Search

EP-4738773-A1 - TECHNIQUES TO OPERATE BASE STATIONS

EP4738773A1EP 4738773 A1EP4738773 A1EP 4738773A1EP-4738773-A1

Abstract

A method for manufacturer-independent configuration of a base station (BTS) in a mobile network, comprising the steps of: • Receiving network specifications in the form of NBX data, • Processing the NBX data by a Cognitive Model Configurator (KMK) module, • Generating manufacturer-specific SBX data by the KMK module using a trained artificial intelligence, • Transmitting the SBX data via an SBI interface to the BTS for configuration and control.

Inventors

  • PAPASTERGIOU, KONSTANTINOS
  • KOCH, KARL
  • FIEDLER, MARC

Assignees

  • Deutsche Telekom AG

Dates

Publication Date
20260506
Application Date
20241029

Claims (15)

  1. A Cognitive Model Configurator module (200), KMK module, configured to transform network specifications in the form of NBX data into manufacturer-specific SBX data using artificial intelligence, AI, specifically trained for the respective base station, BTS, wherein the SBX data is suitable for operating the respective BTS of a manufacturer.
  2. The KMK module according to claim 1, wherein the artificial intelligence of the KMK module is trained using reinforcement learning models, where historical NBX and SBX data from previous configuration data are used to generate SBX data.
  3. The KMK module according to claim 1 or 2, wherein the KMK module is configured to perform security-relevant checks on the generated SBX data and/or verify their compliance with security policies and/or operational policy requirements of the mobile network operator.
  4. A RAN controller for controlling and/or configuring base stations (BTS) in a mobile network, comprising: • a KMK module (200) according to any of the preceding claims, • a SBI interface (210) configured to transmit commands and manufacturer-specific SBX data to the BTS and/or receive feedback from the BTS, • wherein the RAN controller (120) is configured to transmit manufacturer-specific SBX data to the BTS for configuration and control of the BTS via the SBI interface (210).
  5. The RAN controller according to claim 4, further comprising a REST interface (400) for communication with at least one Network Management System (NMS), where the NMS transmits configurable operational data for controlling and monitoring the BTS to the RAN controller via the REST interface.
  6. The RAN controller according to claim 4 or 5, further comprising an interface for communication with a manufacturer's Element Manager, wherein the Element Manager is used to validate the SBX data generated by the KMK module without exerting direct control over the BTS.
  7. The RAN controller according to any of claims 4 to 6, wherein the RAN controller is configured to modify the manufacturer-specific SBX data transmitted to the BTS based on validation results provided by the manufacturer's Element Manager.
  8. The RAN controller according to any of claims 4 to 7, wherein the RAN controller includes multiple artificial intelligences, each trained for different types of BTS to generate SBX data for various BTS from different manufacturers.
  9. A control system (100) of a mobile network operator for operating a base station BTS, comprising: • at least one BTS (110) configured to provide mobile services and communicate with the RAN controller via an SBI interface to receive manufacturer-specific SBX data and commands, • a Network Management System (130), NMS, configured to monitor and/or control the operation of the BTS, where the NMS is connected to the RAN controller via a interface and transmits configurable operational data for controlling and monitoring the BTS to the RAN controller, • a RAN controller according to any of claims 4 to 8, wherein the RAN controller is configured to: ∘ generate manufacturer-specific SBX data and transmit them to the BTS via the SBI interface, ∘ receive operational data from the NMS via the interface, ∘ modify the SBX data based on the operational data provided by the NMS, wherein the RAN controller, the NMS, and the BTS are communicatively connected to ensure that the BTS is controlled based on the data provided by the NMS, and the RAN controller manages the operational states of the BTS by receiving and processing NBX data and generating SBX data.
  10. The control system according to claim 9, further comprising a manufacturer's Element Manager to assist the RAN controller in validating SBX data.
  11. A method for manufacturer-independent configuration of a base station (BTS) in a mobile network, comprising the steps of: • Receiving network specifications in the form of NBX data, • Processing the NBX data by a Cognitive Model Configurator (KMK) module, • Generating manufacturer-specific SBX data by the KMK module using a trained artificial intelligence, • Transmitting the SBX data via an SBI interface to the BTS for configuration and control.
  12. The method according to claim 11, further comprising the step of transmitting configuration data from a Network Management System (NMS) or from multiple NMS systems to the RAN controller via a REST interface, where the RAN controller is configured to transform the transmitted configuration data into SBX data for the BTS.
  13. The method according to any of claims 11 or 12, further comprising the step of the NMS operating or controlling the BTS by transmitting configurable operational data to the BTS via the RAN controller.
  14. The method according to any of claims 11 to 13, further comprising the step of simultaneously configuring multiple BTS by the RAN controller, where each BTS is configured with specific SBX data generated by different artificial intelligences trained for the respective BTS.
  15. The method according to claim 14, further comprising the step of storing a previous operational state of the BTS, allowing the configuration to be rolled back to a previous state if necessary.

Description

The present invention relates to a control system for manufacturer-independent control and configuration of base stations (BTS) in mobile networks. The control system enables operators to control and monitor BTS across different manufacturers, improving flexibility and network security. The national mobile network of German mobile operators consists to a significant extent of base stations from various manufacturers, where the base stations can currently only be operated using a proprietary (closed-source) Element Manager (EM) provided by the manufacturer. As a result, security risks, data security issues, and/or functional problems can arise for the network operator if the Element Manager is prompted to make uncontrolled changes to the base station. Third system have so far been very limited to interact with the BTS without using the Element Manager (EM). Using this proprietary protocol, so-called man-machine language (MML) commands are sent to the BTS to trigger actions (software updates, resets, etc.) and configure the BTS. An operational state (B) of a BTS is defined by several hundred parameter values in a data model (D). To transition the BTS from a current operational state (BA) to a valid operational state (BB), extensive knowledge of the valid operational states and the necessary actions (configuration, commands) is required, taking into account the various BTS types. In current technology, base stations in mobile networks are typically controlled using manufacturer-specific Element Managers (EM). These EMs utilize proprietary protocols and configuration data, which restricts network operators from managing base stations in a cross-manufacturer and independent manner. This dependence on proprietary systems limits operational flexibility and introduces potential security risks, as manufacturer-specific vulnerabilities or proprietary accesses may not be fully under the operator's control. The problem with existing systems is that network operators are tied to manufacturer-specific Element Managers, leading to a lack of flexibility and increased security risks. Hence, it is the task of the invention to provide techniques that enable independent control of base stations from various manufacturers without relying on proprietary EMs. This object is solved by the features of the independent claims. The features of the various aspects of the invention described below or the various examples of implementation may be combined with each other, unless this is explicitly excluded or is technically impossible. Furthermore, the terms first, second, third and the like in the description and in the claims are used for distinguishing between similar elements and not necessarily for describing a sequential or chronological order. It is to be understood that the terms so used are inter- changeable under appropriate circumstances and that the embodiments of the invention described herein are capable of operation in other sequences than described or illustrated herein. According to a first aspect of the invention, a Cognitive Model Configurator (KMK) module is configured to transform network specifications in the form of NBX data into manufacturer-specific SBX data using artificial intelligence (AI) specifically trained for the respective base station (BTS), wherein the SBX data is suitable for operating the respective BTS of a manufacturer. Term Cognitive Model Configurator module can be abbreviated as KMK module (where KMK stands for Kognitive Model Konfigurator). This abbreviation is based on the initial letters of the key words in the term. It can also be referred to simply as CMC module (Cognitive Model Configurator) if its English origin shall be emphasized. The technical effect of this invention is that the KMK module, through the use of AI, can generate manufacturer-specific SBX data independently of proprietary EMs, enabling independence from specific manufacturers. The advantage lies in the flexibility to control BTS from different manufacturers using a centralized system, thereby minimizing security risks associated with proprietary systems. In one embodiment, the artificial intelligence of the KMK module is trained using reinforcement learning models (RLM), where historical NBX and SBX data from previous configuration data are used to generate SBX data. As those SBX are generated very frequently based on NBX data by the respective element manager, there is already a sufficiently large databases to cover various situations and use cases that is necessary to efficiently train the artificial intelligence. Hence, SBX data is especially well suited for this use case. It is a further technical effect of this embodiment that this enables a continuous improvement of SBX data generation through machine learning. Actually, it is also possible to validate SBX data generated by the trained artificial intelligence with the corresponding SBX data generated by the element manager to improve the model of the artificial inte