Abstract
A system is proposed herein for artificial intelligence (AI)-driven, cross-domain optimization of next-generation mobile networks, including fifth-generation (5G) Advanced and sixth-generation (6G) networks. The system provides a Cross-Domain Optimization Function (CDOF) that continuously analyzes peer communication behavior, network function interactions, compute-resource utilization, traffic demand, mobility events, and radio conditions. Based on learned behavioral patterns across network functions, slices, cloud infrastructure, and radio domains, the CDOF dynamically adjusts per-peer signaling intervals across heterogeneous protocols, derives dynamic operational slice characteristics from observed compute and workload behavior, forecasts compute and traffic demand, and generates proactive optimization recommendations for the core network and radio access network (RAN). The CDOF also uses feedback to support closed-loop learning and policy-aware optimization. The resulting framework can reduce signaling overhead, improve failure-detection responsiveness, enhance slice and compute-resource efficiency, and enable predictive radio-resource management for distributed edge deployments, network digital twins, and autonomous network operations.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Barai, Swapnil; Chandra, Sharad; and Shekhar, Ravi, "AI-DRIVEN CROSS-DOMAIN OPTIMIZATION FUNCTION (CDOF) FOR NEXT-GENERATION MOBILE NETWORKS FOR ADAPTIVE SIGNALING, RESOURCE MANAGEMENT AND NETWORK INTELLIGENCE", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12216