Design of intelligent traffic load balancing (ITLB) mechanism for software defined data center (SDDC)

Balakiruthiga, B.; Deepalakshmi, P.

doi:10.21203/rs.3.rs-2407623/v1

Cited by 2 publications

(2 citation statements)

References 22 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms stand out for their ability to discern patterns and anomalies in network traffic, allowing for predictive modeling that is several strides ahead of reactive traditional measures [26]. This proactive stance is especially crucial in contemporary digital environments, which are characterized by their dynamic and often volatile data traffic.…”

Section: Machine Learning For Network Managementmentioning

confidence: 99%

Load Balancing in DCN Servers Through Software Defined Network Machine Learning

Beissenova,

Zhidebayeva,

Kopzhassarova

et al. 2024

IJACSA

View full text Add to dashboard Cite

In this research paper, we delve into the innovative realm of optimizing load balancing in Data Center Networks (DCNs) by leveraging the capabilities of Software-Defined Networking (SDN) and machine learning algorithms. Traditional DCN architectures face significant challenges in handling unpredictable traffic patterns, leading to bottlenecks, network congestion, and suboptimal utilization of resources. Our study proposes a novel framework that integrates the flexibility and programmability of SDN with the predictive and analytical prowess of machine learning. We employed a multi-layered methodology, initially constructing a virtualized environment to simulate real-world DCN traffic scenarios, followed by the implementation of SDN controllers to instill adaptiveness and programmability. Subsequently, we integrated machine learning models, training them on a substantial dataset encompassing diverse traffic patterns and network conditions. The crux of our approach was the application of these trained models to anticipate network congestion and dynamically adjust traffic flows, ensuring efficient load distribution among servers. A comparative analysis was conducted against prevailing load balancing methods, revealing our model's superiority in terms of latency reduction, enhanced throughput, and improved resource allocation. Furthermore, our research illuminates the potential for machine learning's self-learning mechanism to foresee and adapt to future network states or exigencies, marking a significant advancement from reactive to proactive network management. This convergence of SDN and machine learning, as demonstrated, ushers in a new era of intelligent, scalable, and highly reliable DCNs, demanding further exploration and investment for future-ready data centers.

show abstract

Section: Machine Learning For Network Managementmentioning

confidence: 99%

Load Balancing in DCN Servers Through Software Defined Network Machine Learning

Beissenova,

Zhidebayeva,

Kopzhassarova

et al. 2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Almadani et al [23] proposed the distributed SDN control plane framework (DSF)-a framework for the East/West interface for heterogeneous, distributed SDN controllers that used a standard-ized data-centric real-time publish/subscribe paradigm (called Data Distribution Service (DDS)) to synchronize topologies. [24] presented a complete software model of a software-defined data center (SDDC) that provided three different functions such as controller location, routing, and load balancing through different RL-agents in the SDDC.…”

Section: Related Workmentioning

confidence: 99%

DIT: A Dynamic Bandwidth Isolated Transmission System for Large-Scale Inter-DC Wireless Communication Network

Zhang

Wang

et al. 2023

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Large companies are increasingly providing their services over interdomain data centers. Such large-scale wireless communication networks carry various applications, including both online time-sensitive services and offline bandwidth-sensitive services. These applications share the same physical links but have different bandwidth requirements at different time, making the coscheduling problem a key challenge in improving the overall network utility. Most existing commercial systems reserve peak value bandwidth for online time-sensitive services to ensure the quality of service and use the leftover bandwidth to transmit offline data in a best-effort manner. Such systems cannot obtain high link utilizations because of the nonstationarity of online traffic. To solve this problem, we present a dynamic isolated transmission (DIT) system in this paper, where a sliding- k algorithm is designed to predict online traffic, and a bottleneck bypass routing scheme is proposed to schedule the mixed traffic in a shared inter-DC wireless communication network. We conduct a series of experiments in an experimental inter-DC wireless communication network to analyze for efficient network operation of the DIT and compare its performance with typical existing fix-bandwidth-based solutions including Microsoft’s SWAN. The results show that DIT outperforms existing solutions, improving the interdomain link utilization by 18% and the intradomain link utilization by 65%.

show abstract

Design of intelligent traffic load balancing (ITLB) mechanism for software defined data center (SDDC)

Cited by 2 publications

References 22 publications

Load Balancing in DCN Servers Through Software Defined Network Machine Learning

Load Balancing in DCN Servers Through Software Defined Network Machine Learning

DIT: A Dynamic Bandwidth Isolated Transmission System for Large-Scale Inter-DC Wireless Communication Network

Contact Info

Product

Resources

About