Smart Resource Allocation Model via Artificial Intelligence in Software Defined 6G Networks

TL;DR

This paper proposes a flexible, AI-driven resource allocation framework for 6G soft-RAN networks, utilizing deep reinforcement learning with a novel TOC metric to optimize network performance trade-offs.

Contribution

It introduces a hierarchical, traffic-aware soft-RAN architecture with a DRL-based resource management algorithm employing the SAC method and a new TOC metric for improved scalability and flexibility.

Findings

The proposed model outperforms fixed schemes in TOC metrics.

Deep reinforcement learning with SAC enhances resource allocation accuracy.

The framework improves network scalability and adaptability.

Abstract

In this paper, we design a new flexible smart software-defined radio access network (Soft-RAN) architecture with traffic awareness for sixth generation (6G) wireless networks. In particular, we consider a hierarchical resource allocation model for the proposed smart soft-RAN model where the software-defined network (SDN) controller is the first and foremost layer of the framework. This unit dynamically monitors the network to select a network operation type on the basis of distributed or centralized resource allocation procedures to intelligently perform decision-making. In this paper, our aim is to make the network more scalable and more flexible in terms of conflicting performance indicators such as achievable data rate, overhead, and complexity indicators. To this end, we introduce a new metric, i.e., throughput-overhead-complexity (TOC), for the proposed machine learning-based algorithm, which supports a trade-off between these performance indicators. In particular, the decision making based on TOC is solved via deep reinforcement learning (DRL) which determines an appropriate resource allocation policy. Furthermore, for the selected algorithm, we employ the soft actor-critic (SAC) method which is more accurate, scalable, and robust than other learning methods. Simulation results demonstrate that the proposed smart network achieves better performance in terms of TOC compared to fixed centralized or distributed resource management schemes that lack dynamism. Moreover, our proposed algorithm outperforms conventional learning methods employed in recent state-of-the-art network designs.