scholarly journals A 3-CS Distributed Federated Transfer Learning Framework for Intelligent Edge Optical Networks

2021 ◽  
Vol 2 ◽  
Author(s):  
Hui Yang ◽  
Qiuyan Yao ◽  
Bowen Bao ◽  
Chao Li ◽  
Danshi Wang ◽  
...  
Keyword(s):  
Optical Networks ◽  
Transfer Learning ◽  
Network Performance ◽  
Rapid Development ◽  
Optical Network ◽  
Operation Efficiency ◽  
Cross Spectrum ◽  
Distributed Intelligence ◽  
Learning Framework ◽  
Intelligent Approach

With the rapid development of optical network and edge computing, the operation efficiency of the edge optical network has become more and more important, requiring an intelligent approach to enhance the network performance. To enhance the intelligence of the edge optical network, this article firstly provides the demand for the development of edge optical networks. Then, a cross-scene, cross-spectrum, and cross-service (3-CS) architecture for edge optical networks is presented. Finally, a federated transfer learning (FTL) framework, realizing a distributed intelligence edge optical network, is proposed. The usability of the proposed framework is verified by simulation.

Research on CLIB Routing and Spectrum Allocation Algorithm in Elastic Optical Networks

2019 ◽  
Vol 0 (0) ◽  
Author(s):  
Li Li ◽  
Zhai Ya-Fang ◽  
Li Hong-Jie
Keyword(s):  
Optical Networks ◽  
Blocking Probability ◽  
Rapid Development ◽  
Optical Network ◽  
Spectrum Allocation ◽  
Mobile Internet ◽  
High Definition ◽  
Allocation Algorithm ◽  
High Bandwidth ◽  
Routing And Spectrum Allocation

AbstractWith the rapid development of mobile Internet, high-definition video and cloud computing, users’ bandwidth demands are not only larger and larger but also more and more diverse. To solve this problem, there searchers put forward the concept of elastic optical network (EON). EON adopts the transmission mode of elastic grid, which can allocate spectrum resources flexibly and meet high bandwidth and diversity requirements at the same time. Routing and spectrum allocation (RSA) is an important issue in EON. In this paper, we present a heuristic algorithm named constrained-lower-indexed-block (CLIB) allocation algorithm for the RSA problem. The algorithm is based on the K candidate paths. When there are available spectrum blocks on multiple candidate paths, if the increase of the path length does not exceed a given threshold, the lower index spectrum would be selected for the connection request on a longer path. The aim of the algorithm is to concentrate the occupied frequency slices on one side of the spectrum and leave another side of the spectrum to the later arrived connection requests as much as possible, to reduce the blocking probability of connection requests. Simulation results show that comparing with the first-last-fit and hybrid grouping algorithms, the CLIB algorithm can reduce the blocking probability of connection requests.

scholarly journals Optimization of Optical Networks Based on CDC-ROADM Technology

2019 ◽  
Vol 9 (3) ◽  
pp. 399 ◽  
Author(s):  
Stanisław Kozdrowski ◽  
Mateusz Żotkiewicz ◽  
Sławomir Sujecki
Keyword(s):  
Optical Networks ◽  
Network Performance ◽  
Optical Network ◽  
Network Services ◽  
Traffic Demand ◽  
Wavelength Division ◽  
Wavelength Division Multiplexed ◽  
Different Dimensions ◽  
New Generation ◽  
The Impact

New generation of optical nodes in dense wavelength division multiplexed networks enables operators to improve service flexibility and make significant savings, both in operational and capital expenditures. Thus the main objective of the study is to minimize optical node resources, such as transponders, multiplexers and wavelength selective switches, needed to provide and maintain high quality dense wavelength division multiplexed network services using new generation of optical nodes. A model based on integer programming is proposed, which includes a detailed description of an optical network node. The impact on the network performance of conventional reconfigurable optical add drop multiplexer technology is compared with colorless, directionless and contentionless approaches. The main focus of the presented study is the analysis of the network congestion problem arising in the context of both reconfigurable optical add drop multiplexer technologies. The analysis is supported by results of numerical experiments carried out for realistic networks of different dimensions and traffic demand sets.

WDM Node Structure with GMPLS Technology in Optical Transport Networks

2011 ◽  
Vol 474-476 ◽  
pp. 1483-1486
Author(s):  
Ning Zhang ◽  
Mao Chang Ge
Keyword(s):  
Complex Networks ◽  
Optical Networks ◽  
Rapid Development ◽  
Optical Network ◽  
Transmission Network ◽  
Network Technology ◽  
Transport Networks ◽  
Label Switching ◽  
Optical Transport Networks ◽  
Multi Protocol Label Switching

With the rapid development of optical network technology, a thing worth noting is the generalized multi-protocol label switching (GMPLS) technology in optical network has been more used, mainly in auto-switching transmission network. GMPLS is an advanced protocol which is essential for managing a diverse and complex networks, GMPLS has caused technical challenges in its deployment in optical networks. In this paper, we analyze the evolution to optical network, and discuss the GMPLS technology and its applications. GMPLS will become the important protocol in future optical network.

scholarly journals Statistical Assessment of Open Optical Networks

Photonics ◽  
2019 ◽  
Vol 6 (2) ◽  
pp. 64 ◽  
Author(s):  
Emanuele Virgillito ◽  
Alessio Ferrari ◽  
Andrea D’Amico ◽  
Vittorio Curri
Keyword(s):  
Optical Networks ◽  
Network Performance ◽  
Blocking Probability ◽  
Optical Network ◽  
Network Capacity ◽  
Physical Layer ◽  
Point Of View ◽  
Assessment Process ◽  
Physical Parameters ◽  
High Level

In order to cope with the increase of the final user traffic, operators and vendors are pushing towards physical layer aware networking as a way to maximize the network capacity. To this aim, optical networks are becoming more and more open by exposing physical parameters enabling fast and reliable estimation of the lightpath quality of transmission. This comes in handy not only from the point of view of the planning and managing of the optical paths but also on a more general picture of the whole optical network performance. In this work, the Statistical Network Assessment Process (SNAP) is presented. SNAP is an algorithm allowing for estimating different network metrics such as blocking probability or link saturation, by generating traffic requests on a graph abstraction of the physical layer. Being aware of the physical layer parameters and transceiver technologies enables assessing their impact on high level network figures of merit. Together with a detailed description of the algorithm, we present a comprehensive review of several results on the networking impact of multirate transceivers, flex-grid spectral allocation as a means to finely exploit lightpath capacity and of different Space Division Multiplexing (SDM) solutions.

Performance Evaluation of Optical Networks Using Advanced Modulation Format

2018 ◽  
Vol 37 ◽  
pp. 72-77
Author(s):  
Simbarashe Magidi
Keyword(s):  
Performance Evaluation ◽  
Optical Networks ◽  
Network Performance ◽  
Optical Network ◽  
Passive Optical Network ◽  
Maximum Distance ◽  
Q Factor ◽  
Modulation Format ◽  
Triple Play ◽  
Eye Opening

In this paper, we have evaluated the performance of DPSK advanced modulation format in a bidirectional passive optical network for a triple play scenario at a constant symmetrical data rate of 10 Gbps. Data, voice and video signal has been successfully transmitted to a maximum of 128 users for a maximum distance of 100 km. Network performance was measured in terms of the Q factor, BER and eye opening, as a function of the number of users and distance of reach.

Neurofuzzy and Biogeography-Based Optimization of Bandwidth Granularity for PON Based on Optical Path Fragmentation

2018 ◽  
Vol 0 (0) ◽  
Author(s):  
Ashok Kumar ◽  
V. K. Banga ◽  
Amit Wason
Keyword(s):  
Optical Networks ◽  
Bandwidth Allocation ◽  
Orthogonal Frequency Division Multiplexing ◽  
Network Performance ◽  
Fitness Function ◽  
Optical Network ◽  
Passive Optical Network ◽  
Minimum Bandwidth ◽  
And Control

AbstractPassive optical network (PON) supported orthogonal frequency division multiplexing is a network that is designed for subsequent generation of optical networks. During this work, the proposed algorithm consists of neurofuzzy rules which update and control the minimum bandwidth allocation granularity \left( g \right). In order to improve the quality of service, a biogeography-based optimization algorithm is introduced and a new fitness function is proposed which reduces the round trip time by enhancing the distribution scaling factor. Hence, the proposed work reduces the jitter and increases the throughput of the PON for fixed g = 1 which enhances the network performance by 3.4 % and 1.23 %, respectively.

scholarly journals A Research on Routing and Spectrum Allocation Algorithm for Elastic Optical Networks Based on Deep Learning

2021 ◽  
Vol 2 (3) ◽  
pp. 24-26
Author(s):  
Lina Cheng
Keyword(s):  
Deep Learning ◽  
Optical Networks ◽  
Network Performance ◽  
Blocking Probability ◽  
Optical Network ◽  
Spectrum Allocation ◽  
Dynamic Allocation ◽  
Allocation Algorithm ◽  
The Neural Network ◽  
Routing And Spectrum Allocation

Dynamic allocation request and spectrum release will lead to spectrum fragmentation, which will affect the allocation of subsequent services and spectrum resource utilization of elastic optical network. This paper proposes a new routing and spectrum allocation algorithm based on deep learning, which will find the best routing and spectrum allocation method for a specific network, so as to improve the overall network performance. Simulation results show that compared with the traditional resource allocation strategy, the neural network model used in this paper can improve the degree of spectrum fragmentation and reduce the network blocking probability.

Minimization Number of Network-Coded Links Based on Improved Adaptive Genetic Algorithm for Multi-source Optical Networks

2019 ◽  
Vol 40 (3) ◽  
pp. 205-212
Author(s):  
Xiaojin Guo ◽  
Liying Sang ◽  
Huanlin Liu
Keyword(s):  
Genetic Algorithm ◽  
Network Coding ◽  
Optical Networks ◽  
Wavelength Division Multiplexing ◽  
Rapid Development ◽  
Optical Network ◽  
Stable Condition ◽  
Adaptive Genetic Algorithm ◽  
Bandwidth Utilization ◽  
Optical Multicast

Abstract With the rapid development of multi-source optical multicast application, the wavelength division multiplexing (WDM) with limited number of wavelength channels is facing with the new challenge of bandwidth shortage. Optical multicast adopting network coding can improve the bandwidth utilization, but optical network coding needs to increase optical storage and computation overhead in WDM optical network. For reducing the number of optical network-coded links, an improved adaptive genetic algorithm (IAGA) is proposed to minimize the number of network-coded links for multicast. By designing the maximization difference crossover operation, IAGA can guarantee the diversity of population and avoid individuals from falling into a local optimal. By adaptively adjusting the crossover probability, IAGA makes the population diverse at the beginning stages and makes the excellent individuals remain in a stable condition. Compared with other algorithms, the simulation result shows that the proposed algorithm has fastest convergence speed, which means that it takes the shortest time to find the minimum numbers of coded link solutions.

Performance Modeling and Analysis of WDM Optical Networks under Wavelength Continuity Constraint using MILP

2020 ◽  
Vol 13 (2) ◽  
pp. 203-211 ◽  
Author(s):  
Swati Bhalaik ◽  
Ashutosh Sharma ◽  
Rajiv Kumar ◽  
Neeru Sharma
Keyword(s):  
Network Design ◽  
Optical Networks ◽  
Wavelength Division Multiplexing ◽  
Optical Network ◽  
Optimal Path ◽  
Topology Design ◽  
Mixed Integer ◽  
Wdm Optical Networks ◽  
Virtual Topology ◽  
Wdm Network

Objective: Optical networks exploit the Wavelength Division Multiplexing (WDM) to meet the ever-growing bandwidth demands of upcoming communication applications. This is achieved by dividing the enormous transmission bandwidth of fiber into smaller communication channels. The major problem with WDM network design is to find an optimal path between two end users and allocate an available wavelength to the chosen path for the successful data transmission. Methods: This communication over a WDM network is carried out through lightpaths. The merging of all these lightpaths in an optical network generates a virtual topology which is suitable for the optimal network design to meet the increasing traffic demands. But, this virtual topology design is an NP-hard problem. This paper aims to explore Mixed Integer Linear Programming (MILP) framework to solve this design issue. Results: The comparative results of the proposed and existing mathematical models show that the proposed algorithm outperforms with the various performance parameters. Conclusion: Finally, it is concluded that network congestion is reduced marginally in the overall performance of the network.

Sign in / Sign up

Export Citation Format

Share Document