In optical networks, simulation is a cost-efficient and powerful way for network planning and design. It helps researchers and network designers quickly obtain preliminary results on their network performance and easily adjust the design. Unfortunately, most optical simulators are not open-source and there is currently a lack of optical network simulation tools that leverage machine learning techniques for network simulation. Compared to Wavelength Division Multiplexing (WDM) networks, Elastic Optical Networks (EON) use finer channel spacing, a more flexible way of using spectrum resources, thus increasing the network spectrum efficiency. Network resource allocation is a popular research topic in optical networks. In EON, this problem is classified as Routing, Modulation and Spectrum Allocation (RMSA) problem, which aims to allocate sufficient network resources by selecting the optimal modulation format to satisfy a call request. SimEON is an open-source simulation tool exclusively for EON, capable of simulating different EON setup configurations, designing RMSA and regenerator placement/assignment algorithms. It could also be extended with proper modelings to simulate CapEx, OpEx and energy consumption for the network. Deep learning (DL) is a subset of Machine Learning, which employs neural networks, large volumes of data and various algorithms to train a model to solve complex problems. 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.
more »
« less
Machine learning aided optimization for balanced resource allocations in SDM-EONs
A fine-grained flexible frequency grid for elastic optical transmission and space division multiplexing in conjunction with spectrally efficient modulations is an excellent solution to the coming capacity crunch. In space division multiplexed elastic optical networks (SDM-EONs), the routing, modulation, core, and spectrum assignment (RMCSA) problem is an important lightpath resource assignment problem. Intercore cross talk (XT) reduces the quality of parallel transmissions on separate cores, and the RMCSA algorithm must ensure that XT requirements are satisfied while optimizing network performance. There is an indirect trade-off between spectrum utilization and XT tolerance; while higher modulations are more spectrum efficient, they are also less tolerant of XT since they permit fewer connections on neighboring cores on the overlapping spectra. Numerous XT-aware RMCSA algorithms restrict the number of litcores, cores on which overlapping spectra are occupied, to guarantee XT constraints are met. In this paper, we present a machine learning (ML) aided threshold optimization strategy that enhances the performance of
- NSF-PAR ID:
- 10406641
- Publisher / Repository:
- Optical Society of America
- Date Published:
- Journal Name:
- Journal of Optical Communications and Networking
- Volume:
- 15
- Issue:
- 5
- ISSN:
- 1943-0620; JOCNBB
- Page Range / eLocation ID:
- Article No. B11
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Service provisioning can be enhanced with spectrally spatially flexible optical networks (SS-FONs) with multicore fibers; however, intercore crosstalk (XT) is a dominant impairment that complicates the problem of maintaining the quality of transmission (QoT) and resource allocation. The selection of modulation formats (MFs), due to their unique XT sensitivities, further increases the complexity. The routing, modulation, core, and spectrum assignment (RMCSA) problem must select the resources carefully to exploit the available capacity while meeting the desired QoT. In this paper, we propose an RMCSA algorithm called the tridental resource assignment (TRA) algorithm for transparent SS-FONs, and its variant, translucency-aware TRA (TaTRA), for translucent SS-FONs. TRA balances three different factors that affect network performance under dynamic resource allocation. We consider translucent networks with flexible regeneration and with and without modulation and spectrum conversion. Our resource assignment approach includes both an offline network planning component to calculate path priorities and an online/dynamic provisioning component to allocate resources. Extensive simulation experiments performed in realistic network scenarios indicate that TRA and TaTRA significantly reduce the bandwidth blocking probability by several orders of magnitude in some cases.
-
more » « less
Elastic optical networks (EONs) are able to provide high spectrum utilization efficiency due to flexibility in resource assignment. In translucent EONs, by employing regenerators and using advanced modulation formats for transmission, spectrum efficiency can be further improved. Survivability is regarded as an important aspect of EONs, and p-cycle protection is considered to be an attractive scheme due to its fast restoration and high protection efficiency. In this paper, we propose methods for evaluating and selecting p-cycles for both link protection (LP) and failure-independent path protection (FIPP) to survive single-link failures. After considering the various factors that affect the performance of a p-cycle, we propose two evaluation metrics for LP and FIPP, namely, individual p-cycle cost and set of cycles cost. Based on these metrics, we propose two algorithms for selecting a set of p-cycles in translucent EONs: Traffic Independent P-cycle Selection (TIPS), which selects a set of cycles without knowledge of the traffic, and Traffic-Oriented P-cycle Selection (TOPS), which takes given traffic information into account. A routing and spectrum assignment algorithm is designed for translucent EONs, and our p-cycle design algorithms are evaluated using both static and dynamic traffic models. Simulation results show that the proposed algorithms have better performance than commonly used baseline algorithms. We also compare the performance of LP p-cycles and FIPP p-cycles.
-
more » « less
A spatial channel network (SCN) was recently proposed toward the forthcoming spatial division multiplexing (SDM) era, in which the optical layer is explicitly evolved to the hierarchical SDM and wavelength division multiplexing layers, and an optical node is decoupled into a spatial cross-connect (SXC) and wavelength cross-connect to achieve an ultrahigh-capacity optical network in a highly economical manner. In this paper, we report feasibility demonstrations of an evolution scenario regarding the SCN architecture to enhance the flexibility and functionality of spatial channel networking from a simple
fixed-core-access anddirectional spatial channel ring network to a multidegree,any-core-access ,nondirectional , andcore-contentionless mesh SCN. As key building blocks of SXCs, we introduce what we believe to be novel optical devices: amulticore fiber (MCF) splitter, a core selector (CS), and a core and port selector (CPS). We construct free-space optics-based prototypes of these devices using five-core MCFs. Detailed performance evaluations of the prototypes in terms of the insertion loss (IL), polarization-dependent loss (PDL), and intercore cross talk (XT) are conducted. The results show that the prototypes provide satisfactorily low levels of IL, PDL, and XT. We construct a wide variety of reconfigurable spatial add/drop multiplexers (RSADMs) and SXCs in terms of node degree, interport cross-connection architecture, and add/drop port connectivity flexibilities. Such RSADMs/SXCs include a fixed-core-access and directional RSADM using a MCF splitter; an any-core-access, nondirectional SXC with core-contention using a CS; and an any-core-access, nondirectional SXC without core-contention using a CPS. Bit error rate performance measurements for SDM signals that traverse the RSADMs/SXCs confirm that there is no or a very slight optical signal-to-noise-ratio penalty from back-to-back performance. We also experimentally show that the flexibilities in the add/drop port of the SXCs allow us to recover from a single or concurrent double link failure with a wide variety of options in terms of availability and cost-effectiveness. -
We present an efficient and scalable partitioning method for mapping large-scale neural network models with locally dense and globally sparse connectivity onto reconfigurable neuromorphic hardware. Scalability in computational efficiency, i.e., amount of time spent in actual computation, remains a huge challenge in very large networks. Most partitioning algorithms also struggle to address the scalability in network workloads in finding a globally optimal partition and efficiently mapping onto hardware. As communication is regarded as the most energy and time-consuming part of such distributed processing, the partitioning framework is optimized for compute-balanced, memory-efficient parallel processing targeting low-latency execution and dense synaptic storage, with minimal routing across various compute cores. We demonstrate highly scalable and efficient partitioning for connectivity-aware and hierarchical address-event routing resource-optimized mapping, significantly reducing the total communication volume recursively when compared to random balanced assignment. We showcase our results working on synthetic networks with varying degrees of sparsity factor and fan-out, small-world networks, feed-forward networks, and a hemibrain connectome reconstruction of the fruit-fly brain. The combination of our method and practical results suggest a promising path toward extending to very large-scale networks and scalable hardware-aware partitioning.more » « less
