Method and apparatus for efficiently performing discrete Monte Carlo simulation analysis in network-based microservices

Patent metadata

Field	Value
Publication number	US-12561496-B2
Application number	US-202117219191-A
Country	US
Kind code	B2
Filing date	Mar 31, 2021
Priority date	Mar 31, 2021
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

Aspects of the subject disclosure may include, for example, receiving from a database server via a network, a reduced size set of quantile samples of a plurality of variables associated with a dynamic system, wherein the reduced size set of quantile samples is based on a standard set of quantile samples, wherein the standard set of quantile samples comprises M quantile samples based on dividing each distribution of the plurality of variables into 1/M probability steps, and wherein the reduced size set of quantile samples comprises N quantile samples based on dividing each distribution of the plurality of variables into 1/N probability steps, performing a plurality of linear interpolations upon the reduced size set of quantile samples to a restored size set of quantile samples, performing a Monte Carlo simulation using the restored size set of quantile samples to generate a simulation result, and transmitting the simulation result to a client device. Other embodiments are disclosed.

First claim

What is claimed is:

1 . A method, comprising:
training, by a processing system including a processor, an artificial intelligence (AI) model at a database server to modify a set of quantile samples, wherein the training includes a classifier to determine actions for modifying the set of quantile samples; receiving, by the processing system, a first request from a client device via a communication network for a Monte Carlo simulation of a dynamic system; determining, by the processing system, an available bandwidth associated with a portion of the communication network associated with the Monte Carlo simulation of the dynamic system responsive to the receiving the first request; transmitting, by the processing system, via a network, a second request to the database server for quantile samples of a plurality of variables associated with the dynamic system, wherein the second request to the database server specifies a reduced size set of quantile samples of the plurality of variables associated with the dynamic system according to the determining the available bandwidth associated with the portion of the communication network associated with the Monte Carlo simulation; receiving, by the processing system, from the database server via the network, the reduced size set of quantile samples of the plurality of variables associated with the dynamic system, wherein the reduced size set of quantile samples is generated according to the AI model to modify the set of quantile samples, wherein the reduced size set of quantile samples of the plurality of variables is based on a standard set of quantile samples of the plurality of variables associated with the dynamic system, wherein the standard set of quantile samples comprises M quantile samples based on dividing each distribution of the plurality of variables into 1/M probability steps, wherein the reduced size set of quantile samples comprises N quantile samples based on dividing each distribution of the plurality of variables into 1/N probability steps, wherein a third set of quantile samples of a first variable of the plurality of variables is added to the reduced size set of quantile samples according to the first variable being unbounded, wherein M and N are whole numbers, and wherein N is less than M; performing, by the processing system, a plurality of linear interpolations upon the reduced size set of quantile samples of the plurality of variables associated with the dynamic system to generate a restored size set of quantile samples of the plurality of variables associated with the dynamic system; performing, by the processing system, the Monte Carlo simulation using the restored size set of quantile samples of the plurality of variables associated with the dynamic system to generate a simulation result; and transmitting, by the processing system, the simulation result to the client device via the communication network for display at the client device.

2 . The method of claim 1 , wherein there is no definite boundary of a minimum value of the first variable of the plurality of variables, and wherein the third set of quantile samples of the first variable of the plurality of variables comprises E1 quantile samples based on dividing a first distribution of the first variable near a minimum boundary into E1 quantile samples of 1/M probability steps, and where E1 is a whole number.

3 . The method of claim 2 , wherein the third set of quantile samples of the first variable of the plurality of variables is added to the reduced size set of quantile samples of the plurality of variables after a first quantile sample of the reduced sized set of quantile samples.

4 . The method of claim 1 , wherein there is no definite boundary of a maximum value of a second variable of the plurality of variables, and wherein a fourth set of quantile samples of the second variable of the plurality of variables is added to the first set of quantile samples according to the second variable.

5 . The method of claim 4 , wherein the fourth set of quantile samples of the second variable of the plurality of variables comprises E2 quantile samples based on dividing a second distribution of the second variable of the plurality of variables near a maximum boundary into E1 quantile samples of 1/M probability steps, wherein E1 and E2 are whole numbers, and wherein a sum of E1 and E2 is less than M.

6 . The method of claim 4 , wherein the fourth set of quantile samples of the second variable of the plurality of variables is added to the reduced size set of quantile samples before a last quantile sample of the reduced sized set of quantile samples.

7 . The method of claim 1 , wherein the M quantile samples are based on dividing each distribution of the plurality of variables associated with the dynamic system into 1/M probability steps.

8 . The method of claim 1 , wherein the reduced size set of quantile samples is stored at the database server in text format.

9 . The method of claim 5 , wherein E1 and E2 are both equal to 5.

10 . The method of claim 1 , wherein a ratio of M/N comprises ten.

11 . The method of claim 1 , wherein the classifier comprises a support vector machine (SVM), and wherein the SVM determines a hypersurface in a space of possible inputs to the AI model at the database server dynamic system.

12 . 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, the operations comprising:
training an artificial intelligence (AI) model at a database server to modify a set of quantile samples, wherein the training includes a classifier to determine actions for modifying the set of quantile samples;
determining an available bandwidth associated with a portion of a communication network associated with a Monte Carlo simulation of a dynamic system;
transmitting, via a network, a request to the a database server for quantile samples of a plurality of variables associated with the dynamic system, wherein the request to the database server specifies a reduced size set of quantile samples of the plurality of variables associated with the dynamic system according to the determining the available bandwidth associated with the portion of the communication network associated with the Monte Carlo simulation;
receiving from the database server via the network, the reduced size set of quantile samples of the plurality of variables associated with the dynamic system, wherein the reduced size set of quantile samples is generated according to the AI model to modify the set of quantile samples, wherein the reduced size set of quantile samples of the plurality of variables is based on a standard set of quantile samples of the plurality of variables associated with the dynamic system, wherein the standard set of quantile samples comprises M quantile samples based on dividing each distribution of the plurality of variables into 1/M probability steps, wherein the reduced size set of quantile samples comprises N quantile samples based on dividing each distribution of the plurality of variables into 1/N probability steps, wherein M and N are whole numbers, and wherein N is less than M;
performing a plurality of linear interpolations upon the reduced size set of quantile samples of the plurality of variables associated with the dynamic system to generate a restored size set of quantile samples of the plurality of variables associated with the dynamic system;
performing a Monte Carlo simulation using the restored size set of quantile samples of the plurality of variables associated with the dynamic system to generate a simulati

Assignees

• At & T Ip I Lp

Inventors

• Li Chen
• Kosseifi Mario
• Thomas Joseph

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F2111/08

  Probabilistic or stochastic CAD · CPC title

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G06F30/27 Primary

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G06N20/00 Primary

  Machine learning · CPC title