Research on anomaly detection and real-time reliability evaluation with the log of cloud platform

Wang, Bo; Hua, Qingyi; Zhang, Haoming; Tan, Xin; Nan, Yahui; Chen, Rui; Shu, Xinfeng

doi:10.1016/j.aej.2021.12.061

Cited by 24 publications

(21 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• The decision tree-based algorithm [13] • Deep-RBF Network-based algorithm [15] is better than the decision tree-based algorithm [13] and It has 94. 25 of Attack FPR for ascending order of attribute sizes (from 10-115) of dataset Kitsune [45].…”

Section: B Experimental Results and Analysismentioning

confidence: 99%

“…In [24], the authors conducted a comparative analysis of five time-series anomaly detection models. In [25],…”

Section: Of 20mentioning

confidence: 99%

“…Kim et al [24], conducted a comparative analysis of five time-series anomaly detection models. In [25], the authors applied an ensemble learning model to analyze and forecast anomaly of the enormous system logs. Halstead et al [26], devised a strategy for anomaly detection, which permits the use of latest feature selection techniques to idea representation meta-features.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

An Intuitionistic Fuzzy Rough Set Based Classification for Anomaly Detection

Mazarbhuiya¹,

Sahmoudi²

2023

Preprint

View full text Add to dashboard Cite

The challenging issues of Computer Network and Databases are not only the intrusion detection but also the reduction of false positive and increase of detection rate. In any intrusion detection system, anomaly detection mainly focuses on modeling the normal behavior of the users and detecting the deviations from normal behavior which are assumed to be potential intrusions or treat. Several techniques have already been successfully tried for this purpose. However, the normal and suspicious behavior are hard to predict as there is no precise boundary differentiat-ing one from another. Here rough set theory and fuzzy set theory come into the picture. In this article, a hybrid approach based on rough set theory and intuitionistic fuzzy set theory is pro-posed for the detection of anomaly. The proposed approach is a classification approach which takes the advantages of softness properties both rough and fuzzy set theory to deal with uncer-tainty in the dataset. The algorithm classifies the data instances in such a way that they can be expressed using natural language. The experimental results with a real world dataset and a syn-thetic dataset show that the proposed algorithm has normal true positive rates of 91.989% and 96.99% and attack true positive rates of 91.289% and 96.29% respectively

show abstract

Section: B Experimental Results and Analysismentioning

confidence: 99%

“…In [24], the authors conducted a comparative analysis of five time-series anomaly detection models. In [25],…”

Section: Of 20mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Intuitionistic Fuzzy Rough Set Based Classification for Anomaly Detection

Mazarbhuiya¹,

Sahmoudi²

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Cloud platform, as a new research method and means, is slowly changing people's lifestyle and providing research ideas and methods to promote the interconnection between OneNet and cloud platform. The architectural core of cloud computing is cloud service, which consists of software Service Layer (SaaS), platform service layer (PaaS), and infrastructure layer (IaaS) [ 19 ]. The overall system design of the cloud platform is shown in Figure 2 through cloud computing, network function virtualization, multiheterogeneous data database storage, and other key technologies.…”

Section: Onenet Iot and Cloud Platformmentioning

confidence: 99%

A Sport Monitoring System Based on the Optimized Adaptive Fuzzy PID Control Algorithm in OneNet Internet of Things and Cloud Platform

Zhang

Min

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Aiming at some problems existing in the existing sports monitoring system, based on the joint action of OneNet Internet of Things (IoT) and cloud platform, an optimized adaptive fuzzy PID control algorithm is adopted to monitor and analyze sports. Finally, the accuracy of the optimization model is verified through the comparison of different models, and the algorithm is used to predict and analyze sports. The research shows that (1) as the index calculation of cloud platform shows, with the increase of iteration time, the change curve of relevant indexes can be divided into four different stages, namely, rapid fluctuation stage, slow decline stage, slow fluctuation stage, and rapid decline stage. (2) The conventional calculation method (CPID) cannot well describe the change rule of the test data in the early stage of settlement. The fuzzy adaptive calculation method (NPID) also exposes some errors in the fitting and description of the test curve in the calculation process, while the improved adaptive calculation method (GPID) can describe the change characteristics and rules of the test curve well for different stages. (3) Compared with the original model, the optimization model can better describe the first and second stages of index change, indicating the accuracy of the optimization model. And the algorithm can be used to predict and analyze the changes of indicators and sports monitoring better, and the analysis results can provide relevant guidance for sports monitoring. This optimization scheme provides basis and theoretical support for the application of OneNet IoT and cloud platform.

show abstract

“…In fact, power consumption mainly includes three important parts, one is the power generation side, the other is the grid side, and the third is the user side. The power consumption of the power generation side and the grid side in each region is highly controllable, while the power consumption of the user side is affected by various factors, and it is difficult to effectively control [7] . If the power on the user side cannot be controlled, it will lead to excessive load of some power grids and insufficient power transmission capacity of some power grids, which is not conducive to the reliable operation of the power grid.…”

Section: Introductionmentioning

confidence: 99%

Carbon emission monitoring model of digital power grid user side based on cloud platform

Li,

Zhang,

Chen

2023

Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023)

View full text Add to dashboard Cite

Conventional digital grid user side power carbon emission monitoring model mainly determines model parameters based on autoregressive condition heteroscedasticity, which is vulnerable to the lag effect of constraints, resulting in poor monitoring effect of the model. Therefore, a new digital grid user side power carbon emission monitoring model needs to be designed based on the cloud platform. That is to say, the cloud platform is used to obtain the monitoring data of power carbon emissions at the grid user side, and then combined with the carbon load active power relationship, the digital grid user side power carbon emissions monitoring mathematical model is constructed, which realizes effective carbon emissions monitoring. The case analysis results show that the designed carbon emission monitoring model on the user side of the digital power grid based on the cloud platform has a good monitoring effect, and the carbon emission intensity of each node monitored is more consistent with the actual carbon emission intensity, which proves that the designed model has good performance, reliability, and certain application value, and has made certain contributions to the development of subsequent grid operation schemes.

show abstract

Research on anomaly detection and real-time reliability evaluation with the log of cloud platform

Cited by 24 publications

References 24 publications

An Intuitionistic Fuzzy Rough Set Based Classification for Anomaly Detection

An Intuitionistic Fuzzy Rough Set Based Classification for Anomaly Detection

A Sport Monitoring System Based on the Optimized Adaptive Fuzzy PID Control Algorithm in OneNet Internet of Things and Cloud Platform

Carbon emission monitoring model of digital power grid user side based on cloud platform

Contact Info

Product

Resources

About