在IT服务综合监控系统数据集成处理过程中,由于受到数据检测技术的影响,使得数据集成F-Score值较低,无法满足异构数据集成需求.因此,提出基于深度学习的IT服务综合监控系统异构数据集成方法.针对IT服务综合监控系统中的异构数据,通过数据清洗和数据转换进行预处理.依托于DDE技术,将处理后的数据传输至服务器端.利用半监督深度学习方法,构建数据检测模型,完成异构数据的属性检测.在完成异构数据特征关联度约束后,实现数据的高精度集成处理.仿真实验结果表明,应用所提方法能够有效提升数据集成处理能力.

在监控预警系统工作过程中,由于网络IT设备运行数据预处理算法的影响,使得系统的测量误差较高,无法满足设备工作需求.因此,设计了基于自适应窗口的网络IT设备运行监控预警系统.硬件方面,针对数据采集器和网关进行设计.软件方面,通过采集和传输模块的设计,实时获取网络IT设备运行数据.以自适应窗口为基础,设计数据深度处理算法,为监控预警系统的设计提供数据支撑.基于大数据分类算法构建监控预警模型,并将监控预警结果进行可视化界面展示.系统测试结果表明,所设计系统的监控预警结果与实际设备运行状态数据相比平均误差为2.27％,满足了系统测量误差低于5％的要求.

随着电力系统智能化水平的不断提高,电网中产生的数据体系也越来越庞大,而数据的质量会直接影响电力系统的运行分析和规划决策.文中基于数据挖掘技术提出一种电网时序数据质量维护体系,筛选不合格的数据,并确定数据所存在的问题,为分析出现问题的原因提供便利.对电力数据及传输过程进行了分析,并指出了可能存在的问题.不同地区的数据具有自身不同的特点,为了提高检测速度,基于决策树算法先对历史数据样本进行决策分析.以某地区的数据训练集为例,对该地区电力数据检测流程进行分析,得到适合该区的检测顺序.针对数据合理性难以检测的问题,利用基于聚类的离群检测法筛选出问题数据,并尝试分析问题数据产生原因.通过算例证明了所提时序数据质量维护流程的有效性和可靠性.

At present, people attach great importance to information security issues, and the implementation of different security level protection systems continues to deepen. However, some internal networks still need to face various forms of information security issues in the actual trial process. Based on the above content, this paper studies the design of the technical operation and maintenance safety management and control system of fort-and-fort machine, analyzes the main contents of the system design. At the same time, this paper also summarizes the relevant experience, hoping to provide a reasonable reference for workers in the same field.

针对当前电网行业产生的海量数据,提出采用规范化元数据管理等方式来实现对电力行业数据的统一存储与管理方案.首先通过数据预处理,将不同格式的电力数据统一转换为XML格式数据,然后采用中间件技术实现对XML数据抽取与访问;其次,针对大规模数据存储问题,提出基于哈希分桶算法对数据进行存储,以提高数据存储的效率;再次采用MapRe-duce框架对数据进行查询;通过对电力行业的部分数据进行查询试验,结果表明在查询时间方面,具有优势.

针对传统网络流量预测模型泛化能力弱和准确度低的缺点,提出一种组合小波包分解(WPD)和灰狼横纵多维混沌寻优算法(CCGWO)优化Elman神经网络的短期网络流量预测模型(WPD-CCGWO-ELMAN).网络流量在小波包的作用下分解成多个频段序列,各子序列通过CCGWO-ELMAN神经网络优化模型进行单步或多步预测处理,然后重构并叠加各预测值,得到未来短时间段内的网络流量值.实验结果表明,该模型具有较好的预测精度和鲁棒性,并能掌握网络流量时间序列的变化规律.

企业通过应用系统对公众提供业务的同时也收集到了个人隐私数据.这些个人隐私数据在与企业生产数据关联后,成为具有更高附加值的客户隐私数据.客户隐私数据面临诸多的安全威胁,在产生、传输、处理、存储、使用、销毁过程中涉及多个应用系统和多个网络边界,同时由于应用系统的不断扩建,与外部系统数据交换的接口不断增加,造成客户隐私数据分布在网络中的各个节点,无法进行统一管理和集中化安全保障.从客户隐私数据在网络流转过程的角度进行分析和设计,建立1个客户隐私数据流转安全管理系统,用于保护客户的隐私数据.该系统使用了深度包检测技术、文档加解密技术、数据脱密技术和异常行为检测技术,为结构化数据和非结构化数据在全生命周期过程中提供了安全技术保障.

Cloud computing platforms have the characteristics of large scale, complex interaction and dynamic environment, which cause it more and more serious to software and system security, and the monitoring technology is one of the key technologies to ensure the reliability. However, the spatial topology of a cloud computing platform often changes, so static monitoring can bring huge network overhead when collecting multi-node and multi-level monitoring data. To address the above problems, this paper proposes MCloud, an efficient monitoring framework for cloud computing platform. We first propose an organization model for monitoring objects with a tree-linked list. Then, we optimize the indexing mechanism for the efficient retrieval of monitoring data. Finally, we design and implement a monitoring framework MCloud integrated in cloud computing platforms, and the experimental results show that MCloud can effectively reduce the monitoring performance of the cloud platform by more than 20%.

In order to protect vital data in today’s internet environment and prevent misuse, especially insider abuse by valid users, we propose a novel two-step detecting approach to distinguish potential misuse behaviour (namely anomalous user behaviour) from normal behaviour. First, we capture the access patterns of users by using association rules. Then, based on the patterns and users’ sequential behaviour, we try to deter anomalous user behaviour by leveraging the logistic regression model. Experimental results on real dataset indicate that our method can get a better result and outperform two state-of-the-art method. The proposed two-step detecting approach can effectively detect anomalous user behaviour from the log data generated by operation and maintenance staffs.

With more and more widespread use of smartphones, malwares have become increasingly complex and large-scalely. As a free and open source system, Android has currently surpassed other mobile platforms to become the most popular operating system, so that the number of the Android platform malware has also been significantly increased. Focusing on the security issues of the software for the Android platform, this paper proposes an Android malware detection method based on multifeature collaborative decision. This method mainly bases on the analysis of the Android application, and then the feature attributes are extracted, the models according to machine learning are built. Lastly the classification algorithms are used to determine whether the application is malware. Experimental results show that using the proposed method to classify Android application data set has better assessments indicators than the indicators using other classifiers. Therefore, the method based on multi-feature collaborative decision approach to detect malicious software on Android applications can be made effective for detecting unknown malicious nature of the applications, and can avoid damage caused by malicious applications for the users.

In view of the wide application of UML modeling in software design, a new model based software testing scheme is proposed. In order to implement the test plan, the software model is constructed by UML state diagram, and the EFSM model is used to generate the path transformation sequence. The UML state graph is transformed into Petri net and the Petri net is analyzed.

Recently,Identity-based Encryption(IBE) scheme based on lattices becomes one of the focuses of cryptographic research.But the IBE scheme based on standard lattice have large key size and high ciphertext expansion rate.So based on ideal lattices,this paper presents an efficient identity-based encryption scheme with small key size and low ciphertext expansion rate.The proposed scheme uses a method that combines the NTRU digital signature and the dual encryption based on ideal lattices.It is provably secure in the random oracle model.Analysis results show that the public key and the private key of key generation center contain one ring element and four ring elements respectively.The decryption key of each user is comprised of two ring elements.The ciphertext contains only two ring elements and the ciphertext expansion rate is a small constant.The encryption and decryption require four and two multiplications in the polynomial ring.Hence,the IBE scheme is more computationally efficient than that of traditional number theory based IBE scheme.

To model embedded systems with timed automata is a kind of effective approach due to high real-time and strong con-currency properties,and introducing the time dimension into an automaton brings about infinite state spaces in an automaton, which makes it more difficult to test embedded software systems.A compression algorithm of time automata,namely states com-pression method of constraint symbolization,was proposed.Consequentially,based on this method,a formalization of timed au-tomata was presented.The linear temporal logic (LTL)properties represented as bounded model checking (BMC)problem can be determined by satisfiability modulo theories (SMT)solving.Through these methods the problem of state explosion of time automata can be solved to some extent.

In this paper, we design a data processing model based on Hadoop technology, which is based on the analysis of the existing computing and storage technology, and combining with the technology of Hadoop. This paper first introduces the distributed system, then describes the Hadoop architecture, and finally describes the design of mass data processing model. Through a series of design, the model can effectively alleviate the pressure of the network, while it does not need to have the corresponding professional experience with the corresponding professional experience can be a large system to collate and get the required resources. The model has the characteristics of high efficiency, low cost and easy maintenance.

Establishing a complete information security policy is the most important step to solve the problem of information security and the basis for the entire information security system. Using intrusion detection technology to identify the source of threats and adjusting security policy is an effective operation of network protection. Trained BP neural network model is usually adopted as detector, but because of defects of weights training algorithm of BPNN, the weights always fall into local minima area. In order to address this problem, we propose a detection model based on BP neural network training by AFSA (Artificial Fish Swarming Algorithm). The algorithm optimizes the weights of BP neural network by AFSA. It shortens the sample training time and improves BP neural network classification accuracy. Experimental results demonstrated that it has a shorter training time and can achieve a superior detection rate than BPNN.

A multi-party-signature protocol enables an ensemble of entities to sign on a message to produce a compressed signature. Recently, a lot of multi-party-signature protocols have been proposed in the security field. However, these schemes suffer either from impractical assumptions or from loose security reductions. This paper address all these issues by presenting a practical multi-party-signature protocol. Specifically, the designed multiparty-signature protocol is secure tightly connected to the Computational Diffie-Hellman (CDH) problem in the plain model. Moreover, the multi-party-signature size is small and the communication cost is very low.

Project development in a power enterprise always needs to authorize external devices access to the enterprise intranet for testing. In order to avoid an external device with a virus and pose a security risk to the power information system, external devices should have strict security assessment before access the enterprise intranet. But after the security assessment, the device user still be possible to change the platform configuration. Remote attestation is one of important measures when two sides need to communicate. It is concernful to attest the remote platform is trusty but not revealing the any private information of the platform. For this reason, we designed a novel remote anonymous attestation protocol based on TCM. The proposed protocol does not need extra zero knowledge proof and the involvement of the third trusted party and the composite signature scheme is proved secure against existential forgery on adaptively chosen message. So this protocol has better security and execution property.

Module lattices have many advantages over traditional number theory to construct security schemes. Especially, module lattice-based security schemes are potentially able to resist to quantum attacks which can break traditional number theory based ones. In this vein, this paper designed an extremely fast identity-based encryption (for short IBE) scheme from module lattices. Although the security proof has been conducted in the random oracle (for short RO) model, the keys and the ciphertext expansion rate of our scheme are comparatively small. Moreover, the main idea behind the scheme can be easily understood: combining the provably secure NTRU signature of Stehle and Steinfeld [19] with the CPA secure El Gamal-like encryption scheme proposed by Lyubashevsky, Peikert and Regev [15].

At present, the electric power enterprise's information construction has reached a critical stage, using the analytic hierarchy process (ahp) in this paper, first of all, based on the research of needs analysis for the design of the construction of index system, comprehensive management comprehensive management index is discussed, the system coverage, data quality, process support and business support, the subordinate relations between the implementation determine the practical level of the information system level, finally some unit application example is given, and verify the comprehensive evaluation of the degree of the unit's business system practical application for the"good", the research for the current electricity providers of information systems to improve evaluation has a certain reference value.