catalysts logo

Gain access to resources and project updates

Register or log in to save your details for future use
First name
Last name
Business email
Company name
Job title

TM Forum will be processing the above information, with the assistance of our service providers located within and outside the European Union, to manage your registration to this event or report download, as well as to keep you informed about our services and products, future events and special offers, the organization of events, providing training and certification, and facilitating collaboration programs. Privacy policy

I wish to receive further information from the Catalyst Team about their products and service by electronic means. Check the "Team Members" section of this Catalyst Project to review the companies that will receive your information. Companies may join the project in the future, so please check back periodically for any updates

logologo
All projects

AI-ML Smart Network CapEx - Phase II

URN C25.0.768
Topics AI (Artificial Intelligence), Autonomous networks, Sustainability

Smart CapEx, using AI/ML to automate and optimize access and transport rollouts unlocking 15-25% CapEx efficiency gains while maintaining CX

featured image
As networks grow in scale and complexity, CSPs face the challenge of forecasting traffic accurately and planning infrastructure investments efficiently. They need to accurate forecasts to align rollout strategies with real demand. This Catalyst expands the proven smart CapEx model—developed for the radio access network in Phase I—into transport and core networks. Unlike access networks, transport and core layers require different CapEx planning rules. Access connects end devices to local nodes, while transport and core span wide areas, linking nodes for high-capacity data transfer. This Catalyst uses AI and machine learning in a cloud-based big data environment to meet these planning needs. The solution introduces a practical interface where marketing teams share traffic forecasts with network teams. It ingests commercial projections from marketing, and maps them to street-level geographies. It then applies spatio-temporal forecasting to predict traffic growth across time and location. The platform uses constraint-based optimisation to simulate rollout scenarios, balancing investment cost, infrastructure capacity, and quality of experience metrics. For transport and core networks, it applies graph-based algorithms and network simulation models to design efficient, scalable backhaul and core configurations. Results are visualized via a GIS dashboard, enabling data-driven CapEx planning aligned with demand and customer impact. The expected business impact includes 15–25% savings on CapEx and OpEx for new infrastructure, and significant efficiency gains across existing assets, as well improvement in energy efficiency. These savings come from optimized investments, fewer manual decisions, and faster deployment cycles. The real test is in the match between forecast and reality. When traffic predictions align with live network demand, CSPs unlock smarter investments, faster rollouts, and better service outcomes. This Catalyst will demonstrate that with the right data and AI, CapEx planning becomes a strategic advantage—not just a budgeting exercise.

Resources

Explore the previous phases of this project

AI Smart CapEx for green and efficient network investments

Contact team

Email the members of the Catalyst team to request more details.

Name
Email

Team members

EITC  (DU) logo
Champion
Iquall Networks Inc logo
Locatium.AI logo
Minsait Brasil LTDA logo
Ooredoo Group logo
Champion
Safaricom PLC logo
Champion
TELEFONICA logo
Champion

Related projects