Leveraging Cognitive Machine Reasoning and NLP for Automated Intent-Based Networking and e2e Service Orchestration
Modern networks are increasingly complex, necessitating dynamic and automated solutions to connect user intents with network actions effectively. This study presents a new framework for automating Intent Based Networking (IBN) by combining cognitive Machine Reasoning (MR) with Natural Language Proce...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10854217/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Modern networks are increasingly complex, necessitating dynamic and automated solutions to connect user intents with network actions effectively. This study presents a new framework for automating Intent Based Networking (IBN) by combining cognitive Machine Reasoning (MR) with Natural Language Processing (NLP) and utilizing the RASA (Robust Automated Speech Assistant) architecture. RASA is a flexible open-source framework for building conversational AI, adapted for end-to-end (e2e) network orchestration. In contrast to traditional static methods, this innovative system empowers network operators to manage and optimize networks dynamically through intuitive voice commands or a Graphical User Interface (GUI). The system identifies user intents, converts them into actionable network policies, and ensures they align with real-time network states and Quality of Service (QoS) requirements via a feedback loop. Cognitive MR and AI-based optimization techniques are integrated to enhance system performance, enabling intelligent adaptation to network conditions and ensuring optimal resource allocation. A simulated testbed was created to assess the system’s performance using Containernet, a lightweight Container-Based Network Emulator, and Open Networking Operating System (ONOS) Software Defined Networking (SDN) controllers. The results of the testbed indicated a 25% reduction in latency, a 30% increase in throughput, and a 40% enhancement in real-time response times, demonstrating the system’s effectiveness in a controlled environment. These impressive results underscore the system’s potential to enhance network performance, efficiency, and responsiveness. By effectively addressing modern networks’ challenges, this solution proves its ability to confidently and seamlessly convert user intents into automated network actions without manual intervention, providing adaptability and scalability for today’s network environments. |
|---|---|
| ISSN: | 2169-3536 |