Enhance the Performance of Wireless Sensor Network based on Software Define Network and Kalman Filter

The paper proposes a methodology for estimating packet flowing at the sensor level in SDN-WSN based on the partial congestion controller with Kalman filter. Furthermore, the actual purpose of proposing such methodology for predicting in advance the subsequent step of packet flow, and that will consequently contribute in reducing the congestion that might happen. The model proposed (SDN with Kalman filter) is optimized using congestion controller, the methodology of proposed work, the first step random distributed of random node, the apply the Kmean cluster of select the head cluster node in, the connected the network based on LEACH protocol. in this work proposed SDN with Kalman filter for control on network and reduce error of data, where achieve by add buffer memory for each nodes and head cluster to store the data, and SDN control on transmit ion data and receiver data, before transmit apply the Kalman filter on data to reduce error data. The proposed technique, according to simulation findings, extends the network's lifetime by over 30% more than typical WSNs, the reduce the average density of memory to 20% than traditional WSN, and the increase the average capacity of memory to 20% than traditional WSN.

Software Defined Networks: a Comparative Study and Quality of Services Evaluation

Software-Defined Network (SDN) as architecture network that separates the control and forwarding functions, so that network operators and administrators can configure the networks in a simple and centrally between thousands of devices. This study is designed and evaluate the Quality of Services (QoS) performances between the two networks employed SDN-based architecture and without SDN-based. MinNet as a software emulator used as a data plane in the network Software Define Network. In this study, comparison of the value of the QoS on the network based on Software Defined Network and traditional network during the test run from the source node is investigated. Network testing by using traffic loads. Traffic loads are used starting from 20Mbps-100Mbps. The result is verified that the QoS analysis of the Software-Defined Network architecture performed better than conventional network architectures. The value of the latency delay on the Software Define Network range between 0,019-0,084ms, and with 0% packet loss when addressed the network traffics of 10-100Mbps.

Software Defined Network Detection System

The ongoing increase in the use of wireless Internet and smartphones has resulted in changing consumer patterns, which has changed the demand for network usage such that existing hardware-centric devices cannot satisfy this demand. One of the fastest growing technologies is software define network, which can solve this problem. An intrusion detection system is a system that detects and responds to network attacks in real time in a network environment based on software define network. The focus of this paper is to present a deep learning-based network detection system. We describe pre-processing for deep learning algorithms and propose an architecture of the detection system. The analysis results of the system are also described

DDoS Hazard and Precautionary Measures in Software Define Network

Software Defined Network is an emerging technology which is flourishing due to its diversity and by virtue of the fact that there are decoupled planes in this architecture which have some benefits as well as drawbacks, such as the execution of cyber attacks are easy at northbound and southbound interfaces and DDoS attack can easily be manipulated in this architecture. It has been identified that DDoS attack can be countered at northbound API so that appropriate decision about illegitimate traffic can be taken. Java has provided us with a very reliable support for three decades. Hence, all controls are governed by programming interfaces in this architecture with the help of this feature and according to the entropy of information which allows us to track the traffic and compare it with the threshold to identify the malware in the network. Floodlight controller is used in this paper to accommodate the illegitimate traffic. This paper allows the programmers to program such applications in Python or Java based on the basic mechanism of entropy which uses a threshold value from which DDoS attack can be countered, as we are well aware that a large number of systems are involved in producing illegitimate traffic on a network which creates distraction for the legitimate traffic.