Experience-based network resource usage on mobile hosts

Author(s):  
Arjan Peddemors ◽  
Henk Eertink ◽  
Ignas Niemegeers
Author(s):  
Carlos Alberto M. S. Teles ◽  
Carlos Roberto Gonçalves Viana Filho ◽  
Felipe da Rocha Henriques

Information security is gradually becoming an area that plays an important role in our daily lives as information and communications technology assets grow with increasingly connected environments. Increasingly we have information from society having their data leaked due to information security flaws in both hardware and software of ICT assets. To identify failures of ICT assets, through the detection of malicious traffic, this chapter proposes a black-box-based framework that aims to detect malicious traffic. The black-box method allows monitor the network without accessing the software or hardware details. In the proposed framework, information security and network resource usage are used together in order to provide a reliable detection of malicious traffic. Firstly, the authors collected network traffic information, generating a dataset from open source networking tools. The proposed detection scheme can identify risks and threats like malware, suspect traffic, and others. The scheme was validated verifying the correlation between network security alerts and network resource usage.


2011 ◽  
Vol 403-408 ◽  
pp. 2612-2616 ◽  
Author(s):  
Yu Hong Li ◽  
Yan Shi ◽  
Liang Yu ◽  
Bo Fan Zhang

The paper studies the adaptable capability of applications in mobile networks in the context of the optimizing the network resource usage. Based on a thorough analysis of applications’ adaptability, a unified utility framework is proposed to describe the resource requirement of applications and their adaptability. Utility functions of different type of applications are discussed under the utility framework. Examples for how to use the framework are also given. Simulation results show that the proposed utility framework can be used for optimizing network resources and can therefore satisfy the needs of more applications.


Author(s):  
Ryan Blue ◽  
Cody Dunne ◽  
Adam Fuchs ◽  
Kyle King ◽  
Aaron Schulman

2020 ◽  
Vol 3 (2) ◽  
pp. 223-233
Author(s):  
Etibar Vazirov ◽  

The combination of heterogeneous resources within exascale architectures guarantees to be capable of revolutionary compute for scientific applications. There will be some data about the status of the current progress of jobs, hardware and software, memory, and network resource usage. This provisional information has an irreplaceable value in learning to predict where applications may face dynamic and interactive behavior when resource failures occur. What is proposed in this paper is building a scalable framework that uses special performance information collected from all other sources. It will perform an analysis of HPC applications in order to develop new statistical footprints of resource usage. Besides, this framework should predict the reasons for failure and provide new capabilities to recover from application failures. We are applying HPC capabilities at exascale causes the possibility of substantial scientific unproductiveness in computational procedures. In that sense, the integration of machine learning into exascale computations is an encouraging way to obtain large performance profits and introduce an opportunity to jump a generation of simulation improvements.


Sign in / Sign up

Export Citation Format

Share Document