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

RAN! Reinforcing Autonomous Networks: AI-empowered digital twin for optimization

URN C24.5.728
Topics 5G, AI (Artificial Intelligence), Digital twin
Finalist

Creating the future of mobile network optimization.

This project uses innovative technologies such as high-fidelity digital twin simulation, a multi-modal parameter optimization agent, an intelligent beam optimization algorithm, and a realistic network simulation algorithm to enhance wireless network performance, user experience, and operational efficiency while reducing costs and risks. Key innovations include: 1. High-Fidelity Digital Twin Simulation: Accurately maps real-time network performance to predict future network states and performance trends. 2. Multi-Modal Parameter Optimization Agent: Integrates heterogeneous data to optimize network parameters in real-time. 3. MAMO-RL Beam Optimization: Dynamically adjusts 5G beam direction using reinforcement learning for improved coverage and traffic distribution. 4. PCI MOD90 Simulation Optimization: Minimizes interference through advanced modeling and optimization algorithms. The project will significantly improve network performance, user satisfaction, and O&M efficiency, providing a valuable reference for future network development.

Resources

BACKGROUND The explosion of smartphones and HD apps has digitized everyone's way of life and business, leading to an incessant need for CSPs to improve their customer experience and offer the best 360-degree connectivity at all times. To capture this expanding usage opportunity, CSPs have ended up building a complex network that requires continuous fine-tuning of complicated Radio Frequency (RF) parameters (X,000+). Even with the best optimization engineers available and significant OPEX spent on drive testing, by the end of 2022, Ookla still hadn't graded any 5G network as "Outstanding". With the rapid development of the mobile network, all CSPs are calling for an intelligent and efficient way to optimize mobile networks. Furthermore, 5G is also widely applied in vertical industries, such as enabling remote mining and transmitting automotive data. These scenarios have even higher requirements for network speed, latency, and stability. In summary, ensuring a good 5G network experience and Service Level Agreement is key to leveraging the advantages of 5G networks and is also a necessary condition for the healthy development of 5G industry. CHALLENGE The various factors influencing the loss during radio wave transmission and the continuous dynamic changes in the physical environment make accurate signal coverage restoration and network optimization complex. The advent of 5G and Massive MIMO technology — which enables a single antenna to transmit and receive signals in multiple directions simultaneously, like multiple beams of light — further increases complexity, especially during interference optimization. Issues include: (1) Mutual restraint between objectives: Enhancing signal coverage often inadvertently exacerbates interference issues; improving wireless interface performance may encounter difficulties due to insufficient physical resources. (2) "Mutual interference" between base stations: Efforts to enhance the performance of one base station may come at the expense of the performance of surrounding base stations, resulting in no overall improvement or imbalance. (3) Complexity of parameter configuration: A single base station involves hundreds of parameter settings. As the number of 2 of 13 base stations increases, the possibilities for parameter combinations grow exponentially, making the selection of the best configuration scheme an extremely complex task. (4) Necessity of repeated debugging and drive testing: After each parameter adjustment, multiple iterations of optimization through field driving tests are required. This process not only consumes significant funds and time but also increases carbon emissions from vehicles. In summary, 5G network optimization, particularly with advanced antenna technology, is highly complex and demands significant resources. SOLUTION 1. Mobile Network Optimization: SRCON (Simulated Reality of Communication Networks) technology tackles interference optimization (PCI) in mobile networks. It features: (1) Real Signal Coverage Restoration using AI-supported Digital Twin Modelling for high-accuracy coverage estimation; (2) Intelligent Solution Optimization using Graph Partitioning and Colouring Techniques, simplifying network resource reuse. 2. Fast Recovery: ensures 5G CSR uplink restoration via spare ports, triggered by link alarms with pre/post-checking. 3. We've abstracted an industry-applicable solution architecture for AN scenarios, end-to-end.

01 - Summary

Arena Presentation

02 - Storyline and Overall Presentation

Judging Presentation

DEMO

03 - Outcomes

Business Impact

Contact team

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

Name
Email

Team members

China Mobile Communications Corporation logo
Champion
China Telecommunications Corporation logo
Champion
Huawei Technologies Co. Ltd logo
OSSEra logo
Primforce Technologies Ltd. logo
PT Telekomunikasi Selular logo
Champion

Related projects