Granted Patent B2

US 12,627,991 · App. 19/324,920 · Granted May 12, 2026

Inventor: Armando Montalvo (Winter Garden, FL)

Assignee: Digital Global Systems, Inc.

H04W16/10H04W24/02H04W24/08H04W24/10H04W28/24H04W16/14H04W24/04H04W28/0268

Abstract

Claims (48)

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

a Mult-Access Edge Computing (MEC) layer in a wireless network;

at least one data analysis engine in the MEC layer configured to analyze detected signal information from the electromagnetic environment to create measured data;

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

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

a wireless network resource optimization application in the MEC layer; and

a machine learning (ML) engine in the MEC layer programmed according to the customer goals;

wherein the ML engine is configured to use the analyzed data to make predictions about the electromagnetic environment based on the customer goals and the measured data; and

wherein the wireless network resource optimization application is configured to combine the vector ensemble class for each signal in the electromagnetic environment with a customer goals index vector of binary values to create actionable data;

wherein each binary value of the customer goals index vector represents whether or not a specific piece of the detected signal information is relevant to satisfying the customer goals;

wherein the wireless network resource optimization application is configured to analyze each signal in the electromagnetic environment for possible interactions based on center frequency and a combination of bandwidth and an upper and lower frequency component, and utilize the actionable data, the possible interactions, and the predictions about the electromagnetic environment to optimize network resources of a wireless network for the customer application based on environmental conditions.

2 . The system of claim 1 , wherein the wireless network resource optimization application is configured to further optimize the network resources by reconfiguring the MEC layer associated with a network slice or a subnetwork.

3 . The system of claim 1 , wherein the MEC layer is configured to provide a recommendation for optimization of physical layer resources for the customer application.

4 . The system of claim 1 , wherein the system is configured to perform network slicing to create a network slice.

5 . The system of claim 1 , wherein the wireless network resource optimization application utilizes a constraint vector.

6 . The system of claim 1 , wherein the network resources include physical layer resources.

7 . The system of claim 1 , wherein the network resources include resource blocks, modulation parameters, and/or the bandwidth.

8 . The system of claim 1 , wherein the system includes a MEC host deployed at an edge of a radio access network (RAN).

9 . A system for spectrum utilization management in an electromagnetic environment comprising:

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

a wireless network resource optimization application in the MEC layer including at least one data analysis engine for analyzing detected signal information from a radiofrequency (RF) environment to create measured data; and

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

wherein the data analysis engine is 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 in the MEC layer programmed according to the customer goals;

wherein the detected signal information includes a center frequency, bandwidth, upper frequency component, and lower frequency component of at least one signal in the RF environment;

wherein the at least one data analysis engine is configured to analyze each signal in the RF environment to obtain statistical information and analyze possible interactions based on the center frequency, bandwidth, upper frequency component, and lower frequency component to create analyzed data;

wherein the ML engine is configured to use the analyzed data to make predictions about the RF environment based on the customer goals and the measured data;

wherein the wireless network resource optimization application is configured to combine the vector ensemble class for each signal in the RF environment with a customer goals index vector of binary values to create actionable data;

wherein each binary value of the customer goals index vector represents whether or not a specific piece of the detected signal information is relevant to satisfying the customer goals;

wherein the wireless network resource optimization application is configured to utilize the actionable data, the possible interactions, and predictions about the RF environment to optimize network resources of a wireless network for the customer application based on environmental conditions.

10 . The system of claim 9 , wherein the wireless network resource optimization application is configured to optimize network resources of a wireless network by reconfiguring the MEC layer associated with a network slice or a subnetwork.

11 . The system of claim 9 , wherein the MEC layer is configured to provide a recommendation for optimization of physical layer resources for the customer application.

12 . A method for spectrum utilization management in an electromagnetic environment comprising:

at least one data analysis engine analyzing detected signal information from the electromagnetic environment to create measured data;

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

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

at least one machine learning (ML) engine programmed according to the customer goals and making predictions about the electromagnetic environment based on the customer goals and the measured data;

a wireless network resource optimization application analyzing each signal in the electromagnetic environment for possible interactions based on center frequency, and a combination of bandwidth and an upper and lower frequency component; and

the wireless network resource optimization application combining the vector ensemble class for each signal in the electromagnetic environment with a customer goals index vector of binary values to create actionable data;

wherein each binary value of the customer goals index vector represents whether or not a specific piece of the detected signal information is relevant to satisfying the customer goals;

the wireless network resource optimization application utilizing the actionable data, the possible interactions, and the predictions about the electromagnetic environment to optimize network resources of a wireless network for the customer application based on environmental conditions;

wherein the at least one data analysis engine, the ML engine, and the wireless network resource optimization application are in a Multi-Access Edge Computing (MEC) layer of a wireless network.

13 . The method of claim 12 , wherein the wireless network resource optimization application is configured to further optimize the network resources by reconfiguring the MEC layer associated with a network slice or a subnetwork.

14 . The method of claim 12 , further comprising the MEC layer providing a recommendation for optimizing physical layer resources for the customer application based on environmental conditions.

15 . The method of claim 12 , wherein the wireless network resource optimization application utilizes a constraint vector.

16 . The method of claim 12 , further comprising a MEC host deployed at an edge of a radio access network (RAN).

17 . The method of claim 12 , wherein the MEC layer creates a network slice.

18 . The method of claim 17 , further comprising performing network slicing to create the network slice.

Assignments (1)

Continuity (12)

References Cited (289)