Application of Machine Learning Algorithm in Computer Data Remote Backup System

People have higher and higher requirements for information sharing, and have put forward higher demands in terms of storing and exchanging data. Remote backup is the process of copying all or part of the data set from the application host's hard disk or array to other storage media in order to prevent data loss due to system operation errors or system failures. Remote backup is affected by network speed and bandwidth limitations, which sometimes results in low backup efficiency. In addition, there are interruptions, errors, etc. in the backup process, and data backup requires a large amount of storage space, so effective management and optimization of storage resources need to be considered. In order to improve the performance of computer data remote backup, this article proposes to apply machine learning algorithms to the backup system, thereby improving the classification and filtering of data storage and improving the efficiency and quality of data backup. Several common machine learning algorithms (decision tree, artificial neural network, Bayesian, random forest and stochastic gradient algorithm) are systematically tested to compare their advantages in terms of time consumption. In addition, the advantages and disadvantages of full backup, differential backup and incremental backup are compared. The experimental results show that the time spent by the stochastic gradient algorithm in backup is 2100ms when the file size is 2000kb, 3900ms when the file size is 4000kb, and 8907ms when the file size is 10000kb.