Discrete Noetherian ring variational pattern feature sets for space-air-ground network protocol monitoring

Communication protocol is the rule and process of information exchange between every communication entities. It is the technical support of seamless interconnection between heterogeneous networks from SAGN (space-air-ground network). SDN (software-defined network) is a significant attempt framework on SAGN to manage all the entities. However, there are the following problems of protocol monitoring based on SDN. To define a unified monitoring framework on a heterogeneous network is difficult. What’s more, demanded monitoring features are much less than the real traffic in the network. The captured features are always redundancy in the case of protocol monitoring. Therefore, this paper proposes a new method of discrete Noetherian ring variational pattern features set for SAGN protocol monitoring. We build the real time traffic model of SAGN based on discrete Noetherian ring multi-dimensional vector. Employing the traffic between heterogeneous network elements to describe the non-linear features by reasoning the origin traffic. To make the discrete features into finite feature of the Noetherian ring, furtherly operate Legendre equation to design reversible multidimensional feature matrix. Those enhance the aggregation of protocol features. Continuous feature set and content monitoring of real-time monitoring traffic are designed. Associating spatial information features is enhances the adaptive ability of traffic feature set. The simulations and tests demonstrates that the new method has improve the accuracy of protocol test by 28% and response time by 3.53 s.

[1]  Rui Sun,et al.  Estimating online vacancies in real-time road traffic monitoring with traffic sensor data stream , 2015, Ad Hoc Networks.

[2]  Mo Li,et al.  A Participatory Urban Traffic Monitoring System: The Power of Bus Riders , 2017, IEEE Transactions on Intelligent Transportation Systems.

[3]  Jing Tao,et al.  AL-bitmap: Monitoring network traffic activity graphs on high speed links , 2017, Inf. Sci..

[4]  Lanlan Chen,et al.  Detecting driving stress in physiological signals based on multimodal feature analysis and kernel classifiers , 2017, Expert Syst. Appl..

[5]  Ning Li,et al.  A new satellite communication bandwidth allocation combined services model and network performance optimization , 2017, Int. J. Satell. Commun. Netw..

[6]  Marco Mellia,et al.  DBStream: A holistic approach to large-scale network traffic monitoring and analysis , 2016, Comput. Networks.

[7]  Uwe Nagel,et al.  Equivariant Hilbert Series in non-Noetherian Polynomial Rings , 2015, 1510.02757.

[8]  Julong Lan,et al.  OpenFlow based flow slice load balancing , 2014, China Communications.

[9]  Zhiyang Su,et al.  CeMon: A Cost-effective Flow Monitoring System in Software Defined Networks , 2015, Comput. Networks.

[10]  Baosheng Wang,et al.  Exploring the Reliable Multicast Transport of BGP in Geostationary Satellite Networks Based on Network Coding , 2017, IEICE transactions on communications.

[11]  Ilsun You,et al.  SAT-FLOW: Multi-Strategy Flow Table Management for Software Defined Satellite Networks , 2017, IEEE Access.

[12]  Reza Nejabati,et al.  Multilayer network analytics with SDN-based monitoring framework , 2017, IEEE/OSA Journal of Optical Communications and Networking.

[13]  Kosin Chamnongthai,et al.  Thermal-image processing and statistical analysis for vehicle category in nighttime traffic , 2017, J. Vis. Commun. Image Represent..

[14]  Meng Wu,et al.  Combining network coding and compressed sensing for error correction in wireless sensor networks , 2015, Int. J. Commun. Syst..

[15]  Romeo Giuliano,et al.  Integrated Public Mobile Radio Networks/Satellite for Future Railway Communications , 2017, IEEE Wireless Communications.

[16]  Meng Wu,et al.  Compressive network coding for error control in wireless sensor networks , 2014, Wirel. Networks.