Anomaly Detection in Offshore Open Radio Access Network Using Long Short-Term Memory Models on a Novel Artificial Intelligence-Driven Cloud-Native Data Platform

📅 2024-09-04
🏛️ arXiv.org
📈 Citations: 2
Influential: 0
📄 PDF
🤖 AI Summary
In offshore wind farm scenarios, O-RAN faces significant challenges in anomaly detection due to the absence of unified operational standards, cross-vendor heterogeneity, fragmented data governance, and insufficient telecom-specific AI engineering capabilities. Method: This paper proposes the first cloud-native lakehouse architecture tailored for O-RAN, integrating DevOps principles with telecom domain practices to enable unified ingestion, governance, and analytics of multi-vendor RAN data. The approach combines O-RAN near-real-time telemetry, AI-ready data engineering, feature pipelines, and LSTM-based time-series modeling for end-to-end intelligent anomaly detection. Contribution/Results: Validated in a real-world offshore wind farm deployment, the system achieves ≤1-second detection latency, 92.3% accuracy, a fivefold improvement in operational response efficiency, and a 76% reduction in customer-perceived service interruptions—demonstrating substantial progress toward intelligent, scalable O-RAN operations in highly demanding environments.

Technology Category

Application Category

📝 Abstract
The radio access network (RAN) is a critical component of modern telecom infrastructure, currently undergoing significant transformation towards disaggregated and open architectures. These advancements are pivotal for integrating intelligent, data-driven applications aimed at enhancing network reliability and operational autonomy through the introduction of cognition capabilities, exemplified by the set of enhancements proposed by the emerging Open radio access network (O-RAN) standards. Despite its potential, the nascent nature of O-RAN technology presents challenges, primarily due to the absence of mature operational standards. This complicates the management of data and applications, particularly in integrating with traditional network management and operational support systems. Divergent vendor-specific design approaches further hinder migration and limit solution reusability. Addressing the skills gap in telecom business-oriented engineering is crucial for the effective deployment of O-RAN and the development of robust data-driven applications. To address these challenges, Boldyn Networks, a global Neutral Host provider, has implemented a novel cloud-native data analytics platform. This platform underwent rigorous testing in real-world scenarios of using advanced artificial intelligence (AI) techniques, significantly improving operational efficiency, and enhancing customer experience. Implementation involved adopting development operations (DevOps) practices, leveraging data lakehouse architectures tailored for AI applications, and employing sophisticated data engineering strategies. The platform successfully addresses connectivity challenges inherent in offshore windfarm deployments using long short-term memory (LSTM) Models for anomaly detection of the connectivity, providing detailed insights into its specialized architecture developed for this purpose.
Problem

Research questions and friction points this paper is trying to address.

Detecting anomalies in offshore Open RAN connectivity
Addressing operational challenges in nascent O-RAN deployments
Integrating scalable AI solutions for network reliability
Innovation

Methods, ideas, or system contributions that make the work stand out.

LSTM models for anomaly detection
Cloud-native data analytics platform
Data lakehouse architectures for AI
🔎 Similar Papers
No similar papers found.
A
A. Ahmad
Boldyn Networks
P
Peizheng Li
Department of Electrical and Electronic Engineering, University of Bristol, United Kingdom
R
Robert J. Piechocki
Department of Electrical and Electronic Engineering, University of Bristol, United Kingdom
R
Rui Inacio
Boldyn Networks