Performance comparison of state synchronization techniques in a distributed LTE EPC

Satapathy, Pratik; Dave, Jash; Naik, Priyanka; Vutukuru, Mythili

doi:10.1109/nfv-sdn.2017.8169832

Cited by 9 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Satapathy et al 16 propose a network state management system that introduces two different solutions to ensure state synchronization. In the first solution, an instance synchronizes the state at the receipt of each single packet, whereas in the second solution, the state is synchronized after receiving multiple packets.…”

Section: Related Workmentioning

confidence: 99%

“…15 Several studies have recently focused on the state synchronization challenge. For instance, Khalid and Akella 11 and Satapathy et al 16 suggested to set up a common repository storing and managing state shared among instances. Ma et al 17 and Peng et al 18 have considered a different technique where each instance broadcasts its state to the other instances.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards optimal synchronization in NFV‐based environments

et al. 2022

View full text Add to dashboard Cite

Network Function Virtualization (NFV) is known for its ability to reduce deployment costs and improve the flexibility and scalability of network functions. Due to processing capacity limitations, the infrastructure provider may need to instantiate multiple instances of the same network function. However, most of network functions are stateful, meaning that the instances of the same function need to keep a common state and hence the need for synchronization among them. In this paper, we address this problem with the goal of identifying the optimal synchronization pattern between the instances in order to minimize the synchronization costs and delay. We propose a novel network function named Synchronization Function able to carry out data collection and further minimize these costs. We first mathematically model this problem as an integer linear program that finds the optimal synchronization pattern and the optimal placement and number of synchronization functions that minimize synchronization costs and ensure a bounded synchronization delay. We also put forward three greedy algorithms to cope with large-scale scenarios of the problem, and we explore the possibility to migrate network function instances to further reduce costs. Extensive simulations show that the proposed algorithms efficiently find near-optimal solutions with minimal computation time and provide better results compared to existing solutions.

show abstract

Section: Related Workmentioning

confidence: 99%