Abstract:
Protecting data from loss is important in many domains, particularly business. Businesses generally employ third-party protection services to routinely back up data to st...Show MoreMetadata
Abstract:
Protecting data from loss is important in many domains, particularly business. Businesses generally employ third-party protection services to routinely back up data to storage. As the scale of the backup system and the volume of backup data continue to grow significantly, backup jobs fail increasingly frequently. In this study, we present an analysis of data protection system reports written over two years and collected from 3,500 backup systems. We found that inadequate capacity is among the two most frequent causes of the failure of backups. Little research has targeted the development of a forecasting tool to predict the backup storage capacity to mitigate this failure, and accurate prediction becomes more challenging as the number of clients served by the storage increases. Our research highlights the characteristics of enterprise backup storage data and uses the information examined here to develop a forecasting structure. We tested our forecasting structure on empirically obtained data. In comparison with a prevalent backup system forecasting tool, our structure provides better and more robust predictions of the capacity of backup storage systems as well as the size of data generated by a given number of clients and the associated deduplication ratios.
Published in: 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)
Date of Conference: 10-12 October 2019
Date Added to IEEE Xplore: 13 February 2020
ISBN Information: