Analyzing storage systems using machine learning systems
A method is used in analyzing a storage system using a machine learning system. Data gathered from information associated with operations performed in a storage system is analyzed. The storage system is comprised of a plurality of components. A bitmap image is created based on the gathered data, where at least one of the plurality of components is represented in the bitmap image. The machine learning system is trained using the bitmap image, where the bitmap image is organized to depict the plurality of components of the storage system.
1. A method of analyzing a storage system using a machine learning system, the method comprising:
analyzing data gathered from information associated with operations performed in a storage system, wherein the storage system is comprised of a plurality of components;
mapping text messages from event logs into a bitmap image, wherein the gathered data comprises the text messages;
creating the bitmap image based on the gathered data, wherein at least one of the plurality of components is represented in the bitmap image; and
training the machine learning system using the bitmap image, wherein the bitmap image is organized to depict the plurality of components of the storage system, wherein the machine learning system is trained to detect malfunctions of hardware and software components represented by a bitmap image using a plurality of hidden layers, wherein the plurality of components of the storage system comprises the hardware and software components and wherein the detected malfunctions are mapped to bitmap pixels in the bitmap image.
2. The method of claim 1 , further comprising:
detecting, by the machine learning system, a malfunction attributed to at least one component of the plurality of components depicted in the bitmap image by analyzing the bitmap image.
3. The method of claim 2 , further comprising:
detecting a change between the bitmap image and a second bitmap image created from a different set of data.
4. The method of claim 2 , further comprising:
modifying a representation of the at least one component of the plurality of components in a graphical user interface to indicate the detected malfunction.
5. The method of claim 1 , wherein the information associated with the operations performed in the storage system includes at least one of event logs and statistics gathered from the plurality of components of the storage system upon detection of a malfunction in at least one component of the plurality of components.
6. The method of claim 1 , wherein the data gathered from information associated with operations performed in the storage system is gathered by using a cloud based management application.
7. The method of claim 1 , wherein creating the bitmap image based on the gathered data further comprises:
depicting each component of the plurality of components as a bitmap object in the bitmap image, wherein each bitmap object has a different shape and is associated with a different sized pixel based on an importance associated with the each component in the storage system.
8. The method of claim 1 , wherein training the machine learning system using the bitmap image comprises:
training the machine learning system to detect at least one of:
i) an object shape;
ii) an object edge;
iii) a plurality of pixels;
iv) a color associated with at least one pixel in the bitmap image; and
v) at least one interaction between the plurality of components in the storage system.
9. The method of claim 1 , wherein training the machine learning system using the bitmap image comprises:
training the machine learning system to analyze the bitmap image to detect the difference between occurrence of at least one of malfunctions in the storage system and normal functioning of the storage system.
10. A system for use in analyzing a storage system using a machine learning system, the system comprising a processor configured to:
analyze data gathered from information associated with operations performed in a storage system, wherein the storage system is comprised of a plurality of components;
map text messages from event logs into a bitmap image, wherein the gathered data comprises the text messages;
create the bitmap image based on the gathered data, wherein at least one of the plurality of components is represented in the bitmap image; and
train the machine learning system using the bitmap image, wherein the bitmap image is organized to depict the plurality of components of the storage system, wherein the machine learning system is trained to detect malfunctions of hardware and software components represented by a bitmap image using a plurality of hidden layers, wherein the plurality of components of the storage system comprises the hardware and software components and wherein the detected malfunctions are mapped to bitmap pixels in the bitmap image.
11. The system of claim 10 , further configured to:
detect, by the machine learning system, a malfunction attributed to at least one component of the plurality of components depicted in the bitmap image by analyzing the bitmap image.
12. The system of claim 11 , further configured to:
detect a change between the bitmap image and a second bitmap image created from a different set of data.
13. The system of claim 11 , further configured to:
modify a representation of the at least one component of the plurality of components in a graphical user interface to indicate the detected malfunction.
14. The system of claim 10 , wherein the information associated with the operations performed in the storage system includes at least one of event logs and statistics gathered from the plurality of components of the storage system upon detection of a malfunction in at least one component of the plurality of components.
15. The system of claim 10 , wherein the data gathered from information associated with operations performed in the storage system is gathered by using a cloud based management application.
16. The system of claim 10 , wherein the processor configured to create the bitmap image based on the gathered data further is further configured to:
depict each component of the plurality of components as a bitmap object in the bitmap image, wherein each bitmap object has a different shape and is associated with a different sized pixel based on an importance associated with the each component in the storage system.
17. The system of claim 10 , wherein the processor configured to train the machine learning system using the bitmap image is further configured to:
train the machine learning system to detect at least one of:
i) an object shape;
ii) an object edge;
iii) a plurality of pixels;
iv) a color associated with at least one pixel in the bitmap image; and
v) at least one interaction between the plurality of components in the storage system.
18. The system of claim 10 , wherein the processor configured to train the machine learning system using the bitmap image is further configured to:
train the machine learning system to analyze the bitmap image to detect the difference between occurrence of at least one of malfunctions in the storage system and normal functioning of the storage system.
19. A computer program product for analyzing a storage system using a machine learning system, the computer program product comprising:
a computer readable storage medium having computer executable program code embodied therewith, the program code executable by a computer processor to:
analyze data gathered from information associated with operations performed in a storage system, wherein the storage system is comprised of a plurality of components;
map text messages from event logs into a bitmap image, wherein the gathered data comprises the text messages;
create the bitmap image based on the gathered data, wherein at least one of the plurality of components is represented in the bitmap image; and
train the machine learning system using the bitmap image, wherein the bitmap image is organized to depict the plurality of components of the storage system, wherein the machine learning system is trained to detect malfunctions of hardware and software components represented by a bitmap image using a plurality of hidden layers, wherein the plurality of components of the storage system comprises the hardware and software components and wherein the detected malfunctions are mapped to bitmap pixels in the bitmap image.
20. A method of analyzing a storage system using a machine learning system, the method comprising:
analyzing data gathered from information associated with operations performed in a storage system, wherein the storage system is comprised of a plurality of components, wherein the data is gathered from a cloud based management application;
mapping text messages from event logs into a bitmap image, wherein the gathered data comprises the text messages;
creating the bitmap image based on the gathered data, wherein at least one of the plurality of components is represented in the bitmap image; and
training the machine learning system to analyze, in a cloud based environment, the bitmap image to detect the difference between occurrence of at least one of malfunctions in the storage system and normal functioning of the storage system, wherein the machine learning system is trained to detect malfunctions of hardware and software components represented by a bitmap image using a plurality of hidden layers, wherein the plurality of components of the storage system comprises the hardware and software components and wherein the detected malfunctions are mapped to bitmap pixels in the bitmap image.