System for real-time overload detection using image processing analysis
Systems, computer program products, and methods are described herein for real-time overload detection using image processing analysis. The present disclosure is configured to receive a first set of images associated with a device, wherein the one or more images are associated with a resiliency status of the device; deploy, using a machine learning (ML) subsystem, a trained ML model on the first set of images of the device; determine, using the trained ML model, a change in the resiliency status of the device based on the first set of images; and generate a notification indicating the change in the resiliency status of the device; and transmit control signals configured to cause a first user input device to display the notification.
1 . A system for real-time overload detection using image processing analysis, the system comprising:
a processing device;
a non-transitory storage device containing instructions that, when executed by the processing device, cause the processing device to:
periodically capture a resiliency status of a device;
transform the resiliency status of the device into a first set of images, wherein transforming further comprises:
comparing each performance parameter of the device to a corresponding performance threshold; and
mapping each performance parameter to a color spectrum in a heat map, wherein performance parameters that exceed their corresponding performance thresholds are mapped to warm colors in the color spectrum according to a value of the performance parameters relative to the corresponding performance thresholds, and performance parameters that do not exceed their corresponding performance thresholds are mapped to cool colors in the color spectrum according to the value of the performance parameters relative to the corresponding performance thresholds;
deploy, using a machine learning (ML) subsystem, a trained ML model on the first set of images of the device;
determine, using the trained ML model, a change in the resiliency status of the device based on the first set of images to preemptively identify instances of device malfunction;
generate a notification indicating the change in the resiliency status of the device; and
transmit control signals configured to cause a first user input device to display the notification, wherein the notification comprises one or more actions configured to cause a change in the resiliency status of the device, wherein the change comprises at least turning off the device.
2 . The system of claim 1 , wherein, the instructions, when executed, further cause the processing device to:
retrieve one or more sets of images associated with the device;
receive, from a second user input device, one or more known resiliency statuses of the device corresponding to the one or more sets of images associated with the device;
generate a first feature set using the one or more sets of images associated with the device and the one or more known resiliency statuses corresponding to the one or more sets of images associated with the device; and
train an ML model using the first feature set to generate the trained ML model.
3 . The system of claim 2 , wherein, the instructions, when executed, further cause the processing device to:
retrieve one or more sets of images associated with one or more peer devices;
receive, from the second user input device, one or more known resiliency statuses of the one or more peer devices corresponding to the one or more sets of images associated with the one or more peer devices;
generate a second feature set using the one or more sets of images associated with one or more peer devices, and the one or more known resiliency statuses corresponding to the one or more sets of images associated with the one or more peer devices; and
train the ML model using the second feature set to generate the trained ML model.
4 . The system of claim 3 , wherein, the instructions, when executed, further cause the processing device to:
train the ML model using the first feature set and the second feature set to generate the trained ML model.
5 . The system of claim 1 , wherein the first set of images are periodic snapshots representing performance telemetry of the device, wherein the first set of images are captured at period time intervals during a first time period.
6 . The system of claim 1 , wherein, the instructions, when executed, further cause the processing device to:
determine a first resiliency status of the device, wherein the first resiliency status indicates that the device is currently operational; and
determine, using the trained ML model, that resiliency status of the device has changed from the first resiliency status to a second resiliency status, wherein the second resiliency status indicates that the device is malfunctioning based on the first set of images.
7 . A computer program product for real-time overload detection using image processing analysis, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to:
periodically capture a resiliency status of a device;
transform the resiliency status of the device into a first set of images, wherein transforming further comprises:
comparing each performance parameter of the device to a corresponding performance threshold; and
mapping each performance parameter to a color spectrum in a heat map, wherein performance parameters that exceed their corresponding performance thresholds are mapped to warm colors in the color spectrum according to a value of the performance parameters relative to the corresponding performance thresholds, and performance parameters that do not exceed their corresponding performance thresholds are mapped to cool colors in the color spectrum according to the value of the performance parameters relative to the corresponding performance thresholds;
deploy, using a machine learning (ML) subsystem, a trained ML model on the first set of images of the device;
determine, using the trained ML model, a change in the resiliency status of the device based on the first set of images to preemptively identify instances of device malfunction;
generate a notification indicating the change in the resiliency status of the device; and
transmit control signals configured to cause a first user input device to display the notification, wherein the notification comprises one or more actions configured to cause a change in the resiliency status of the device, wherein the change comprises at least turning off the device.
8 . The computer program product of claim 7 , wherein the code further causes the apparatus to:
retrieve one or more sets of images associated with the device;
receive, from a second user input device, one or more known resiliency statuses of the device corresponding to the one or more sets of images associated with the device;
generate a first feature set using the one or more sets of images associated with the device and the one or more known resiliency statuses corresponding to the one or more sets of images associated with the device; and
train an ML model using the first feature set to generate the trained ML model.
9 . The computer program product of claim 8 , wherein the code further causes the apparatus to:
retrieve one or more sets of images associated with one or more peer devices;
receive, from the second user input device, one or more known resiliency statuses of the one or more peer devices corresponding to the one or more sets of images associated with the one or more peer devices;
generate a second feature set using the one or more sets of images associated with one or more peer devices, and the one or more known resiliency statuses corresponding to the one or more sets of images associated with the one or more peer devices; and
train the ML model using the second feature set to generate the trained ML model.
10 . The computer program product of claim 9 , wherein the code further causes the apparatus to:
train the ML model using the first feature set and the second feature set to generate the trained ML model.
11 . The computer program product of claim 7 , wherein the first set of images are periodic snapshots representing performance telemetry of the device, wherein the first set of images are captured at period time intervals during a first time period.
12 . The computer program product of claim 7 , wherein the code further causes the apparatus to:
determine a first resiliency status of the device, wherein the first resiliency status indicates that the device is currently operational; and
determine, using the trained ML model, that resiliency status of the device has changed from the first resiliency status to a second resiliency status, wherein the second resiliency status indicates that the device is malfunctioning based on the first set of images.
13 . A method for real-time overload detection using image processing analysis, the method comprising:
periodically capturing a resiliency status of a device;
transforming the resiliency status of the device into a first set of images, wherein transforming further comprises:
comparing each performance parameter of the device to a corresponding performance threshold; and
mapping each performance parameter to a color spectrum in a heat map, wherein performance parameters that exceed their corresponding performance thresholds are mapped to warm colors in the color spectrum according to a value of the performance parameters relative to the corresponding performance thresholds, and performance parameters that do not exceed their corresponding performance thresholds are mapped to cool colors in the color spectrum according to the value of the performance parameters relative to the corresponding performance thresholds;
deploying, using a machine learning (ML) subsystem, a trained ML model on the first set of images of the device;
determining, using the trained ML model, a change in the resiliency status of the device based on the first set of images to preemptively identify instances of device malfunction;
generating a notification indicating the change in the resiliency status of the device; and
transmitting control signals configured to cause a first user input device to display the notification, wherein the notification comprises one or more actions configured to cause a change in the resiliency status of the device, wherein the change comprises at least turning off the device.
14 . The method of claim 13 , wherein the method further comprises:
retrieving one or more sets of images associated with the device;
receiving, from a second user input device, one or more known resiliency statuses of the device corresponding to the one or more sets of images associated with the device;
generating a first feature set using the one or more sets of images associated with the device and the one or more known resiliency statuses corresponding to the one or more sets of images associated with the device; and
training an ML model using the first feature set to generate the trained ML model.
15 . The method of claim 14 , wherein the method further comprises:
retrieving one or more sets of images associated with one or more peer devices;
receiving, from the second user input device, one or more known resiliency statuses of the one or more peer devices corresponding to the one or more sets of images associated with the one or more peer devices;
generating a second feature set using the one or more sets of images associated with one or more peer devices, and the one or more known resiliency statuses corresponding to the one or more sets of images associated with the one or more peer devices; and
training the ML model using the second feature set to generate the trained ML model.
16 . The method of claim 15 , wherein the method further comprises:
training the ML model using the first feature set and the second feature set to generate the trained ML model.
17 . The method of claim 13 , wherein the first set of images are periodic snapshots representing performance telemetry of the device, wherein the first set of images are captured at period time intervals during a first time period.