Impact of Multi-flow Traffic in Wireless Mobile Ad-hoc Networks

Ikeda, Makoto; Kulla, Elis; Hiyama, Masahiro; Barolli, Leonard; Takizawa, Makoto

doi:10.1109/aina.2012.55

Cited by 5 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With respect to data sampling, the method of handling class overlapping region can be further improved from the data level, such as using data cleaning method (Wang et al 2014). Additionally, this paper only works on wired network traffic without considering the wireless mobile networks (Ikeda et al 2013). With the imperative evolution from IPv4 to IPv6, the applications in mobile IPv6 networks (Tao et al 2012(Tao et al , 2014) experience a rapid growth, we will facilitate the network traffic classification problem on the mobile traffic traces collected from IPv6 network as our future work.…”

Section: Discussionmentioning

confidence: 99%

SmoteAdaNL: a learning method for network traffic classification

Liu

Wang

Tao

2015

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Machine learning based network traffic classification is a critical technique for network management, and has attracted much attention. Recently, most of the researchers focus on achieving high flow classification accuracy (FCA). However the amount of ''mice'' flows is more than that of ''elephant'' flows in the Internet, these classifiers hence are more suitable for ''mice'' flows, but have low byte classification accuracy (BCA). To address this issue, the notion of byte misclassification is firstly explored. According to the exploration that most misclassified bytes belong to the minority class, a novel method of network traffic classification is proposed by combining the data re-sampling and ensemble learning algorithms. To enhance the classification accuracy of the minority class, the data re-sampling algorithm is employed to increase the number of minority class flows. The data re-sampling however will change the data distribution and degrade the generalization of a classifier. A boosting-style ensemble learning algorithm with the consideration of ensemble diversity hence is employed to improve the generalization. The experiments conducted on the real-world traffic datasets show that the proposed method achieves over 90 % BCA and 96 % FCA on average, and improves about 7.15 % BCA by comparing with the existing methods.

show abstract

Section: Discussionmentioning

confidence: 99%

SmoteAdaNL: a learning method for network traffic classification

Liu

Wang

Tao

2015

J Ambient Intell Human Comput

View full text Add to dashboard Cite

show abstract

“…In [14], we evaluated by simulations, average throughput and percentage of received CBR packets of a MANET, comparing AODV and OLSR protocols with UDP single or UDP multiple flows. Regarding AODV for 100m×100m area with maximum speed set to 6 m/s, the performance is almost the same for different number of nodes.…”

Section: Related Workmentioning

confidence: 99%

Congestion Control for Multi-flow Traffic in Wireless Mobile Ad-Hoc Networks

Ikeda

Kulla

Hiyama

et al. 2012

2012 Sixth International Conference on Complex, Intelligent, and Software Intensive Systems

Self Cite

View full text Add to dashboard Cite

In this paper, we deal with congestion control for multi-flow traffic in wireless mobile ad-hoc networks (MANET). For simulations, we used ns-3 open source network simulator considering Optimized Link State Routing (OLSR) routing protocol. We present the MANET performance considering random waypoint mobility model for different number of nodes and different area sizes, by sending multi-flow traffic in the network. We found that coupling congestion control mechanisms between multi-flows have problems in some cases.

show abstract