Is Machine Learning Ready for Traffic Engineering Optimization?

Bernárdez, Guillermo; Suárez-Varela, José; López, Albert València; Xiao, Shihan; Cheng, Xiangle; Barlet‐Ros, Pere; Cabellos‐Aparicio, Albert

doi:10.1109/icnp52444.2021.9651930

Cited by 42 publications

(42 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ryu et al [19] build a nearest neighbor graph to form homogeneity within the agent adjacencies. Similarly to our work, [15], [17] extract the agent embedding without modeling the system adjacencies directly. From an algorithmic perspective, [13], [16], [17] introduced attention mechanism in GNN for extracting agent state embedding.…”

Section: Related Workmentioning

confidence: 98%

A Graph Attention Learning Approach to Antenna Tilt Optimization

Jin¹,

Vannella²,

Bouton³

et al. 2021

Preprint

View full text Add to dashboard Cite

6G will move mobile networks towards increasing levels of complexity. To deal with this complexity, optimization of network parameters is key to ensure high performance and timely adaptivity to dynamic network environments. The optimization of the antenna tilt provides a practical and cost-efficient method to improve coverage and capacity in the network. Previous methods based on Reinforcement Learning (RL) have shown effectiveness for tilt optimization by learning adaptive policies outperforming traditional tilt optimization methods. However, most existing RL methods are based on single-cell features representation, which fails to fully characterize the agent state, resulting in suboptimal performance. Also, most of such methods lack scalability and generalization ability due to state-action explosion. In this paper, we propose a Graph Attention Q-learning (GAQ) algorithm for tilt optimization. GAQ relies on a graph attention mechanism to select relevant neighbors information, improving the agent state representation, and updates the tilt control policy based on a history of observations using a Deep Q-Network (DQN). We show that GAQ efficiently captures important network information and outperforms standard DQN with local information by a large margin. In addition, we demonstrate its ability to generalize to network deployments of different sizes and density.

show abstract

Section: Related Workmentioning

confidence: 98%

A Graph Attention Learning Approach to Antenna Tilt Optimization

Jin¹,

Vannella²,

Bouton³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Since communication networks are fundamentally represented as graphs, GNNs offer unique advantages for network modeling when compared to traditional NN architectures (e.g., multilayer perceptron, recurrent NN). In the last years, GNNs have demonstrated outstanding performance to solve a wide variety of network-related problems [2], [6], [10], [5], [11]. In this context, GNNs may be a central technology to enable the construction of ML-based network models that can generalize to different network topologies, configurations, and traffic distributions.…”

Section: A Leveraging Machine Learning To Build Ndtsmentioning

confidence: 99%

Network Digital Twin: Context, Enabling Technologies and Opportunities

Almasan,

Ferriol-Galmés,

Paillisse

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The proliferation of emergent network applications (e.g., telesurgery, metaverse) is increasing the difficulty of managing modern communication networks. These applications entail stringent network requirements (e.g., ultra-low deterministic latency), which hinders network operators to manage their resources efficiently. In this article, we introduce the network digital twin (NDT), a renovated concept of classical network modeling tools whose goal is to build accurate data-driven network models that can operate in real-time. We describe the general architecture of the NDT and argue that modern machine learning (ML) technologies enable building some of its core components. Then, we present a case study that leverages a ML-based NDT for network performance evaluation and apply it to routing optimization in a QoS-aware use case. Lastly, we describe some key open challenges and research opportunities yet to be explored to achieve effective deployment of NDTs in real-world networks.

show abstract

“…Moreover, RouteNet has shown its ability to precisely infer characteristics of input (e.g., topology) unseen in the training [8]. Especially, in [9], the authors have shown a novel integration of GNNs into a Deep Reinforcement Learning (DRL) framework to solve routing problems by which trained models are capable of inferring solutions for unseen testing topologies. Comprehensive machine learning approaches to graph combinatorial optimization problems, including GNN design for several algorithms are presented in [10].…”

Section: Related Workmentioning

confidence: 99%

Addressing RouteNet scalability through input and output design

Ziazet¹,

Boudreau²,

Jaumard³

et al. 2022

ITU J-FET

View full text Add to dashboard Cite

With recent advances in the field of Machine Learning (ML), a multitude of problems related to communication systems and networks can be solved with data-driven solutions. Since data in these systems is mostly represented as graphs, Graph-based Neural Networks (GNNs) are a good candidate for solving such problems. These GNNs can be used as a computer network modeling technique to build models that accurately estimate the Key Performance Indicators (KPI) such as delay or jitter in real network scenarios in order to ensure their requirements in terms of service assurance. To build GNN solutions with higher accuracy, low computational resource requirements, and easy deployment of synthetic network training results into real-world networks, it is more than necessary to develop efficient and effective GNN models. This paper presents a GNN model capable of accurately estimating the average delay per flow in networks. By designing scale-independent features and using notions from queuing theory, the proposed model successfully generalizes to large size topologies, routing configurations, and traffic matrices not seen during the training phase.

show abstract

Is Machine Learning Ready for Traffic Engineering Optimization?

Cited by 42 publications

References 41 publications

A Graph Attention Learning Approach to Antenna Tilt Optimization

A Graph Attention Learning Approach to Antenna Tilt Optimization

Network Digital Twin: Context, Enabling Technologies and Opportunities

Addressing RouteNet scalability through input and output design

Contact Info

Product

Resources

About