Ensuring performance and provider profit through data replication in cloud systems

Abstract

Cloud computing is a relatively recent computing paradigm that is often the answer for dealing with large amounts of data. Tenants expect the cloud providers to keep supplying an agreed upon quality of service, while cloud providers aim to increase profits as it is a key ingredient of any economic enterprise. In this paper, we propose a data replication strategy for cloud systems that satisfies the response time objective for executing queries while simultaneously enables the provider to return a profit from each execution. The proposed strategy estimates the response time of the queries and performs data replication in a way that the execution of any particular query is still estimated to be profitable for the provider. We show with simulations that how the proposed strategy fulfills these two criteria.

Security Enhanced Model for Cloud Data Based on Dynamic Data Fragmentation and Replication (DDFR)

“…N.Mansouri and M.M.Javidi [9] develops a Prefetching-aware Data Replication methods for enhance the availability of cloud data. With the file access history replication scheme determines the connection of the files and retrieve the widely accessed files.…”

Comparing energy-aware vs. cost-aware data replication strategy

“…Other strategies take into account the provider profit as decision criterion when replicating. In the proposed strategy in [6], data replication is triggered in order to simultaneously satisfy both the QoS for the tenant and the profit for the provider. Both revenues and expenditures of the provider are estimated when the expenditures include the replication cost.…”

“…Strategy Availability Performance Profit Energy [24] yes no no no [25] yes yes no no [26] yes yes no no [4] no yes no no [27] yes yes no no [3] yes no no no [28] no no no yes [21] yes yes no yes [5] no yes no yes [22] yes yes no yes [23] yes no no yes [18] yes no yes no [19] yes yes yes no [20] yes yes yes no [6] yes yes yes no [13] yes yes yes yes In this article, we estimate the energy consumption for each component of a computing server from Central Processing Unit (CPU) to Network Interface Controller (NIC). For each one of them, we provide: (i) an estimation of the static energy consumption, which represents the idle energy consumption of the component, and (ii) the dynamic energy consumption of the component, which is the energy consumed by executing a task.…”

“…In fact, data replication strategies have been set up to increase availability [3], to decrease response time [4] and to reduce energy consumption [5]. These strategies answer to four questions [6] : Which data to replicate? When to replicate?…”

A data replication strategy for document-oriented NoSQL systems

“…Hence, provider expenditures should include these penalties. In formula (7), the penalties paid from the provider to this tenant when one/several SLO i is/are not satisfied is also considered (Tos et al, 2017). The estimation of the provider expenditures when evaluating Q (Expense Q ) is shown in formula (7).…”