Wenhong Wei

BSN-mesh and its basic parallel algorithms

Mesh is the most famous, common and effective interconnection network, which has become the preferred topology of parallel processing and parallel computing systems. At the same time the Biswapped Network BSN provides an efficient two-level structure for large scalable, inheritance, modular architecture. In this paper, we present BSN-mesh as two-tier architecture with the advantages of both BSN and mesh. On the basis of the presented BSN-mesh, topological structure and many basic algorithms such as broadcast, data sum, prefix sum, packet routing and sorting are investigated. Compared with other two-tier architectures, especially OTIS-mesh, the time complexities of the mentioned algorithms running on BSN-mesh are much lower and BSN-mesh is more competitive.

Active overload prevention based adaptive MAP selection in HMIPv6 networks

Multi-level mobile anchor points (MAP) architecture is deployed in large-scale wireless/mobile networks using HMIPv6 to achieve better mobility service, while selecting the most suitable serving MAP for the mobile nodes (MNs) to enhance the whole network performance has been a critical issue. An adaptive MAP selection based on active overload prevention (MAP-AOP) hence is proposed. The MAP periodically evaluates the load status by using dynamic weighted load evaluation algorithm, and then sends the load information to the covered access routers (AR) by using the expanded routing advertisement message in a dynamic manner. Taking achieving the load balancing among the available MAPs, the current serving AR executes the active overload prevention to select MAP candidates for the MN pending a handover, and then adaptively selects an optimal one from the candidates by comprehensively considering the system cost and the average handover latency caused by each candidate. The simulation conducted on the NS-2 platform indicates that MAP-AOP outperforms the comparative MAP selection schemes with the optimized system cost and average handover latency, and better load balancing.

Parallel Prefix Algorithm on BSN-Mesh

A parallel algorithm for prefix computation of N=2n4 elements on a Biswapped network (BSN) whose basis network is n×n mesh network is presented. BSN is a recently proposed network model of parallel computing, which is built of 2n copies of an n-node basis network and its basic network may be Hypercube, Mesh and other networks, BSN-Mesh is Biswapped network whose basis network is Mesh network. In this paper, the parallel prefix algorithm proposed takes time on N processors N communication steps.

Feature-Aware Cooperative Relaying for Multiflow Wireless Sensor Networks

Addressing the energy efficiency in data-centric and application-oriented wireless sensor networks is an eternal theme, and in the practical scenarios deployed multiple flows, often a serious problem of collisions among multiple paths caused by the fierce network resource competition directly influences the whole network performance. To address this issue, in terms of the delay sensitivity imposed on the deployed flows, a feature-aware cooperative relay selection scheme is developed by comprehensively taking both the routing selection and contention avoidance into account, in which the concept of abstract domain is introduced to extend the covered relay nodes. The optimal relays for the deployed multiflow with specific probing and transmission requirements are selected to find collision-free and energy-efficient cooperative routings. Simulations conducted on NS-2 platform demonstrate that the proposed cooperative routing outperforms the compared routing selection strategies in significantly balancing the energy distribution and prolonging the network lifetime.

A multi-objective multicast routing optimization based on differential evolution in MANET

Purpose The purpose of this paper is to propose a multi-objective differential evolution algorithm named as MOMR-DE to resolve multicast routing problem. In mobile ad hoc network (MANET), multicast routing is a non-deterministic polynomial -complete problem that deals with the various objectives and constraints. Quality of service (QoS) in the multicast routing problem mainly depends on cost, delay, jitter and bandwidth. So the cost, delay, jitter and bandwidth are always considered as multi-objective for designing multicast routing protocols. However, mobile node battery energy is finite and the network lifetime depends on node battery energy. If the battery power consumption is high in any one of the nodes, the chances of network’s life reduction due to path breaks are also more. On the other hand, node’s battery energy had to be consumed to guarantee high-level QoS in multicast routing to transmit correct data anywhere and at any time. Hence, the network lifetime should be considered as one objective of the multi-objective in the multicast routing problem. Design/methodology/approach Recently, many metaheuristic algorithms formulate the multicast routing problem as a single-objective problem, although it obviously is a multi-objective optimization problem. In the MOMR-DE, the network lifetime, cost, delay, jitter and bandwidth are considered as five objectives. Furthermore, three QoS constraints which are maximum allowed delay, maximum allowed jitter and minimum requested bandwidth are included. In addition, we modify the crossover and mutation operators to build the shortest-path multicast tree to maximize network lifetime and bandwidth, minimize cost, delay and jitter. Findings Two sets of experiments are conducted and compared with other algorithms for these problems. The simulation results show that our proposed method is capable of achieving faster convergence and is more preferable for multicast routing in MANET. Originality/value In MANET, most metaheuristic algorithms formulate the multicast routing problem as a single-objective problem. However, this paper proposes a multi-objective differential evolution algorithm to resolve multicast routing problem, and the proposed algorithm is capable of achieving faster convergence and more preferable for multicast routing.

Cooperative Routing for Multi-flow Wireless Sensor Networks

In data-centric and application-oriented Wireless Sensor Network, effective energy-saving is an eternal theme, while in the scenarios deployed multiple flows, the network resource competition directly influences the whole network performance. To address this issue, a cooperative routing scheme is developed by comprehensively taking both the routing selection and contention avoidance into account, in which, for the delay-tolerant sensing tasks, the concept of abstract domain is introduced to extend the coverage relay nodes, and the cooperative routings are carefully selected in terms of the specific sensing and transmission requirements. Simulation conducted on NS-2 platform demonstrates that the proposed cooperative routing outperforms the compared routing selection strategies in significantly balancing the energy distribution and prolonging the network lifetime.

Version-vector based video data online cloud backup in smart campus

As a kind of popular multimedia service, the video business in smart campus is fully developed, and the data volume is experiencing a continuous tremendous growth. However, the video data storage also needs to cope with many security threats resulted from some uncertainly factors. Recently, data backup has been credited as an important method to address these issues. Yet, how to improve the efficiency of video data online backup remains a critical challenge. In the context of cloud computing, a version-vector based video data online backup system is proposed in this paper, which fully implements three important functions, e.g., backup, indexing and recovery. At the time of the client backuping the data to the server, the version vectors of files and data chunks are produced as metadata. Accordingly, only through exchanging a small amount of metadata between the data nodes, it can identify the redundant data such that breaking the limitations on file-level deduplication and data-chunk-level deduplication in the existing backup systems, and can further improve the performance of backup, indexing and recovery. The conducted experiments have been shown to demonstrate the efficiency.

A Multi-objective Differential Evolution for QoS Multicast Routing

This paper presents a new multi-objective differential evolution algorithm (MODEMR) to solve the QoS multicast routing problem, which is a well-known NP-hard problem in mobile Ad Hoc networks. In the MODEMR, the network lifetime, cost, delay, jitter and bandwidth are considered as five objectives. Furthermore, three QoS constraints which are maximum allowed delay, maximum allowed jitter, and minimum requested bandwidth are included. In addition, we modify the crossover and mutation operators to build the shortest-path multicast tree to maximize network lifetime and bandwidth, minimize cost, delay and jitter. In order to evaluate the performance and the effectiveness of MODEMR, the experiments are conducted and compared with other algorithms for these problems. The simulation results show that our proposed method is capable of achieving faster convergence and more preferable for multicast routing in mobile Ad Hoc networks.

A DDOS defence scheme based on two-stage traffic flow control

In distributed denial of service (DDoS) attack, the detection techniques have existed for a relatively longer period of time than defence mechanisms, researchers have categorised almost all the existing and expected forthcoming attacks. However, techniques for defence are still nurturing. Researchers have explored that there could be diverse ways of launching DDoS attacks. Consequently, need of defence scheme that adapts and responds autonomously to these variety of attacks is imperative. This paper proposed a distributed defence scheme based on two-stage traffic flow control against DDoS attacks that present the most serious threats to the internet. The defence using this scheme deploys two kinds of coordinated modules through specific mechanism to protect internet servers. And the performance of the scheme was evaluated by network simulation. Simulation results show that the proposed scheme can greatly increase the throughput of legitimate traffic and reduce the attack traffic during DDos attacks, and it performs well even when it is only partially deployed.

Movement prediction assisted timely L2 trigger in FMIPv6

Providing continuity services for end-users roaming across the overlapping access networks has been a challenging issue, the IETF hence proposes FMIPv6 acting the cross layer handover management to provide better mobile services. FMIPv6 mainly achieves the pre-registration by obtaining the timely link layer (L2) trigger. The timely L2 trigger hence is crucial for guaranteeing the handover performance, but difficult to be obtained in the practical application scenarios. To address this issue, taking the measured received signal strength (RSS) as the evaluated index, a movement prediction model based on the combination of Empirical Mode Decomposition and Support Vector Regression is proposed to obtain the timely L2 trigger. The efficiency of the movement prediction model has been verified by the simulation conducted on the NS-2 platform.