Granted Patent B2

US 12,470,938 · App. 19/088,344 · Granted Nov 11, 2025

Inventor: Armando Montalvo (Winter Garden, FL)

Assignee: Digital Global Systems, Inc.

H04W16/10H04W16/14H04W24/02H04W24/04H04W24/08H04W28/0925H04W28/0967H04W72/0453

Abstract

Claims (38)

1 . A system for dynamic spectrum management in an electromagnetic environment comprising:

at least one sensor configured to create measured data from the electromagnetic environment;

a Multi-Access Edge Computing (MEC) layer in a network slice; and

a wireless network resource optimization application in the MEC layer configured to receive the measured data from the at least one sensor;

wherein the measured data is represented as a vector ensemble class for each signal in the electromagnetic environment;

wherein the MEC layer is part of a virtualized infrastructure;

a data analysis engine configured to identify information in the measured data relevant to customer goals for a customer application to create analyzed data;

a machine learning (ML) engine programmed according to the customer goals for a customer application, wherein the ML engine is configured to make predictions about the electromagnetic environment using the analyzed data;

wherein the wireless network resource optimization application is configured to use the measured data, the analyzed data, and the predictions about the electromagnetic environment from the ML engine to create actionable data for optimizing network resources in the electromagnetic environment.

2 . The system of claim 1 , wherein the MEC layer is reconfigured through a management and orchestration (MANO) module based on the actionable data.

3 . The system of claim 1 , wherein the wireless network resource optimization application is run in the MEC layer as a third-party function.

4 . The system of claim 1 , wherein the at least one sensor includes at least one software defined radio.

5 . The system of claim 1 , wherein a MEC host for the MEC layer is deployed at an edge of a radio access network (RAN).

6 . The system of claim 5 , wherein the RAN includes a real-time control loop for components of the RAN, wherein actions in the real-time control loop occur in less than 10 milliseconds.

7 . The system of claim 5 , wherein the RAN includes a near real-time RAN intelligent controller (near-RT RIC) configured to provide control or optimization of RAN components and resources.

8 . The system of claim 7 , wherein the near-RT RIC includes an xApp, wherein the xApp is independent of the near-RT RIC.

9 . The system of claim 1 , wherein the MEC layer includes a plurality of applications, wherein the plurality of applications are configured to provide streaming services, gaming services, Internet of Things (IoT) services, and vehicle-to-everything (V2X) communications.

10 . The system of claim 1 , further comprising a slice manager configured to provide a real-time feedback control loop for the network slice.

11 . The system of claim 10 , wherein the slice manager is connected to virtual network functions (VNFs) operable to provide slice-level management support.

12 . A system for dynamic spectrum management in an electromagnetic environment comprising:

at least one sensor configured to create measured data from the electromagnetic environment;

a Multi-Access Edge Computing (MEC) layer; and

a wireless network resource optimization application in the MEC layer;

wherein the measured data is represented as a vector ensemble class for each signal in the electromagnetic environment;

a data analysis engine configured to identify information in the measured data relevant to customer goals for a customer application to create analyzed data;

a machine learning (ML) engine programmed according to the customer goals for a customer application, wherein the ML engine is configured to make predictions about the electromagnetic environment using the analyzed data;

wherein the wireless network resource optimization application is configured to use the measured data, the analyzed data, and the predictions about the electromagnetic environment from the ML engine to create actionable data for optimizing network resources in the electromagnetic environment.

13 . The system of claim 12 , wherein the wireless network resource optimization application allows the MEC layer to generate radio access network (RAN) commands to change appropriate RAN parameters based on the actionable data.

14 . The system of claim 12 , wherein the analyzed data includes data relating to detection or analysis of an anomalous signal.

15 . A method for dynamic spectrum management in an electromagnetic environment comprising:

at least one sensor creating measured data from the electromagnetic environment;

a wireless network resource optimization application in a Multi-Access Edge Computing (MEC) layer receiving the measured data from the at least one sensor; and

wherein the measured data is represented as a vector ensemble class for each signal in the electromagnetic environment;

a data analysis engine identifying information in the measured data relevant to customer goals for a customer application to create analyzed data;

a machine learning (ML) engine programmed according to the customer goals for a customer application, making predictions about the electromagnetic environment using the analyzed data; and

the wireless network resource optimization application using the measured data, the analyzed data, and the predictions about the electromagnetic environment from the ML engine to create actionable data for optimizing network resources in the electromagnetic environment.

16 . The method of claim 15 , further comprising a management and orchestration (MANO) module reconfiguring the MEC layer based on the actionable data provided by the wireless network resource optimization application.

17 . The method of claim 15 , wherein the wireless network resource optimization application allows the MEC layer to generate radio access network (RAN) commands to change appropriate RAN parameters based on the actionable data.

Assignments (1)

Continuity (13)

References Cited (264)