Chat-Driven Optimal Management for Virtual Network Services
Yuya Miyaoka, Masaki Inoue, Kengo Urata, Shigeaki Harada
TL;DR
The paper addresses automating user intent in virtual network management by uniting NLP-based interpretation with optimization-based allocation. The core method is a two-stage Interpreter-Optimizer framework: the Interpreter converts natural-language prompts into updateable specifications $\theta$, and the Optimizer solves an ILP to place VMs and route traffic. The ILP objective is min_{x,y} $\omega_1 J_1(x,y) + \omega_2 J_2(x,y) + \omega_3 J_3(x,y)$, with $J_1$ capturing max link utilization, $J_2$ total latency, and $J_3$ VM-placement changes relative to the previous step, subject to constraints on link capacity, per-DC CPU limits, latency bounds, and the one-VM-per-user rule. Experiments in single- and multi-user scenarios show the LLM-based interpreter improves intent accuracy with limited labeled data, while the Sentence-BERT+SVM variant offers lower latency, and arbitration preserves feasibility under contention, indicating a pathway to safe, interpretable, chat-driven network management.
Abstract
This paper proposes a chat-driven network management framework that integrates natural language processing (NLP) with optimization-based virtual network allocation, enabling intuitive and reliable reconfiguration of virtual network services. Conventional intent-based networking (IBN) methods depend on statistical language models to interpret user intent but cannot guarantee the feasibility of generated configurations. To overcome this, we develop a two-stage framework consisting of an Interpreter, which extracts intent from natural language prompts using NLP, and an Optimizer, which computes feasible virtual machine (VM) placement and routing via an integer linear programming. In particular, the Interpreter translates user chats into update directions, i.e., whether to increase, decrease, or maintain parameters such as CPU demand and latency bounds, thereby enabling iterative refinement of the network configuration. In this paper, two intent extractors, which are a Sentence-BERT model with support vector machine (SVM) classifiers and a large language model (LLM), are introduced. Experiments in single-user and multi-user settings show that the framework dynamically updates VM placement and routing while preserving feasibility. The LLM-based extractor achieves higher accuracy with fewer labeled samples, whereas the Sentence-BERT with SVM classifiers provides significantly lower latency suitable for real-time operation. These results underscore the effectiveness of combining NLP-driven intent extraction with optimization-based allocation for safe, interpretable, and user-friendly virtual network management.