View source for 17869002. DATA STORAGE SYSTEM WITH SELF TUNING BASED ON CLUSTER ANALYSIS OF WORKLOAD FEATURES simplified abstract (Dell Products L.P.)

=DATA STORAGE SYSTEM WITH SELF TUNING BASED ON CLUSTER ANALYSIS OF WORKLOAD FEATURES=


==Organization Name==

[[:Category:Dell Products L.P.|Dell Products L.P.]]


[[Category:Dell Products L.P.]]

==Inventor(s)==

[[:Category:Shaul Dar of Petach Tikva (IL)|Shaul Dar of Petach Tikva (IL)]][[Category:Shaul Dar of Petach Tikva (IL)]]

[[:Category:Paras Pandya of Anand (IN)|Paras Pandya of Anand (IN)]][[Category:Paras Pandya of Anand (IN)]]

[[:Category:Vamsi K. Vankamamidi of Hopkinton MA (US)|Vamsi K. Vankamamidi of Hopkinton MA (US)]][[Category:Vamsi K. Vankamamidi of Hopkinton MA (US)]]

[[:Category:Owen Martin of Hopedale MA (US)|Owen Martin of Hopedale MA (US)]][[Category:Owen Martin of Hopedale MA (US)]]

==DATA STORAGE SYSTEM WITH SELF TUNING BASED ON CLUSTER ANALYSIS OF WORKLOAD FEATURES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17869002 titled 'DATA STORAGE SYSTEM WITH SELF TUNING BASED ON CLUSTER ANALYSIS OF WORKLOAD FEATURES

==Simplified Explanation==

The patent application describes a data storage system that uses a tuner to collect data samples and calculate feature measures for data storage operations. These feature measures are then analyzed using cluster and classification analysis to identify dominating features and generate workload profiles. The system can automatically adjust processing mechanisms based on these profiles and performance or efficiency goals.

* The data storage system includes a tuner that collects data samples and calculates feature measures for data storage operations.
* Cluster analysis is applied to the feature measures to define clusters and assign the feature measures to these clusters.
* Classification analysis is then applied to the feature measures labeled by their clusters to identify dominating features of each cluster.
* Workload profiles are generated for the clusters based on the dominating features.
* Configurable processing mechanisms, such as caching or tiering, are automatically adjusted based on the workload profiles and performance or efficiency goals.

Potential applications of this technology:

* Data storage optimization: The system can help optimize data storage operations by automatically adjusting processing mechanisms based on workload profiles and performance or efficiency goals.
* Performance improvement: By identifying dominating features and generating workload profiles, the system can help improve the performance of data storage operations.
* Efficiency enhancement: The automatic adjustment of processing mechanisms based on workload profiles can lead to increased efficiency in data storage operations.

Problems solved by this technology:

* Manual workload analysis: The system eliminates the need for manual analysis of workload data by automatically generating workload profiles based on feature measures and dominating features.
* Inefficient processing mechanisms: The system addresses the problem of inefficient processing mechanisms by automatically adjusting them based on workload profiles and performance or efficiency goals.

Benefits of this technology:

* Automation: The system automates the process of workload analysis and adjustment of processing mechanisms, reducing the need for manual intervention.
* Optimization: By adjusting processing mechanisms based on workload profiles and performance or efficiency goals, the system helps optimize data storage operations.
* Improved performance and efficiency: The identification of dominating features and generation of workload profiles can lead to improved performance and efficiency in data storage operations.


==Original Abstract Submitted==

A data storage system includes a tuner that obtains data samples for data storage operations of workloads and calculates feature measures for a set of features of the data storage operations over aggregation intervals of an operating period. It further (1) applies a cluster analysis to the feature measures to define a set of clusters, and assigns the feature measures to the clusters, and (2) applies a classification analysis to the feature measures labelled by their clusters to identify dominating features of each cluster, and generates workload profiles for the clusters based on the dominating features, and then automatically adjusts configurable processing mechanisms (e.g., caching or tiering) based on the workload profiles and performance or efficiency goals.



[[Category:G06F3/06]]