V. S. Shankar Sriram

A computational model for ranking cloud service providers using hypergraph based techniques

Abstract In a cloud marketplace, the existence of wide range of Cloud Service Providers (CSPs) makes it hard for the Cloud Users (CUs) to find an appropriate CSP based on their requirements. The design of a suitable service selection framework helps the users in the selection of a suitable CSP, while motivating the CSPs to satisfy the assured Service Level Agreement (SLA) and enhance the Quality of Service (QoS). Existing service selection models employ random assignment of weights to the QoS attributes, replacement of missing data by random values, etc. which results in an inaccurate ranking of the CSPs. Moreover, these models have high computational overhead. In this study, a novel cloud service selection architecture, Hypergraph based Computational Model (HGCM) and Minimum Distance-Helly Property (MDHP) algorithm have been proposed for ranking the cloud service providers. Helly property of the hypergraph had been used to assign weights to the attributes and reduce the complexity of the ranking model, while arithmetic residue and Expectation–Maximization (EM) algorithms were used to impute missing values. Experimental results provided by MDHP under different case studies (dataset used by various research communities and synthetic dataset) confirms the ranking algorithm to be scalable and computationally attractive.

A Hypergraph and Arithmetic Residue-based Probabilistic Neural Network for classification in Intrusion Detection Systems

Over the past few decades, the design of an intelligent Intrusion Detection System (IDS) remains an open challenge to the research community. Continuous efforts by the researchers have resulted in the development of several learning models based on Artificial Neural Network (ANN) to improve the performance of the IDSs. However, there exists a tradeoff with respect to the stability of ANN architecture and the detection rate for less frequent attacks. This paper presents a novel approach based on Helly property of Hypergraph and Arithmetic Residue-based Probabilistic Neural Network (HG AR-PNN) to address the classification problem in IDS. The Helly property of Hypergraph was exploited for the identification of the optimal feature subset and the arithmetic residue of the optimal feature subset was used to train the PNN. The performance of HG AR-PNN was evaluated using KDD CUP 1999 intrusion dataset. Experimental results prove the dominance of HG AR-PNN classifier over the existing classifiers with respect to the stability and improved detection rate for less frequent attacks.

A Trust Evaluation Model for Cloud Computing Using Service Level Agreement

To access cloud services the user needs to negotiate a service level agreement (SLA) with the service provider. There will be inadequate assurances to customers on whether the services are trustworthy to pick. Trust management plays a major role in guiding the users to access trustworthy services. Hence a trust mining model (TMM) is proposed to identify trusted cloud services while negotiating an SLA. The knowledge is discovered from a previously monitored dataset and a trust value is generated. The proposed trust model helps both the service provider and cloud user, where the user can make a decision on whether to continue or discontinue the service with the service provider. A Rough set and Bayesian inference are used together to generate the overall results. Using rough sets previously monitored data are mined and the indiscernibility in them is analyzed. Bayesian inference is applied to infer the overall trust degree. The accuracy of the results is compared with the previous models and the result shows that the TMM gives better accuracy. The model is simulated using CloudSim.

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

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.

An efficient intrusion detection system based on hypergraph - Genetic algorithm for parameter optimization and feature selection in support vector machine

Abstract Realization of the importance for advanced tool and techniques to secure the network infrastructure from the security risks has led to the development of many machine learning based intrusion detection techniques. However, the benefits and limitations of these techniques make the development of an efficient Intrusion Detection System (IDS), an open challenge. This paper presents an adaptive, and a robust intrusion detection technique using Hypergraph based Genetic Algorithm (HG - GA) for parameter setting and feature selection in Support Vector Machine (SVM). Hyper – clique property of Hypergraph was exploited for the generation of initial population to fasten the search for the optimal solution and to prevent the trap at the local minima. HG-GA uses a weighted objective function to maintain the trade-off between maximizing the detection rate and minimizing the false alarm rate, along with the optimal number of features. The performance of HG-GA SVM was evaluated using NSL-KDD intrusion dataset under two scenarios (i) All features and (ii) informative features obtained from HG – GA. Experimental results show the prominence of HG-GA SVM over the existing techniques in terms of classifier accuracy, detection rate, false alarm rate, and runtime analysis.

Development of Rough Set – Hypergraph Technique for Key Feature Identification in Intrusion Detection Systems

Abstract ‘Curse of dimensionality’ - an unresolved challenge in the design of an intelligent system makes dimensionality reduction a significant topic of research for the identification of informative features from high-dimensional data sets. This paper presents a novel feature selection technique based on Rough Sets (RS) and few interesting properties of Hypergraph (RSHGT), such as minimal transversal and vertex linearity for the identification of the optimal feature subset. Experiments were carried out using KDD cup 1999 intrusion dataset obtained from the UCI repository. Validation using Weka tool shows the dominance of RSHGT over the existing feature selection techniques with respect to the reduct size, classifier accuracy and time complexity. To summarize, RSHGT was found to be flexible, accommodative and computationally attractive for high dimensional data sets.

Trust aware identity management for cloud computing

Today, companies across the world are adopting cloud services for efficient and cost effective resource management. However, cloud computing is still in developing stage where there are lots of research problems yet to be solved. One such area is security which addresses issues like privacy, identity management, and trust management among other things. As of now, there exists no standard identity management system for a cloud environment. The aspect of trusted propagation still needs to be tackled. This research work proposes a trusted security architecture for cloud identity management that can dynamically federate user identities. The trust architecture proposed use Bayesian inference and roulette wheel selection technique to evaluate trust scores. Using the proposed trust model, dynamic trust relationships are formed across multiple cloud service providers and identity providers thereby eliminating fragmentation of user identities. The trust model was implemented and tested in Google App Engine. The performance of the trust measures was analysed.

Scalable and direct vector bin-packing heuristic based on residual resource ratios for virtual machine placement in cloud data centers

Abstract Virtual Machine (VM) placement consolidates VMs into a minimum number of Physical Machines (PMs), which can be viewed as a Vector Bin-Packing (VBP) problem. Recent literature reveals the significance of first-fit-decreasing variants in solving VBP problems, however they suffer from reduced packing efficiency and delayed packing speed. This paper presents VM NeAR (VM Nearest and Available to Residual resource ratios of PM), a novel heuristic method to address the above said challenges in VBP. Further, we have developed Bulk-Bin-Packing based VM Placement (BBPVP) and Multi-Capacity Bulk VM Placement (MCBVP) as a solution for VBP. The simulation results on real-time Amazon EC2 dataset and synthetic datasets obtained from CISH, SASTRA shows that VM NeAR based MCVBP achieves about 1.6% reduction in the number of PMs and possess a packing speed which was found to be 24 times faster than exisiting state-of-the-art VBP heuristics.

E-FPROMETHEE: An Entropy Based Fuzzy Multi Criteria Decision Making Service Ranking Approach for Cloud Service Selection

The immense popularity and rapid adoption of cloud computing has led to the emergence of various cloud service providers, offering functionally-equivalent services. This scenario complicates the identification of an appropriate and trustworthy cloud service provider with respect to the unique Quality of Service (QoS) requirement of the users. Trust based service selection approaches prove to be a prominent solution for the cloud service selection problem since trust evaluation of the cloud services exploits the intrinsic relations between the QoS attributes. This paper presents Shannon entropy based Fuzzy PROMETHEE service ranking approach for the identification of trustworthy cloud service providers. A case study using real world QoS data from Cloud Harmony demonstrates the effectiveness and robustness of the proposed approach in terms various quality metrics (trustworthiness, untrustworthiness, uncertainty) and sensitivity analysis.

A trust centric optimal service ranking approach for cloud service selection

Abstract Cloud service selection, a promising research directive provides an intelligent solution via. service ranking based on the Quality of Service (QoS) attributes for the identification of trustworthy Cloud Service Providers (CSPs) among a wide range of functionally-equivalent CSPs. Further, the impact of objective and subjective assessment data on the accuracy of the service selection model makes the credibility of the assessment data, a major concern for the researchers in service-oriented environments. To address the challenges with respect to the identification of the user requirement compliant CSPs, data credibility, service ranking, etc. we present Hypergraph –Binary Fruit Fly Optimization based service ranking Algorithm (HBFFOA), a trust-centric approach for the identification of suitable and trustworthy cloud service providers. HBFFOA employs hypergraph partitioning, time-varying mapping function, helly property, and binary fruit fly optimization algorithm for the identification of similar service providers, credibility based trust assessment, selection of trustworthy service providers, and optimal service ranking respectively. Experiments using synthetic QoS dataset from WSDream#2 illustrates the effectiveness, practicability, scalability and computational attractiveness of HBFFOA over the existing service selection approaches in terms of precision, stability, statistical test, and time complexity analysis.