17847449. SYSTEMS AND METHODS OF FORECASTING TEMPERATURES OF STORAGE OBJECTS USING MACHINE LEARNING simplified abstract (Dell Products L.P.)
Contents
SYSTEMS AND METHODS OF FORECASTING TEMPERATURES OF STORAGE OBJECTS USING MACHINE LEARNING
Organization Name
Inventor(s)
Shaul Dar of Petach Tikva (IL)
Ramakanth Kanagovi of Bengaluru, Karnataka (IN)
Vamsi K. Vankamamidi of Hopkinton MA (US)
Guhesh Swaminathan of Chennai, Tamil Nadu (IN)
Swati Smita Sitha of Bommanahalli, Bengaluru (IN)
SYSTEMS AND METHODS OF FORECASTING TEMPERATURES OF STORAGE OBJECTS USING MACHINE LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 17847449 titled 'SYSTEMS AND METHODS OF FORECASTING TEMPERATURES OF STORAGE OBJECTS USING MACHINE LEARNING
Simplified Explanation
The patent application describes techniques for using machine learning to forecast temperatures of storage objects in a storage system. These techniques involve using machine learning models to forecast temperatures, adjusting storage based on the forecasted temperatures, and obtaining performance metrics associated with the storage objects.
- Techniques for forecasting temperatures of storage objects using machine learning models
- Modifying storage based on the forecasted temperatures
- Obtaining performance metrics associated with the storage objects
- Varying the frequency of temperature forecasting based on performance metrics
- Retraining machine learning models based on performance metrics
- Adjusting operational parameters of the system based on performance metrics
Potential applications of this technology:
- Data centers and cloud storage systems
- Industrial storage systems
- Cold storage facilities
Problems solved by this technology:
- Inaccurate temperature forecasting in storage systems
- Inefficient storage management based on inaccurate temperature forecasts
Benefits of this technology:
- Increased accuracy in temperature forecasting
- Improved performance in terms of IO latency, IO operations per second, and bandwidth
- More efficient storage management
Original Abstract Submitted
Techniques for forecasting temperatures of storage objects in a storage system using machine learning (ML). The techniques can include forecasting at least one temperature of a storage object using at least one ML model, modifying storage of the storage object based on the at least one temperature of the storage object, and, having modified storage of the storage object, obtaining at least one performance metric associated with the storage object. The techniques can further include, based on the performance metric(s), varying a frequency of forecasting the at least one temperature of the storage object, retraining the at least one ML model used in forecasting the at least one temperature, and/or adjusting at least one operational parameter of the system. The techniques provide increased accuracy over known statistical approaches to forecasting temperatures of storage objects, leading to increased performance gains in terms of IO latency, IO operations per second, and bandwidth.
