Towards Safe Load Balancing based on Control Barrier Functions and Deep Reinforcement Learning

TL;DR

This paper presents a safe load balancing algorithm for SD-WAN that combines Deep Reinforcement Learning with Control Barrier Functions to ensure safety and improve training efficiency, achieving near-optimal QoS.

Contribution

The paper introduces a novel safe learning-based load balancing method integrating CBF with DRL, enhancing safety and training speed in SD-WAN environments.

Findings

The approach achieves approximately 110x faster training on GPU.

It delivers near-optimal QoS in terms of end-to-end delay.

On-policy PPO outperforms off-policy DDPG when combined with CBF.

Abstract

Deep Reinforcement Learning (DRL) algorithms have recently made significant strides in improving network performance. Nonetheless, their practical use is still limited in the absence of safe exploration and safe decision-making. In the context of commercial solutions, reliable and safe-to-operate systems are of paramount importance. Taking this problem into account, we propose a safe learning-based load balancing algorithm for Software Defined-Wide Area Network (SD-WAN), which is empowered by Deep Reinforcement Learning (DRL) combined with a Control Barrier Function (CBF). It safely projects unsafe actions into feasible ones during both training and testing, and it guides learning towards safe policies. We successfully implemented the solution on GPU to accelerate training by approximately 110x times and achieve model updates for on-policy methods within a few seconds, making the solution practical. We show that our approach delivers near-optimal Quality-of-Service (QoS performance in terms of end-to-end delay while respecting safety requirements related to link capacity constraints. We also demonstrated that on-policy learning based on Proximal Policy Optimization (PPO) performs better than off-policy learning with Deep Deterministic Policy Gradient (DDPG) when both are combined with a CBF for safe load balancing.