scholarly journals Layer 2 Path Evaluation System using Machine Learning

2021 ◽  
Vol 19 (3) ◽  
Author(s):  
Mahamah Sebakor
Keyword(s):  
Machine Learning ◽  
Spanning Tree ◽  
Evaluation System ◽  
Software Defined Network ◽  
Data Preparation ◽  
Spanning Tree Protocol ◽  
Novel Approach ◽  
Layer 2 ◽  
And Performance ◽  
Network Administrators

Is it strange that the spanning tree protocol (STP) has been the only thing used to defend the Layer-2 backbone against looping? Do we trust it? For several decades, the campus backbone has often been an unsuspected problem, one of which is STP failure. Meanwhile, the MAC address flapping is probably a feasible issue for modern network fabrics. According to the serious Layer-2 issues, particularly the legacy switches extended STP design, this work uses the notion of a software-defined network fashion to evaluate the traditional and modern networks. Through the MAC address lookup of all bridge devices, this work proposes the Layer-2 evaluation system (LES), which uses a novel approach known as support supervised learning to create the data preparation for machine learning. Additionally, the LES enabled network administrators to determine their backbones. This study is intended to evaluate the potential slowdown network caused by MAC address problems. Furthermore, this work investigates the proposed method in a real network, and it also covers the evaluation and performance of our proposed method.

An Improved Approach for Eliminating the Loop in Hybrid Software Defined Network (SDN) Using Modified Bellman-Ford Algorithm

2020 ◽  
Vol 20 (04) ◽  
pp. 2150001
Author(s):  
J. MOHAN ◽  
SHWETA M. DEVANAGAONKAR ◽  
VINEETA V. GARUR ◽  
A. KARTHIK ◽  
K. ROHITAKSHA ◽  
...  
Keyword(s):  
Bandwidth Allocation ◽  
Spanning Tree ◽  
Optimal Solution ◽  
Global Network ◽  
Software Defined Network ◽  
Spanning Tree Protocol ◽  
Layer 2 ◽  
Sdn Controller ◽  
Loop Problem ◽  
Hybrid Sdn

SDN is approaching its own structure of acceptance. Therefore, the increasing deployment of SDNs is being discussed as a possible approach, appearing in the development of the hybrid SDN networks. An foremost work in the hybrid SDN networks is bandwidth allocation, taking into account the integration of both SDN-enabled and conventional switches. The network loop in layer 2 switches is skipped in Spanning Tree Protocol (STP) by ceaselessly watching the network to trace all links and block the unwanted ones. Bridge loops will occur anytime there’s a redundant Layer2 way between ends. By default, switches forward broadcast/multicast out all ports, other than the port from that the broadcast/multicast was delivered. Once a switch loop is brought in the network, broadcast messages are going to be broadcasted more often leading to broadcast storms. The Spanning-tree algorithm enforces a distributed divergent of the Bellman-Ford iterative algorithm that always looks for the optimal solution and selects an optimal influential switch anytime. In this paper we use controller’s global network view for resolving loop problem in layer 2 network. SDN controller acts on broadcast packets received from switch-ports and host-ports differently that is if the broadcast packets received from host ports, the SDN controller broadcasts these packets to all ports and if broadcast packets is received from switch ports, only some switches broadcasts these packets on all ports instead of all switches.

Performance Analysis of POX and RYU Controller on Software Defined Network with Spanning Tree Protocol

2021 ◽  
Author(s):  
Nurul Zaenal Abidin ◽  
Andrew Fiade ◽  
Arini ◽  
Saepul Aripiyanto ◽  
Nuryasin ◽  
...  
Keyword(s):  
Performance Analysis ◽  
Spanning Tree ◽  
Software Defined Network ◽  
Spanning Tree Protocol

scholarly journals PENERAPAN SPANNING TREE PROTOCOL UNTUK MENCEGAH TERJADINYA LOOPING PADA FRAME ETHERNET

EXPLORE ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 7
Author(s):  
Moh. Subli ◽  
Hoiriyah ◽  
Erfan Wahyudi
Keyword(s):  
Spanning Tree ◽  
Tree Algorithm ◽  
Network Layer ◽  
Spanning Tree Protocol ◽  
Layer 2 ◽  
Loop Network

Spanning Tree Protocol (STP) adalah layanan yang memungkinkan LAN switch dan LAN bridge terinterkoneksi secara berlebih dengan cara menyediakan mekanisme untuk mencegah loop yang tidak diinginkan dalam jaringan yang terjadi pada bridge. Tanpa adanya STP, pada frame Ethernet akan terjadi loop untuk periode tak terbatas di dalam waktu jaringan dengan link berlebihan secara fisik. Untuk mencegah loop pada frame Ethernet, STP memblok beberapa port dari frame Ethernet  sehingga hanya satu jalur yang aktif ada di antara setiap pasang segmen LAN (collision domain). Hasil STP adalah loop frame Ethernet tidak terbatas yang membuat LAN dapat digunakan. Satu hal yang perlu diperhatikan adalah bahwa Redundant link tidak untuk keseimbangan beban, karena hanya satu link aktif. Cara kerja Spanning Tree Protocol adalah menggunakan algoritma spanning tree yang secara otomatis menemukan topologi jaringan dan membentuk suatu jaringan tunggal yang optimal melalui suatu bridge jaringan dengan menugasi fungsi-fungsi yang ada pada setiap bridge. STP Menghentikan terjadinya loo-loop network pada network layer 2 (bridge atau switch). STP secara terus menerus memonitor network untuk menemukan semua link, memastikan bahwa tidak ada loop yang terjadi dengan cara mematikan semua link yang redundant. STP menggunakan algoritma yang disebut Spanning Tree Algorithm (STA) untuk menciptakan sebuah topologi database, kemudian mencari dan menghancurkan link-link redundant. Dengan menjalankan STP, frame-frame hanya akan diteruskan pada link-link utama yang dipilih oleh STP.

scholarly journals Implementasi Redundant Switch Menggunakan CISCO Catalyst Di PT. Citra Solusi Pratama

2021 ◽  
Vol 7 (2) ◽  
pp. 77-85
Author(s):  
Muhammad Syihabuddin ◽  
Jenih Jenih
Keyword(s):  
Spanning Tree ◽  
Spanning Tree Protocol ◽  
Layer 2

Spanning Tree protocol atau yang sering disingkat dengan STP adalah metode pada jaringan yang menjamin tidak adanya loop dalam jaringan. Dengan model jaringan OSI untuk jaringan komputer, STP ada di layer 2 OSI. Spanning tree protocol memperbolehkan desain jaringan memiliki redundant link untuk membuat jalur backup otomatis. Dengan menggunakan metode spanning tree protocol maka apabila perangkat switch cisco catalyst tersebut down maka akan berimbas pada jaringan tersebut karena sudah ada backup link. Apabila main link down atau terputus, maka port yang tadi terblok akan terbuka oleh switch, sehingga data dari komputer pengirim akan melewati redundant.Kata Kunci: Jaringan, Komputer, Spanning

scholarly journals Detecting P2P Botnet in Software Defined Networks

2018 ◽  
Vol 2018 ◽  
pp. 1-13 ◽  
Author(s):  
Shang-Chiuan Su ◽  
Yi-Ren Chen ◽  
Shi-Chun Tsai ◽  
Yi-Bing Lin
Keyword(s):  
Machine Learning ◽  
Network Management ◽  
P2p Network ◽  
Software Defined Network ◽  
Software Defined Networks ◽  
Security Issues ◽  
Network Equipment ◽  
Traditional Approaches ◽  
Network Administrators ◽  
Sdn Controller

Software Defined Network separates the control plane from network equipment and has great advantage in network management as compared with traditional approaches. With this paradigm, the security issues persist to exist and could become even worse because of the flexibility on handling the packets. In this paper we propose an effective framework by integrating SDN and machine learning to detect and categorize P2P network traffics. This work provides experimental evidence showing that our approach can automatically analyze network traffic and flexibly change flow entries in OpenFlow switches through the SDN controller. This can effectively help the network administrators manage related security problems.

Intelligent system of English composition scoring model based on improved machine learning algorithm

2020 ◽  
pp. 1-11
Author(s):  
Jie Liu ◽  
Lin Lin ◽  
Xiufang Liang
Keyword(s):  
Machine Learning ◽  
Evaluation System ◽  
Intelligent System ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Assessment System ◽  
English Composition ◽  
Region Extraction ◽  
Constraint Model

The online English teaching system has certain requirements for the intelligent scoring system, and the most difficult stage of intelligent scoring in the English test is to score the English composition through the intelligent model. In order to improve the intelligence of English composition scoring, based on machine learning algorithms, this study combines intelligent image recognition technology to improve machine learning algorithms, and proposes an improved MSER-based character candidate region extraction algorithm and a convolutional neural network-based pseudo-character region filtering algorithm. In addition, in order to verify whether the algorithm model proposed in this paper meets the requirements of the group text, that is, to verify the feasibility of the algorithm, the performance of the model proposed in this study is analyzed through design experiments. Moreover, the basic conditions for composition scoring are input into the model as a constraint model. The research results show that the algorithm proposed in this paper has a certain practical effect, and it can be applied to the English assessment system and the online assessment system of the homework evaluation system algorithm system.

Sign in / Sign up

Export Citation Format

Share Document