Intent Profiling and Translation Through Emergent Communication

TL;DR

This work tackles automated, scalable intent-based networking for machine-to-machine interactions by introducing an emergent-communication framework that jointly handles intent profiling and translation. It casts the problem as a cooperative MARL scenario (MAPPO) with discrete emergent signaling, where applications express abstract QoE intents and the network learns to map these messages to suitable network slices to guarantee QoS. The main contribution is a novel AI-driven protocol that decouples intent profiling from translation, enabling learning-based translation of domain-language intents into resource allocations, and demonstrating near-ideal performance against a perfect-knowledge baseline. The approach promises practical impact by reducing the need for predefined mappings, improving scalability across diverse IIoT applications, and enabling adaptive, autonomous network orchestration in 5G+-style infrastructures.

Abstract

To effectively express and satisfy network application requirements, intent-based network management has emerged as a promising solution. In intent-based methods, users and applications express their intent in a high-level abstract language to the network. Although this abstraction simplifies network operation, it induces many challenges to efficiently express applications' intents and map them to different network capabilities. Therefore, in this work, we propose an AI-based framework for intent profiling and translation. We consider a scenario where applications interacting with the network express their needs for network services in their domain language. The machine-to-machine communication (i.e., between applications and the network) is complex since it requires networks to learn how to understand the domain languages of each application, which is neither practical nor scalable. Instead, a framework based on emergent communication is proposed for intent profiling, in which applications express their abstract quality-of-experience (QoE) intents to the network through emergent communication messages. Subsequently, the network learns how to interpret these communication messages and map them to network capabilities (i.e., slices) to guarantee the requested Quality-of-Service (QoS). Simulation results show that the proposed method outperforms self-learning slicing and other baselines, and achieves a performance close to the perfect knowledge baseline.

Figures (6)

• Figure 1: Interaction of the main IBN components.
• Figure 2: System Model.
• Figure 3: Normalized successful QoS translations versus the number of episodes.
• Figure 4: Normalized failed QoS translations versus number of episodes.
• Figure 5: Normalized successful QoS translations versus the number of users.