A rough set-based hypergraph trust measure parameter selection technique for cloud service selection

Abstract

Selection of trustworthy cloud services has been a major research challenge in cloud computing, due to the proliferation of numerous cloud service providers (CSPs) along every dimension of computing. This scenario makes it hard for the cloud users to identify an appropriate CSP based on their unique quality of service (QoS) requirements. A generic solution to the problem of cloud service selection can be formulated in terms of trust assessment. However, the accuracy of the trust value depends on the optimality of the service-specific trust measure parameters (TMPs) subset. This paper presents TrustCom—a novel trust assessment framework and rough set-based hypergraph technique (RSHT) for the identification of the optimal TMP subset. Experiments using Cloud Armor and synthetic trust feedback datasets show the prominence of RSHT over the existing feature selection techniques. The performance of RSHT was analyzed using Weka tool and hypergraph-based computational model with respect to the reduct size, time complexity and service ranking.

Glossary

Abstract

CSPs:

Cloud service providers

CUs:

Cloud users

QoS:

Quality of service

TMPs:

Trust measure parameters

RSHT:

Rough set-based hypergraph technique

HGCM:

Hypergraph-based computational model

Introduction

XaaS:

Something as a Service

RST:

Rough set theory

SQR:

Supervised quick reduct

QRR:

Quick relative reduct

CSMIC–SMI:

Cloud Services Measurement Initiative Consortium–Service Measurement Index

IEEE:

Institute of Electrical and Electronics Engineers

TrustCom and RSHT for the identification of trustworthy cloud service providers

CSRD:

Cloud service registry and discovery

TCE:

Trust computation engine

SLA:

Service-level agreement

IdM:

Identity management

Rough set-hypergraph-based trust measure parameter selection technique

$D_T$ :

Decision table

$S= \left\{ {S_1, S_2, \ldots , S_n }\right\}$ :

Samples in the decision table

$\hbox {CA}= \left\{ {\hbox {CA}_1, \hbox {CA}_2, \ldots , \hbox {CA}_m }\right\}$ :

Set of conditional attributes

$\hbox {DA}$ :

Decisional attribute

$H \leftarrow \{\hbox {TMP}, \hbox {TMPR}^{\prime }\}$ :

Hypergraph constructed with TMPs as vertices and TMPR$^{\prime }$ as hyperedges

$TMP \leftarrow \{\hbox {TMP}_1, \hbox {TMP}_2, \ldots , \hbox {TMP}_n \}$ :

TMPs in a reduct

$\hbox {TMPR}^{{\prime }}\leftarrow \left\{ {\hbox {TMPR}_1^{\prime }, \hbox {TMPR}_2^{\prime }, \ldots , \hbox {TMPR}_t^{\prime } }\right\}$ :

Reduct obtained from RST

$\gamma \hbox {TMPR}^{{\prime }}\left( {\hbox {DA}}\right)$ :

The dependency of $\hbox {TMPR}^{{\prime }}$ with $\hbox {DA}$

$\gamma \hbox {CA}\left( {\hbox {DA}}\right)$ :

The dependency of $\hbox {CA}$ with $\hbox {DA}$

$H_T \left\{ {\hbox {TMP}}\right\}$ :

Sets that satisfy minimal transversal property of hypergraph

$H_\mathrm{EXT} \left\{ {\hbox {TMP}}\right\}$ :

Sets that satisfy vertex linearity property of hypergraph

$H_\mathrm{DIS} \left\{ {\hbox {TMP}}\right\}$ :

Sets that neither satisfy minimal transversal nor vertex linearity property

k :

Number of elements in $\hbox {TMPR}_1^{\prime }$

r :

Number of reducts

$\hbox {TMP}_\mathrm{Opt}$ :

Optimal TMP subset

KPIs:

Key performance indicators

Experimental analysis

$T_n$ :

Number of features

$S_n$ :

Number of samples

$H_n$ :

Number of elements in hyperedges