Prioritized Value-Decomposition Network for Explainable AI-Enabled Network Slicing

TL;DR

This paper introduces PVDN, an explainable AI approach for network slicing that decomposes value functions and prioritizes outputs, significantly improving resource allocation transparency and network performance.

Contribution

The paper proposes a novel PVDN method that enhances explainability in multi-agent network slicing, enabling better understanding and optimization of resource management strategies.

Findings

Improves throughput by up to 67%

Reduces latency by up to 35%

Provides explainability in resource allocation decisions

Abstract

Network slicing aims to enhance flexibility and efficiency in next-generation wireless networks by allocating the right resources to meet the diverse requirements of various applications. Managing these slices with machine learning (ML) algorithms has emerged as a promising approach however explainability has been a challenge. To this end, several Explainable Artificial Intelligence (XAI) frameworks have been proposed to address the opacity in decision-making in many ML methods. In this paper, we propose a Prioritized Value-Decomposition Network (PVDN) as an XAI-driven approach for resource allocation in a multi-agent network slicing system. The PVDN method decomposes the global value function into individual contributions and prioritizes slice outputs, providing an explanation of how resource allocation decisions impact system performance. By incorporating XAI, PVDN offers valuable insights into the decision-making process, enabling network operators to better understand, trust, and optimize slice management strategies. Through simulations, we demonstrate the effectiveness of the PVDN approach with improving the throughput by 67% and 16%, while reducing latency by 35% and 22%, compared to independent and VDN-based resource allocation methods.