پديد آورنده :
احمدزاده، سارا
عنوان :
كنترل ازدحام در شبكه هاي مبتني بر نرم افزار به كمك پيش بيني ترافيك شبكه با روش شبكه هاي عصبي مصنوعي
مقطع تحصيلي :
كارشناسي ارشد
گرايش تحصيلي :
هوش مصنوعي
محل تحصيل :
اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر
صفحه شمار :
[دوازده]، 89ص.: مصور، جدول، نمودار
يادداشت :
ص. ع. به فارسي و انگليسي
استاد راهنما :
علي فانيان
استاد مشاور :
مهران صفاياني
توصيفگر ها :
شبكه هاي تعريف شده با نرم افزار , كنترل ازدحام , پيش بيني ترافيك شبكه
استاد داور :
محمدحسين منشئي، احسان يزديان
تاريخ ورود اطلاعات :
1396/05/15
رشته تحصيلي :
برق و كامپيوتر
دانشكده :
مهندسي برق و كامپيوتر
چكيده انگليسي :
Congestion Control in Software Defined Networking with Traffic Prediction Using Artificial Neural Networks Sarah Ahmadzadeh Jun 2017 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor Dr Ali Fanian Advisor Dr Mehran SafayaniAbstract Software Defined networking SDN is a new architecture for communication networks that provides centralcontrol in networking by separating control plane and data plane Also the ability of provisioning and managingof the network through high level programming languages become available by providing the user interface forhigh level control in SDN The high level control caused the wide and rapid development of novel approches incontrol and managing of the network In the other hand SDN centralized the network control by separate controlplane and data plane but it distributes the development among researchers Congestion control approaches inSDN are conceivable by using high level languages and they will translate to low level languages for switches androuters by OpenFlow protocol In this thesis a SDN controller is designed to avoid congestion in the network this controller is composedof multiple modules such as collecting information predicting network traffic congestion detection routing anda routeing algorithm to avoid congestion In the prediction approach that uses neural networks the aim is usingjust one neural network to predict all flows of the network For this purpose two kinds of neural network FeedForward and Recurrent are made and tested Both are able to predict traffic network in a short time slot Therouting module has tow different algorithm a static algorithm for a light load of traffic and a dynamic one for highloaded links The dynamic algorithm uses an optimization approach to find the best routes based traffic loads onthe links Normally this optimization is not calculatable in real time but by relaxing constraints it s solved inreal time The dataset used in this thesis is captured from a router of the Isfahan University of Technology andmodified for use as SDN traffic data Simulation results represent prediction and routing approaches are suitableto reduce the congestion on links Key Words Software defined networking congestion control network traffic pre diction recurrent neural networks LSTM dynamic routing
استاد راهنما :
علي فانيان
استاد مشاور :
مهران صفاياني
استاد داور :
محمدحسين منشئي، احسان يزديان
