Long short-term memory neural networks demonstrate a classification accuracy larger than 99% for highly variable and bursty, real-time server traffic flows. Their performance in terms of forecasting precision displays promising results, both for one-step as well as multi-step predictions. These capabilities make the a priori detection of heavy data streams possible, thus enabling the employment of

High deployment cost with respect to expected revenue is the main barrier to fiber-to-the-home (FTTH) roll-out in rural areas. This problem, as shown in this paper, is exacerbated by the uncertainty associated with the end-user take-up rate. The randomness associated with subscribers’ service take-up yields considerable fluctuation and escalation in the total cost of deployment. This adverse and varying

By associating machine learning and an analytical model (i.e., the Gaussian noise model), we reduce uncertainties on the output power profile and the noise figure of each amplifier in an optical network. We leverage the signal-to-noise ratio (SNR) of all the light paths of an optical network, monitored in all the coherent receivers. The learning process is based on a gradient-descent algorithm where

This paper proposes, designs, and validates a filterless metro network employing bidirectional transmission over a single fiber. Transmission impairments, dominated by cross talk, are specifically estimated leveraging on what we believe to be novel closed-form expressions to determine optical reach, launch power, and number of supported cascaded nodes. Results show that extremely good transmission

This paper proposes a machine-learning (ML)-aided cognitive approach for effective bandwidth reconfiguration in optically interconnected datacenter/high-performance computing (HPC) systems. The proposed approach relies on a Hyper-X-like architecture augmented with flexible-bandwidth photonic interconnections at large scales using a hierarchical intra/inter-POD photonic switching layout. We first formulate

We propose a fast and accurate signal quality monitoring scheme that uses convolutional neural networks for error vector magnitude (EVM) estimation in coherent optical communications. We build a regression model to extract EVM information from complex signal constellation diagrams using a small number of received symbols. For the additive-white-Gaussian-noise-impaired channel, the proposed EVM estimation

This paper proposes an evolutionary transfer learning approach (Evol-TL) for scalable quality-of-transmission (QoT) estimation in multi-domain elastic optical networks (MD-EONs). Evol-TL exploits a broker-based MD-EON architecture that enables cooperative learning between the broker plane (end-to-end) and domain-level (local) machine learning functions while securing the autonomy of each domain. We

Flexible grid networks need rigorous resource planning to avoid network over-dimensioning and resource over-provisioning. The network must provision the hardware and spectrum resources statically, even for dynamic random bandwidth demands, due to the infrastructure of flexible grid networks, hardware limitations, and reconfiguration speed of the control plane. We propose a flexible online–offline probabilistic

Availability is a key service metric when deploying service function chains (SFCs) over network slices in 5G networks. We study the problem of determining the composition of a slice for a service function chain and the mapping of the slice to the physical transport network in a way that guarantees availability of the SFC while minimizing cost. To improve the availability, we design a slice that provides

With the stringent requirements of fifth-generation and beyond wireless communications technology coupled with the potential bottleneck in the optical fronthaul, radio-over-fiber (RoF) technology offers an alternative solution to distribute the wireless signals while meeting these requirements. The inherent centralized architecture of RoF enables advanced coordination functionality to be performed

As the communication infrastructure that sustains critical societal services, optical networks need to function in a secure and agile way. Thus, cognitive and automated security management functionalities are needed, fueled by the proliferating machine learning (ML) techniques and compatible with common network control entities and procedures. Automated management of optical network security requires

Reliable and conservative computation of the quality of transmission (QoT) of transparent lightpaths (LPs) is a crucial need for software-defined control and management of the wavelength division multiplexing optical transport. The LP QoT is summarized by the generalized SNR (GSNR) that can be computed by a QoT estimator (QoT-E). Within the context of network automation, the QoT-E must rely only on

This paper proposes and demonstrates a hybrid-learning-assisted impairments abstraction framework for planning and provisioning intra- and inter-domain services in a field-trial multi-domain optical network testbed. The proposed abstraction strategy consists of a parametric and a non-parametric machine learning technique to allow the control plane to implement impairments abstraction with different

Optical wireless access networks have seen rapid progress. With beam-steering capability, optical wireless communications can deliver very high capacity, support user mobility with indoor localization supported directly at the optical layer, be resilient against the blocking of beams by exploiting spatial diversity at the optical layer, and guarantee low-latency links with modified protocols and network

To deal with the challenging requirements of metropolitan area networks (MANs), it is essential to design cost-effective systems that can support high capacity and dynamic adaptation, as well as a synergy of programmability and efficient photonic technologies. This becomes crucial for very large MANs that support 5G, where multihop connections will need to be dynamically established at target capacities

The fifth generation (5G) mobile communications system is envisioned to serve various mission-critical services such as industrial automation, cloud robotics, and safety-critical vehicular communications. To satisfy the stringent end-to-end latency requirement of these services, fog computing has been regarded as a promising technology to be integrated into 5G networks, in which computing, storage

The future-generation passive optical network (PON) physical layer, targeting 100 Gbps/wavelength, will have to deal with severe optoelectronics bandwidth and chromatic dispersion limitations. In this paper, largely extending our Optical Fiber Communication Conference (OFC) 2020 invited paper, we review 100 Gbps/wavelength PON downstream alternatives over standard single-mode fiber in the O- and C-bands

Toward the forthcoming spatial division multiplexing (SDM) era, a spatial channel network (SCN) was recently proposed in which the optical layer is explicitly decoupled from the hierarchical SDM and wavelength division multiplexing (WDM) layers, and an optical node evolves into a spatial cross-connect (SXC) and wavelength cross-connect (WXC) to achieve a hierarchical optical cross-connect (HOXC). In

Coherent optics has been proved to be a promising candidate for 100 Gb/s and even beyond single-wavelength time-division multiplexing passive optical networks (TDM-PONs). However, one of the key issues in TDM coherent-PON is how to efficiently and robustly achieve upstream burst-mode coherent detection. To solve this problem, we proposed and demonstrated a reliable and efficient preamble design with

SDN Enabled Broadband Access (SEBA) is a large open-source development and integration project hosted by the Open Networking Foundation (ONF). Built using white-box hardware, merchant silicon, and SDN principles, SEBA brings the benefits of virtualization and cloudification to passive optical network (PON)-based broadband access networks for FTTH/FTTB deployments. Already in field trials with several

Channel measurements for a 50G passive optical network (PON) show a significant amount of intersymbol interference (ISI) due to chromatic dispersion (CD) and the use of low-cost, bandwidth-limited 25 Gbaud class components. The channel characteristics at the input of the forward error correction (FEC) decoder are measured for several receiver equalization schemes, and the error correlation at the output

We investigate the advantages of using co-packaged optics for building low-diameter, large-scale high-performance computing (HPC) and data center networks. The increased escape bandwidth offered by co-packaged optics can enable high-radix switch implementations of more than 150 switch ports, which can be combined with data rates of up to 400 Gb/s per port. From the network architecture perspective

In this paper, we identify challenges in developing future optical network infrastructure for new services based on technologies such as 5G, virtual reality, and artificial intelligence, and we suggest approaches to handling these challenges that include a business model, architecture, and diversity. Through activities in multiservice agreement and de facto standard organizations, we have shown how

Machine learning (ML) is currently being investigated as an emerging technique to automate quality of transmission (QoT) estimation during lightpath deployment procedures in optical networks. Even though the potential network-resource savings enabled by ML-based QoT estimation has been confirmed in several studies, some practical limitations hinder its adoption in operational network deployments. Among

This paper provides an overview of transceiver technologies to be used for current and next-generation passive optical networks (PONs). The uninterrupted scaling of PONs to higher bitrates in a cost-effective way to meet future bandwidth demands will drive the need for continuous improvement in PON transceiver technologies. In this paper we try to analyze the requirements needed and the impact on this

Network operators are facing a critical issue on their optical transport networks to deploy 5G$+$+ and Internet of Things services. They need to address the capacity increase by a factor of 10, while keeping a similar cost per user. Over the past years, network operators have been working on the optical disaggregated approach with great interest for achieving the required efficiency and cost reduction

Machine learning (ML) is increasingly applied in optical network management, especially in cross-layer frameworks where physical layer characteristics may trigger changes at the network layer due to transmission performance measurements (quality of transmission, QoT) monitored by optical equipment. Leveraging ML-based QoT estimation approaches has proven to be a promising alternative to exploiting

The dis-aggregated passive optical network (PON) optical line terminal (OLT) architecture is attracting attention in academia and industry. This paper first reviews the evolution in dynamic bandwidth allocation (DBA) dis-aggregation. We further enhance the scalability of the dis-aggregated PON-OLT by reducing the bandwidth overhead of REPORT/GATE, the time division multiplexing (TDM) control information

The introduction of 5G, the increasing number of connected devices, and the exponential growth of services relying on connectivity are pressuring multilayer networks to improve their scaling, efficiency, and controlling capabilities. However, enhancing those features consistently results in a significant amount of complexity in operating the resources available across heterogeneous vendors and technology

We propose a single-stage network architecture for intra-node connectivity that makes use of nanosecond-scale photonic switches. Although buffering at the switch points is of vital importance for complex multistage networks, this is not the case for smaller-scale single-stage networks where the end nodes are located only one hop apart. By limiting the buffering to the end points, the proposed architecture

To support newly emerging and highly dynamic 5G services, optical metro networks must be capable of provisioning services on the fly. Network function virtualization (NFV) is leveraged to fulfill these dynamic service demands by placing virtual network functions (VNFs) in NFV-capable network nodes and chaining them together (“service chaining”). In addition, new 5G service chains often have bandwidth

In space-division multiplexing elastic optical networks (SDM-EONs) based on multicore fibers, the problem of finding a lightpath for a new connection request involves routing, modulation, spectrum, and core assignment (RMSCA). A lightpath can be constructed using contiguous free frequency slot (FS) blocks with different frequency slot allocation patterns (FSAPs), where each FSAP can incur different

An online parameter-tuning method for the energy-efficient data center network (DCN) named HOLST (high-speed optical layer 1 switch system for time-slot-switching-based optical data center networks) is proposed. HOLST comprises an optical circuit switching network, optical slot switching network, and electrical packet switching network for the spine layer. It requires flows to be assigned to optimal

This paper provides a performance analysis of a simultaneous free-space-optics (FSO) and millimeter wave (mmWave) communication system with selection-combining and maximal-ratio-combining receivers over the ${\cal F}$F-distribution channel. The ${\cal F}$F-distribution model can be used to represent both the mmWave and FSO channels with proper selection of parameters. In particular, an exact-form analysis

The dynamicity of today’s optical networks is far from its potential. Optical components, such as fast-tunable lasers or semiconductor optical amplifiers, can react on a nanosecond time scale, while the reconfiguration time of optical networks is many orders of magnitude larger, normally above a hundreds of milliseconds timescale. In this work, we address this gap with real-time control plane strategies

Network connectivity, i.e., the reachability of any network node from all other nodes, is often considered as the default network survivability metric against failures. However, in the case of a large-scale disaster disconnecting multiple network components, network connectivity may not be achievable. On the other hand, with the shifting service paradigm towards the cloud in today’s networks, most

In this paper, we study the quality of transmission (QoT) aware routing, modulation level, and resource assignment problem for transparent flexible optical networks over few-mode multi-core fibers. We consider two three-dimensional resource assignment (3DRA) algorithms, called liberal and conservative, that are compatible with fractional joint switching. The three resource dimensions are core, mode

With a focus on service interruptions occurring in optical networks, we propose a failure prognostics scheme based on a bi-directional gated recurrent unit (BiGRU) from the perspective of time-series processing, which leverages actual datasets from the network operator. BiGRU neural networks can capture the temporal features of multi-sourced data and incorporate contextual information. A principal

Industry 4.0 represents a new industrial revolution that will dramatically change the landscape in many sectors, including manufacturing and logistics. Robotics, machine intelligence, and new forms of connectivity are key ingredients of this paradigm. 5G mobile networks are expected to play a crucial role, supporting a lower cost per transported bit in air and a lower latency compared with 4G. 5G radio

To cope with the dynamic datacenter (DC) traffic matrix generated by multiple applications, load balancing algorithms can be deployed to improve the datacenter network (DCN) performance. OPSquare, as a promising optical DCN architecture, adopts fast optical switches to provide high bandwidth, low latency, large scalability, and cost and energy efficiency. Current load balancing algorithms are not optimal

Aiming to solve the low utilization and high operational cost in current data centers and the diversified resource requirements for different application types, we propose and investigate what we believe to be a novel rack-scale disaggregated optical data center network (RDON). Different types of hardware resources (i.e., CPU, memory, and storage) are deployed in standalone resource pools of the RDON

Hybrid light fidelity (LiFi) and wireless fidelity (WiFi) networks provide a promising solution for future indoor wireless communication. Hybrid networks face the challenge of imbalanced cell load due to the uneven distribution of user equipment (UE), and they need to suppress inter-cell interference induced by the dense deployment of LiFi access points (APs). In this paper, with the aim to efficiently

Fixed optical transport is the predominant fronthaul technology for 4G mobile access networks, carrying the traffic between the central office and subtended antenna sites. With the new functional splits and related standards introduced in 5G, new capacity and quality-of-service requirements are imposed on optical transport. In this paper, we discuss low-cost high-capacity optical fronthaul solutions

We present a fixed mobile convergence topology for analog intermediate frequency over fiber (A-IFoF)/millimeter-wave (mmWave) transmission, benefiting from the reuse of the deployed passive optical network (PON) infrastructure, towards future mobile fronthaul architectures. Powerful fully programmable gate array boards located inside the access nodes convert the Ethernet-based traffic to orthogonal

Passive optical networks (PONs) have been widely used in access networks and are today the access technology of choice for operators, especially when they need to build new infrastructure. Significant effort has been put in place across the years to scale the speed of passive optical networks. The super-PON concept has also been proposed in order to scale reach and customer aggregation of PONs. However

Discrete multitone (DMT) modulation, due to its water-filling nature, is proposed to enable flexibility in passive optical networks (PONs), optimizing the PON resource usage. The use of DMT signals to directly modulate long-wavelength vertical-cavity surface-emitting lasers (VCSELs) can provide energy-efficient transmitters for 50G PONs. First, we present preliminary experimental measures employing

This paper discusses the future direction of optical access networks and proposes a new optical access architecture that will support the evolution of optical access systems from a fiber-to-the-home infrastructure to a common optical access platform that connects various devices and systems to anywhere they want to reach. We describe two technologies for its implementation. One is “modularization,”

As the capacity of the next-generation passive optical network (PON) is reaching 100 Gb/s and beyond, cost-effective transceivers have been widely discussed. In this work, we provide a comprehensive comparison of various simplified coherent and direct detection (DD) schemes operating at a ${100\; {\rm Gb/s/}}\lambda$100Gb/s/λ 4-ary pulse amplitude modulation signal through numerical simulation. According

Coherent wavelength division multiplexing (WDM) technologies have leveraged the optical communication systems in core networks, increasing the fiber capacity by transmission with advanced modulation formats and mitigation of impairments with digital signal processing. However, these solutions are too expensive for access networks, where cost, power budget, and footprint are limited. Hence, the key

Standardization activities are nearly complete for single wavelength 25 Gb/s time-division multiplexed (TDM) passive optical networks (PONs) and well underway for 50 Gb/s TDM PONs. There is considerable debate in the industry about which technology will be the “next step” after 10 Gb/s TDM PON, now finally starting to ramp up to mass deployment. 50 Gb/s PON clearly brings a ${2} \times$2× bandwidth

We propose a new automation concept for access network equipment called “Plug & Provision.” This concept aims at reducing the workload in provisioning passive optical network (PON) service by utilizing a modular optical line terminal (OLT) and automating the setup sequence. To realize this concept, the automation platform must automatically detect the modular OLT plugged into a switch port and execute

With 10G time division multiplexed passive optical network (TDM-PON) systems ready for massive deployment worldwide, the next generation PON standards are being intensively discussed in both IEEE and ITU-T. Compared with the IEEE’s wavelength stacked ${2}{ *}{25}\text{G}$2∗25G solution, the ITU-T’s single carrier non-return-to-zero-based 50G TDM-PON has the advantages of low cost, easy operation, and

This paper proposes an elastic RF-optical networking (ERON) architecture solution for millimeter wave (mmWave) 5G radio access networks. The ERON architecture achieves energy efficiency and throughput elasticity using photonic-enhanced multibeam mmWave spatial multiplexing capability at the radio units. The centralization of the hardware resources and the converged management of the RF and optical

With the stringent requirements of high reliability and low latency, ultra-reliable low latency communications (URLLCs) are one of three typical services in the fifth generation of mobile network (5G) paradigm. The packet duplication (PD) technique has been proposed as a promising solution to satisfy the extreme requirements of URLLC services. However, the benefit of PD comes at the cost of doubling

Dynamic network slicing has emerged as a promising and fundamental framework for meeting 5G’s diverse use cases. As machine learning (ML) is expected to play a pivotal role in the efficient control and management of these networks, in this work, we examine the ML-based quality-of-transmission (QoT) estimation problem under the dynamic network slicing context, where each slice has to meet a different

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

Rapidly growing and fluctuating traffic demands lead to unbalanced traffic scenarios in optical access networks, which have an impact on network efficiency. Thus, the flexible software-defined reconfigurable passive optical network (PON) architecture has been proposed to handle this challenge. To improve the efficiency of a reconfigurable PON facing unbalanced traffic demands, this paper proposes a

The reduction of system margin in open optical line systems (OLSs) requires the capability to predict the quality of transmission (QoT) within them. This quantity is given by the generalized signal-to-noise ratio (GSNR), including both the effects of amplified spontaneous emission (ASE) noise and nonlinear interference accumulation. Among these, estimating the ASE noise is the most challenging task

In this paper, we present Alibaba’s practices and views on open and disaggregated optical transport networks, with a focus on metro data center interconnects (DCIs). We first discuss technology developments that have enabled open optical transport networks, followed by a presentation of our open optical network architecture for DCI networks. We then describe an overall data center network architecture

Multi-vendor interoperability and disaggregation are attracting the interest of network operators as a way to avoid vendor lock-in, thus opening the market and, possibly, reducing costs. NETCONF, in concert with YANG data models, has been identified as the software defined networking (SDN) configuration protocol for these networks. Currently, several YANG models describe devices in a vendor-neutral