Tuesday, 22 July 2014

Stochastic Bandwidth Estimation in Networks With Random Service

Numerous methods for available bandwidth estimation have been developed for wireline networks, and their effectiveness is well-documented. However, most methods fail to predict bandwidth availability reliably in a wireless setting. It is accepted that the increased variability of wireless channel conditions makes bandwidth estimation more difficult. However, a (satisfactory) explanation why these methods are failing is missing. This paper seeks to provide insights into the problem of bandwidth estimation in wireless networks or, more broadly, in networks with random service. We express bandwidth availability in terms of bounding functions with a defined violation probability. Exploiting properties of a stochastic min-plus linear system theory, the task of bandwidth estimation is formulated as inferring an unknown bounding function from measurements of probing traffic. We present derivations showing that simply using the expected value of the available bandwidth in networks with random service leads to a systematic overestimation of the traffic departures. Furthermore, we show that in a multihop setting with random service at each node, available bandwidth estimates requires observations over (in principle infinitely) long time periods. We propose a new estimation method for random service that is based on iterative constant-rate probes that take advantage of statistical methods. We show how our estimation method can be realized to achieve both good accuracy and confidence levels. We evaluate our method for wired single-and multihop networks, as well as for wireless networks.
In bandwidth estimation methods, end-systems exchange timestamped probe packets and study the dispersion of these packets after they have traversed a network of nodes. In recent years, available bandwidth estimation has attracted significant interest, and a wide variety of measurement tools and techniques have been developed. Many of the most popular methods for available bandwidth estimation are based on congestion-inducing packet trains, where a packet train consists of a sequence of probe packets. By sending packet trains at a rate exceeding the available bandwidth, the network becomes congested, thereby imprinting information on the network state on the dispersion of probe packets. Virtually all available bandwidth methods were developed for wireline networks, where communication channels consist of fixed-capacity links, and where the available bandwidth of a link is given by its unconsumed capacity. Some of these methods have been adapted for wireless networks (see Section II), in particular WiFi networks, however, they generally lack the robustness and reliability achieved in fixed-capacity wireline environments. A potential source of errors are unsuitable model assumptions.
·       FIFO queueing may be highly prevalent in wired network infrastructures today, FIFO assumptions are difficult to justify in wireless multi access networks
·       Its latencies incurred during channel access lead to non-work-conserving systems.

In this paper, we investigate fundamental difficulties of measuring the available bandwidth in wireless networks with congestion- inducing packet trains. Rather than revising or adapting wireline approaches to wireless channels, e.g., by trying to eliminate superimposed random “noise,” we seek to develop from the ground up a new modeling and inference approach for networks that are subject to randomness of both traffic and transmission channels. We dispense with the modeling assumption of a work-conserving queueing system and, taking advantage of concepts from the stochastic network calculus [20], replace it with that of a general stationary system.
The point of departure of our efforts is a recent system-theoretic approach of bandwidth estimation [28]. Here, the network is viewed as a time-invariant deterministic system where throughput and delays of traffic are governed by an unknown bounding function, referred to as service curve. Service curves can express work-conserving as well as non-work-conserving systems.
·       FIFO links with cross traffic can be replaced by a more general network model without specific requirements on the multiplexing method.
·       It present measurement results for wired single-hop and multihop networks as well as for wireless networks.



ü Processor                  -        Pentium –IV

ü Speed                        -        1.1 Ghz
ü RAM                         -        512 MB(min)
ü Hard Disk                 -        40 GB
ü Key Board                -        Standard Windows Keyboard
ü Mouse                       -        Two or Three Button Mouse
ü Monitor                     -        LCD/LED

         Operating system :         Windows XP
         Coding Language :         Java
         Data Base             :         MySQL
         Tool                     :         Net Beans IDE

 Ralf Lübben, Markus Fidler, and Jörg Liebeherr, Stochastic Bandwidth Estimation in Networks With Random Service IEEE/ACM TRANSACTIONS ON NETWORKING, VOL. 22, NO. 2, APRIL 2014.

No comments:

Post a Comment