Method and system for determining computer fan usage and maintenance
A system, method, and computer-readable medium are disclosed for attesting determining computer system fan usage and maintenance. A determination is made as to the architectural diagram or layout of a computer system. The diagram or layout shows components and fans that support the components. The architectural diagram or layout, where each virtual section shows a fan and the components. Operational load is determined for each virtual section over a period of time. A threshold value for particular periods to time, where the threshold value either is to low load periods or as to periods to increase or decrease speed of the fan to address operational load of the components.
1. A computer-implementable method for determining computer system fan usage and maintenance comprising:
determining by a machine learning/artificial intelligence (ML/AI) platform an architectural layout of the computer system;
dividing by the ML/AI platform, the architectural layout into machine readable virtual sections as to multiple and distinct sections that include operational boundaries of cooling fans;
reading and applying algorithms of the ML/AI platform to each virtual section to predict work load of the cooling fans, by summing the load of each cooling fan represented in a respective virtual section based on a period of time;
using the loads to adjust speed of cooling fans and proactively address temperature changes;
collecting loads of the virtual section used for replacing and adjusting fans based on historical and predicted loads;
calculating by the ML/AI platform based on a threshold value applied to the algorithms, periods of operational load over the period of time; and
adjusting the speed of the cooling fans based on the periods of operational load.
2. The method of claim 1 further comprising providing periods for fan replacement if the threshold value is a low operational load value.
3. The method of claim 2 , wherein a value of “n” are time units a dispatch for a replacement fan was last provided, and “n” can be determined by a service agreement or the number of time units left for fan failure.
4. The method of claim 1 further comprising providing periods to adjust fan speed based on an increase or decrease of operational load value.
5. The method of claim 1 , wherein the determining architectural layout of the computer system comprises fetching a specific architectural layout from a repository.
6. The method of claim 1 , wherein the determining operational load comprises creating a load graph.
7. The method of claim 1 , wherein the determining operational load is based on historical and current telemetry information of components.
8. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
determining by a machine learning/artificial intelligence (ML/AI) platform an architectural layout of the computer system;
dividing by the ML/AI platform, the architectural layout into machine readable virtual sections as to multiple and distinct sections that include operational boundaries of cooling fans;
reading and applying algorithms of the ML/AI platform to each virtual section to predict work load of the cooling fans, by summing the load of each cooling fan represented in a respective virtual section based on a period of time;
using the loads to adjust speed of cooling fans and proactively address temperature changes;
collecting loads of the virtual section used for replacing and adjusting fans based on historical and predicted loads;
calculating by the ML/AI platform based on a threshold value applied to the algorithms, periods of operational load over the period of time; and
adjusting the speed of the cooling fans based on the periods of operational load.
9. The system of claim 8 further comprising providing periods for fan replacement if the threshold value is a low operational load value.
10. The system of claim 9 , wherein a value of “n” are time units a dispatch for a replacement fan was last provided, and “n” can be determined by a service agreement or the number of time units left for fan failure.
11. The system of claim 8 further comprising providing periods to adjust fan speed based on an increase or decrease of operational load value.
12. The system of claim 8 , wherein the determining architectural layout of the computer system comprises fetching a specific architectural layout from a repository.
13. The system of claim 8 , wherein the determining operational load comprises creating a load graph.
14. The system of claim 8 , wherein the determining operational load is based on historical and current telemetry information of components.
15. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured to:
determine by a machine learning/artificial intelligence (ML/AI) platform an architectural layout of the computer system;
divide by the ML/AI platform, the architectural layout into machine readable virtual sections as to multiple and distinct sections that include operational boundaries of cooling fans;
read and apply algorithms of the ML/AI platform to each virtual section to predict work load of the cooling fans, by summing the load of each cooling fan represented in a respective virtual section based on a period of time;
use the loads to adjust speed of cooling fans and proactively address temperature changes;
collect loads of the virtual section used for replacing and adjusting fans based on historical and predicted loads;
calculate by the ML/AI platform based on a threshold value applied to the algorithms, periods of operational load over the period of time; and
adjust the speed of the cooling fans based on the periods of operational load.
16. The non-transitory, computer-readable storage medium of claim 15 further comprising instructions to provide periods for fan replacement if the threshold value is a low operational load value.
17. The non-transitory, computer-readable storage medium of claim 15 further comprising instructions to provide periods to adjust fan speed based on an increase or decrease of operational load value.
18. The non-transitory, computer-readable storage medium of claim 15 , wherein the instructions to determine architectural layout of the computer system comprises fetching a specific architectural layout from a repository.
19. The non-transitory, computer-readable storage medium of claim 15 , wherein the instructions to determine operational load comprises creating a load graph.
20. The non-transitory, computer-readable storage medium of claim 15 , wherein the instructions to determine operational load is based on historical and current telemetry information of components.