Toward Explainable Reasoning in 6G: A Proof of Concept Study on Radio Resource Allocation

TL;DR

A novel graph reinforcement learning (GRL) framework named TANGO which relies on a symbolic subsystem which consists of a Bayesian-graph neural network (GNN) Explainer, whose outputs are periodically translated to a logical GRL reward function through defined symbolic reasoning rules within a Reasoner.

Abstract

The move toward artificial intelligence (AI)-native sixth-generation (6G) networks has put more emphasis on the importance of explainability and trustworthiness in network management operations, especially for mission-critical use-cases. Such desired trust transcends traditional post-hoc explainable AI (XAI) methods to using contextual explanations for guiding the learning process in an in-hoc way. This paper proposes a novel graph reinforcement learning (GRL) framework named TANGO which relies on a symbolic subsystem. It consists of a Bayesian-graph neural network (GNN) Explainer, whose outputs, in terms of edge/node importance and uncertainty, are periodically translated to a logical GRL reward function. This adjustment is accomplished through defined symbolic reasoning rules within a Reasoner. Considering a real-world testbed proof-of-concept (PoC), a gNodeB (gNB) radio resource allocation problem is formulated, which aims to minimize under- and over-provisioning of physical resource blocks (PRBs) while penalizing decisions emanating from the uncertain and less important edge-nodes relations. Our findings reveal that the proposed in-hoc explainability solution significantly expedites convergence compared to standard GRL baseline and other benchmarks in the deep reinforcement learning (DRL) domain. The experiment evaluates performance in AI, complexity, energy consumption, robustness, network, scalability, and explainability metrics. Specifically, the results show that TANGO achieves a noteworthy accuracy of 96.39% in terms of optimal PRB allocation in inference phase, outperforming the baseline by 1.22x.

Figures (11)

• Figure 1: Infrastructure and network setup rezazadeh2023x.
• Figure 2: Amarisoft 5G RAN equipment.
• Figure 3: The TANGO framework workflow illustrates the process from network state transformation to decision-making and refining radio resource allocation policies.
• Figure 4: The graph compares TANGO's average reward trajectories per episode to Baseline (without symbolic subsystem) and other DRL benchmarks during 70 episodes. The curves are smoothed (Gaussian smoothingGaussianfilterref) for visual clarity.
• Figure 5: The heatmap provides a visual representation of the TANGO reward pattern throughout the episodes in the training phase. Each row is an episode, and each column represents a step within that episode. The color intensity indicates the amount of reward earned at each step.