Rate Assignment in Micro-Buffered High Speed Networks

نویسندگان

  • Mustafa Arisoylu
  • R. L. Cruz
  • Tara Javidi
چکیده

Micro-buffered networks are high speed optical packet switched networks, and consist of either nodes with no buffering or nodes with limited buffering. We focus on the case of bufferless nodes, where there is no specific collision resolution mechanisms inside the core. Packet losses inside the core may be frequent, and are dealt with using end-to-end or edgeto-edge coding techniques. In this study, we discuss the rate allocation problem for a micro-buffered high speed network. Various rate assignment policies are defined and related features and algorithms are discussed. First the classical slotted aloha type protocols with exponential backoff are examined and it is observed that in the case of asymmetry in collision sets, classical aloha protocols with exponential backoff may result in unfair rate allocations such that some flows may end up with zero rates. Next, we consider (weighted) α-proportional , (weighted) max-min and hierarchical max-min fair rate assignments. Simple distributed algorithms achieving these notions of fairness by exchanging local information are discussed. It is found that (weighted) max-min fair information rate allocation assigns information rates to each flow in the same group inversely proportional to their weights, where groups correspond to connected components in the contention graph between flows. As a special case, max-min fairness assigns the same information rate to any two flows in the same group even though they do not directly contend with each other. Furthermore, we also show that hierarchical max-min fairness can be achieved in a micro-buffered network if and only if weighted max-min fairness among the flows is ensured.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Optimization of micro hardness of nanostructure Cu-Cr-Zr alloys prepared by the mechanical alloying using artificial neural networks and genetic algorithm

Cu–Cr-Zr alloys had wide applications in engineering applications such as electrical and welding industrial especially for their high strength, high electrical as well as acceptable thermal conductivities and melting points. It was possible to prepare the nano-structure of these age hardenable alloys using mechanical alloying method as a cheap and mass production technique to prepare the non-eq...

متن کامل

Design of Arrayed Waveguide Grating based Optical Switch for High Speed Optical Networks

This paper demonstrates the design of an Arrayed Waveguide Gratings (AWG) based optical switch. In the design both physical and network layer analysis is performed. The physical layer power and noise analysis is done to obtain Bit Error Rate (BER). This has been found that at the higher bit rates, BER is not affected with number of buffer modules. Network layer analysis is done to obtain perfor...

متن کامل

Performance of a Dynamic Channel Assignment Technique in Hierarchical Structure for Mobile Communications Networks

This paper presents a dynamic channel assignment technique in hierarchical structure for Mobile Communications Networks. This technique optimizes the handover call blocking probability performance of High-Speed Moving Terminals (HSMT). Traffic of Low-Speed Moving Terminals (LSMT) is absorbed by a micro cellular architecture solution and traffic of new calls of HSMT is abrorbed by a higher layer...

متن کامل

Experimental Study of a High Speed Micro Waterwheel

Waterwheels are the oldest types of hydraulic machines. These turbines are of relatively simple design, large diameter, low rotational speed and high torques. But applying them as micro hydros of high speed and small diameter is yet to be explored. A micro hydro waterwheel of one meter diameter was designed and manufactured at the Iranian  esearc†h Organization for Science and Technology (IROST...

متن کامل

High-speed All- Optical Time Division Multiplexed Node

In future high-speed self-routing photonic networks based on all-optical time division multiplexing (OTDM) it is highly desirable to carry out packet switching, clock recovery and demultplexing in the optical domain in order to avoid the bottleneck due to the optoelectronics conversion. In this paper we propose a self-routing OTDM node structure composed of an all-optical router and demultiplex...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005