18507519. IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS simplified abstract (Google LLC)
Contents
- 1 IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS
Organization Name
Inventor(s)
Gufeng Zhang of San Jose CA (US)
Milad Olia Hashemi of San Francisco CA (US)
Ashish V. Naik of Los Altos CA (US)
IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18507519 titled 'IMAGE MODELS TO PREDICT MEMORY FAILURES IN COMPUTING SYSTEMS
Simplified Explanation
The patent application describes a method for predicting the likelihood of a future computer memory failure using machine learning models trained on correctable memory error data.
- Training data inputs are obtained, each including correctable memory error data and data indicating whether the errors produced a failure.
- Image representations of the correctable memory error data are generated for each training data input.
- Machine learning models process the image representations to output an estimated likelihood of a future memory failure.
- Model parameters are updated based on the computed difference between the estimated likelihood and actual failure data.
Potential Applications
This technology could be applied in:
- Data centers to proactively identify and replace faulty memory modules.
- Manufacturing processes to improve quality control by predicting memory failures in advance.
Problems Solved
This technology addresses the following issues:
- Unplanned downtime due to memory failures.
- Data loss or corruption caused by memory errors.
Benefits
The benefits of this technology include:
- Increased reliability and uptime of computer systems.
- Cost savings by replacing faulty memory components before failures occur.
Potential Commercial Applications
The technology could be commercially applied in:
- IT infrastructure management tools.
- Hardware diagnostic software solutions.
Possible Prior Art
One possible prior art is the use of machine learning models to predict hardware failures in other components, such as hard drives or processors.
=== What is the accuracy rate of the machine learning model in predicting memory failures? The article does not specify the exact accuracy rate of the machine learning model in predicting memory failures.
=== How does this method compare to traditional methods of detecting memory errors? The article does not provide a direct comparison between this method and traditional methods of detecting memory errors.
Original Abstract Submitted
Methods, systems and apparatus, including computer programs encoded on computer storage medium, for predicting a likelihood of a future computer memory failure. In one aspect training data inputs are obtained, where each training data input includes correctable memory error data that describes correctable errors that occurred in a computer memory and data indicating whether the correctable errors produced a failure of the computer memory. For each training data input, image representations of the correctable memory error data included in the training data input are generated. The image representations are processed using a machine learning model to output an estimated likelihood of a future failure of the computer memory. A difference between the estimated likelihood of the future failure of the computer memory and the data indicating whether the correctable errors produced a failure of the computer memory is computed. Values of model parameters are updated using the computed difference.
