Organization of multi-level data storage

Introduction: The implementation of data storage process requires timely scaling of the infrastructure to accommodate the data received for storage. Given the rapid accumulation of data, new models of storage capacity management are needed, which should take into account the hierarchical structure of the data storage, various requirements for file storage and restrictions on the storage media size. Purpose: To propose a model for timely scaling of the storage infrastructure based on predictive estimates of the moment when the data storage media is fully filled. Results: A model of storage capacity management is presented, based on the analysis of storage system state patterns. A pattern is a matrix each cell of which reflects the filling state of the storage medium at an appropriate level in the hierarchical structure of the storage system. A matrix cell is characterized by the real, limit, and maximum values of its carrier capacity. To solve the scaling problem for a data storage system means to predict the moments when the limit capacity and maximum capacity of the data carrier are reached. The difference between the predictive estimatesis the time which the administrator has to connect extra media. It is proposed to calculate the values of the predictive estimates programmatically, using machine learning methods. It is shown that when making a short-term prediction, machine learning methods have lower accuracy than ARIMA, an integrated model of autoregression and moving average. However, when making a long-term forecast, machine learning methods provide results commensurate with those from ARIMA. Practical relevance: The proposed model is necessary for timely allocation of storage capacity for incoming data. The implementation of this model at the storage input allows you to automate the process of connecting media, which helps prevent the loss of data entering the system.

show abstract

“…The state of a DSS can be formalized as a matrix B of size m  n [17], whose elements are sets of files with assigned parameters…”

Section: Description Of the Research Object And Statement Of The Problemmentioning

confidence: 99%

Storage scaling management model

Sovetov

Tatarnikova

Poymanova

2020

ICS

Self Cite

View full text Add to dashboard Cite

show abstract

Redundant multi-path service of a flow heterogeneous in delay criticality with defined node passage paths

Bogatyrev

Bogatyrev²,

Bogatyrev³

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

An analytical model is proposed for estimating the probability of timely redundant servicing of a heterogeneous flow, which implies the creation of replicas of requests with a multiplicity depending on the total allowable waiting time in the sequence of nodes involved in servicing the request. It is shown that the reservation of queries critical to the admissible waiting time allows increasing the probability of timely execution of queries and the intensity of the profit received from servicing a non-uniform flow.

show abstract

Autoregressive models of network traffic prediction

Tatarnikova

Sovetov

Chehanovsky

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The relevance of the network traffic prediction is due to the requirement to store a large amount of data for a long time. In this regard, it is necessary to predict traffic volumes in order to take the necessary measures to protect and preserve data. The paper substantiates the use of autoregressive class models to construct predictive estimates. The results allowing substantiating the prospective requirements for the memory volumes of the node equipment of the infocommunication network are given.

show abstract

Organization of multi-level data storage

Cited by 13 publications

References 8 publications

Storage scaling management model

Storage scaling management model

Redundant multi-path service of a flow heterogeneous in delay criticality with defined node passage paths

Autoregressive models of network traffic prediction

Contact Info

Product

Resources

About