that encompass private, public and hybrid cloud
- Security of Networks
- End point protection IPSec and DTLS
- Open data platforms and mTLS for scalability
- Platform attention for disaggregated cloud
Today the secure networking using NSM is a reality in Core . 5G CNF’s like NEF ,NRF,AUSF however due to high performance and resilience requirement the nodes like UPF,DU,CU,AMF,SMF is not hardened today however the Kubernetes’s 1.23 is adding a number of enhancements around like secondary networking , monitoring , CNI extensive models and storage acceleration which means we are converging faster towards to open and standard deployment of 5G Networks .
Below is a recording of a recent summit of which i were part of , do check it out here .
5G , Cloud ,Edge and Automation for Telecom, Applications and Enterprise 