# US 11,223,546 B2 · Method, apparatus and system for real-time optimization of computer-implemented application operations using machine learning techniques

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,223,546 B2
- Document ID: US11223546B2
- Status: Granted
- Kind: B2
- Application number: 17/000,313
- Filed: 2020-08-22
- Published: 2020-12-17
- Granted: 2022-01-11
- Earliest claimed: 2015-07-27
- Assignees: Datagrid Systems, Inc.
- Applicants: Datagrid Systems, Inc.
- Inventors: Ross Schibler; Peter Nickolov; Stephen Quintero
- Web page: https://patentgrep.com/patent/US11223546B2

## CPC

- G06F 8/65: Updates (security arrangements therefor G06F21/57)
- G06F 9/44505: {Configuring for program initiating, e.g. using registry, configuration files}
- G06F 9/45558: {Hypervisor-specific management and integration aspects}
- H04L 41/082: the condition being updates or upgrades of network functionality
- H04L 41/0823: characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability (for optimising operational conditions of wireless networks H04W24/02)
- H04L 41/0869: Validating the configuration within one network element
- H04L 41/16: using machine learning or artificial intelligence
- H04L 43/0817: by checking functioning
- H04L 63/1433: {Vulnerability analysis}
- G06F 8/658: Incremental updates; Differential updates
- G06F 2009/45591: {Monitoring or debugging support}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Various aspects described or referenced herein are directed to different methods, systems, and computer program products for facilitating real-time optimization of computer-implemented application operations using machine learning techniques.

## Claims

### Claim 1

A computer implemented method for optimizing at least one runtime configuration of a first plurality of applications hosted at a remote networked environment, the remote networked environment being communicatively coupled to a computer network, the computer network including an Optimizer System, the Optimizer System including a plurality of optimizer algorithms, the method comprising causing at least one processor to execute instructions stored in non-transient memory to automatically:
cause at least one network device to identify a first application of the first plurality of applications;
initiate a first measurement of a first operational metric of the first application while the first application is operating in accordance with a first runtime configuration;
generate first measurement information relating to the first measurement of the first operational metric of the first application;
calculate, using the first measurement information, a first score in relation to a first optimization objective, the first score being calculated using a first scoring function;
determine a first set of updated application settings relating to a runtime configuration of the first application;
deploy the first set of updated application settings at the first application to thereby cause the first application to operate in accordance with a second runtime configuration;
initiate a second measurement of the first operational metric of the first application while the first application is operating in accordance with the second runtime configuration;
generate second measurement information relating to the second measurement of the first operational metric of the first application;
calculate, using the second measurement information, a second score in relation to the first optimization objective, the second score being calculated using a second scoring function;
compute, using at least the second score, a first reward;
update at least one of the plurality of optimizer algorithms using information relating to the first reward;
select, from the plurality of optimizer algorithms, a first optimizer algorithm to be used for determining a second set of updated application settings relating to the runtime configuration of the first application;
determine, using the first optimizer algorithm, a second set of updated application settings relating to the runtime configuration of the first application;
deploy the second set of updated application settings at the first application to thereby cause the first application to operate in accordance with a third runtime configuration;
cause the at least one network device to initiate a third measurement of the first operational metric of the first application while the first application is operating in accordance with the third runtime configuration;
generate third measurement information relating to the third measurement of the first operational metric of the first application;
calculate, using the third measurement information, a third score in relation to the first optimization objective, the third score being calculated using a third scoring function;
compute, using at least the third score, a second reward;
update at least one of the plurality of optimizer algorithms using information relating to the second reward;
select, from the plurality of optimizer algorithms, a second optimizer algorithm to be used for determining a third set of updated application settings relating to the runtime configuration of the first application;
determine, using the second optimizer algorithm, a third set of updated application settings relating to the runtime configuration of the first application; and
deploy the third set of updated application settings at the first application to thereby cause the first application to operate in accordance with a fourth runtime configuration.

### Claim 2 (depends on 1)

The computer implemented method of claim 1 further comprising causing the at least one processor to execute additional instructions to automatically:
initiate a fourth measurement of a second operational metric of a second application of the first plurality of applications while the second application is operating in accordance with a fifth runtime configuration;
generate fourth measurement information relating to the fourth measurement of the second operational metric of the second application;
calculate, using the fourth measurement information, a fourth score in relation to a second optimization objective, the fourth score being calculated using a fourth scoring function;
determine a fourth set of updated application settings relating to the runtime configuration of the second application;
deploying the fourth set of updated application settings at the second application to thereby cause the second application to operate in accordance with a sixth runtime configuration;
initiate a fifth measurement of the second operational metric of the second application while the second application is operating in accordance with the sixth runtime configuration;
generate fifth measurement information relating to the fifth measurement of the second operational metric of the second application;
calculate, using the fifth measurement information, a fifth score in relation to the second optimization objective, the fifth score being calculated using a fifth scoring function;
compute, using at least the fifth score, a third reward;
update at least one of the plurality of optimizer algorithms using information relating to the third reward;
select, from the plurality of optimizer algorithms, a third optimizer algorithm to be used for determining a fifth set of updated application settings relating to the runtime configuration of the second application;
determine, using the third optimizer algorithm, a fifth set of updated application settings relating to the runtime configuration of the second application;
deploy the fifth set of updated application settings at the second application to thereby cause the second application to operate in accordance with a seventh runtime configuration;
initiate a sixth measurement of the second operational metric of the second application while the second application is operating in accordance with the seventh runtime configuration;
generate sixth measurement information relating to the sixth measurement of the second operational metric of the second application;
calculate, using the sixth measurement information, a sixth score in relation to the second optimization objective, the sixth score being calculated using a sixth scoring function;
compute, using at least the sixth score, a fourth reward;
update at least one of the plurality of optimizer algorithms using information relating to the fourth reward;
select, from the plurality of optimizer algorithms, a fourth optimizer algorithm to be used for determining a sixth set of updated application settings relating to the runtime configuration of the second application;
determine, using the fourth optimizer algorithm, a sixth set of updated application settings relating to the runtime configuration of the second application; and
deploy the sixth set of updated application settings at the second application to thereby cause the second application to operate in accordance with an eighth runtime configuration.

### Claim 3 (depends on 1)

The computer implemented method of claim 1 further comprising causing the at least one processor to execute additional instructions to automatically:
determine if additional cycles of optimization adjustment are to be performed for the first application;
if it is determined that additional cycles of optimization adjustment are to be performed for the first plurality of applications cause the at least one processor to execute additional instructions to automatically:
initiate a fourth measurement of the first operational metric of the first plurality of applications while the first plurality of applications is operating in accordance with the fourth runtime configuration;
generate forth measurement information relating to the fourth measurement of the first operational metric of the first plurality of applications;
calculate, using the fourth measurement information, a fourth score in relation to the first optimization objective, the fourth score being calculated using the first scoring function;
compute, using at least the fourth score, a third reward;
update at least one of the plurality of optimizer algorithms using information relating to the third reward;
select, from the plurality of optimizer algorithms, a third optimizer algorithm to be used for determining a fourth set of updated application settings relating to the runtime configuration of the first plurality of applications;
determine, using the third optimizer algorithm, a fourth set of updated application settings relating to the runtime configuration of the first plurality of applications; and
deploy the fourth set of updated application settings at the first plurality of applications to thereby cause the first plurality of applications to operate in accordance with a fifth runtime configuration.

### Claim 4 (depends on 1)

The computer implemented method of claim 1 wherein the at least one network component includes a servo component deployed at the remote networked environment and configured or designed to implement instructions received from the Optimizer System, and to initiate interactions with the first plurality of applications in response to the received instructions.

### Claim 5 (depends on 1)

The computer implemented method of claim 1 wherein the at least one network component includes a servo component deployed at the Optimizer System and configured or designed to implement instructions generated by the Optimizer System and to initiate interactions with the first plurality of applications in response to the instructions.

### Claim 6 (depends on 1)

The computer implemented method of claim 1 further comprising causing the at least one processor to execute additional instructions to automatically:
calculate, using the first measurement information, a first performance indicator of the first plurality of applications, the first performance indicator being representative of a first performance of the first plurality of applications while operating in accordance with the first runtime configuration;
calculate, using information relating to the first runtime configuration, a first cost indicator of the first plurality of applications, the first cost indicator being representative of a first cost of resources utilized for operating the first plurality of applications in accordance with the first runtime configuration;
wherein the first score is calculated using the first performance indicator and first cost indicator;
calculate, using the second measurement information, a second performance indicator of the first plurality of applications, the second performance indicator being representative of a second performance of the first plurality of applications while operating in accordance with the second runtime configuration;
calculate, using information relating to the second runtime configuration, a second cost indicator of the first plurality of applications, the second cost indicator being representative of a second cost of resources utilized for operating the first plurality of applications in accordance with the second runtime configuration; and
wherein the second score is calculated using the second performance indicator and second cost indicator.

### Claim 7 (depends on 1)

The computer implemented method of claim 1 wherein the first reward corresponds to the second score.

### Claim 8 (depends on 1)

The computer implemented method of claim 1 wherein the first reward is calculated based on a comparison of the second score and the first score.

### Claim 9 (depends on 1)

The computer implemented method of claim 1 further comprising causing the at least one processor to execute additional instructions to automatically:
calculate, using the first measurement information, a first performance measurement of the first plurality of applications;
calculate, using information relating to the first runtime configuration, a first cost of the application;
wherein the first score is calculated using the first performance measurement and first cost; and
wherein the first scoring function corresponds to a scoring function selected from a group consisting of:
performance measurement/cost;
performance measurement W1/cost, where W1 represents a weighted value;
performance measurement, where cost is represented as constant;
performance measurement bounded by a maximum cost; and
cost while maintaining a minimum performance measurement value.

### Claim 10 (depends on 1)

The computer implemented method of claim 1:
wherein at least one set of updated application settings is selected from a group consisting of:
at least one virtual machine associated with the first plurality of applications;
at least one container associated with the first plurality of applications;
at least one CPU core associated with the first plurality of applications;
at least one memory associated with the first plurality of applications;
network bandwidth associated with the first plurality of applications;
at least one provisioned disk TOPS associated with the first plurality of applications;
at least one resource setting associated with the first plurality of applications; and
number of replicas of a component deployed at the first plurality of applications.

### Claim 11 (depends on 1)

The computer implemented method of claim 1:
wherein at least one set of updated application settings is selected from a group consisting of:
the number of Apache worker threads associated with the first plurality of applications;
My SQL memory pool size associated with the first plurality of applications;
kernel tuning parameters associated with the first plurality of applications;
number of virtualized components of the first plurality of applications which are co-located on a same physical machine; and
number of virtualized container components of the first plurality of applications which are co-located on a same host.

### Claim 12 (depends on 1)

The computer implemented method of claim 1 wherein at least one selected optimizer algorithm corresponds to a reinforced learning algorithm configured or designed to employ Q-learning using a neural network as a Q function.

### Claim 13 (depends on 1)

The computer implemented method of claim 1:
wherein the first optimizer algorithm corresponds to a first type of optimizer algorithm selected from a group consisting of: a reinforced learning algorithm configured or designed to employ Q-learning using a neural network as a Q function, a Bayesian algorithm, an Evolutionary algorithm, an Ouch heuristic algorithm, a Stochastic algorithm, and a Bruteforce algorithm;
wherein the second optimizer algorithm corresponds to a second type of optimizer algorithm selected from a group consisting of: a reinforced learning algorithm configured or designed to employ Q-learning using a neural network as a Q function, a Bayesian algorithm, an Evolutionary algorithm, an Ouch heuristic algorithm, a Stochastic algorithm, and a Bruteforce algorithm; and
wherein the first type of optimizer algorithm is different from the second type of optimizer algorithm.

### Claim 14 (depends on 1)

The computer implemented method of claim 1 further comprising causing the at least one processor to execute instructions to cause at least one set of updated application settings to be deployed at the first plurality of applications while the first plurality of applications are running in a live production environment.

### Claim 15 (depends on 1)

The computer implemented method of claim 1 further comprising causing the at least one processor to execute instructions to cause at least one set of updated application settings to be deployed at the first plurality of applications while the first plurality of applications are running in a test bed environment.

### Claim 16 (depends on 1)

The computer implemented method of claim 1 further comprising causing the at least one processor to execute instructions to cause at least one set of updated application settings to be deployed at the first plurality of applications while the first plurality of applications are running in a canary environment.

### Claim 17 (depends on 1)

The computer implemented method of claim 1 wherein the method is implemented as a SaaS service which is configured or designed to utilize the Optimizer System to remotely and securely optimize the first plurality of applications.

### Claim 18

A computer implemented system for optimizing a runtime configuration of a first plurality of applications hosted at a remote networked environment, the remote networked environment being communicatively coupled to a computer network, the computer network including an Optimizer System, the Optimizer System including a plurality of optimizer algorithms, the system comprising:
at least one non-transient memory;
at least one processor operable to execute a plurality of instructions stored in the at least one non-transient memory to automatically:
cause at least one network device to identify a first application of the first plurality of applications;
initiate a first measurement of a first operational metric of the first application while the first application is operating in accordance with a first runtime configuration;
generate first measurement information relating to the first measurement of the first operational metric of the first application;
calculate, using the first measurement information, a first score in relation to a first optimization objective, the first score being calculated using a first scoring function;
determine a first set of updated application settings relating to a runtime configuration of the first application;
deploy the first set of updated application settings at the first application to thereby cause the first application to operate in accordance with a second runtime configuration;
initiate a second measurement of the first operational metric of the first application while the first application is operating in accordance with the second runtime configuration;
generate second measurement information relating to the second measurement of the first operational metric of the first application;
calculate, using the second measurement information, a second score in relation to the first optimization objective, the second score being calculated using a second scoring function;
compute, using at least the second score, a first reward;
update at least one of the plurality of optimizer algorithms using information relating to the first reward;
select, from the plurality of optimizer algorithms, a first optimizer algorithm to be used for determining a second set of updated application settings relating to the runtime configuration of the first application;
determine, using the first optimizer algorithm, a second set of updated application settings relating to the runtime configuration of the first application;
deploy the second set of updated application settings at the first application to thereby cause the first application to operate in accordance with a third runtime configuration;
cause the at least one network device to initiate a third measurement of the first operational metric of the first application while the first application is operating in accordance with the third runtime configuration;
generate third measurement information relating to the third measurement of the first operational metric of the first application;
calculate, using the third measurement information, a third score in relation to the first optimization objective, the third score being calculated using a third scoring function;
compute, using at least the third score, a second reward;
update at least one of the plurality of optimizer algorithms using information relating to the second reward;
select, from the plurality of optimizer algorithms, a second optimizer algorithm to be used for determining a third set of updated application settings relating to the runtime configuration of the first application;
determine, using the second optimizer algorithm, a third set of updated application settings relating to the runtime configuration of the first application; and
deploy the third set of updated application settings at the first application to thereby cause the first application to operate in accordance with a fourth runtime configuration.

### Claim 19 (depends on 18)

The computer implemented method of claim 18 being further operable to cause the at least one processor to execute additional instructions to automatically:
initiate a fourth measurement of a second operational metric of a second application of the first plurality of applications while the second application is operating in accordance with a fifth runtime configuration;
generate fourth measurement information relating to the fourth measurement of the second operational metric of the second application;
calculate, using the fourth measurement information, a fourth score in relation to a second optimization objective, the fourth score being calculated using a fourth scoring function;
determine a fourth set of updated application settings relating to the runtime configuration of the second application;
deploying the fourth set of updated application settings at the second application to thereby cause the second application to operate in accordance with a sixth runtime configuration;
initiate a fifth measurement of the second operational metric of the second application while the second application is operating in accordance with the sixth runtime configuration;
generate fifth measurement information relating to the fifth measurement of the second operational metric of the second application;
calculate, using the fifth measurement information, a fifth score in relation to the second optimization objective, the fifth score being calculated using a fifth scoring function;
compute, using at least the fifth score, a third reward;
update at least one of the plurality of optimizer algorithms using information relating to the third reward;
select, from the plurality of optimizer algorithms, a third optimizer algorithm to be used for determining a fifth set of updated application settings relating to the runtime configuration of the second application;
determine, using the third optimizer algorithm, a fifth set of updated application settings relating to the runtime configuration of the second application;
deploy the fifth set of updated application settings at the second application to thereby cause the second application to operate in accordance with a seventh runtime configuration;
initiate a sixth measurement of the second operational metric of the second application while the second application is operating in accordance with the seventh runtime configuration;
generate sixth measurement information relating to the sixth measurement of the second operational metric of the second application;
calculate, using the sixth measurement information, a sixth score in relation to the second optimization objective, the sixth score being calculated using a sixth scoring function;
compute, using at least the sixth score, a fourth reward;
update at least one of the plurality of optimizer algorithms using information relating to the fourth reward;
select, from the plurality of optimizer algorithms, a fourth optimizer algorithm to be used for determining a sixth set of updated application settings relating to the runtime configuration of the second application;
determine, using the fourth optimizer algorithm, a sixth set of updated application settings relating to the runtime configuration of the second application; and
deploy the sixth set of updated application settings at the second application to thereby cause the second application to operate in accordance with an eighth runtime configuration.

### Claim 20 (depends on 18)

The computer implemented system of claim 18 being further operable to cause the at least one processor to execute additional instructions to automatically:
determine if additional cycles of optimization adjustment are to be performed for the first application;
if it is determined that additional cycles of optimization adjustment are to be performed for the first plurality of applications cause the at least one processor to execute additional instructions to automatically:
initiate a fourth measurement of the first operational metric of the first plurality of applications while the first plurality of applications is operating in accordance with the fourth runtime configuration;
generate forth measurement information relating to the fourth measurement of the first operational metric of the first plurality of applications;
calculate, using the fourth measurement information, a fourth score in relation to the first optimization objective, the fourth score being calculated using the first scoring function;
compute, using at least the fourth score, a third reward;
update at least one of the plurality of optimizer algorithms using information relating to the third reward;
select, from the plurality of optimizer algorithms, a third optimizer algorithm to be used for determining a fourth set of updated application settings relating to the runtime configuration of the first plurality of applications;
determine, using the third optimizer algorithm, a fourth set of updated application settings relating to the runtime configuration of the first plurality of applications; and
deploy the fourth set of updated application settings at the first plurality of applications to thereby cause the first plurality of applications to operate in accordance with a fifth runtime configuration.

### Claim 21 (depends on 18)

The computer implemented system of claim 18 wherein the at least one network component includes a servo component deployed at the remote networked environment and configured or designed to implement instructions received from the Optimizer System, and to initiate interactions with the first plurality of applications in response to the received instructions.

### Claim 22 (depends on 18)

The computer implemented system of claim 18 wherein the at least one network component includes a servo component deployed at the Optimizer System and configured or designed to implement instructions generated by the Optimizer System and to initiate interactions with the first plurality of applications in response to the instructions.

### Claim 23 (depends on 18)

The computer implemented system of claim 18 being further operable to cause the at least one processor to execute additional instructions to automatically:
calculate, using the first measurement information, a first performance indicator of the first plurality of applications, the first performance indicator being representative of a first performance of the first plurality of applications while operating in accordance with the first runtime configuration;
calculate, using information relating to the first runtime configuration, a first cost indicator of the first plurality of applications, the first cost indicator being representative of a first cost of resources utilized for operating the first plurality of applications in accordance with the first runtime configuration;
wherein the first score is calculated using the first performance indicator and first cost indicator;
calculate, using the second measurement information, a second performance indicator of the first plurality of applications, the second performance indicator being representative of a second performance of the first plurality of applications while operating in accordance with the second runtime configuration;
calculate, using information relating to the second runtime configuration, a second cost indicator of the first plurality of applications, the second cost indicator being representative of a second cost of resources utilized for operating the first plurality of applications in accordance with the second runtime configuration; and
wherein the second score is calculated using the second performance indicator and second cost indicator.

### Claim 24 (depends on 18)

The computer implemented system of claim 18 wherein the first reward corresponds to the second score.

### Claim 25 (depends on 18)

The computer implemented system of claim 18 wherein the first reward is calculated based on a comparison of the second score and the first score.

### Claim 26 (depends on 18)

The computer implemented system of claim 18 being further operable to cause the at least one processor to execute additional instructions to automatically:
calculate, using the first measurement information, a first performance measurement of the first plurality of applications;
calculate, using information relating to the first runtime configuration, a first cost of the application;
wherein the first score is calculated using the first performance measurement and first cost; and
wherein the first scoring function corresponds to a scoring function selected from a group consisting of:
performance measurement/cost;
performance measurement W1/cost, where W1 represents a weighted value;
performance measurement, where cost is represented as constant;
performance measurement bounded by a maximum cost; and
cost while maintaining a minimum performance measurement value.

### Claim 27 (depends on 18)

The computer implemented system of claim 18:
wherein at least one set of updated application settings is selected from a group consisting of:
at least one virtual machine associated with the first plurality of applications;
at least one container associated with the first plurality of applications;
at least one CPU core associated with the first plurality of applications;
at least one memory associated with the first plurality of applications;
network bandwidth associated with the first plurality of applications;
at least one provisioned disk TOPS associated with the first plurality of applications;
at least one resource setting associated with the first plurality of applications; and
number of replicas of a component deployed at the first plurality of applications.

### Claim 28 (depends on 18)

The computer implemented system of claim 18:
wherein at least one set of updated application settings is selected from a group consisting of:
the number of Apache worker threads associated with the first plurality of applications;
My SQL memory pool size associated with the first plurality of applications;
kernel tuning parameters associated with the first plurality of applications;
number of virtualized components of the first plurality of applications which are co-located on a same physical machine; and
number of virtualized container components of the first plurality of applications which are co-located on a same host.

### Claim 29 (depends on 18)

The computer implemented system of claim 18 wherein at least one selected optimizer algorithm corresponds to a reinforced learning algorithm configured or designed to employ Q-learning using a neural network as a Q function.

### Claim 30 (depends on 18)

The computer implemented system of claim 18:
wherein the first optimizer algorithm corresponds to a first type of optimizer algorithm selected from a group consisting of: a reinforced learning algorithm configured or designed to employ Q-learning using a neural network as a Q function, a Bayesian algorithm, an Evolutionary algorithm, an Ouch heuristic algorithm, a Stochastic algorithm, and a Bruteforce algorithm;
wherein the second optimizer algorithm corresponds to a second type of optimizer algorithm selected from a group consisting of: a reinforced learning algorithm configured or designed to employ Q-learning using a neural network as a Q function, a Bayesian algorithm, an Evolutionary algorithm, an Ouch heuristic algorithm, a Stochastic algorithm, and a Bruteforce algorithm; and
wherein the first type of optimizer algorithm is different from the second type of optimizer algorithm.

### Claim 31 (depends on 18)

The computer implemented system of claim 18 being further operable to cause the at least one processor to execute instructions to cause at least one set of updated application settings to be deployed at the first plurality of applications while the first plurality of applications are running in a live production environment.

### Claim 32 (depends on 18)

The computer implemented system of claim 18 being further operable to cause the at least one processor to execute instructions to cause at least one set of updated application settings to be deployed at the first plurality of applications while the first plurality of applications are running in a test bed environment.

### Claim 33 (depends on 18)

The computer implemented system of claim 18 being further operable to cause the at least one processor to execute instructions to cause at least one set of updated application settings to be deployed at the first plurality of applications while the first plurality of applications are running in a canary environment.

### Claim 34 (depends on 18)

The computer implemented system of claim 18 wherein the system is implemented as a SaaS service which is configured or designed to utilize the Optimizer System to remotely and securely optimize the first plurality of applications.

### Claim 35

A non-transitory computer usable medium for use in a computer network, the computer network including a first plurality of applications hosted at a remote networked environment, and including an Optimizer System configured to access a at least one of the plurality of optimizer algorithms, the computer network further including at least one processor, the computer usable medium having computer readable code embodied therein, the computer readable code comprising computer code for causing at least one processor to execute instructions stored in at least one memory to automatically:
cause at least one network device to identify a first application of the first plurality of applications;
initiate a first measurement of a first operational metric of the first application while the first application is operating in accordance with a first runtime configuration;
generate first measurement information relating to the first measurement of the first operational metric of the first application;
calculate, using the first measurement information, a first score in relation to a first optimization objective, the first score being calculated using a first scoring function;
determine a first set of updated application settings relating to a runtime configuration of the first application;
deploy the first set of updated application settings at the first application to thereby cause the first application to operate in accordance with a second runtime configuration;
initiate a second measurement of the first operational metric of the first application while the first application is operating in accordance with the second runtime configuration;
generate second measurement information relating to the second measurement of the first operational metric of the first application;
calculate, using the second measurement information, a second score in relation to the first optimization objective, the second score being calculated using a second scoring function;
compute, using at least the second score, a first reward;
update at least one of the plurality of optimizer algorithms using information relating to the first reward;
select, from the plurality of optimizer algorithms, a first optimizer algorithm to be used for determining a second set of updated application settings relating to the runtime configuration of the first application;
determine, using the first optimizer algorithm, a second set of updated application settings relating to the runtime configuration of the first application;
deploy the second set of updated application settings at the first application to thereby cause the first application to operate in accordance with a third runtime configuration;
cause the at least one network device to initiate a third measurement of the first operational metric of the first application while the first application is operating in accordance with the third runtime configuration;
generate third measurement information relating to the third measurement of the first operational metric of the first application;
calculate, using the third measurement information, a third score in relation to the first optimization objective, the third score being calculated using a third scoring function;
compute, using at least the third score, a second reward;
update at least one of the plurality of optimizer algorithms using information relating to the second reward;
select, from the plurality of optimizer algorithms, a second optimizer algorithm to be used for determining a third set of updated application settings relating to the runtime configuration of the first application;
determine, using the second optimizer algorithm, a third set of updated application settings relating to the runtime configuration of the first application;
deploy the third set of updated application settings at the first application to thereby cause the first application to operate in accordance with a fourth runtime configuration;
initiate a fourth measurement of a second operational metric of a second application of the first plurality of applications while the second application is operating in accordance with a fifth runtime configuration;
generate fourth measurement information relating to the fourth measurement of the second operational metric of the second application;
calculate, using the fourth measurement information, a fourth score in relation to a second optimization objective, the fourth score being calculated using a fourth scoring function;
determine a fourth set of updated application settings relating to the runtime configuration of the second application;
deploying the fourth set of updated application settings at the second application to thereby cause the second application to operate in accordance with a sixth runtime configuration;
initiate a fifth measurement of the second operational metric of the second application while the second application is operating in accordance with the sixth runtime configuration;
generate fifth measurement information relating to the fifth measurement of the second operational metric of the second application;
calculate, using the fifth measurement information, a fifth score in relation to the second optimization objective, the fifth score being calculated using a fifth scoring function;
compute, using at least the fifth score, a third reward;
update at least one of the plurality of optimizer algorithms using information relating to the third reward;
select, from the plurality of optimizer algorithms, a third optimizer algorithm to be used for determining a fifth set of updated application settings relating to the runtime configuration of the second application;
determine, using the third optimizer algorithm, a fifth set of updated application settings relating to the runtime configuration of the second application;
deploy the fifth set of updated application settings at the second application to thereby cause the second application to operate in accordance with a seventh runtime configuration;
initiate a sixth measurement of the second operational metric of the second application while the second application is operating in accordance with the seventh runtime configuration;
generate sixth measurement information relating to the sixth measurement of the second operational metric of the second application;
calculate, using the sixth measurement information, a sixth score in relation to the second optimization objective, the sixth score being calculated using a sixth scoring function;
compute, using at least the sixth score, a fourth reward;
update at least one of the plurality of optimizer algorithms using information relating to the fourth reward;
select, from the plurality of optimizer algorithms, a fourth optimizer algorithm to be used for determining a sixth set of updated application settings relating to the runtime configuration of the second application;
determine, using the fourth optimizer algorithm, a sixth set of updated application settings relating to the runtime configuration of the second application; and
deploy the sixth set of updated application settings at the second application to thereby cause the second application to operate in accordance with an eighth runtime configuration.