International Journal of Internet Protocol Technology (9 papers in press)
An Optimal Spectrum-Efficient Routing Protocol for Multi-hop 802.11s Networks
by Mohammed Ba-Hutair, Mohamed Saad
Abstract: Routing in multi-hop wireless networks is considered one of the main challenges and a vital aspect that should be carefully addressed to sustain a good performance. Standard routing schemes, such as ad-hoc on-demand vector routing (AODV) and dynamic source routing (DSR), use the number of hops from source to destination as the routing metric without paying attention to the physical layer properties of the wireless links. Therefore, some recent studies have addressed the problem of finding the path with maximum end-to-end spectral efficiency, while fully considering the physical layer characteristics of the wireless channel. These studies focused on the route computation algorithms and their optimality analysis under generic network settings. This paper, however, presents a full, new spectrum-efficient routing protocol implementation for real-world IEEE 802.11s networks. In particular, the contribution of this paper is twofold. First, our protocol implementation fully considers the interaction between network layer route computation and medium access control (MAC) contention resolution, in addition to all necessary information gathering and exchange performed by the wireless nodes in IEEE 802.11s networks. Second, to the best of our knowledge for the first time, we provide a full comparison between spectrum-efficient routing and standard routing protocols (such as AODV and DSR), using the NS-2 simulation package, and using various performance metrics such as end-to-end data rate, end-to-end delay, packet loss and information gathering overhead time.
Keywords: multi-hop wireless networks; spectrum-efficient routing; distributed protocols; ns-2 simulations.
Load balancing, Cost and Response Time Minimization Issues in Agent Based Multi Cloud Service Composition
by Hioual Ouassila, Boufaïda Zizette, Hemam Sofiane Mounine
Abstract: These years, cloud computing has gradually evolved as a widely used computing platform where several web services are published and available. Since, generally, no single web service can satisfy the functionally required by the user, there is a need to combine existing services together in order to fulfill user requirements. Hence, there has been an increasing interest in web service composition. In multi-cloud environments, we need to find services from multiple clouds, if a single cloud cannot give us all the required component services. In such a situation, however, it is challenging to find an appropriate composition sequence by taking into consideration load balancing between the different clouds and in the same time by minimizing the composite service cost and response time. How to effectively and efficiently choose a service plan that minimizes these three criteria is an open issue. In this paper, an agent-based Cloud service composition architecture is presented. It includes two main agents CSCA (Cloud Service Composer Agent) and CMA (Cloud Manager Agent) which use MCDA (Multi-Creteria Decision Analysis) methods to support cloud services selection. These agents use load balancing mechanisms and the contract net protocol in order to evolve and adapt cloud service composition. We have performed a comprehensive analytical and experimental study to evaluate the effectiveness of our approach. The experimental results, based on CloudSim simulator, show that the proposed architecture can effectively achieve good performance (load balancing), improve the response time and minimize cost.
Keywords: Cloud Services; Composition; Load balancing; Multi cloud computing; Cost minimization; Multi Agent System; Multi Criteria Decision Analysis; CNP (Contract Net Protocol); Cloud computing; ; TOPSIS (Technique for Order of Preferences by Similarity to Ideal Solution); AHP (Analytical Hierarchy Process).
A Hybrid Load Balancing Algorithm for P2P-Cloud System Aware of Constraints Optimization of Cost and Reliability Criteria
by Hemam Sofiane Mounine, Hioual Ouassila
Abstract: P2P-Cloud, also known as volunteer cloud, is a new paradigm which aims at moving volunteer computing towards the cloud. It could be built from reliable resources found in the cloud with a cost, and from unreliable resources found in many private homes with essentially a very low cost.
However, the reliability and cost are contradictory related and have a negative impact on load between resources. This paper proposes a Hybrid load balancing algorithm, which takes into consideration user requirements (cost and reliability) and system performance (the load) in the context of volunteer cloud. The proposed algorithm regulates the load between load balancers in a distributed manner, and between resources in a centralized manner by optimizing cost and reliability criteria. Our approach is evaluated through simulation by using PeerSim simulator. The experimental results show that we can effectively achieve good performance (load balancing between resources) and improve the user requirements.
Keywords: Cloud system; P2P system; dynamicity; volunteer cloud; reliability; failure probability; load balancing; Pareto optimal; TOPSIS; multi-objective optimization; cost.
Workload Consolidation Techniques to Optimize Energy in Cloud: Review
by Sanjeevi P, Viswanathan P
Abstract: The major issue threatening the cloud computing is that it consumes an enormous amount of energy for providing valuable computational services. Many workload
consolidation attempts were taken to reduce the energy consumption of data center. Broad research on all workload consolidation issues in the cloud environment is extremely challenging since it entails developers to deliberate network setup and the cloud environment, which could be beyond the control. Moreover, the consolidation of workload cannot be predicted or restrained. Though, existing literature lacks the crucial agility for workload consolidation to reduce energy in cloud data center, producing poor responsiveness and inadequate scalability. In this paper, we present the background and motivation of workload consolidation techniques in the cloud. Moreover, we acquaintance four recent workload consolidation algorithms considering metrics for reducing energy and the features of the best workload consolidation algorithm is highlighted. Finally, research areas and challenges are boasted based on the strengths and weakness of prevailing workload consolidation methods.
Keywords: Cloud Computing; Data centers; Workload Consolidation; DVFS; Energy
Consumption; Scheduling; QoS.
Security in wireless ad hoc network
by Sachin Ubarhande, Dharmpal Doye, Prakash Nalwade
Abstract: The mobile ad hoc network is open medium, easy to deploy and free of the centralized control network. But these features of mobile ad hoc network come along with serious security attacks, such as black hole attack and gray hole attack. The black hole attack is outrank among all security attacks, in which malicious node degrades the security and performance of the network. This paper proposes a dual identity-based intrusion detection system to improve security and performance of mobile ad hoc network. The proposed system works based on the head node identities, namely, base and virtual. The head node uses the virtual identity to detect the malicious nodes and serves source node to establish a secure path to destination node. The simulation conducted using the network simulator revealed that proposed system improves the performance of the network for packet delivery ratio by 5%, throughput by 43%, packet loss rate by 57% and routing overhead by 13% as compared to another system.
Keywords: mobile ad hoc network; security vulnerability; black hole attack; dual identity-based intrusion detection system.
A Proactive Spectrum Handoff Scheme with Efficient Spectrum Utilization for Cognitive Radio Ad hoc Networks
by Krishan Kumar, Arun Prakash, Ganesh Prasad Mishra, Rajeev Tripathi
Abstract: This paper proposes a proactive spectrum handoff scheme for Cognitive Radio (CR) ad hoc networks by exploiting the efficient utilization of the available wireless spectrum by CR. The novelty of this spectrum handoff scheme is that it is able to use the available free channels which are idle for one complete CR packet transmission as well as idle for less than one packet transmission. This has been done by channel scheduling and packet fragmentation to reduce unusable channels. In this scheme, spectrum sensing is done during packet transmission. The main contribution of the proposed spectrum handoff scheme is that it outperforms the existing proactive and reactive spectrum handoff schemes in terms of reduced CR average service time, improved throughput, and improved spectrum utilization under the different Primary User (PU) arrival rates. It is also analysed that the proposed spectrum handoff scheme is best suited scheme in heavy PU traffic arrival rates.
Keywords: Average service time; Channel scheduling; Cognitive radio adhoc networks; Efficient spectrum utilization; Packet fragmentation; Proactive; Spectrum handoff.
A SPARQL Query Processing System using Map-Phase-Multi-Join for Big Data in Clouds
by Ce-Kuen Shieh, Sheng-Wei Huang, Chia-Ho Yu, Ming-Fong Tsai
Abstract: Big Data refers to large data sets collect from various sources which are huge, complex and hard to be stored and analyzed by traditional data processing tools. The Linked Data is one of the approaches to deal with Big Data. These data sets can be integrated by using linked data approaches and therefore the users can access these data for useful information. These linked data are stored and processed in TripleStore. With the data growing in a rapid manner, the TripleStore requires more scalable and efficient techniques. The programming model MapReduce is the most representative of Cloud technology which aims to improve the scalability and efficiency of computing. There were several researches using cloud technologies to construct their TripleStore. The implementations of these approaches use a MapReduce algorithm to serve the SPARQL query and a distributed storage system like HDFS or HBase to store billions of data. However, these systems still exhibit unacceptable performance in processing complex SPARQL queries. Therefore, in this paper, we propose a Map-Phase-Multi Join algorithm for processing SPARQL queries. By using multi-join can reduce the job initialization time by avoiding iterative of MapReduce jobs. Furthermore, map-phase join can save bandwidth cost by preventing join-less data transferring among cluster. We also design a storage schema in HBase which enhances the performance of our join algorithm. Finally, we formulate a join-order rule which aims to reduce the input size of mappers and the number of join computations. The evaluation results show that our system defeats traditional join approaches in most simple queries and complex queries.
Keywords: Big Data; Linked Data; MapReduce; SPARQL; TripleStore; NoSQL.
Special Issue on: Novel Architectures and Approaches for Resolving Service Discovery, Communication and Integration Issues in the Internet of Things
Providing Efficient User Management for large-scale Enterprise by Achieving high Scalability over cloud
by Nalini Priya G, Arun Kumar Sangaiah, Aishwarya Thangavelu, Thusitha Murali, Balamurugan Balusamy
Abstract: Cloud computing is an emerging computing technology, almost used by all the big enterprises to store and access their private organizational data. It also helps to manage the complex work and to process in easy and secure manner. Access control models provide authorization and authentication to the users in pursuance of providing security over the data in the cloud. Many big enterprises suffer a scalability problem in storing the data of the employees and their related access data due to the exponentially increasing freshers randomly. These big enterprises prefer Role Based Access control (RBAC) model to manage the different roles in the management. A drastic problem called Role Explosion occurs in RBAC due to the random increase in the number of users and roles in an organization. In this paper we propose a variant data structure model for the Role Based Access Control model namely Scalable Bloom Filter-Role Based Access Control (SBF-RBAC) model. Our proposed model implements Scalable Bloom Filters for each role so that there could be a dynamic accommodation of users in the roles that reduce space complexity. This also helps in reducing the Role Explosion to a greater extent. We also merge the roles with the same access grant in order to avoid the overlapping of roles. Thus, the SBF-RBAC model could help a management to manage a number of employee records and their respected grants with much more efficiency and without any hindrance.
Keywords: Role Based Access Control; Scalable Bloom Filters; User’s scalability problem; Role Explosion; access control techniques.
Recent Advances in QoS Provisioning in Wireless Ad hoc Networks
by Prakash Srivastava, Rakesh Kumar
Abstract: With rapid increase in multimedia and other real time applications, incorporating Quality of Service (QoS) requirements like end to end delay, bandwidth, jitter and energy in MANET is necessary. MANET has some unique features such as self-organizing and easy deployment. It has great potential in many applications such as military and civil. Existing QoS aware routing protocols designed for wired networks cannot be directly applied to wireless ad hoc networks due to its dynamic topological scenario and error prone nature of these wireless links. Best-effort QoS routing protocols are needed to ensure optimum network operation in an unpredictable wireless environment. Besides, QoS routing also ensures that a network performance should not be degraded in the event of disruption of links, failure of mobile devices and short residual connectivity time. In this paper, comprehensive description of QoS routing along with its taxonomy is presented and different QoS routing proposals are analyzed in terms of its performance and limitations.
Keywords: MANET (Mobile Ad hoc Networks); QoS; Framework; Provisioning.