Scholarlink

<p>Simulations play a critical role in the planning and design of optical networks, offering a cost-effective and flexible means to evaluate network performance and explore design alternatives. Despite their importance, many existing optical simulators remain proprietary, limiting accessibility and extensibility, particularly in the context of emerging technologies. Notably, there is a significant gap in simulation tools that integrate machine learning techniques within the optical networking domain. Elastic Optical Networks (EONs) represent a major advancement over traditional Wavelength Division Multiplexing (WDM) systems, primarily due to their finer channel granularity and dynamic spectrum allocation capabilities, which substantially improve spectral efficiency. One of the central challenges in EONs is the efficient allocation of network resources, formalized as the Routing, Modulation, and Spectrum Allocation (RMSA) problem. This problem involves selecting optimal paths, modulation formats, and spectrum slots to satisfy connection requests while optimizing overall network utilization. Addressing RMSA effectively is essential for realizing the full potential of EONs and advancing intelligent, adaptive optical network design. SimEON stands out as a unique open-source simulation tool tailored for EON, adept at simulating an array of EON configurations and designing RMSA alongside regenerator placement/assignment algorithms. Moreover, it can be augmented with appropriate models to simulate CapEx, OpEx, and network energy consumption metrics. Deep learning (DL), a specialized branch of machine learning, leverages neural networks, extensive data sets, and algorithms to cultivate models adept at unraveling intricate challenges. In this paper, we extended the capabilities of SimEON by integrating the DeepRMSA algorithm into the existing simulator. We compared the performance of conventional RMSA and DeepRMSA algorithms and provided a convenient way for users to compare different algorithms’ performance and integrate other machine learning algorithms.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating SimEON with DeepRMSA for dynamic network simulation of elastic optical networks

  • 期刊论文

  • 发表日期：

    2026年2月6日

查看全文
  • Boyang Hu,
  • Mohammad Jafar Majid,
  • Byrav Ramamurthy

摘要

Simulations play a critical role in the planning and design of optical networks, offering a cost-effective and flexible means to evaluate network performance and explore design alternatives. Despite their importance, many existing optical simulators remain proprietary, limiting accessibility and extensibility, particularly in the context of emerging technologies. Notably, there is a significant gap in simulation tools that integrate machine learning techniques within the optical networking domain. Elastic Optical Networks (EONs) represent a major advancement over traditional Wavelength Division Multiplexing (WDM) systems, primarily due to their finer channel granularity and dynamic spectrum allocation capabilities, which substantially improve spectral efficiency. One of the central challenges in EONs is the efficient allocation of network resources, formalized as the Routing, Modulation, and Spectrum Allocation (RMSA) problem. This problem involves selecting optimal paths, modulation formats, and spectrum slots to satisfy connection requests while optimizing overall network utilization. Addressing RMSA effectively is essential for realizing the full potential of EONs and advancing intelligent, adaptive optical network design. SimEON stands out as a unique open-source simulation tool tailored for EON, adept at simulating an array of EON configurations and designing RMSA alongside regenerator placement/assignment algorithms. Moreover, it can be augmented with appropriate models to simulate CapEx, OpEx, and network energy consumption metrics. Deep learning (DL), a specialized branch of machine learning, leverages neural networks, extensive data sets, and algorithms to cultivate models adept at unraveling intricate challenges. In this paper, we extended the capabilities of SimEON by integrating the DeepRMSA algorithm into the existing simulator. We compared the performance of conventional RMSA and DeepRMSA algorithms and provided a convenient way for users to compare different algorithms’ performance and integrate other machine learning algorithms.