Augmented wavelength division allocation method for peak traffic grooming in optical networks using 2-layer perceptron learning

As optical networks evolve toward dynamic, multi-band (C + L) architectures, efficient and QoT-aware resource management becomes essential to ensure scalable and low-service downtime operation. This paper introduces a novel, to our knowledge, unified hybrid grooming framework that addresses the unique challenges of traffic grooming in dynamic multi-band elastic optical networks (MB-EONs). Motivated by the need for cost-effective and adaptive high-capacity infrastructures, we propose a policy-based framework incorporating three heuristic algorithms tailored to distinct optimization goals. The unique challenges of multi-band optical networks, such as the non-uniform QoT performance caused by inter-channel stimulated Raman scattering (ISRS) are explicitly considered in our design, as they directly impact grooming efficiency, spectrum utilization, and achievable modulation formats. The algorithms include (i) Min–Max Channel, which minimizes spectrum fragmentation and reduces the partial bit rate blocking probability by up to 35%; (ii) Max Grooming Capacity, which improves line card interface (LCI) reuse and reduces deployment by 20%; and (iii) Time Aware, which minimizes reconfiguration counts by up to 80%, significantly lowering control overhead and service downtime. Unlike prior works limited to static or single-band scenarios, our framework is the first, to our knowledge, to dynamically integrate routing, band selection, modulation format, grooming, and spectrum assignment (RBMGSA) in a QoT-aware manner. Simulation results over the NSFNET, Japan, and Spain topologies under dynamic traffic conditions demonstrate that our approach supports flexible trade-offs among performance, cost, and reconfiguration complexity. Notably, the reconfigurable variants of our algorithms consistently outperform non-reconfigurable approaches by enhancing resource utilization and reducing blocking. The proposed system also supports partial grooming, enabling improved service accommodation and laying the groundwork for scalable and efficient operation in future multi-band optical networks.

Multi-band (MB) optical transmission is a promising solution to support the ever-increasing network capacity demand of 5 G/6 G applications. By exploiting extra optical spectrum beyond the C- and L-bands, such as the L+C+S-band, the network can use up to 20 THz, quadrupling the original capacity of the C-band. The extensive spectrum resources and complex physical layer interactions in MB systems present challenges for traditional resource management solutions that are evaluated only for the C-band. Effective algorithms tailored for MB optical networks are needed to enable optical networks to provision services efficiently, thereby reducing service blocking and improving network throughput. In this study, we propose a deep reinforcement learning (DRL)-assisted framework for dynamic service provisioning in MB elastic optical networks. The proposed DRL framework aims to minimize long-term bit-rate blocking and includes several innovations. First, an accurate quality of transmission estimation model is employed to profile the performance of the supported modulation formats for each channel on pre-computed routes. Within the DRL agent design, a novel state representation incorporating both route-level and band-level features is designed to enhance the DRL agent's ability to perceive the network conditions. Moreover, a new reward function has been developed to enhance performance and accelerate convergence. Simulations are performed using a number of L+C+S MB systems with and without traffic grooming support. The results indicate that the proposed DRL-assisted framework can reduce bit rate blocking by an average of 35% to 85% compared to the existing heuristic methods from the literature while maintaining an appropriate inference time.

The Energy Efficient Regional Area Metropolitan Optical Access Network (MOAN) is a modern optical communication system specifically designed for metropolitan areas. It addresses the increasing demand for high-speed data transmission while optimizing energy consumption. In this paper, energy-efficient traffic data aggregation and energy-aware routing are presented to increase the network lifetime of the system. The traffic data aggregation reduces redundant transmissions, while energy-aware routing minimizes energy consumption by selecting energy-efficient paths. Initially, the wavelength utility-based dynamic wavelength allocation approach (WU-DWA) was developed to facilitate efficient resource utilization. Then, the data aggregation is performed in the context of traffic grooming using the adaptive principal component analysis (APCA)technique. APCA combines or grooms multiple low-bandwidth data streams into higher-capacity data channels to optimize the use of available network resources, such as wavelengths in optical networks or channels in general communication systems. The aggregated data is routed with the proposed energy efficient adaptive Tuna slap Swarm Optimization strategy (ATSSO). By using the proposed approach, the performance obtained in terms of energy consumption is 88, throughput is 131.63, average packet delay is 3.551, and energy savings are 29.99, respectively. The proposed approach is implemented, and the performance is evaluated in terms of standard performance metrics and analyzed using traditional approaches. The better performance indicates that the proposed approach is more efficient than existing approaches.

During the brownfield migration process from wavelength division multiplexing networks to elastic optical networks (EONs), fixed-grid and flex-grid devices coexist in the network, resulting in mixed-grid optical networks (MGONs). To improve the resource utilization of MGONs, we propose an auxiliary-graph-based traffic grooming with hybrid single/multipath routing (ATGHR) algorithm for MGONs. Specifically, we propose a hybrid single/multipath routing (HSMR) scheme to reasonably split the connection request into multiple sub-requests with the aim of satisfying the different transmission capabilities of flex-grid and fixed-grid nodes and avoiding excessive connection division. Based on it, we formulate an integer linear programming (ILP) model using traffic grooming (TG) with the objective of minimizing the spectrum and transponder usage for static MGON scenarios. Moreover, for a large-scale MGON where the ILP model is not tractable, we develop an auxiliary graph (AG) to support better characterization of TG and distance-adaptive modulation in MGONs and present several TG policies for different purposes by adjusting the edge weights of AG. Based on the AG, we propose a heuristic algorithm combined with TG and HSMR to further improve resource utilization. Extensive simulations are conducted to evaluate our proposals. Simulation results show that the ILP model can achieve the best performance in a small-scale network. Moreover, in large-scale networks, different TG policies for the same algorithm can achieve different targets, and our ATGHR has the best bandwidth blocking ratio compared with two benchmark algorithms using the same TG policy.

ABSTRACTThe emergence of 5G networks has emerged as innovative solutions for traffic grooming and resource management in optical fronthaul networks. Traditional methods are often incapable of managing the complexity of different traffic patterns, low latencies, and high bandwidth consumption, which leads to suboptimal resource allocation and, consequently, high operating costs. The objective is to develop an innovative machine learning (ML) architecture called Intelligent Multi‐Attentive Generative Adversarial Networks (IMAGAN) for maximizing resource utilization and traffic grooming (TG) in 5G optical fronthaul networks. The suggested IMAGAN‐based architecture consists of a multi‐attentive model for identifying spatiotemporal traffic patterns combined with a generative adversarial model to provide synthetic network scenarios. The findings indicate that the IMAGAN‐based architecture enhances the performance of energy management systems in terms of resource utilization ratio, bandwidth utilization ratio, rejection ratio, MAE, and RMSE. The findings of the study offer a strong foundation for further improvements in intelligent 5G network design and management.

With the ability to provide worldwide communication coverage, satellite networks are drawing greater attention. The translucent optical payload enables the implementation of IP-over-WDM satellite optical networks (SONs), which can achieve great bandwidth capacity while providing the flexibility of IP routing. The rechargeable battery is the sole energy support for satellites in the eclipse region. Unrestrained discharge will accelerate battery aging and shorten the satellite operation period, causing extremely high expenditure costs. Satellite movement causes time-scheduled energy supply and traffic fluctuation, complicating the problem of energy consumption in IP-over-WDM SONs. This paper studies green traffic grooming (GTG) in IP-over-WDM SONs from the perspective of battery lifetime consumption (BLC). A grooming graph is designed to implement GTG with the physical impairment constraint in IP-over-WDM SONs, and battery-aware GTG (BA-GTG) and time-aware GTG (TA-GTG) are proposed by taking battery information and time information as prior knowledge. Numerical results indicate that BA-GTG and TA-GTG, especially the latter, can effectively reduce BLC. In addition, multiple link configurations are set in performance comparison to evaluate the effect of the physical impairment on battery efficiency in IP-over-WDM SONs.

Deep learning model of semantic direction exploration based on English V+able corpus distribution and semantic roles

Cost minimization of multi-class demands groomed over multi-rate OTN interfaces considering WDM-layer constraints

With the increase in global wireless traffic, the use of large-scale satellite networking to provide ubiquitous access is one of the essential trends of future 6G network development. Elastic optical satellite networks (EOSNs) are widely considered a flexible solution for future satellite communication. However, with the continuous proliferation of network devices and users, the growing disparity between user demands and the limited bandwidth and capacity of the network is becoming increasingly noticeable. This has led to issues such as constrained network resource utilization and resource fragmentation. Therefore, EOSNs must efficiently address the challenge of allocating scarce bandwidth resources. Effective traffic grooming methods will be applied to EOSNs to solve the problem of bandwidth shortage. This paper proposed a dynamic traffic grooming algorithm based on virtualization-plane-aided optimization (DTG-VPO) to facilitate the bandwidth allocation for EOSNs. Firstly, the nodes of the alternative paths were graded, and the weights of the subsequent hop links were modified. Then, the path was evaluated using link weights, alternative paths were selected in the virtual and physical topologies, respectively, and a path set was constructed. Finally, a resource block evaluation parameter was designed to quantify the quality of candidate resource blocks and rank them. A series of simulations have evaluated the traffic-blocking probability and wavelength utilization under different traffic loads. The link resource was more fully utilized compared with other traffic grooming algorithms. The blocking probability can be reduced by 75%, while wavelength utilization can be improved by 8.1%.

This paper reports our study on the multilayer path (MLP) planning method in multilayer networks to achieve the flexible accommodation of large-capacity and diversified traffic. In addition to traffic grooming of sub-lambda paths, MLP design requires optimal selection of the operational mode. In this paper, we discuss MLP design methods that use reinforcement learning and auxiliary graphs to achieve MLP designs that satisfy various requirements such as cost, energy, and low blocking probability. We introduce a heuristic MLP planning method using auxiliary graphs. This method can determine link weights of auxiliary graphs to comply with arbitrary predefined policies; it yields MLPs whose characteristics satisfy the MLP requirements. We then describe an approach to optimize the weights of the auxiliary graph using reinforcement learning. In simulations, we evaluate the number of successfully allocated MLP paths, the required number of transceivers, and the capacity distribution of optical paths in a scenario where MLP requests are generated sequentially. The quantitative results show that our MLP design method can adaptively adjust the link weights of the auxiliary graphs under various network conditions. This can significantly improve the performance compared to heuristic design methods that assume fixed policies.

Abstract Today, in passive optical networks (PON) the major issue is call blocking and it is getting worse as there is an increase in the number of connection requests but the wavelength channels in fiber links are limited. In this research, greedy-based priority routing and wavelength assignment traffic grooming (GPRWATG) technique is proposed aimed at reducing call blockage. In this scheme, to avoid optical–electrical–optical correspondence, firstly the grooming of connection requests with same source destination (s–d) is performed. According to the priority of these groomed connection requests, wavelength assignment and routing is assigned. This approach not only addresses the call blocking issue but also aligns with industry demands for improved network infrastructure. The proposed work performance is analyzed for blocking probability (BP), congestion, and its performance is compared with the non-priority-based routing and wavelength assignment traffic grooming (NPRWATG) and priority-based routing and wavelength assignment traffic grooming (PRWATG) schemes. The proposed method has 23.6 % lower congestion as compared to PRWATG and 21 % lower congestion as compared to NPRWATG. Also, the BP of GPRWATG is 26 % less than PRWATG and 21 % less than NPRWATG. Thus, it can be analyzed that by using the proposed technique, the BP as well as the congestion of the network altogether is reduced in comparison to the existing state-of-art techniques.

Design of CapEx and OpEx aware IP-over-WDM network using different types of traffic bypass and grooming techniques

Metro network operators aim to design scalable and cost-effective network architectures to address the capacity expansion due to ongoing traffic growth. While coherent transmission (e.g., at 100 Gbps and 200 Gbps) can address capacity growth, operators must also support legacy non-coherent transmission technology (e.g., at 10 Gbps). Therefore, operators must devise new practical solutions to jointly support new and legacy transmission technologies, while minimizing the network cost. This study investigated the optimization problem arising when deploying a metro network with a hierarchical architecture of grooming nodes. More precisely, we optimized the deployment cost of hierarchical traffic-grooming stacked optical transport network (OTN) boards with a mix of coherent and non-coherent transmission technologies in metro/regional networks composed of interconnected rings, while considering a filterless node architecture. We formulated the optimization problem using integer linear programming. Then, to deal with problem scalability, we proposed a comprehensive set of novel heuristic approaches based on genetic algorithms, simulated annealing, and a knowledge-domain heuristic (local search). We also compared the proposed approaches with baseline strategies used by network operators and showed that we can reach up to 50% cost savings compared to these baselines.

Multi-band transmission over existing fibers would be a key strategy for ongoing capacity expansion even though upgrading from the conventional C band to multi-band, such as the C+L-band transmission being deployed by operators, would be a slow and complex process. After the C+L band, which band should be upgraded first in the next stage is an open question. We try to answer this by proposing three different band upgrade strategies, including near-to-far, far-to-near, and performance-prediction strategies, and comparing the potential capacity increase and the investment cost to upgrade different bands. We introduce an optical signal-to-noise ratio (OSNR) estimation model comprehensively covering various impairments to evaluate the quality of transmission of an optical channel and develop what we believe to be a novel method to find optimal launch powers for optical channels. Along with routing and spectrum assignment, an OSNR-aware traffic grooming algorithm is also developed to evaluate the capacity that can be achieved after upgrading different bands in an optical network. Our study shows that the performance-prediction strategy always outperforms the other two strategies. When capacity is considered a key performance metric, the E band should be the first to be upgraded next since it both expands the transmission capacity significantly using only a few additional amplifiers and the band upgrade sequence should be E, O, S, and U. For the performance-prediction strategy, we also evaluate the impact of the upgraded band on the performance of other bands. It is found that the upgraded band always has a significant impact on adjacent bands, with the upgrade of high-frequency bands improving the performance of existing low-frequency bands and the upgrade of low-frequency bands degrading the performance of existing high-frequency bands. In addition, the “C+L+E+O+S+U” scenario can achieve 3 times the capacity of the “C+L” scenario when all the bands are upgraded.

The advent of next-generation networks has revolutionized modern networking practices through its improved service capability as well as its numerous emerging use cases. Coupled with the increasing number of connected devices, 5G and beyond (5G+) network traffic is expected to be increasingly diverse and high in volume. To address the large amount of data exchanged between the 5G+ core and external data networks, optical transport networks (OTNs) with dense wavelength-division multiplexing (DWDM) will be leveraged. In order to prepare for this increase in traffic, network operators (NOs) must develop and expand their existing backbone networks, requiring significant levels of capital expenditures. To this end, the traffic grooming and infrastructure placement problem is critical to supporting NO decisions. The work presented in this paper considers the traffic grooming and infrastructure placement problem for OTN-over-DWDM networks. The dynamicity and diversity of 5G+ network traffic are addressed through the use of robust optimization, allowing for increasing levels of solution conservativeness to protect against various levels of demand uncertainty. Furthermore, a robust traffic grooming and infrastructure placement heuristic (RGIP-H) solution capable of addressing the scalability concerns of the optimization problem formulation is presented. The results presented in this work demonstrate how the tuning of the robust parameters affects the cost of the objective function. Additionally, the ability of the robust solution to protect the solution under demand uncertainty is highlighted when the robust and deterministic solutions are compared during parameter deviation trials. Finally, the performance of the RGIP-H is compared to the optimization models when applied to larger network sizes.

Traffic grooming for massive light-path blockages in D2D-enabled hybrid LiFi and WiFi networks

Benefiting from the distributed concept and ultradense constellation deployment, the distributed satellite cluster (DSC) networks have emerged as a promising architecture to enhance single-satellite capability and network capacity. Integrating data center (DC) into the DSC networks can promote the rapid development of satellite Internet. This article innovatively proposes the satellite data center networks (SDCNs) framework to accommodate future extensive applications. Networking of the SDCNs suffers network heterogeneity, dynamic change, constrained resources, and multigranular services. To tackle these issues, many key techniques are detailed, including topology control, wavelength assignment and routing, traffic grooming, SDCNs virtualization, and OpenFlow controller deployment. Based on the framework, we conduct traffic grooming to enhance wavelength efficiency and evaluate the proposed grooming schemes through simulations. To heighten the overall resource efficiency, the cross-layer resource scheduling approach is developed enabling physical-layer sources to fulfill the requirements of upper-layer applications. Finally, three promising directions of the SDCNs are discussed.

In elastic optical networks (EON), routing, modulation selection, and spectrum assignment (RMSA) is crucial in provisioning connection requests. Multipath RMSA offers a number of benefits including provisioning of ultra-high bandwidth demands and better utilization of fragmented spectrum resource. By Combining with traffic grooming, multipath RMSA and traffic grooming is able to provide better utilization of network resource in provisioning connection requests. Adding multi-hop routing mechanism to multipath RMSA and traffic grooming increases the flexibility for selecting paths resulting in higher probability of successfully finding routing paths for connection requests. Dynamic multipath RMSA problem in EON has been investigated extensively in the literature. Dynamic multi-hop multipath RMSA and traffic grooming problem in EON is far from been well studied. This paper proposes an algorithm for the dynamic multi-hop multipath RMSA and traffic grooming problem in OFDM-based elastic optical networks with sliceable bandwidth-variable transponders. Performance of the proposed algorithm is studied via simulation. Our simulation results show that the proposed algorithm yields lower bandwidth blocking ratio than an existing algorithm.

X-Haul aims to provide a unified transport network for integrating mobile fronthaul/midhaul/backhaul. Its architecture is inherited from the IP-over-WDM paradigm, in which the upper layer is an electrical packet-switched network and the bottom layer is an optical circuit-switched network. Traffic grooming in X-Haul poses a big challenge, as the mobile traffic load has shown. As a multi-layer routing problem, traffic grooming has been well studied through some classic mathematical models, such as the auxiliary graph (AG). Recently, a new approach based on machine learning has been attracting much attention for its network routing decision making. According to previous studies, either of the two approaches has its limitations, but the combination of the two may achieve profit maximization. To this end, we propose and demonstrate, for the first time, to our knowledge, a collaborative data-driven (using machine learning) and model-driven (using experiential knowledge) intelligent routing engine (ADMIRE) for traffic grooming in an X-Haul testbed with a real mobile dataset. The principle of ADMIRE is to exploit the capability of machine learning for an accurate AG model in a dynamic network environment. We compare ADMIRE with a traditional model-driven approach (i.e., the AG), and the evaluation results show that ADMIRE can achieve good performance and a strong generalization ability. In addition, we also verify the influence of data correlation on ADMIRE.