Amount Of Network Data Research Articles

A Fast Resource Allocation Algorithm Based on Reinforcement Learning in Edge Computing Networks Considering User Cooperation

In the 5G era, the amount of network data has grown explosively. A large number of new computation-intensive applications have created demand for edge computing in mobile networks. Traditional optimization methods are difficult to adapt to the dynamic wireless network environment because they solve the problem online, which is not suitable in edge computing scenarios. Therefore, in order to obtain a mobile network with better performance, we propose a network frame with a resource allocation algorithm based on power consumption, delay and user cooperation. This algorithm can quickly realize the optimization of a network to improve performance. Specifically, compared with heuristic algorithms, such as particle swarm optimization, ant colony algorithm, etc., commonly used to solve such problems, the algorithm proposed in this paper can reduce some aspects of network performance (including delay and user energy consumption) by about 10% in a network dominated by downlink tasks. The performance of the algorithm under certain network conditions was demonstrated through simulations.

Network security analysis using big data technology and improved neural network

Network security is an important part of the future information world. The degree of social informatization is maturing and network infrastructure is gradually improving, the network has become an indispensable part of human life. With the frequent occurrence of cyber security incidents around the world, cyber security research has become very important. The amount of network data is huge, and it is necessary to use big data (BD) analysis technology and various machine learning algorithms to analyze and predict the network security (NS) situation. In the NS situation awareness technology, the network behavior and the possible impact are mainly identified by analyzing data records. However, existing NS situation awareness models need to be improved, such as large resource overhead, low accuracy of analysis results, low processing efficiency, and inability to apply to real-time and large-scale scenarios. To solve these shortcomings, a new NS BD analysis model is proposed using improved BP neural network. In the model, data is simplified and cleaned according to the characteristics of the data records, thereby solving the problems of heterogeneous data sources and high noise. With the classic BP neural network as the core of the model, the error inverse feedback strategy of the neural network is used to improve the accuracy of the model analysis. The innovation of this article is that when preprocessing the input data, the proposed blocked fuzzy C-means clustering algorithm (BFCM) is used to cluster the features of the data records to strengthen the features of the data, thereby improving the model's precision. First, the structure of the NS awareness model is introduced in detail, and then the relevant steps in the model are described in detail. Finally, a series of experiments have been performed to verify that the proposed model has certain reference value for the perception of NS situations.

A Review on Various Methods of Intrusion Detection System

Detection of Intrusion is an essential expertise business segment as well as a dynamic area of study and expansion caused by its requirement. Modern day intrusion detection systems still have these limitations of time sensitivity. The main requirement is to develop a system which is able of handling large volume of network data to detect attacks more accurately and proactively. Research conducted by on the KDDCUP99 dataset resulted in a various set of attributes for each of the four major attack types. Without reducing the number of features, detecting attack patterns within the data is more difficult for rule generation, forecasting, or classification. The goal of this research is to present a new method that Compare results of appropriately categorized and inaccurately categorized as proportions and the features chosen. Data mining is used to clean, classify and examine large amount of network data. Since a large volume of network traffic that requires processing, we use data mining techniques. Different Data Mining techniques such as clustering, classification and association rules are proving to be useful for analyzing network traffic. This paper presents the survey on data mining techniques applied on intrusion detection systems for the effective identification of both known and unknown patterns of attacks, thereby helping the users to develop secure information systems. Keywords: IDS, Data Mining, Machine Learning, Clustering, Classification DOI : 10.7176/CEIS/11-1-02 Publication date: January 31 st 2020

Data Mining Approaches on Network Data: Intrusion Detection System

In the modern era having tremendous growth and the usage of networking over computer systems and its applications mainly focuses to make our system as secure as possible. So with the help of intrusion detection system we can implement security on the system that protects our system data to access from unauthorized persons. Intrusion Detection System (IDS) takes responsibility to monitor the networks or host packets to find the malicious activities which occurs in the system. This paper consists data mining techniques to implement on IDS to identify both of the attacks that is known and unknown attacking patterns, so IDS helps the user to secure the information system. A Network Intrusion Detection System (NIDS) must be installed into the system to work as software application for detecting and monitoring the network activities and also protects from malicious and illegal access of devices. Data mining provides a way to analyze, classify, clean and eliminate the large amount of network data. Therefore, to come out from huge volume of dataset we use different data mining techniques like as classification, clustering along with association rules to analyze the network traffic and make the information as confidentiality and integrity. Keywords: Intrusion Detection System, Classification, Clustering, Data Mining, Misuse Detection, Anomaly Detection, False Alarm Rate, Network Security

Network Security Behavior Recognition Based on Consensus Decision-Making Feature Selection

Due to the large amount of network data and complex representation, traditional network security behavior recognition system always leads to high redundancy and dimension, resulting in taking up more resources, larger computation. To solve this problem, we do the features selection. This article presents a consensus decision-making method, which combines current famous feature selection algorithms to obtain a more reasonable result and to sort the features in order of importance to facilitate the appropriate selection of features under different conditions. With this method tested on SVM (Support Vector Machine) as classification algorithm, it proves that the algorithm effectively improves the recognition accuracy with fewer features and performs better in terms of result stability.

Research on the Application of Spatial Logic in the Security Protocol Verification of Computer

The security protocol is the core technology of the network communication security system which can maintain the security of the network environment effectively. With the increasing of the amount of network data, how to make security protocol to meet customers needs for network and information security and how to improve the efficiency of the security agreement are the focuses of exploration of the field of computer security. This paper introduces the security agreement composite form based on the theory of computer logic program, strand space model theory and certification test method. It also expands the Kailar logic and concludes the automotive verification algorithm of security protocol AAAP-KM algorithm. At last, this paper verifies the effectiveness and fastness of AAAP-KM algorithm taking the KM security protocol for example which provide a theoretical reference and technical support for the application and research of cyberspace logical security agreement.

Super-threshold Procedures and Their Application to the Search Problem

The paper examines a choice problem in case of large number of alternatives characterized by a set of criteria. Very often existing choice procedures cannot be used due to their computational complexity. In contrast, the approach proposed in this paper utilizes a set of easy to use techniques having complexity less than the quadratic. We apply super-threshold procedures sequentially in order to find the best alternatives. The application to learning to rank problem is also considered. Finally, two methods of defining thresholds and order of criteria in super-threshold procedures are studied. While the first method is based on the etalon criterion, the second method uses the distribution function. Both methods developed are mainly oriented on the cho ice of search results in search engines and capable of processing large amount of data in networks, but can also be applied to any system in which the alternatives are represented by a set of criteria.

The architecture and performance evaluation of iSCSI-based United Storage Network merging NAS and SAN

With the ever increasing amount of data in network, the traditional storage architecture is challenged greatly, more and more people are beginning to pay attention to network storage. Currently, the main technologies of network storage are Network Attached Storage (NAS) and Storage Area Network (SAN).They are different, but they are mutually complementary and used in different occasions, it is possible that both NAS and SAN are needed in the same company. To reduce the total of cost (TOC), and simple to implement and so on, people hope to merge the two technologies. Additionally, the main internetworking technology of SAN is Fibre Channel, but its poor interoperability, lack of trained personnel and high implementation costs, etc., remain major obstacles. To solve the above-mentioned issues, this paper introduces creatively, a novel storage architecture called United Storage Networks (USN), which uses the iSCSI to build the storage network, and merges the NAS and SAN, supplying the virtues and overcoming the drawbacks of the NAS and SAN, and providing both file I/O and block I/O service simultaneously.