Deep Reinforcement Learning-Based Traffic Sampling for Multiple Traffic Analyzers on Software-Defined Networks

Kim, Sunghwan; Yoon, Seunghyun; Lim, Hyuk

doi:10.1109/access.2021.3068459

Cited by 19 publications

(16 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [23,24] present a QoS optimization algorithm based on DDPG that ultimately improves the load-balancing degree and throughput rate to ensure delay and packet-loss rate. The authors in [25] propose an intelligent traffic-sampling system based on DDPG that can maintain the load balance of multiple traffic analyzers. The authors in [26] propose an intelligence-driven experiential network architecture for automatic routing (EARS) to optimize a network intelligently.…”

Section: Related Researchmentioning

confidence: 99%

“…Reinforcement learning opens a new way for solving complex network problems [15]. Some researchers have used traditional algorithms of reinforcement learning such as deep Q-learning network (DQN) [16][17][18][19], proximal policy optimization (PPO) [20], deep deterministic policy gradient (DDPG) [21][22][23][24][25][26][27][28], and twin delayed deep deterministic policy gradient (TD3) [29][30][31]. The DQN algorithm uses Q-tables to store value functions, but it leads to excessive memory overhead and sizeable computational complexity when the network size increases.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

Chen

Wang

Ou³

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Due to the rapid development of network communication technology and the significant increase in network terminal equipment, the application of new network architecture software-defined networking (SDN) combined with reinforcement learning in network traffic scheduling has become an important focus of research. Because of network traffic transmission variability and complexity, the traditional reinforcement-learning algorithms in SDN face problems such as slow convergence rates and unbalanced loads. The problems seriously affect network performance, resulting in network link congestion and the low efficiency of inter-stream bandwidth allocation. This paper proposes an automatic load-balancing architecture based on reinforcement learning (ALBRL) in SDN. In this architecture, we design a load-balancing optimization model in high-load traffic scenarios and adapt the improved Deep Deterministic Policy Gradient (DDPG) algorithm to find a near-optimal path between network hosts. The proposed ALBRL uses the sampling method of updating the experience pool with the SumTree structure to improve the random extraction strategy of the empirical-playback mechanism in DDPG. It extracts a more meaningful experience for network updating with greater probability, which can effectively improve the convergence rate. The experiment results show that the proposed ALBRL has a faster training speed than existing reinforcement-learning algorithms and significantly improves network throughput.

show abstract

Section: Related Researchmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

Chen

Wang

Ou³

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Kim et al proposed a DDPG-based traffic sampling algorithm on an SDN-capable network equipped with multiple traffic analyzers. They proposed system can learn a sampling resource allocation policy for multiple traffic analyzers by taking the inspection results of previously traffic flow samples as the reward of the learning system [16].…”

Section: A Traffic Inspectionmentioning

confidence: 99%

DIVERGENCE: Deep Reinforcement Learning-Based Adaptive Traffic Inspection and Moving Target Defense Countermeasure Framework

Kim

Yoon

Cho

et al. 2022

IEEE Trans. Netw. Serv. Manage.

Self Cite

View full text Add to dashboard Cite

Reinforcement learning (RL) is a promising approach for intelligent agents to protect a given system under highly hostile environments. RL allows the agent to adaptively make sequential defense decisions based on the perceived current state of system security aiming to achieve the maximum defense performance in terms of fast, efficient, and automated detection, threat analysis, and response to the threat. In this paper, we propose a deep reinforcement learning (DRL)-based adaptive traffic inspection and moving target defense countermeasure framework, called 'DIVERGENCE,' for building a secure networked system. The DIVERGENCE provides two main security services: (1) a DRL-based network traffic inspection mechanism to achieve scalable and intensive network traffic visibility for rapid threat detection; and (2) an address shufflingbased moving target defense (MTD) technique to defend against threats as a proactive intrusion prevention mechanism. Through extensive simulations and experiments, we demonstrate that the DIVERGENCE successfully caught malicious traffic flows while significantly reducing the vulnerability of the network through MTD.

show abstract

“…By configuring the sampling rate for each switch, Kim et al [184] propose a deep reinforcement learning-based traffic monitoring system in an SDN environment. They utilized a deep deterministic policy gradient-based method to manage MDPs with continuous action spaces to address intrusion utilizing realtime traffic analyzers and monitoring findings dynamically.…”

Section: Hybrid Models Based Ids In Sdnmentioning

confidence: 99%

“…Shallow ML [121], [122], [276], [127], [133], [139], [149], [170]- [172], [250] DL [195]- [197], [202], [216] RL [184] Sessionbased Shallow ML [148] DL [187] HBM Log-based Shallow ML [84], [88], [133], [171] DBM ABM…”

Section: Packetbasedmentioning

confidence: 99%

Intrusion Detection System in Software-Defined Networks Using Machine Learning and Deep Learning Techniques –A Comprehensive Survey

Rayhan¹,

Islam²,

Shatabda³

et al. 2022

Preprint

View full text Add to dashboard Cite

<div>At present, the Internet is facing numerous attacks of different kinds that put its data at risk. The safety of information within the network is, therefore, a significant concern. In order to prevent the loss of incredibly valuable information, the Intrusion Detection System (IDS) was developed to recognize the outbreak of a stream of attacks and notify the network system administrator providing network security. IDS is an extrapolative model used to detect network traffic as routine or attack. Software-Defined Networks (SDN) is a revolutionary paradigm that isolates the control plane from the data plane, transforming the concept of a software-driven network. Through this data and control plane separation, SDN provides us the opportunity to create a manageable and programmable network, allowing applications in the top plane to access physical devices via the controller. The controller functioning inside the control plane executes network modules and establishes flow rules to forward packets in the switches residing in the data plane. Cyber attackers target the SDN controller to subdue the control plane, which is considered the brain of the SDN, providing a plethora of functionalities such as regulating flow control to switches or routers in the data plane below via southbound Application Programming Interfaces (APIs) and business and application logic in the application plane above via northbound APIs to implement sophisticated networks. However, the control plane becomes a tempting prospect for security attacks from adversaries because of its centralization feature. This paper includes an in-depth overview of the notable published articles from 2015 to 2021 that used Machine Learning (ML) and Deep Learning (DL) techniques to construct an IDS solution to provide security for SDN. We also present two detailed taxonomic studies regarding IDS, and ML-DL techniques based on their learning categories, exploring various IDS solutions to secure the SDN paradigm. We have also conducted brief research on a few benchmark datasets used to construct IDS in the SDN paradigm. To conclude the survey, we provide a discussion that sheds light on continuous challenges and IDS issues for SDN security.</div>

show abstract

Deep Reinforcement Learning-Based Traffic Sampling for Multiple Traffic Analyzers on Software-Defined Networks

Cited by 19 publications

References 24 publications

ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

DIVERGENCE: Deep Reinforcement Learning-Based Adaptive Traffic Inspection and Moving Target Defense Countermeasure Framework

Intrusion Detection System in Software-Defined Networks Using Machine Learning and Deep Learning Techniques –A Comprehensive Survey

Contact Info

Product

Resources

About