US2023084905A1PendingUtilityA1

Autonomous cloud design and control

63
Assignee: AT & T IP I LPPriority: Aug 27, 2018Filed: Nov 22, 2022Published: Mar 16, 2023
Est. expiryAug 27, 2038(~12.1 yrs left)· nominal 20-yr term from priority
H04L 41/5025H04L 41/5054H04L 41/5096H04L 41/145H04L 41/0806G06T 19/006G06T 17/00
63
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

The autonomous cloud design system may determine a design that may appropriately mix emerging technologies and operations to provide a versatile and cost-effective or efficient solution for a given cloud site.

Claims

exact text as granted — not AI-modified
What is claimed: 
     
         1 . A method comprising:
 obtaining, by a processing system including a processor, a network design template;   obtaining, by the processing system, constraints for use in design of a network site for a network, wherein the network design template is provided by a template engine in communication with the processor, wherein the template engine obtains definitions of network faults and actions, the actions including a closed loop control procedure to resolve at least one of the network faults;   based on the network design template and design constraints, creating a plurality of candidate site designs;   selecting, by the processing system, a first site design in accordance with a cost criterion for a power cost to operate the network in accordance with the first site design;   sending, by the processing system, instructions to automatically implement the first site design by initiating an automated site build plan, the initiating based on a predetermined trigger, resulting in a first site;   monitoring, by the processing system, the first site to determine a first performance of the first site; and   automatically generating, by the processing system based on determining that the first performance of the first site is below a performance threshold, a second site design.   
     
     
         2 . The method of  claim 1 , wherein the design constraints comprise space constraints, power constraints, or a combination thereof. 
     
     
         3 . The method of  claim 1 , wherein the plurality of candidate site designs is created based on a machine learning cycle that optimizes design options used to create the plurality of candidate site designs. 
     
     
         4 . The method of  claim 3 , wherein the machine learning cycle improves creating the plurality of candidate site designs using previous site installation information and technology cost trend information. 
     
     
         5 . The method of  claim 1 , wherein the cost criterion comprises a threshold cost, wherein the threshold cost is a determined maximum power cost to operate the network in accordance with the first site design. 
     
     
         6 . The method of  claim 1 , further comprising determining, by the processing system, that the second site design provides a second performance meeting the performance threshold. 
     
     
         7 . The method of  claim 1 , further comprising:
 based on the first site design of the plurality of candidate site designs meeting the cost criterion, providing, by the processing system, instructions to generate a three-dimensional (3D) model of the first site design.   
     
     
         8 . The method of  claim 7 , wherein the 3D model is an interactive virtual model, and further comprising displaying, by the processing system, the interactive 3D virtual model. 
     
     
         9 . The method of  claim 1 , further comprising updating, by the processing system, the network design template to an updated network design template, wherein the second site design is based on the updated network design template. 
     
     
         10 . A device comprising:
 a processing system including a processor; and   a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations comprising:   obtaining a network design template;   obtaining constraints for use in design of a network site for a network, wherein the network design template is provided by a template engine in communication with the processor, wherein the template engine obtains definitions of network faults and actions, the actions including a closed loop control procedure to resolve at least one of the network faults;   creating a plurality of candidate site designs, based at least in part on the network design template and on design constraints;   selecting a first site design in accordance with a cost criterion for a power cost to operate the network in accordance with the first site design;   sending instructions to automatically implement the first site design by initiating an automated site build plan, the initiating based on a predetermined trigger, resulting in a first site;   monitoring the first site to determine a first performance of the first site; and   automatically generating a second site design, based on determining that the first performance of the first site is below a performance threshold.   
     
     
         11 . The device of  claim 10 , wherein the design constraints comprise space constraints, power constraints, or a combination thereof. 
     
     
         12 . The device of  claim 10 , wherein the plurality of candidate site designs is created based on a machine learning cycle that optimizes design options used to create the plurality of candidate site designs. 
     
     
         13 . The device of  claim 12 , wherein the machine learning cycle improves creating the plurality of candidate site designs using previous site installation information and technology cost trend information. 
     
     
         14 . The device of  claim 10 , wherein the cost criterion comprises a threshold cost, wherein the threshold cost is a determined maximum power cost to operate the network in accordance with the first site design. 
     
     
         15 . The device of  claim 10 , further comprising determining, by the processing system, that the second site design provides a second performance meeting the performance threshold. 
     
     
         16 . The device of  claim 10 , wherein the operations further comprise updating the network design template to an updated network design template, wherein the second site design is based on the updated network design template. 
     
     
         17 . A non-transitory machine-readable medium comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations comprising:
 obtaining a network design template;   obtaining constraints for use in design of a network site for a network, wherein the network design template is provided by a template engine in communication with the processor, wherein the template engine obtains definitions of network faults, the actions including a closed loop control procedure to resolve at least one of the network faults;   creating a plurality of candidate site designs, based at least in part on the network design template and on design constraints, wherein at least one of the candidate site designs is created based on a machine learning cycle;   selecting a first site design in accordance with a cost criterion for a power cost to operate the network in accordance with the first site design;   sending instructions to automatically implement the first site design by initiating an automated site build plan, the initiating based on a predetermined trigger, resulting in a first site;   monitoring the first site to determine a first performance of the first site; and   automatically generating a second site design, based on determining that the first performance of the first site is below a performance threshold.   
     
     
         18 . The non-transitory machine-readable medium of  claim 17 , wherein the design constraints comprise space constraints, power constraints, or a combination thereof. 
     
     
         19 . The non-transitory machine-readable medium of  claim 17 , wherein the machine learning cycle optimizes design options used to create the plurality of candidate site designs, and wherein the machine learning cycle improves creating the plurality of candidate site designs using previous site installation information and technology cost trend information. 
     
     
         20 . The non-transitory machine-readable medium of  claim 17 , wherein the operations further comprise:
 providing instructions to generate an interactive three-dimensional (3D) model of the first site design based on the first site design of the plurality of candidate site designs meeting the cost criterion; and   displaying the interactive 3D virtual model.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.