Using Counterfactuals to Proactively Solve Service Level Agreement Violations in 5G Networks

Terra, Ahmad; Inam, Rafia; Batista, Paula; Fersman, Elena

doi:10.1109/indin51773.2022.9976075

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This makes counterfactual examples more human-interpretable than other explanation methods. CFML has been applied by researchers as an optimization technique for wireless power control [14], agreement violations [15] and cellular responses [16].…”

Section: A Motivation and Research Problemsmentioning

confidence: 99%

Cellular Operator Data Meets Counterfactual Machine Learning

Kala,

Mishra,

Sathya

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Unlicensed cellular networks and spectrum-sharing standards assist operators in meeting the ever-increasing demand for mobile data. However, several incumbents are already operational in these frequencies, rendering the wireless environment extremely dynamic and unpredictable. The challenges associated with unlicensed Licensed Assisted Access (LAA) operations in the 5 GHz band and New Radio in Unlicensed (NR-U) in the 6 GHz band are best addressed through a data-driven approach. This requires operator data from current cellular deployments. Further, from an operator's perspective, the precision and reliability of predictive models must be analyzed before deployment. Counterfactual machine learning is ideal for quantifying causal impact in a dynamic, unlicensed cellular environment. However, the literature lacks a framework that combines data-driven solutions, counterfactual analysis, and conventional optimization. This work contributes a dataset from the LAA networks of three major cellular operators in Chicago consisting of 15 features and 9676 samples. Additionally, it proposes a framework for analyzing the performance of unlicensed networks that leverages machine learning for predictive modeling, employs counterfactual analysis for model explainability and network performance enhancement, and utilizes optimization for validation. We show that operator data is necessary to build reliable prediction models for network throughput, signal strength, etc. Further, the impact of network parameters is shown to differ in unlicensed and licensed cellular network models. Next, a counterfactual machine learning framework is proposed to explain and analyze the predictive models. The framework proposes counterfactual policies to enhance unlicensed cellular network performance. Finally, we validate the suggested counterfactual policies through joint network optimization.

show abstract

Section: A Motivation and Research Problemsmentioning

confidence: 99%

Cellular Operator Data Meets Counterfactual Machine Learning

Kala,

Mishra,

Sathya

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In crossdomain and multi-stakeholder scenarios, as the representative one under 5G marketplaces, Service Level Agreements (SLAs) need to be signed in order to legalize settlements among stakeholders. As a result of such agreements, multiple tasks are initialized across domains to monitor the Service Level Indicators (SLIs), forecast possible breach predictions, and identify SLA violations [10], to name but a few. In this sense, events generated during the whole SLA life-cycle management, for instance, breach predictions, breach detections, and SLA violations, are really meaningful for updating a previously computed trust score.…”

Section: Introductionmentioning

confidence: 99%

SLA-Driven Trust and Reputation Management Framework for 5G Distributed Service Marketplaces

Valero

Theodorou

Pérez

et al. 2024

IEEE Trans. Dependable and Secure Comput.

View full text Add to dashboard Cite

The fifth generation (5G) of mobile telecommunications is characterized by massive growth in the number of stakeholders, interconnected devices, and available services distributed under different administrative domains. Distributed marketplaces aim at facilitating stakeholders in the quest and hiring of third party resources and services. Establishing trustworthiness in such an open ecosystem is a cornerstone for the final deployment of these marketplaces in 5G networks and beyond. Hence, building trust management systems that ensure the selection of reliable parties or assets in 5G distributed marketplaces is essential. Thus, a reputation-based trust management framework is proposed to analyze stakeholder behavior patterns and predict trust scores to establish trustworthy relationships across domains. Furthermore, an Service Level Agreement (SLA)-driven reward and punishment mechanism is designed and developed on top of the reputationbased trust framework. Such a mechanism enables continuously adapting trust scores by gathering breach predictions, breach detections, and SLA violations in real time. Furthermore, an edgebased use case is presented to contextualize our reputation-based framework in a tangible enforcement scenario. In conclusion, three experiments were conducted on real-life testbeds demonstrating that our framework fairly distinguishes bad-mouthing attacks with 67% accuracy, when 50% recommenders are corrupted, and is resilient to continuous misbehavior bursts.

show abstract

Using Counterfactuals to Proactively Solve Service Level Agreement Violations in 5G Networks

Cited by 2 publications

References 12 publications

Cellular Operator Data Meets Counterfactual Machine Learning

Cellular Operator Data Meets Counterfactual Machine Learning

SLA-Driven Trust and Reputation Management Framework for 5G Distributed Service Marketplaces

Contact Info

Product

Resources

About