In TCP over OBS networks, the parameters from both of TCP and OBS layers will affect the network performance when
supporting the upper layer applications, such as Grid application. According to our previous work, we found that TCP
window is the key limitation for such a network to support Grid application. The embedded AIMD model of TCP is too
conservative. Especially in the network with high bandwidth-delay product scenario, it will take TCP a long time to
increase the TCP window according to the slow start and the congestion avoidance rules. In this paper, according to the
established analytical model, the TCP window size is optimized in Grid over OBS network. The analytical results show
that the optimization of TCP window can improve the TCP throughput significantly.
OBS is envisioned as a promising infrastructure for the next generation optical network, and TCP is likely to be the
dominant transport protocol in the next generation network. Therefore, it is necessary to evaluate the performance of
TCP over OBS networks. The assembly at the ingress edge nodes will impact the network performance. There have been
several Fixed Assembly Period (FAP) algorithms proposed. However, the assembly period in FAP is fixed, and it can not
be adjusted according to the network condition. Moreover, in FAP, the packets from different TCP sources are
assembled into one burst. In that case, if such a burst is dropped, the TCP windows of the corresponding sources will
shrink and the throughput will be reduced. In this paper, we introduced a flow-oriented Dynamic Assembly Period (DAP)
algorithm for TCP over OBS networks. Through comparing the previous and current burst lengths, DAP can track the
variation of TCP window, and update the assembly period dynamically for the next assembly. The performance of DAP
is evaluated over a single TCP connection and multiple connections, respectively. The simulation results show that DAP
performs better than FAP at almost the whole range of burst dropping probability.
Dynamic Assembly Period (DAP) is a novel assembly algorithm, which is based on the dynamic TCP window. The
assembly algorithm can track the variation of the current TCP window aroused by the burst loss events, and update the
assembly period dynamically for the next assembly. The analytical model provides the theoretical foundation for the
proposed assembly algorithm. Nowadays, there are several kinds of TCP flavors proposed to enhance the performance of
TCP, such as Default, Tahoe, Reno, New Reno, SACK, etc., which are adopted in the current internet. In this paper, we
evaluated the performance of DAP under the different TCP flavors. The simulation results show that the performance of
DAP under Default TCP flavor is the best. The difference in the performance of DAP under such flavors is correlated
with the inside mechanism of the flavors. We also compared the performance of DAP and FAP under the same TCP
flavor. It indicates that the performance of DAP is better than that of FAP in a wide range of burst loss rate.
We proposed a novel drop policy in the core nodes which is combined with the determinant strategy in the ingress edge
nodes. The proposed drop policy is based on the field of Hop Number (HN) taken by the burst control packets, which is
introduced to determine which burst should be dropped when the contention happened in the core nodes. In the drop
policy, the long-hop traffic is given the high priority, and most of the retransmitted traffic is left to be short-hop traffic.
Therefore, there is a trade-off between the short-hop traffic and the long-hop traffic. The determinant strategy in the edge
nodes is an initialized threshold, Retransmission Number Threshold (RNT), which is introduced to determine whether to
start a retransmission operation when NAK is received. The unnecessary retransmissions in the network are limited, and
the burst loss rate is reduced. The mechanism also takes the upper layer, TCP layer, into account. When the network has
already been in the state of real congestion, the retransmission will only deteriorate the network performance. In the case,
the combined mechanism leaves the retransmission process to the TCP layer. It can improve the network performance
cost-effectively.
In this paper, the architecture of the optical networks based on Time-Space Label (TSL) Switching is described in detail,
including Time-Space Label and Time-Space Routing algorithm. The switching mode is more flexible and scalable. The
labels can be changed to fit for different kinds of optical switching technologies, such as Optical Circuit Switching
(OCS), Optical Burst Switching (OBS) and Optical Packet Switching (OPS). The TSL switching has a very wide range
of applications in the optical networks. In the existing signaling protocols of OBS, the routing and the signaling are
separated. However, TSL switching combines both of them together. Moreover, the resource reservations are realized in
a two-dimension Time-Space plane, and the blocking probability is reduced greatly. The mature electronic processing
technologies and the high-speed optical transport are cooperated effectively in the TSL switching. On the other hand,
Multi-Granularity (MG) Switching can groom the vast bypass traffic in the optical networks effectively, with which the
core nodes are simplified, and the throughput is increased significantly. When MG switching is combined with TSL
switching, the performance of the entire network will be improved greatly. A test system built for validating the MG
switching based on TSL is described, and the results show the switching performance of different granularities correctly.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.