by Wolfgang Wolker, Deutsche Telekom, and Angela Shen-Hsieh, Telefonica, project group co-chairs

Introducing the TIP AI and Applied Machine Learning Project Group

Today at the Telecom Infra Project (TIP) Summit, TIP announced the launch of the Artificial Intelligence (AI) and Applied Machine Learning (ML) Project Group, co-chaired by Deutsche Telekom and Telefonica.

The continuous increase in network size, traffic volume, service complexity, and customer expectations is compelling network operators to apply new approaches for network operations and customer assurance. In addition, the adoption of new over-the-top services, autonomous vehicles, drones, augmented reality (AR), virtual reality (VR) and more, will only increase the demands on operator networks.

In order to keep pace, network operators must supplement today’s human centric trouble-shooting and manual remediation methods with machine-based decision making and auto-remediation approaches to enable the accelerated deployment of new services while supporting hyper traffic growth at a lower cost structure.

The AI/ML group will apply artificial intelligence and machine learning to network planning, operations and customer behavior identification to optimize service experience and increase automation. Additionally, the group will leverage opportunities to optimize network operator and web-scale platform provider services to ensure the best end-to-end customer experience.

The objective of this project group is to define and share reusable, proven practices, models and technical requirements for applying AI and ML to reduce the cost of planning and operating telecommunications networks and to understand and leverage customer behavior, optimizing service quality for an improved experience.

The project group will collaborate across three work streams:

ML-based network operations, optimization, and planning

  • Define and validate ML-based monitoring and analysis methods for Predictive Maintenance to readily identify and predict faults before they adversely impact network performance or the customer experience.
  • Develop AI/ML methods to guide automated recovery processes and to reduce individual failures caused during the provisioning and activation phases.
  • Define and validate ML-based network optimization and management methods to enhance network utilization and customer satisfaction through dynamic resource allocation and proactive maintenance via autonomous scheduling and configuration. This will enable operators to analyze and optimize network traffic in real time.
  • Enable autonomous anomaly and fault detection to ready network operations for future demands including the expected large increase of managed Internet of Things (IoT) devices.

Customer behavior-driven service optimization

  • Predict customer behavior to help optimize the network for improved performance.
  • Project best outcomes in bandwidth-intensive, latency-sensitive, and/or data-heavy applications (e.g. virtual assistants, autonomous vehicles).
  • Provide a customer-centric approach that analyzes needs by customer segment.

Multi-vendor ML-AI data exchange formats

  • Select and adapt existing common data exchange formats that enable the network operations and customer behavior work streams.
  • Develop methods to minimize the handling and conversion of different vendor and network operator data formats.
  • Unify data model definition and the meaning of individual data attributes within the multi-vendor data exchange formats.

Project group kickoff

The TIP AI/ML group will hold a project kick off meeting at the TIP Summit on November 9th at the Santa Clara Convention Center in Santa Clara, California.

Organizations and individuals interested in joining TIP and the AI/ML Project Group can learn more and join here.