Integrated failure prediction with system modeling

A computer system comprising:

• a memory storing instructions;
• and
• a processor communicatively coupled to the memory and configured to execute the instructions to:
• receive operations data of a device in a data center, the operations data comprising operations conducted by the device associated with processor compute operations, memory operations, and input/output (I/O) operations;
• determine a consumption ratio from the operations data with the processor compute operations as a ratio of the memory operations to the I/O operations during a time range, wherein the processor compute operations comprise instruction dumps of the device;
• generate a consumption variance tree data structure using the consumption ratio associated with the processor compute operations, the memory operations, and the I/O operations, wherein the consumption variance tree data structure records a pattern of the consumption ratio over the time range and a failure event of the device, and wherein the failure event is identified in the consumption variance tree data structure;
• provide the consumption variance tree data structure for training a system characterization machine learning (ML) model, wherein the system characterization ML model is trained to detect operational events prior to a failure event of the device in the data center, and wherein the failure event of the device involves an adjustment to the consumption ratio associated with the operations conducted by the device;
• and
• implement an inference process using the trained system characterization ML model, output from the trained system characterization ML model generating a failure prediction of other devices in the data center in association with the time range.

A non-transitory computer-readable storage medium storing a plurality of instructions executable by a processor, the plurality of instructions when executed by the processor cause the processor to:

• receive operations data of a device in a data center, the operations data comprising operations conducted by the device associated with processor compute operations, memory operations, and input/output (I/O) operations, wherein the processor compute operations, the memory operations, and the I/O operations are determined by processing offline analytics on instruction dumps;
• determine a consumption ratio from the operations data with the processor compute operations as a ratio of the memory operations to the I/O operations during a time range;
• generate a consumption variance tree data structure using the consumption ratio associated with the processor compute operations, the memory operations, and the I/O operations, wherein the consumption variance tree data structure records a pattern of the consumption ratio over the time range and a failure event of the device, and wherein the failure event is identified in the consumption variance tree data structure;
• provide the consumption variance tree data structure for training a system characterization machine learning (ML) model, wherein the system characterization ML model is trained to detect operational events prior to a failure event of the device in the data center, and wherein the failure event of the device involves an adjustment to the consumption ratio associated with the operations conducted by the device;
• and
• implement an inference process using the trained system characterization ML model, output from the trained system characterization ML model generating a failure prediction of other devices in the data center in association with the time range.