US 11,748,185 B2
Multi-factor cloud service storage device error prediction
Yong Xu, Beijing (CN); Qingwei Lin, Beijing (CN); and Kaixin Sui, Beijing (CN)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Appl. No. 17/56,721
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
PCT Filed Jun. 29, 2018, PCT No. PCT/CN2018/093768
§ 371(c)(1), (2) Date Nov. 18, 2020,
PCT Pub. No. WO2020/000404, PCT Pub. Date Jan. 2, 2020.
Prior Publication US 2021/0200616 A1, Jul. 1, 2021
Int. Cl. G06F 11/00 (2006.01); G06F 11/07 (2006.01); G06F 3/06 (2006.01); G06F 11/30 (2006.01); G06F 11/34 (2006.01)
CPC G06F 11/0751 (2013.01) [G06F 3/0617 (2013.01); G06F 3/0647 (2013.01); G06F 3/0683 (2013.01); G06F 11/3034 (2013.01); G06F 11/3457 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A system for proactive storage device error forecasting, the system comprising:
at least one processor; and
memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
obtain a set of storage device metrics and a set of computing system metrics, wherein the set of storage device metrics include self-monitoring, analysis, and reporting technology signals from storage devices in a cloud computing storage system and the set of computing system metrics includes system-level signals from virtual machines with operating system data residing on storage devices in the cloud computing storage system;
generate a feature set including the set of storage device metrics and the set of computing system metrics;
perform validation of features of the feature set by evaluating a validation training dataset using the features of the feature set;
create a modified feature set including validated features of the feature set;
create a storage device failure model using the modified feature set, wherein the storage device failure model determines a probability that a given storage device is likely to fail;
determine a storage device rating range by minimization of a cost of misclassification of a storage device, wherein a first cost of misclassification of a storage device is identified as having a high probability of failure and a second cost of misclassification of the storage device is identified as not having a high probability of failure, wherein the storage device rating range is a number of misclassified storage devices that result in the lowest sum of the number multiplied by each of the first cost and the second cost;
identify a set of storage devices to produce an indication of storage devices having a high probability of failure, wherein the set of storage devices includes a number of storage devices within the storage device rating range, and wherein a storage device in the set of storage devices is ranked based on an evaluation of the storage device using the storage device failure model; and
migrate a virtual machine instance from a first storage device of the set of storage devices to a second storage device of the set of storage devices based on the ranked set of storage devices.