检索结果-内蒙古大学图书馆

routing and spectrum assignment employing long short-term memory technique for elastic optical networks

OPTICAL SWITCHING AND NETWORKING 2022年第0期45卷

作者： Cheng, Lina Qiu, Yang Southwest Minzu Univ Coll Elect & Informat State Ethn Affairs Commiss Key Lab Elect & Informat Engn Chengdu Peoples R China

With the prevalence of some high bandwidth-demanding applications, such as cloud computing, traditional wavelength-division-multiplexing passive optical networks have difficulties in satisfying such growing bandwidth demands due to its limited allocation-flexibility and utilization-efficiency. Therefore, elastic optical networks (EONs). In order to realize the flexibility in EONs, sophisticated routing and spectrum allocation (RSA) algorithms areone of the keyenabling technologies. However, most of the previous RSA algorithms were proposed with invariant routing and spectrum allocation strategies, which ignored considering the time-varying characteristics of EONs due to the variable network architecture and service provisioning. And such timevarying characteristics can deteriorate the spectrum fragmentation and the service blocking performances of EONs, which stimulates the application of various machine-learning technologies in EONs. In this paper, a long short-term memory based routing and spectrum assignment (LSTM-RSA) algorithm is proposed for EONs. By employing the long short-term memory technique to sense the complex status of EONs (e.g. spectral usage on the selected paths), the proposed LSTM-RSA algorithm gradually learns successful strategies through accumulating operation experience in the process of interaction and obtains higher returns through enhanced operation, which helps improve the spectrum fragmentation and the service blocking performances in EONs. Simulation results show that the spectrum fragmentation rate and the blocking rate of the proposed LSTM-RSA algorithm are reduced by about 6% and 8.9%, respectively, when compared to the traditional shortest-path-routing first-fitting RSA algorithm.

关键词： routing and spectrum assignment Long short-term memory Elastic optical networks

来源：评论

学校读者我要写书评

暂无评论

routing and spectrum assignment Based on Reinforcement Learning in Multi-Band Optical Networks

Routing and Spectrum Assignment Based on Reinforcement Learn...

引用

International Conference on Photonics in Switching and Computing (PSC)

作者： Ben Terki, Abdennour Pedro, Joao Eira, Antonio Napoli, Antonio Sambo, Nicola Scuola Super Sant Anna Pisa Italy IST Inst Telecomunicacoes Infinera Unipessoal Lda Lisbon Portugal Infinera Unipessoal Lda Carnaxide Portugal Infinera Munich Germany

A routing and spectrum assignment strategy based on Reinforcement Learning (RL-RSA) is proposed for multi-band optical networks. RL-RSA accounts for Stimulated Raman Scattering using the Generalized Gaussian Noise mod... 详细信息

ISBN: (纸本)9798350323702

关键词： routing and spectrum assignment Reinforcement Learning Multi-band Optical networks

来源：评论

学校读者我要写书评

暂无评论

routing and spectrum assignment in Spatial Channel Network-Based Inter-Datacenter Networks

Routing and Spectrum Assignment in Spatial Channel Network-B...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Zheng, Weichang Zheng, Yu Yang, Mingcong Yang, Kun School of Information and Communication Engineering Yangtze Delta Region Institute University of Electronic Science and Technology of China Quzhou China Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Japan Huawei Technologies Department of R&d Wuhan China School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan China

We introduce spatial channel networks (SCNs) to the interconnection of data center networks (DCNs). We propose an integer linear programming (ILP) model to solve the routing and spectrum assignment problem for SCN-bas... 详细信息

ISBN: (纸本)9798350312614

关键词： datacenter network (DCN) integer linear programming (ILP) routing and spectrum assignment Spatial channel network (SCN)

来源：评论

学校读者我要写书评

暂无评论

PtrNet-RSA: A Pointer Network-Based QoT-Aware routing and spectrum assignment Scheme in Elastic Optical Networks

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2024年第17期42卷 5808-5819页

作者： Cheng, Yuansen Ding, Shifeng Shao, Yingjie Chan, Calvin Chun-Kit Chinese Univ Hong Kong Dept Informat Engn Hong Kong Peoples R China Fraunhofer UK Res Ltd Ctr Appl Photon Glasgow G11RD Scotland

To enable flexible service provisioning in elastic optical networks (EONs), quality of transmission (QoT) estimation and dynamic routing and spectrum assignment (RSA) are critical network management tasks. Recently, machine learning approaches have been extensively investigated to address these tasks individually. We propose to take an integrative approach to design a Pointer Network (PtrNet)-based QoT-aware RSA (PtrNet-RSA) scheme to optimize the blocking probability and the generalized signal-to-noise ratio (GSNR) for the lightpath allocation in EONs. Given the profiles of the physical network and the service requests, the proposed scheme can generate high-GSNR lightpaths without pre-calculated candidate paths. Reinforcement learning is employed to train the model while the parameters of the PtrNets are optimized by utilizing the actor-critic algorithm. Extensive simulations have been conducted in EON environments based on the Gaussian Noise (GN) model with dynamic traffic. The results show that the proposed PtrNet-RSA scheme consistently outperforms the benchmarks with various network topologies, significantly reducing the blocking probability while guaranteeing a good lightpath QoT.

关键词： Elastic optical networks pointer network quality of transmission reinforcement learning routing and spectrum assignment Elastic optical networks pointer network quality of transmission reinforcement learning routing and spectrum assignment

来源：评论

学校读者我要写书评

暂无评论

Congestion aware ant colony optimisation algorithm for routing and spectrum assignment in flexi-grid optical burst switching networks

引用

PHOTONIC NETWORK COMMUNICATIONS 2023年第2期45卷 67-78页

作者： Oladipo, Joshua du Plessis, Mathys C. Gibbon, Tim Nelson Mandela Univ Dept Comp Sci POB 77000 ZA-6001 Port Elizabeth South Africa Nelson Mandela Univ Ctr Broadband Commun Port Elizabeth South Africa

This paper presents an improved distributed ant colony optimisation algorithm for routing and spectrum assignment (RSA) on optical burst switched (OBS), flexible spectrum networks, with the spectrum continuity constraint imposed. The improved algorithm incorporates a distributed method for monitoring the congestion along the links and using this information to determine what route-spectrum combination should be selected to minimise the burst loss probability (BLP). Evaluations were performed on an optical burst switching simulator to determine the effect on BLP when a dynamic route congestion measure is considered as opposed to the use of the static route length measure. The evaluations, considering the effects of optical impairments, were made on different network topologies, with multiple spectrum widths provisioned on the network, and with different loads. The incorporation of congestion measures into the algorithm showed improvements in BLP over previous work in the range of 2-32% depending on the evaluation conditions.

关键词： Flex-spectrum Optical burst switching Ant colony optimisation routing and spectrum assignment

来源：评论

学校读者我要写书评

暂无评论

Experimental Validation of an Efficient DRL-based routing and spectrum assignment for Optical Network Automation 24

Experimental Validation of an Efficient DRL-based Routing an...

引用

24th International Conference on Transparent Optical Networks (ICTON)

作者： Hernandez-Chulde, Carlos Casellas, Ramon Martinez, Ricardo Vilalta, Ricard Munoz, Raul Ctr Tecnol Telecomunicac Catalunya CTTC CERCA Barcelona 08860 Spain

ISBN: (纸本)9798350377330;9798350377323

This work explores the application of Deep Reinforcement Learning (DRL) for routing and spectrum assignment (RSA) in Elastic Optical Networks (EONs). By capitalizing on the inherent capabilities of DRL to manage complex and dynamic service demands and network conditions, this demo showcases the seamless integration of a DRL approach with an enhanced Software-Defined Networking (SDN) control plane for enabling more intelligent, flexible, and efficient optical network management. We validate this integration by utilizing CTTC's ADRENALINE testbed (R), where a trained DRL agent assisting on the path and resource selection function is effectively interfaced with a full-fledge SDN control plane implementation. This validation confirms both the practical applicability of the DRL approach on supporting selected control functions, and industry-standard interfaces in operational EON infrastructures, while also highlighting the potential for future innovations in optical network automation.

关键词： routing and spectrum assignment Elastic Optical Networks Deep Reinforcement Learning Software Defined Networking

来源：评论

学校读者我要写书评

暂无评论

Dynamic routing and spectrum assignment Based on the Consecutive Sub-Channels in Flexible-Grid Optical Networks

引用

IEEE ACCESS 2022年 10卷 128354-128365页

作者： Lohani, Varsha Sharma, Anjali Singh, Yatindra Nath Indian Inst Technol Kanpur Dept Elect Engn Kanpur India

Variable bandwidth channels can be created in Flexible Grid Optical Networks using Optical Orthogonal Frequency Division Multiplexing (O-OFDM). This allows more efficient spectrum use by allocating integral multiple of basic bandwidth slots (sub-channels) to the lightpath requests. In these networks, the constraint of keeping all the allocated slots together is added when deciding routes for the requests. This makes the routing and spectrum assignment (RSA) algorithms in Flexible Grid Optical Networks more challenging. In any network, the lightpath requests will arrive and depart dynamically, leading to spectrum fragmentation. It leads to a reduction of maximum possible utilization as well as an increase in blocking probability. In this paper, we have presented an improvised RSA algorithm using consecutive spectrum slots as an adaptive parameter, that leads to reduced fragmentation. It is evident from the results that the presented RSA algorithm using adaptive parameters reduces the blocking probability and fragmentation more effectively than the shortest path and k-shortest path algorithms reported in the earlier works.

关键词： routing Optical fiber networks Bandwidth Heuristic algorithms Optical fibers Spread spectrum management Resource management Flexible-grid optical networks routing and spectrum assignment dynamic algorithms fragmentation blocking probability spectrum utilization

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based routing and spectrum assignment of EONs by Exploiting GCN and RNN for Feature Extraction

引用

JOURNAL OF LIGHTWAVE TECHNOLOGY 2022年第15期40卷 4945-4955页

作者： Xu, Liufei Huang, Yue-Cai Xue, Yun Hu, Xiaohui South China Normal Univ Sch Phys & Telecommun Engn Guangzhou 510006 Peoples R China South China Normal Univ Sch Elect & Informat Engn Foshan 528200 Peoples R China

Deep reinforcement learning (DRL) has been introduced to the routing and spectrum assignment (RSA) of elastic optical networks (EONs) where the RSA policies are learnt during the interaction of a DRL agent with the EON environment. Upon each new traffic arrival, the DRL agent senses the EON state, and makes the RSA decision accordingly. Therefore, the EON state feature extraction is essential for the performance. However, current approaches, mainly based on fully connected neural networks or convolutional neural networks, are unsatisfactory in EON state feature extraction due to the following two reasons. (1) The optical network topology information is not well considered. (2) The path-level features are highly related to the RSA decision, due to the spectrum continuity constraint, while path-level feature extraction has not been well exploited. To overcome the above shortcomings, in this paper, we propose to utilize the Graph Convolutional Neural Network (GCN) and the Recurrent Neural Network (RNN) for the feature extraction of the network topology, and the aggregation of link-level features to path-level features. By doing this, critical RSA-related information can be sensed by the DRL agent to make better actions. Simulation results demonstrate that our proposed method outperforms previous approaches.

关键词： Feature extraction Network topology Topology Recurrent neural networks Optical fiber networks Convolutional neural networks routing routing and spectrum assignment elastic optical network deep reinforcement learning graph convolutional network recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning applied to the routing and spectrum assignment in Elastic Optical Networks 8

Reinforcement Learning applied to the Routing and Spectrum A...

引用

IEEE Latin American Conference on Computational Intelligence (LA-CCI)

作者： Arce, Santiago Ayala Albertini, Luis Rios, Ivan Pinto-Roa, Diego P. Colbes, Jose Villagra, Marcos Univ Nacl Asuncion Fac Politecn San Lorenzo Paraguay

ISBN: (数字)9781665488587

ISBN: (纸本)9781665488587

Elastic Optical Networks (EON) has emerged as technology in optical networks whose architecture can respond to the growing need for elasticity in allocating optical network resources. EON imposes physical layer constraints on traffics. In this context, developing efficient routing and spectrum assignment (RSA) algorithms for dynamic traffic is critical to EON's success. Strategies based on Reinforcement Learning (RL) emerge as a valid alternative to dynamic RSA, due to its ability to adapt to changes in the state of the network by learning process. In this work, we propose RL algorithms based on Q-learning to solve the dynamic RSA problem. First, we study the performance of routing algorithms that evaluate the learning Q values for a set of pre-calculated disjoint routes by selecting a route that corresponds to a minimum blocking rate. Similarly, we studied Q-learning algorithms for spectrum assignment, which selects a block of the spectrum from a pre-routed path to minimize the blocking rate. Numerical simulations on different dynamic traffic loads show that the performance of the Q-learning-based proposals is promising in obtaining a better blocking rate than the state-of-the-art heuristic approaches.

关键词： Reinforcement Learning routing and spectrum assignment Elastic Optical Networks

来源：评论

学校读者我要写书评

暂无评论

Latency-Aware routing and spectrum assignment with Deep Reinforcement Learning 18

Latency-Aware Routing and Spectrum Assignment with Deep Rein...

引用

18th International Conference on the Design of Reliable Communication Networks (DRCN)

作者： Hernandez-Chulde, Carlos Casellas, Ramon Martinez, Ricardo Vilalta, Ricard Munoz, Raul Ctr Tecnol Telecomunicac Catalunya CTTC CERCA Castelldefels Barcelona Spain

ISBN: (纸本)9781665409872

This paper evaluates different aspects of the performance of a solution for routing and spectrum allocation in elastic optical networks. The evaluation includes the experimentation under different traffic loads and the use of a previously trained deep reinforcement learning (DRL) agent. The obtained results show that the DRL agent further outperforms a traditional algorithm as network resources become scarce. Moreover, the results show the proper operation of the pre-trained agent when provisioning lightpaths.

关键词： Deep reinforcement learning elastic optical networks routing and spectrum assignment

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：