ML-driven risk estimation for memory failure in a data center environment with convolutional neural networks, self-supervised data labeling and distribution-based model drift determination.
Tim BreitenbachShrikanth Malavalli DivakarLauritz RasbachPatrick JahnkePublished in: J. Parallel Distributed Comput. (2024)
Keyphrases
- probability distribution
- experimental data
- data sets
- data center
- estimation process
- input data
- real time
- probability density
- subject specific
- database
- databases
- low cost
- sensor data
- data distribution
- data sources
- sensor networks
- computer systems
- energy consumption
- probabilistic model
- statistical methods
- historical data
- risk assessment
- information technology
- training data