Server classification using machine learning techniques
Methods, apparatus, and processor-readable storage media for server classification using machine learning techniques are provided herein. An example computer-implemented method includes obtaining, from at least one data source, data pertaining to server activity attributed to one or more servers; processing at least a portion of the obtained data using one or more rule-based analyses; selecting at least a particular machine learning classification algorithm from a set of multiple machine learning classification algorithms, based at least in part on results from the processing and one or more portions of the obtained data; classifying an activity level of at least a portion of the one or more servers by processing at least a portion of the obtained data using the selected machine learning classification algorithm; and performing at least one automated action based at least in part on results of the classifying.
1. A computer-implemented method comprising:
obtaining, from at least one data source, data pertaining to server activity attributed to one or more servers;
processing at least a portion of the obtained data using one or more rule-based analyses, wherein processing at least a portion of the obtained data comprises performing at least one rule-based classification of at least a portion of the one or more servers based at least in part on data pertaining to one or more of login history and reboot activity;
selecting at least a particular machine learning classification algorithm from a set of multiple machine learning classification algorithms, based at least in part on results from the processing and one or more portions of the obtained data, wherein selecting at least a particular machine learning classification algorithm comprises determining multiple metric measurements for the multiple machine learning classification algorithms using at least one confusion matrix and the one or more portions of the obtained data;
classifying at least a portion of the one or more servers as belonging to one of multiple designated activity level-based categories by processing at least a portion of the obtained data using the selected machine learning classification algorithm, wherein the multiple designated activity level-based categories are based at least in part on usage of processing resources and memory resources relative to given amounts of processing resources and memory resources attributed to the at least a portion of the one or more servers; and
performing at least one automated action based at least in part on results of the classifying, wherein performing at least one automated action comprises initiating one or more reclamation operations relating to at least one of the one or more servers based at least in part on the results of the classifying;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2. The computer-implemented method of claim 1 , wherein determining multiple metric measurements comprises determining, for each of the multiple machine learning classification algorithms, a recall score, a precision score, and an F-score.
3. The computer-implemented method of claim 1 , wherein the set of multiple machine learning classification algorithms comprises two or more of at least one logistic regression algorithm, at least one linear discriminant analysis algorithm, at least one random forest algorithm, at least one support vector machine algorithm, at least one K-nearest neighbors algorithm, at least one Gaussian naïve Bayes algorithm, and at least one decision tree algorithm.
4. The computer-implemented method of claim 1 , wherein performing at least one automated action comprises initiating one or more of reclaiming at least one of the one or more servers and decommissioning at least one of the one or more servers.
5. The computer-implemented method of claim 1 , wherein performing at least one automated action comprises initiating adding resources to at least one of the one or more servers.
6. The computer-implemented method of claim 1 , wherein performing at least one automated action comprises training at least a portion of the multiple machine learning classification algorithms using the results of the classifying.
7. The computer-implemented method of claim 1 , wherein performing at least one automated action comprises generating and outputting one or more notifications, pertaining to the results of the classifying, to one or more users associated with the one or more servers.
8. The computer-implemented method of claim 1 , wherein the classifying comprises classifying the at least a portion of the one or more servers as belonging to one of at least one inactive category and at least one active category based at least in part on a given threshold level of activity.
9. The computer-implemented method of claim 1 , wherein obtaining data pertaining to server activity comprises obtaining data pertaining to one or more of login history, running processes, central processing unit (CPU) usage, memory usage, disk usage, virtual machine history reports, and network input-output analysis.
10. A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:
to obtain, from at least one data source, data pertaining to server activity attributed to one or more servers;
to process at least a portion of the obtained data using one or more rule-based analyses, wherein processing at least a portion of the obtained data comprises performing at least one rule-based classification of at least a portion of the one or more servers based at least in part on data pertaining to one or more of login history and reboot activity;
to select at least a particular machine learning classification algorithm from a set of multiple machine learning classification algorithms, based at least in part on results from the processing and one or more portions of the obtained data, wherein selecting at least a particular machine learning classification algorithm comprises determining multiple metric measurements for the multiple machine learning classification algorithms using at least one confusion matrix and the one or more portions of the obtained data;
to classify at least a portion of the one or more servers as belonging to one of multiple designated activity level-based categories by processing at least a portion of the obtained data using the selected machine learning classification algorithm, wherein the multiple designated activity level-based categories are based at least in part on usage of processing resources and memory resources relative to given amounts of processing resources and memory resources attributed to the at least a portion of the one or more servers; and
to perform at least one automated action based at least in part on results of the classifying, wherein performing at least one automated action comprises initiating one or more reclamation operations relating to at least one of the one or more servers based at least in part on the results of the classifying.
11. The non-transitory processor-readable storage medium of claim 10 , wherein determining multiple metric measurements comprises determining, for each of the multiple machine learning classification algorithms, a recall score, a precision score, and an F-score.
12. The non-transitory processor-readable storage medium of claim 10 , wherein the set of multiple machine learning classification algorithms comprises two or more of at least one logistic regression algorithm, at least one linear discriminant analysis algorithm, at least one random forest algorithm, at least one support vector machine algorithm, at least one K-nearest neighbors algorithm, at least one Gaussian naïve Bayes algorithm, and at least one decision tree algorithm.
13. The non-transitory processor-readable storage medium of claim 10 , wherein performing at least one automated action comprises initiating one or more of reclaiming at least one of the one or more servers and decommissioning at least one of the one or more servers.
14. An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to obtain, from at least one data source, data pertaining to server activity attributed to one or more servers;
to process at least a portion of the obtained data using one or more rule-based analyses, wherein processing at least a portion of the obtained data comprises performing at least one rule-based classification of at least a portion of the one or more servers based at least in part on data pertaining to one or more of login history and reboot activity;
to select at least a particular machine learning classification algorithm from a set of multiple machine learning classification algorithms, based at least in part on results from the processing and one or more portions of the obtained data, wherein selecting at least a particular machine learning classification algorithm comprises determining multiple metric measurements for the multiple machine learning classification algorithms using at least one confusion matrix and the one or more portions of the obtained data;
to classify at least a portion of the one or more servers as belonging to one of multiple designated activity level-based categories by processing at least a portion of the obtained data using the selected machine learning classification algorithm, wherein the multiple designated activity level-based categories are based at least in part on usage of processing resources and memory resources relative to given amounts of processing resources and memory resources attributed to the at least a portion of the one or more servers; and
to perform at least one automated action based at least in part on results of the classifying, wherein performing at least one automated action comprises initiating one or more reclamation operations relating to at least one of the one or more servers based at least in part on the results of the classifying.
15. The apparatus of claim 14 , wherein the set of multiple machine learning classification algorithms comprises two or more of at least one logistic regression algorithm, at least one linear discriminant analysis algorithm, at least one random forest algorithm, at least one support vector machine algorithm, at least one K-nearest neighbors algorithm, at least one Gaussian naïve Bayes algorithm, and at least one decision tree algorithm.
16. The apparatus of claim 14 , wherein performing at least one automated action comprises initiating one or more of reclaiming at least one of the one or more servers and decommissioning at least one of the one or more servers.