Mingchuan Zhang

A QoS-Satisfied Prediction Model for Cloud-Service Composition Based on a Hidden Markov Model

Various significant issues in cloud computing, such as service provision, service matching, and service assessment, have attracted researchers’ attention recently. Quality of service (QoS) plays an increasingly important role in the provision of cloud-based services, by aiming for the seamless and dynamic integration of cloud-service components. In this paper, we focus on QoS-satisfied predictions about the composition of cloud-service components and present a QoS-satisfied prediction model based on a hidden Markov model. In providing a cloud-based service for a user, if the user’s QoS cannot be satisfied by a single cloud-service component, component composition should be considered, where its QoS-satisfied capability needs to be proactively predicted to be able to guarantee the user’s QoS. We discuss the proposed model in detail and prove some aspects of the model. Simulation results show that our model can achieve high prediction accuracies.

Analysis and application of Bio-Inspired Multi-Net Security Model

With the rapid development of network technologies and deteriorating of network environment, traditional single-net security system cannot satisfy the security requirement. The excellent security performance of biological systems impels the bio-inspired network security theory to be a hot research area currently. Based on Bio-inspired Multidimensional Network Security Model we have put forward, we have advanced Bio-inspired Multi-Net Security system by implementing the functional distribution of different subnets of different transient states in Multi-Net Paralleling structure. Firstly, parameter estimation and modified algorithms of Hidden Markov Model are introduced to construct the mathematical mode of B-MNS; secondly, the integrated performance of our modified B-MNS has been tested and its simulation has been carried out. So the feasibility, validity and high efficiency of our model have been demonstrated theoretically, and practically.

Research on Grade Optimization Self-tuning Method for System Dependability Based on Autonomic Computing

In order to enhance the service performance, the preservation and increase of system dependability are researched and a system dependability self-tuning method is proposed based on autonomic computing. The self-tuning method attempts to achieve the sustained growth of system dependability by on-line evaluation, dynamic prediction and tuning of self-tuning scheme. There are four tuning methods random interval, settled interval, dependability threshold value and event trigger, which are discussed in the simulation experimentation. The tuning effects that affect system dependability increment are analyzed, and the optimal tuning opportunities for each tuning method are given. The result of simulation experiment shows that the tuning methods will ensure the positive increase of system dependability increment except random interval.

A Cloud Service Resource Classification Strategy Based on Feature Similarity

There are now a vast array of heterogeneous cloud service resources, which makes it difficult to identify suitable services for the various types of cloud users. A classification of cloud service resources would help users find suitable cloud services more easily. We propose such a classification strategy, which has two parts. First, we improve the original naive Bayesian classification algorithm, designing a Bayesian classification algorithm based on feature similarity. Second, to improve the efficiency of the classification algorithm, we design a parallel programming model using the Hadoop platform. Simulation results show that the proposed classification strategy is feasible and effective, improving not only the resource classification accuracy but also greatly enhancing the processing efficiency for large-scale cloud service resources

A Novel Multi-x Cooperative Decision-making Mechanism for Cognitive Internet of Things

Cognitive Internet of Things (CIoT) mainly consists of a group of autonomous nodes (ANs) which are commonly combined into domains and should have the intelligence to perceive, analyze, decide and act. Cooperation has shown to be a good technique for collective behavior of ANs that locally interact with each other in distributed environments. In this paper, we study the cooperative decision-making mechanism of multi-ANs and multi-domains and present the corresponding cooperative decision-making process in CIoT. Multi-ANs cooperation deals with the cases that one AN cannot meet the QoS and network performance object (NPO) and multi-domains cooperation addresses the cases that the ANs of only one domain cannot meet the QoS and NPO. Based on the cooperative decision-making mechanism, the simulative experiments are done and show that the NPO can be satisfied perfectly.

Smart perception and autonomic optimization: A novel bio-inspired hybrid routing protocol for MANETs

Abstract Routing in mobile ad hoc networks (MANETs) is an extremely challenging issue due to the features of MANETs. In this paper, we present a novel bio-inspired hybrid trusted routing protocol (B-iHTRP) based on trusted assessment, ant colony optimization (ACO) and physarum autonomic optimization (PAO). Firstly, we introduce the cross-layer perception into ACO to obtain perceptive ants. Then, we divide the network into multiple zones. Within each zone, the route table is maintained proactively by the perceptive ants which can sense concerned parameters. Among zones, the perceptive ants are sent to reactively find routes to destinations while sensing concerned parameters. Secondly, B-iHTRP uses PAO to select the optimal one from the found routes and autonomically optimize the local routes during the course of multi-zone communication sessions. Simulation results show that B-iHTRP can achieve better performance comparing with existing state-of-the-art algorithms.

B-iTRS: A Bio-Inspired Trusted Routing Scheme for Wireless Sensor Networks

In WSNs, routing algorithms need to handle dynamical changes of network topology, extra overhead, energy saving, and other requirements. Therefore, routing in WSNs is an extremely interesting and challenging issue. In this paper, we present a novel bio-inspired trusted routing scheme (B-iTRS) based on ant colony optimization (ACO) and Physarum autonomic optimization (PAO). For trust assessment, B-iTRS monitors neighbors’ behavior in real time, receives feedback from Sink, and then assesses neighbors’ trusts based on the acquired information. For routing scheme, each node finds routes to the Sink based on ACO and PAO. In the process of path finding, B-iTRS senses the load and trust value of each node and then calculates the link load and link trust of the found routes to support the route selection. Moreover, B-iTRS also assesses the route based on PAO to maintain the route table. Simulation results show how B-iTRS can achieve the effective performance compared to existing state-of-the-art algorithms.

A^3srC: Autonomic Assessment Approach to IOT Security Risk Based on Multidimensional Normal Cloud

Around autonomic assessment problem of security risk, considering the high hybrid and heterogeneity of Internet of Things (IOT, for short), the potential influence and occurrence possibility of each main threat is described, evaluated and measured in accordance with fuzziness and randomicity of IOT security index. By which, the security risk grade and system tolerance degree of hybrid IOT security scene with incremental deployment characteristics is qualitatively analyzed. Multidimensional Normal Cloud is adopted to make synthesis of risk indicators, and the autonomic assessment strategy of security risk is constructed. On the basis of above work, transmission multi-rules mapping between qualitative input of security risk and quantitative inference of assessment rules is researched, autonomic inference rules and the optimization strategy are proposed. At last, the effectiveness, autonomy and accuracy of the proposed approach are verified by simulations.

A collaborative analysis method of user abnormal behavior based on reputation voting in cloud environment

Abstract It is the foundation of accessing and controlling cloud environment to establish the mutual trust relationship between users and clouds. How to identify the credible degree of the user identity and its behaviors have become the core problems. Combining with the abnormal recognition and misuse recognition, this paper proposes a collaborative analysis method of user abnormal behavior based on reputation voting. Firstly, the under-sampling and pruning technique are used to construct training samples to avoid high overhead for identifying all data, meanwhile it has solved the problem of unbalanced data learning. Moreover, reputation computing model combining with semi-supervised learning constructs ensemble classifier, and 2-level Chord is used to store reputation to realize its bidirectional query. On this basis, the base classifier is used to vote user behaviors by reputation in order to improve the speed of identifying abnormal behavior. The experimental results show that the scheme could improve the detection speed and clustering accuracy obviously in big data of the mobile user environment, and it has better effect for larger dataset with unbalanced rate especially.

Network Security Situation Evaluation Strategy Based on Cloud Gravity Center Judgment

Aiming at the problems of subjectivity and complexity in network security situation assessment process, the Cloud model is introduced to the network security situation assessment, and a network security evaluation method based on Cloud Model is proposed. Firstly, the level of network security situation is judged by Cloud gravity center evaluation method. Secondly, Maximum boundary based Cloud Model (MCM) method is applied to obtain the final assessment results. Thirdly, future security situation is predicted by adopting BP neural network based on improved genetic algorithm according to the result of situation assessment. Finally, the effectiveness and feasibility of the proposed evaluation method and the prediction effect for GA-BPNN are verified by the simulation experiment. The results show that the proposed evaluation and prediction method is feasible, and the results of the assessment are more objective and accurate.