Figure - available from: Transactions on Emerging Telecommunications Technologies
This content is subject to copyright. Terms and conditions apply.
Source publication
Data exchange between headquarters and local branches represents a major challenge issue for business success. For this issue, traditional solutions applied to wide area networks (WAN) remain unrealistic and require a good knowledge of the systems. Recently, software‐defined wide area networking (SD‐WAN) plays a pivotal role and constitutes, in gen...
Citations
... In [2], the authors explore machine learning techniques applied in SDN. The authors optimize delay and connectivity for SD-WAN environments using a multi-agent deep reinforcement learning algorithm. ...
... Similarly, [22], implemented an RL-based strategy to optimize data scheduling in MPTCP, but the proposal primarily focuses on improving throughput, leaving out the critical factors such as energy consumption and latency. Also, the work in the studies in [24,25], proposed a Deep Reinforcement Learning (DRL) based technique predominantly concentrating on single-agent scenarios. The ReLes scheme [26], was the first to apply Deep Reinforcement Learning (DRL) to solve the scheduling problem in multi-path TCP (MPTCP). ...
This paper proposes an energy-efficient scheduling scheme for multi-path TCP (MPTCP) in heterogeneous wireless networks, aiming to minimize energy consumption while ensuring low latency and high throughput. Each MPTCP sub-flow is controlled by an agent that cooperates with other agents using the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. This approach enables the agents to learn decentralized policies through centralized training and decentralized execution. The scheduling problem is modeled as a multi-agent decision-making task. The proposed energy-efficient scheduling scheme, referred to as EE-MADDPG, demonstrates significant energy savings while maintaining lower latency and higher throughput compared to other state-of-the-art scheduling techniques. By adopting a multi-agent deep reinforcement learning approach, the agents can learn efficient scheduling policies that optimize various performance metrics in heterogeneous wireless networks.
... This impacts the QoS of the network. To cater to this issue, authors in [8,9] presented deep reinforcement learning (DRL) in SD-WAN. They achieved optimization of load-balancing, minimizing the average request delay and increasing the survivability of the network. ...
... 2 [9] In this system, DRL with multi-agent Q-Network algorithm is applied in SD-WAN to minimize the average request delay and increase the network life. Improvement to these parameters results in better QoS of the network. ...
The internet of things (IoT) is a complex system that includes multiple technologies
and services. However, its heterogeneity can result in quality-of-service (QoS) issues, which may
lead to security challenges. Software-defined network (SDN) provides unique solutions to handle
heterogeneity issues in large-scale IoT networks. Combining SDN with IoT networks has great
potential for addressing extreme heterogeneity issues in IoT networks. Numerous researchers are
investigating various techniques to resolve heterogeneity issues in IoT networks by integrating
SDN. Our study focuses on the SDN-IoT domain to improve QoS by addressing heterogeneityHeterogeneity in SDN-IoT networks can increase the response time of controllers. We propose
a framework that can alleviate heterogeneity while maintaining QoS in SDN-IoT networks. The
framework converts m heterogeneous controllers into n homogeneous groups based on their response
time. First, we examine the impact of the controller’s bandwidth and find that the system throughput
decreases when the controller’s bandwidth is lowered. Next, we implement a simple strategy that
considers both the bandwidth and service time when selecting the peer controller. Our results
show some improvement in the framework, indicating its potential to alleviate heterogeneity while
maintaining QoS and other metrics.
Keywords: software-defined networks; internet of things; quality of service; security
... These features also promote novel security solutions, e.g., stateful firewalls [3], dynamic access control [4], and suspicious traffic redirection [5]. The dynamic reconfiguration and centralized management capabilities of SDN have also been applied to various scenarios, such as IoT [6], cloud, and WAN [7], in recent years. ...
Software-defined networking (SDN) enables dynamic management and flexible network control by employing reactive rule installation. Due to high power consumption and cost, current OpenFlow switches only support a limited number of flow rules, which is a major limitation for deploying massive fine-grained policies. This bottleneck can be exploited by attackers to launch saturation attacks to overflow the flow table. Moreover, flow table overflow can occur in the absence of malicious attackers. To cope with this, researchers have developed many proposals to relieve the load under benign conditions. Among them, the dynamic timeout mechanism is one of the most effective solutions. We notice that when the SDN controller adopts dynamic timeouts, existing flow table saturation attacks can fail, or even expose the attackers, due to inaccurate inferring results. In this paper, we extract the common features of dynamic timeout strategies and propose an advanced flow table saturation attack. We explore the definition of flow rule lifetime and use a timing-based side-channel to infer the timeout of flow rules. Moreover, we leverage the dynamic timeout mechanisms to proactively interfere with the decision of timeout values and perform an attack. We conduct extensive experiments in various settings to demonstrate its effectiveness. We also notice that some replacement strategies work differently when the controller assigns dynamic timeouts. The experiment results show that the attack can incur significant network performance degradation and carry out the attack in a stealthy manner.
As the complexity of the network structure increases, so do the requirements for the network architecture are also increasing, and Software Defined Network (SDN) technology has emerged. SDN technology has successfully simplified network management, but its open programming nature poses a risk of network attacks. In complex network environments, the recognition accuracy of traditional recognition models cannot meet the requirements of accuracy and speed. In view of this, this study proposes an attack recognition model based on Convolutional Neural Network (CNN), aiming to solve the attack recognition problems faced in SDN environments, improve the accuracy of the model, and ensure the security of SDN. The study used the NSL-KDD dataset and the MIT LL DARPA dataset. In the performance testing experiment of the model, the results show that the proposed model has an accuracy of 98.25% in SDN attack recognition, and its performance is significantly better than traditional CNN models. The accuracy of traditional attack recognition reaches 98.25%, and its performance is superior to the KNN-PSO model. Verifying its superiority and further confirming its application value in SDN attack identification.
