Figure 4 compares UDP transfer rates for simple
tree and fat-tree topologies with and without conflict
rules. The bare tree had transfer rates of 19.1-20
Gb/s, while the fat tree had rates of 18.1-21 Gb/s.
With conflict rules, both topologies experienced
declines, with introductory tree rates at 17.1-18.2
Gb/s and fat-tree rates at 10.1-13 Gb/s. UDP
transmission decreased by 11% for simple trees and
44% for fat trees over 0-3600 seconds.
Fig. 4. UDP Ttransfer Rrate for Two Topologies
The evaluation of two scenarios, one employing
the TCP protocol and the other utilizing the UDP
protocol, is conducted by assessing the quantity of
data transmitted. Figure 3 displays a decline in TCP
transferred data within time intervals ranging from 0
to 3600 seconds. The simple tree topology shows a
loss of 10%, while the fat-tree topology shows a
drop of 31%. Similarly, Figure 4 compares UDP
data transmission over extended time intervals
ranging from 0 to 3600 seconds. The conflicting
flows in UDP protocol also lead to a reduction in
data transfer, specifically by 11% for a basic tree
topology and 44% for a fat-tree topology. Lastly,
Table 2 presents a comparison of the mean decrease
in TCP and UDP protocols under both implemented
conditions.
Table 2. Comparison of the average drop-in transfer
rate with flow conflict.
6 Conclusion
This investigation focuses on evaluating the
message transmission variable in Software-Defined
Networking (SDN) for both regular and conflict
flows in a standard forwarded SDN environment. To
achieve this, we utilized the Mininet software
simulator to execute an algorithmic model. Our
findings demonstrate that the implementation of
conflict rules significantly impacts data transport for
both TCP and UDP protocols. Additionally, the data
highlights an apparent difficulty with conflict flows
in OpenFlow switches, suggesting that further
research is necessary to address this issue by
resolving the observed losses. One of the key
takeaways from this research is that while
implementing software-defined networking (SDN),
it is essential to consider the issue of conflict flows,
especially if the programs or services that are
utilized demand an improvement in transfer rate. As
such, subsequent investigators ought to emphasize
the improvement of safety attributes in the SDN
network while maintaining the network's quality of
service.
References:
[1] Pisharody, S., et al., Brew: A security policy
analysis framework for distributed SDN-
based cloud environments. IEEE
Transactions on Dependable and Secure
Computing, 2017. 16(6): p. 1011-1025.
[2] Khairi, M.H.H., et al., Detection and
classification of conflict flows in SDN using
machine learning algorithms. IEEE Access,
2021. 9: p. 76024-76037.
[3] Cui, J., et al. Transaction-based flow rule
conflict detection and resolution in SDN. In
2018 27th International Conference on
Computer Communication and Networks
(ICCCN), 2018, IEEE.
[4] Khairi, M.H.H., et al., A Review of Flow
Conflicts and Solutions in Software Defined
Networks (SDN). IIUM Engineering
Journal, 2021. 22(2): p. 178-187.
[5] McKeown, N., et al., OpenFlow: enabling
innovation in campus networks. ACM
SIGCOMM Computer Communication
Review, 2008. 38(2): p. 69-74.
[6] Adeniji Oluwashola David, O.I.O., "Scalable
Flow based Management Scheme in
Software Define Network (SDN) using
sFlow," WSEAS Transactions on Computers,
vol. 22, pp. 64-69, 2023,
https://doi.org/10.37394/23205.2023.22.7.
[7] Lo, C.-C., P.-Y. Wu, and Y.-H. Kuo. Flow
entry conflict detection scheme for software-
defined network. In 2015 International
Telecommunication Networks and
Applications Conference (ITNAC). 2015.
IEEE.
[8] Hauser, F., et al., P4-MACsec: Dynamic
topology monitoring and data layer
protection with MACsec in P4-SDN. arXiv
preprint arXiv:1904.07088, 2019.
WSEAS TRANSACTIONS on COMPUTERS
DOI: 10.37394/23205.2023.22.35
Mutaz Hamed Hussien, Mohamed Khalafalla Hassan