Towards Intelligent Load Balancing in Data Centers

Zhiyuan Yao (1, 2) , Yoann Desmouceaux (1) , Mark Townsley (1) , Thomas Heide Clausen (2)

1 Cisco Systems France
2 X - École polytechnique

Network load balancers are important components in data centers to provide scalable services. Workload distribution algorithms are based on heuristics, e.g., Equal-Cost Multi-Path (ECMP), Weighted-Cost Multi-Path (WCMP) or naive machine learning (ML) algorithms, e.g., ridge regression. Advanced ML-based approaches help achieve performance gain in different networking and system problems. However, it is challenging to apply ML algorithms on networking problems in real-life systems. It requires domain knowledge to collect features from low-latency, high-throughput, and scalable networking systems, which are dynamic and heterogenous. This paper proposes Aquarius to bridge the gap between ML and networking systems and demonstrates its usage in the context of network load balancers. This paper demonstrates its ability of conducting both offline data analysis and online model deployment in realistic systems. The results show that the ML model trained and deployed using Aquarius improves load balancing performance yet they also reveals more challenges to be resolved to apply ML for networking systems.

Domaines: Réseaux et télécommunications [cs.NI]; Intelligence artificielle [cs.AI]

Zhiyuan Yao, Yoann Desmouceaux, Mark Townsley, Thomas Heide Clausen. Towards Intelligent Load Balancing in Data Centers. 5th Workshop on Machine Learning for Systems at 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Dec 2021, Sydney, Australia. ⟨hal-03405812⟩