Scholarlink

<p>Next-generation wireless networks need to meet increasingly strict performance requirements across a&#xa0;wide range of use cases, from ultra-reliable industrial automation to high-bandwidth consumer services. Common static rule-based network configuration has reached its peak, and now cellular deployments require continuous optimization based on current network data, e.g., cell load. Traditional data gathering techniques, e.g., drive testing, often prove expensive and insufficient due to limited spatial and temporal coverage.</p><p>The Minimization of Drive Tests (MDT) standard addresses these challenges by gathering data directly from user equipment (UE) under real operational conditions, resulting in large-scale, high-fidelity datasets. This paper examines how to leverage MDT data in conjunction with artificial intelligence (AI) for real-time analysis, dynamic optimization, and predictive decision-making in advanced radio access networks. We show that combining AI-driven analytics with both immediate and logged MDT measurements offers effective modelling of user mobility, interference patterns, and coverage quality, enabling proactive resource allocation and faster issue resolution. By integrating these methods into digital twin frameworks, operators can test and refine network configurations in a&#xa0;virtual setting before implementing them in live environments. We highlight the growing significance of AI in telecommunication systems, positioning MDT as a&#xa0;key enabler of self-optimizing, next-generation network architectures.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Auf dem Weg zum KI-gestützten Mobilfunknetz: die Rolle von MDT-Daten zur Echtzeitoptimierung

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月5日

查看全文
  • Wilfried Wiedner,
  • Lukas Eller,
  • Mariam Mussbah,
  • Philipp Svoboda

摘要

Next-generation wireless networks need to meet increasingly strict performance requirements across a wide range of use cases, from ultra-reliable industrial automation to high-bandwidth consumer services. Common static rule-based network configuration has reached its peak, and now cellular deployments require continuous optimization based on current network data, e.g., cell load. Traditional data gathering techniques, e.g., drive testing, often prove expensive and insufficient due to limited spatial and temporal coverage.

The Minimization of Drive Tests (MDT) standard addresses these challenges by gathering data directly from user equipment (UE) under real operational conditions, resulting in large-scale, high-fidelity datasets. This paper examines how to leverage MDT data in conjunction with artificial intelligence (AI) for real-time analysis, dynamic optimization, and predictive decision-making in advanced radio access networks. We show that combining AI-driven analytics with both immediate and logged MDT measurements offers effective modelling of user mobility, interference patterns, and coverage quality, enabling proactive resource allocation and faster issue resolution. By integrating these methods into digital twin frameworks, operators can test and refine network configurations in a virtual setting before implementing them in live environments. We highlight the growing significance of AI in telecommunication systems, positioning MDT as a key enabler of self-optimizing, next-generation network architectures.