Due to the development of the Internet and the smart end systems such as smartphones, portable laptop, and other smart mobile devices, as well as the emergence of concepts such as cloud computing, social networks, and Internet of Things, 4G and 5G have changed network requirements. A software-defined network (SDN) is a new architecture to support new network requirements. This architecture is composed of three layers, data, control, and application plane. A lot of papers have been published in well-known journals to improve network performance, so we classify the solutions for performance improvement based on three SDN layers and three SDN-based spheres which are (a) SDN-data center, (b) wireless networks, and (c) software-defined wide area network. This paper surveys the articles which have been published by Springer, IEEE, Elsevier, and ACM. We extract the performance improvement solutions and resources which are required for performance control and the metrics to evaluate the network performance. This article can help network enthusiasts to better understand, investigate, and improve the performance of SDN-based networks.

Performance issues and solutions in SDN-based data center: a survey

Software defined network (SDN) is a promising new network abstraction that aims to improve and facilitate network management. Due to its centralized architecture and the lack of intelligence on the data plane, SDN suffers from many security issues that slows down its deployment. Man in the Middle (MitM) attack is considered as one of the most devastating attacks in an SDN context. In fact, MitM attack allows the attackers to capture, duplicate and spoof flows by targeting southbound interfaces and SDN nodes. Furthermore, it’s very difficult to detect MitM attacks since it is performed passively at the SDN level. To reduce the impact of this attack, we generally set up security policies and authentication mechanisms. However, these techniques are not applicable for a large scale SDN architecture as they require complexes and static configurations and as they negatively influence on network performance. In this paper, we propose an intrusion detection and prevention framework by using machine learning techniques to detect and stop MitM attempts. To do so, we build a context-based node acceptance based on the random forest model (CBNA-RF), which helps to setting-up appropriate security policies and to automating defense operations on a large-scale SDN context. This mechanism can realize a quick and early detection of MitM attacks by automatically detecting malicious nodes without affecting performances. The evaluation of the proposed framework demonstrates that our model can correctly classify and detect malicious connections and nodes while keeping high accuracy and precision scores.

MitM detection and defense mechanism CBNA-RF based on machine learning for large-scale SDN context

Using a massive number of coordinated and distributed machines, botnets have become one of the most sophisticated cyber threats. However, software defined networking leads to more effective mitigation approaches by providing a flexible and dynamic way to control the network. Existing botnet detection approaches fail to detect unknown botnet threats and are time consuming. Facing these shortcomings motivates us to employ honeypots as a competent solution. We propose a novel blocking approach that uses honeypots to detect and efficiently prevent botnet propagation in software defined networks. This approach identifies the relationship among botnet members and intelligently blocks them. We also design and implement a deception system based on our blocking approach with two goals: reducing the botnet infection rate and wasting the adversary’s time. Experimental results, which are based on a real malware, show that our proposed system compared with current blocking approaches can reduce the infection rate up to 25% and increase the adversary’s wasted time by a factor of four. Our system also provides a satisfactory detection performance.

An intelligent botnet blocking approach in software defined networks using honeypots

The breakdown of vital communication infrastructures is one of the most common characteristics of all disasters. It can cause severe communication problems such as time delays and data loss, which cause deterioration in system performance. New techniques are needed to cope with such situations, many of which have been made possible due to the ongoing evolution of artificial intelligence technologies. In this study, we consider the case of a network consisting of several router allocation problems in situations of high priority and emergency data allocation. A novel network component called the scheduler is introduced and window constraints for routers are imposed. To solve the studied problem, four different algorithms are developed in this work. These algorithms were then applied in a particular scenario consisting of several routers and 2200 instances. In terms of the gap and running time, the proposed algorithms provide acceptable results. The best performances were achieved using the critical packet algorithm for 80% of instances with an average gap value of 0.009 and an average time of 0.209 s. 

A Novel Model Based on Window-Pass Preferences for Data Emergency Aware Scheduling in Computer Networks

Software-Defined Networks (SDN) is a promising network technology that delivers the programable networks by separating control and data plane from the traditional architecture. The key issue in the SDN is to identify the number of controllers needed and its optimal location in the network. There are three major objectives of this paper. The primary objective is identifying the number of controllers needed. To identify it, a graph theory approach is adapted. The second objective is to identify optimal location of controllers in the network and what are all the nodes to be connected to the controller to enhance the performance of the network. For that, Pareto Integrated Tabu Search (PITS) algorithm is proposed. The final objective is to perform controller migration to handle dynamic situations like link failure and imbalance load of controller. A heuristic approach is proposed to perform migration. Real time topologies from Internet Topology Zoo are considered for experiment and the experimental results shows that the proposed methodology outperforms well in all situations considered for experiment.

Enhanced optimal placements of multi-controllers in SDN

In Software defined networking (SDN) based datacenters, flow-level management seriously limits system scalability due to large amount of control messages between data and control planes; and mice flows often are blocked by elephant flows because of the indiscriminate flow scheduling. To improve management efficiency and system performance, it is prerequisite to schedule elephant and mice flows respectively. Unfortunately, existing flow scheduling approaches in SDN consider only elephant flows. In this paper, we firstly propose an efficient flow detection mechanism. Then, we propose a novel DIFFERENtiated sChEduling (DIFFERENCE) approach that dynamically sets up paths for elephant and mice flows separately, based on current link workload. Our DIFFERENCE schedules mice flows with proactively installed weighted multipath routing algorithm and adjusts path weight according to link utilization. Instead, we propose a blocking island based path setup algorithm for elephant flows, which find the least congested path with shorter searching space. To balance traffic in a SDN networks, we design an algorithm to dynamically reschedule data flows in terms of current link utilization ratio. Experiment results on real public datacenter traces demonstrate that our approach outperforms related proposals in terms of various system performance.

Heteng Zhang

Papers

Efficient flow detection and scheduling for SDN-based big data centers