System and method for generating predictions of protracted outages of software applications and computing systems

1 . A system, comprising:

a memory configured to store a software application and software application performance data, wherein the software application performance data is associated with an operational performance of the software application; and

a processor operably coupled to the memory and configured to:

access the software application performance data;

preprocess the software application performance data, wherein preprocessing the software application performance data comprises normalizing disparate key performance indicator (KPI) data indicative of the operational performance of the software application;

train an artificial-intelligence algorithm based at least in part on a training data set of publicly-available software application performance data associated with at least a first protracted outage of a software application and a training data set of proprietary software application performance data associated with at least a second protracted outage of a software application;

execute, based at least in part on the preprocessed software application performance data, and, in response to the training of the artificial-intelligence algorithm, an artificial-intelligence model to generate a prediction of an impending outage for the software application, wherein the prediction of the impending outage comprises a prediction of a potentially protracted outage of the software application;

output, by the artificial-intelligence model, the prediction of the impending outage for the software application;

cause a computing device to display a visual representation of the outputted prediction of the impending outage for the software application; and

in response to receiving one or more user inputs, cause a remediation of the software application to be executed to preempt the potentially protracted outage of the software application.

2 . The system of claim 1 , wherein the software application performance data comprises software application performance metrics or software application telemetry data.

3 . The system of claim 1 , wherein the disparate key KPI data comprises one or more of a data set of hardware computing KPI data, a data set of software computing KPI data, or a data set of hybrid computing KPI data.

4 . The system of claim 1 , wherein the artificial-intelligence model comprises a pretrained foundation model (FM) trained and executed to generate a prediction of one or more KPI values indicative of the impending outage for the software application, and wherein the pretrained FM comprises one or more of a language model (LM), a large language model (LLM), a bidirectional and auto-regressive transformer (BART) model, a bidirectional encoder representations for transformer (BERT) model, a generative pretrained transformer (GPT) model, or a diffusion model.

5 . The system of claim 1 , wherein the artificial-intelligence model comprises a foundation model (FM) fine-tuned to generate the prediction of the impending outage for the software application based at least in part on:

only a data set of hardware computing KPI data;

only a data set of software computing KPI data;

only a data set of hybrid computing KPI data; or

only a data set of real-time computing KPI data.

6 . The system of claim 1 , wherein the processor is further configured to output the prediction of the impending outage for the software application by outputting, by the artificial-intelligence model, a prediction of one or more KPI values indicative of the impending outage for the software application, and wherein the one or more KPI values comprises one or more of a service uptime value, a downtime duration value, a mean time between failures (MTBF) value, an average response time value, a latency value, a throughput value, an error rate value, an incident event count value, a mean time to recover (MTTR) value, a utilization rate value, a scalability value, or a response and resolution time value.

7 . The system of claim 1 , wherein the processor is further configured to:

cause the computing device to display a software application monitoring dashboard including the visual representation of the outputted prediction of the impending outage for the software application; and

in response to receiving the one or more user inputs, provide to the computing device a set of instructions for patching the software application to preempt the potentially protracted outage of the software application.

8 . A method, comprising:

accessing software application performance data, wherein the software application performance data is associated with an operational performance of a software application;

preprocessing the software application performance data, wherein preprocessing the software application performance data comprises normalizing disparate key performance indicator (KPI) data indicative of the operational performance of the software application;

training an artificial-intelligence algorithm based at least in part on a training data set of publicly-available software application performance data associated with at least a first protracted outage of a software application and a training data set of proprietary software application performance data associated with at least a second protracted outage of a software application;

executing, based at least in part on the preprocessed software application performance data, and, in response to the training of the artificial-intelligence algorithm, an artificial-intelligence model to generate a prediction of an impending outage for the software application, wherein the prediction of the impending outage comprises a prediction of a potentially protracted outage of the software application;

outputting, by the artificial-intelligence model, the prediction of the impending outage for the software application; and

causing a computing device to display a visual representation of the outputted prediction of the impending outage for the software application; and

in response to receiving one or more user inputs, causing a remediation of the software application to be executed to preempt the potentially protracted outage of the software application.

9 . The method of claim 8 , wherein the software application performance data comprises software application performance metrics or software application telemetry data.

10 . The method of claim 8 , wherein the disparate key KPI data comprises one or more of a data set of hardware computing KPI data, a data set of software computing KPI data, or a data set of hybrid computing KPI data.

11 . The method of claim 8 , wherein the artificial-intelligence model comprises a pretrained foundation model (FM) trained and executed to generate a prediction of one or more KPI values indicative of the impending outage for the software application, and wherein the pretrained FM comprises one or more of a language model (LM), a large language model (LLM), a bidirectional and auto-regressive transformer (BART) model, a bidirectional encoder representations for transformer (BERT) model, a generative pretrained transformer (GPT) model, or a diffusion model.

12 . The method of claim 8 , wherein the artificial-intelligence model comprises a foundation model (FM) fine-tuned to generate the prediction of the impending outage for the software application based at least in part on:

only a data set of hardware computing KPI data;

only a data set of software computing KPI data;

only a data set of hybrid computing KPI data; or

only a data set of real-time computing KPI data.

13 . The method of claim 8 , further comprising outputting the prediction of the impending outage for the software application by outputting, by the artificial-intelligence model, a prediction of one or more KPI values indicative of the impending outage for the software application, and wherein the one or more KPI values comprises one or more of a service uptime value, a downtime duration value, a mean time between failures (MTBF) value, an average response time value, a latency value, a throughput value, an error rate value, an incident event count value, a mean time to recover (MTTR) value, a utilization rate value, a scalability value, or a response and resolution time value.

14 . The method of claim 8 , further comprising:

causing the computing device to display a software application monitoring dashboard including the visual representation of the outputted prediction of the impending outage for the software application; and

in response to receiving the one or more user inputs, provide to the computing device a set of instructions for patching the software application to preempt the potentially protracted outage of the software application.

15 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

access software application performance data, wherein the software application performance data is associated with an operational performance of a software application;

preprocess the software application performance data, wherein preprocessing the software application performance data comprises normalizing a disparate key performance indicator (KPI) data indicative of the operational performance of the software application;

train an artificial-intelligence algorithm based at least in part on a training data set of publicly-available software application performance data associated with at least a first protracted outage of a software application and a training data set of proprietary software application performance data associated with at least a second protracted outage of a software application;

execute, based at least in part on the preprocessed software application performance data, and, in response to the training of the artificial-intelligence algorithm, an artificial-intelligence model to generate a prediction of an impending outage for the software application, wherein the prediction of the impending outage comprises a prediction of a potentially protracted outage of the software application;

output, by the artificial-intelligence model, the prediction of the impending outage for the software application;

cause a computing device to display a visual representation of the outputted prediction of the impending outage for the software application; and

in response to receiving one or more user inputs, cause a remediation of the software application to be executed to preempt the potentially protracted outage of the software application.

16 . The non-transitory computer-readable medium of claim 15 , wherein the software application performance data comprises software application performance metrics or software application telemetry data.

17 . The non-transitory computer-readable medium of claim 15 , wherein the disparate key KPI data comprises one or more of a data set of hardware computing KPI data, a data set of software computing KPI data, or a data set of hybrid computing KPI data.

18 . The non-transitory computer-readable medium of claim 15 , wherein the artificial-intelligence model comprises a pretrained foundation model (FM) trained and executed to generate a prediction of one or more KPI values indicative of the impending outage for the software application, and wherein the pretrained FM comprises one or more of a language model (LM), a large language model (LLM), a bidirectional and auto-regressive transformer (BART) model, a bidirectional encoder representations for transformer (BERT) model, a generative pretrained transformer (GPT) model, or a diffusion model.

19 . The non-transitory computer-readable medium of claim 15 , wherein the artificial-intelligence model comprises a foundation model (FM) fine-tuned to generate the prediction of the impending outage for the software application based at least in part on:

only a data set of hardware computing KPI data;

only a data set of software computing KPI data;

only a data set of hybrid computing KPI data; or

only a data set of real-time computing KPI data.

20 . The non-transitory computer-readable medium of claim 15 , wherein the instructions further cause the one or more processors to output the prediction of the impending outage for the software application by outputting, by the artificial-intelligence model, a prediction of one or more KPI values indicative of the impending outage for the software application, and wherein the one or more KPI values comprises one or more of a service uptime value, a downtime duration value, a mean time between failures (MTBF) value, an average response time value, a latency value, a throughput value, an error rate value, an incident event count value, a mean time to recover (MTTR) value, a utilization rate value, a scalability value, or a response and resolution time value.