Data storage device adjusting refresh monitor based on a learning based feedback control

1. A data storage device, comprising:

a magnetic media comprising a plurality of data tracks;

a head actuated over the magnetic media; and

control circuitry configured to:

maintain an adaptive feedback control refresh monitor for a refresh zone of the magnetic media, the refresh monitor being based on a reinforcement learning system;

analyze a read operation with the refresh monitor;

adjust the refresh monitor by updating the one or more probability distributions based on the analyzed read operation;

execute a refresh operation to refresh data in the refresh zone based on the adjusted refresh monitor;

update a distribution curve;

calculate a new estimated degree of data degradation per write; and

increment a refresh counter based on the calculated new estimated degree of data degradation per write.

2. The data storage device as recited in claim 1 , wherein the control circuitry is further configured to adjust refresh monitor by:

determining a level of damage at the location of the read operation; and

updating the one or more probability distributions based on the determined level of damage.

3. The data storage device as recited in claim 2 , wherein the control circuitry is further configured to adjust the refresh monitor by:

using the updated one or more probability distributions to derive an updated weight value of damage per write operation; and

using the damage per write operation weight value to estimate accumulated damage a media location has experienced to update a refresh policy for the media location.

4. The data storage device as recited in claim 2 , wherein the control circuitry is further configured to determine a level of damage from a read operation by measuring the degradation of the data read in the read operation based on a depth of an error recovery procedure.

5. The data storage device as recited in claim 4 , wherein the read operation is a host read operation.

6. The data storage device as recited in claim 4 , wherein the read operation is a refresh read operation.

7. A data storage device, comprising:

a magnetic media;

a head actuated over the magnetic media; and

control circuitry configured to:

maintain a reinforcement learning based refresh monitor for a refresh zone of the magnetic media;

analyze a read operation to determine a level of damage to the data occurring at the location being read;

update one or more probability distributions based on that determined level of damage;

determine an updated weight associated with a damage per write count for a location within the refresh zone;

use the updated weight to control a frequency of refresh operations to refresh data in the refresh zone;

update a distribution curve;

calculate a new estimated degree of data degradation per write; and

increment a refresh counter based on the calculated new estimated degree of data degradation per write.

8. The data storage device as recited in claim 7 , wherein the control circuitry is further configured to determine a level of damage to the data from the read operation by using one or more of:

a quality of the read signal,

a number of bit errors detected by an error correction code,

a depth of error recovery procedures needed to recovery the data, and

a time needed to recovery the data.

9. The data storage device as recited in claim 7 , wherein the read operation is a host read operation.

10. The data storage device as recited in claim 7 , wherein the read operation is a refresh read operation.

11. A method of mitigating adjacent track interference, the method comprising:

maintaining a reinforcement learning based refresh monitor for a refresh zone of the magnetic media, the reinforcement learning being based on one or more probability distributions correlated to respective write counts being tracked by the refresh monitor;

analyzing a read operation;

deriving a damage metric from a read operation to determine a level of damage occurring at the location being read;

updating one or more probability distributions based on the damage metric;

using the updated one or more probability distributions to control frequency of refresh operations in the refresh zone;

updating a distribution curve;

calculating a new estimated degree of data degradation per write; and

incrementing a refresh counter based on the calculated new estimated degree of data degradation per write.

12. The method as recited in claim 11 , wherein the one or more probability distributions are correlated to respective write counts being tracked by the refresh monitor.

13. The method as recited in claim 11 , wherein the one or more probability distributions is used to generate damage per write estimates used by the refresh monitor to control the frequency of refresh operations.

14. The method as recited in claim 11 , wherein frequency of deriving damage metric from a read operation is controlled by the refresh monitor.

15. The method as recited in claim 11 , wherein the read operation is a host read operation.

16. The method as recited in claim 11 , wherein the read operation is a refresh read operation.