System, method, and apparatus for providing dynamic, prioritized spectrum management and utilization
Systems, methods, and apparatuses for providing dynamic, prioritized spectrum utilization management. The system includes at least one monitoring sensor, at least one data analysis engine, at least one application, a semantic engine, a programmable rules and policy editor, a tip and cue server, and/or a control panel. The tip and cue server is operable utilize the environmental awareness from the data processed by the at least one data analysis engine in combination with additional information to create actionable data.
1. A system for spectrum management in an electromagnetic environment comprising:
at least one monitoring sensor operable to monitor the electromagnetic environment and create measured data based on the electromagnetic environment; and
at least one data analysis engine for analyzing the measured data to create analyzed data; and
a geolocation engine operable to use artificial intelligence (AI) or machine learning (ML) geolocation techniques, including graphical comparison of precomputed results and the analyzed data, to determine an approximate location of at least one signal of interest; and
wherein the geolocation engine is operable to use a convolutional neural network (CNN) for the graphical comparison.
2. The system of claim 1 , wherein the at least one monitoring sensor includes at least one antenna, at least one antenna array, at least one radio server, and/or at least one software defined radio.
3. The system of claim 1 , wherein one or more of the at least one monitoring sensor is mounted on a drone, a vehicle, in or on a street light, in or on a traffic pole, and/or on top of a building.
4. The system of claim 1 , wherein one or more of the at least one monitoring sensor is integrated with at least one camera to capture video and/or still images.
5. The system of claim 1 , wherein the geolocation engine is operable to determine the approximate location of the at least one signal of interest based on an angle of arrival, a time difference of arrival, a frequency difference of arrival, and power distribution ratio measurements.
6. The system of claim 1 , wherein the geolocation engine is operable to use statistical approximations to remove error causes from noise, timing and power measurements, multipath, and non-line of sight (NLOS) measurements.
7. The system of claim 1 , wherein the geolocation engine includes passive methods of geolocation, wherein the passive methods of geolocation include single directional beam antenna response, multidirectional beam antenna response, multi-antenna element response, line of bearing (LOB)-to-position solutions, general optimization, phase interferometry, beamforming, conventional array manifold processing approaches, and/or high-resolution array manifold processing approaches using signals subspace, digital pre-distortion (DPD), convex programming, and/or distributed swarm approaches.
8. The system of claim 1 , wherein the graphical comparison uses the CNN to compare a precomputed cross ambiguity function (CAF) image to an image representation of the analyzed data.
9. The system of claim 1 , wherein the graphical comparison is performed between image or volumetric data representations of the possible outputs and the analyzed data.
10. The system of claim 9 , wherein the image or volumetric data representations are operable to be subdivided, downscaled, or downsampled before the graphical comparison.
11. A system for spectrum management in an electromagnetic environment comprising:
at least one monitoring sensor operable to create measured data based on the electromagnetic environment; and
at least one data analysis engine for analyzing the measured data;
a geolocation engine operable to use artificial intelligence (AI) or machine learning (ML) geolocation techniques, including graphical comparison of a precomputed correlation ambiguity function (CAF) and the analyzed data, to determine an approximate location of at least one signal of interest; and
wherein the graphical comparison includes a subdivision of at least one CAF image or volumetric data representing the at least one precomputed CAF.
12. The system of claim 11 , wherein the geolocation engine is operable to determine the approximate location of the at least one signal of interest based on an angle of arrival, a time difference of arrival, a frequency difference of arrival, and power distribution ratio measurements.
13. The system of claim 11 , wherein the geolocation engine is operable to use statistical approximations to remove error causes from noise, timing and power measurements, multipath, and non-line of sight (NLOS) measurements.
14. The system of claim 11 , wherein the geolocation engine is operable to provide for at least one passive method of geolocation, wherein the at least one passive method of geolocation includes single directional beam antenna response, multidirectional beam antenna response, multi-antenna element response, line of bearing (LOB)-to-position solutions, general optimization, phase interferometry, beamforming, conventional array manifold processing approaches, and/or high-resolution array manifold processing approaches using signals subspace, digital pre-distortion (DPD), convex programming, and/or distributed swarm approaches.
15. The system of claim 11 , wherein the graphical comparison is performed using a convolutional neural network (CNN), ML, AI, deep learning (DL), neural networks (NN), artificial neural networks (ANN), support vector machines (SVMs), and/or Markov decision process (MDP).
16. The system of claim 11 , wherein the graphical comparison is performed between image or volumetric data representations of the possible outputs and the analyzed data.
17. The system of claim 16 , wherein the image or volumetric data representations are operable to be downscaled or downsampled before the graphical comparison.
18. A method for spectrum management in an electromagnetic environment comprising:
creating measured data based on the electromagnetic environment using at least one monitoring sensor;
at least one data analysis engine analyzing the measured data to create analyzed data;
a geolocation engine using artificial intelligence (AI) or machine learning (ML) geolocation techniques, including graphical comparison of a precomputed correlation ambiguity function (CAF) and the analyzed data, to determine an approximate location of at least one signal of interest; and
creating actionable data for dynamic spectrum utilization based on the analyzed data from the at least one data analysis engine.
19. The method of claim 18 , wherein the graphical comparison is conducted between a two or three-dimensional map of possible outputs and the analyzed data using a convolutional neural network (CNN), ML, AI, deep learning (DL), neural networks (NN), artificial neural networks (ANN), support vector machines (SVMs), and/or Markov decision process (MDP).
20. The method of claim 19 , wherein the graphical comparison is performed between image or volumetric data representations of the possible outputs and the analyzed data.