Switching Granularity Research Articles

Optimizing Spatial Channel Networks (SCNs) in Hierarchical Optical Cross-Connect (HOXC) architectures: Impact of wavelength switching granularity on performance

The increasing demand for network bandwidth highlights the critical need to enhance optical transmission systems. Utilizing the entire C-band for a single optical channel(OCh) eliminates the requirement for wavelength switching, prompting the emergence of spatial channel networks (SCNs). SCNs transform the optical layer into hierarchical spatial division multiplexing (SDM) and wavelength division multiplexing (WDM) layers through the implementation of hierarchical optical cross-connects (HOXCs). A HOXC comprises a spatial channel cross-connect (SXC) for spatial bypass switching and multiple wavelength cross-connects (WXCs) for wavelength channel switching, ensuring efficient optical transmission. Therefore, the design of the HOXC plays a pivotal role in determining both the device cost and network performance in SCNs. This study investigates the impact of wavelength switching granularity on core-selective switch (CSS)-based HOXC architectures. We propose an adaptive dynamic Routing, Spatial Channel, and Spectrum Assignment (RSCSA) algorithm to solve routing and resource allocation problems in SCNs. By examining SCN designs with varying wavelength switching granularities, we assess the overall network deployment cost, considering both network throughput and spectrum resource utilization. Our findings indicate that adjusting the granularity of wavelength switching in SCNs can significantly affect device costs and performance, highlighting the importance of identifying an optimal SCN design that strikes a balance between these factors. These insights offer valuable guidance for the practical planning and management of future SCN deployments.

HG: Leveraging Hybrid Switching Granularity to Balance Heterogeneous Data Center Traffic Load for Cloud-Based Industrial Applications

HG: Leveraging Hybrid Switching Granularity to Balance Heterogeneous Data Center Traffic Load for Cloud-Based Industrial Applications

Load balancing for heterogeneous traffic in datacenter networks

In modern datacenter networks (DCNs), the overwhelming heterogeneous flows have various stringent demands, ranging from delay-sensitive short flows, throughput-sensitive long flows to best-effort flows without deadline. Recently, many load balancing schemes are proposed to deliver good performance for datacenter applications. However, the existing solutions cannot meet all the above requirements simultaneously. Especially, the short flows experience head-of-line blocking due to queued behind the long and best-effort flows. The long flows often suffer from throughput degradation due to bursty congestion. To solve these issues, we present LBT, a traffic-differentiated load balancer. The key design point of LBT is to adaptively adjust the switching granularity of long flows and best-effort flows according to the two calculated switching thresholds based on the traffic strength. Specifically, under heavy load, the switching granularity is increased to guarantee required bandwidth capacity for delay-sensitive short flows to finish quickly. In contrary, the switching granularity is reduced to enable the long flows to make full of parallel equal-cost paths. Moreover, we adopt different routing strategies for the three different categories flows. We conduct NS-2 simulations to evaluate the effectiveness of LBT. The experimental results show that LBT significantly reduces the average flow completion time of short flows by up to 55.9% ∼ 65.4% compared to the state-of-the-art solutions and achieves high throughput for long flows concurrently.

Asymmetry-Aware Load Balancing With Adaptive Switching Granularity in Data Center

Datacenter networks provide large bisection bandwidth by load balancing traffic over rich parallel paths in multi-rooted tree topologies. Nevertheless, production datacenters operate under various path diversities caused by traffic dynamics, hardware failures and heterogeneous switching equipment. Therefore, the load balancing schemes in data center should be resilient to network asymmetry. Prior fine-grained schemes such as RPS and Presto are prone to experience packet reordering problem under asymmetric topology since they split flows into small units which are spread across all parallel paths. The coarse-grained solutions such as ECMP and LetFlow effectively avoid packet reordering, but easily leading to under-utilization of multiple paths. To solve these problems, we propose a load balancing mechanism called AG, which adaptively adjusts switching granularity according to the asymmetric degree of multiple paths. AG increases switching granularity to alleviate packet reordering under large degrees of topology asymmetry, while reducing switching granularity to obtain high link utilization under small degrees of topology asymmetry. Moreover, we design a switch-based scheme which measures the difference of one-way delay of multiple paths to obtain accurate state of topology asymmetry with low overhead. AG is a practical switch-based solution without modification at end hosts. The experimental results of NS2 simulations and real implementation show that AG reduces the average and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$99^{th}$</tex-math> </inline-formula> flow completion time by up to 54% and 65% compared with the state-of-the-art load balancing schemes, respectively.

Energy Efficient Waveband Translucent Optical Burst Switching Network

The fast development of translucent Optical Burst Switching (OBS) technology, which employs multiple wavelengths per fiber, increases the size (i.e., the number of ports) as well as the cost and power consumption of Optic Cross-Connects (OXCs). This paper studies the impact of OBS network parameter settings, where switching is performed at the Waveband Switching (WS) granularity using an end-to-end grouping method to reduce the number of lightpaths and switch ports. The simulation results illustrate that using OBS networks with WS by the suitable parameter settings, namely the Burstification Time (BT) and waveband granularity, offers considerable energy savings in the core network compared to using an OBS network without WS, where overall power consumption is decreased by maximizing BT values and waveband granularity.

Adjusting Switching Granularity of Load Balancing for Heterogeneous Datacenter Traffic

The state-of-the-art datacenter load balancing designs commonly optimize bisection bandwidth with homogeneous switching granularity. Their performances surprisingly degrade under mixed traffic containing both short and long flows. Specifically, the short flows suffer from long-tailed delay, while the throughputs of long flows also degrade dramatically due to low link utilization and packet reordering. To solve these problems, we design a traffic-aware load balancing (TLB) scheme to adaptively adjust the switching granularity of long flows according to the load strength of short ones. Under the heavy load of short flows, the long flows use large switching granularity to help short ones obtain more opportunities in choosing short queues to complete quickly. On the contrary, the long flows reroute flexibly with small switching granularity to achieve high throughput. Furthermore, under extremely bursty scenario, we utilize the packet slicing scheme for long flows to release bandwidth for short ones. The experimental results of NS2 simulation and testbed implementation show that TLB significantly reduces the average flow completion time of short flows by 16%-67% over the state-of-the-art load balancers and achieves the high throughput for long flows. Moreover, for extreme bursty case, at the acceptable throughput degradation of long flows, TLB with packet slicing reduces the deadline missing ratio of bursty short flows by up to 80%.

A novel channel-based model for the problem of routing, space, and spectrum assignment

Space-division multiplexing (SDM) is regarded as one of the most promising technologies to satisfy the explosively growing internet traffic. Elastic optical networks with SDM is one of the newest network architectures for network planning in the future. However, the resource allocation problem in these networks becomes more complicated due to the expansion of spatial dimensions. In this paper, we propose a novel channel-based integer linear programming (ILP) model for the problem of routing, space, and spectrum assignment (RSSA) in consideration of space lane change in SDM-EON. To evaluate our model, we make a comparison with the slot-based model [15] via simulation experiments. Different spatial switching granularities are considered in our performance evaluation because they will greatly change the detailed results of allocation. By the numerical results, we find that our novel model has an overwhelming advantage over the previous slot-based one in computing time for the optimization process.

Comparison of switching policies in terms of switching cost and network performance in static SDM-EONs

In this paper, we concentrate on the comparison of different switching policies, as well as their corresponding spatially-spectrally flexible super-channel transmission technologies, in static SDM-EONs. These switching policies are different due to their different spatial switching granularities and/or whether the space lane change (SLC) is supported. According to our simulation results, the switching policy with a finer switching granularity can achieve better network performance in terms of required frequency slices in the networks but meanwhile results in higher device cost. Moreover, we find that the application of SLC can only provide negligible improvements (0.1% ~ 3.1%) on network performance. SLC is encouraged only when the spectrum resource is highly valued by network operators compared to the additional device cost it brings. Moreover, in some previous works, the application of SLC can achieve a 7% ~ 14% improvement on the network throughput in dynamic network scenarios, especially when a finer spatial switching granularity is applied. Consequently, the results in this paper suggest that such an improvement is likely to be achieved by the means of network planning, such as the design of an efficient algorithm considering spectrum defragmentation, because if the re-routing/re-assignment of spectrum is allowed, the dynamic scenario can be treated as a sequence of static scenarios that change with time.

Evaluation of Device Cost, Power Consumption, and Network Performance in Spatially and Spectrally Flexible SDM Optical Networks

To keep pace with the rapidly increasing network traffic demand anticipated in the coming years, space-division multiplexing (SDM) has become a promising technology for overcoming the limitations of the current wavelength-division multiplexing based optical networks. The key advantage of SDM-based optical transmission is that it increases the network capacity by extending the available spatial dimensions. In this context, several innovative technologies have been proposed to support spatially and spectrally flexible all-optical transmission. One typical technology of this kind is called spatial and spectral super-channel (Spa & Spe SpCh) transmission. Newly designed Spa & Spe SpCh transceivers can support high-speed transmission with excellent spectral efficiency by allowing the optical carriers to be flexibly distributed in both the spatial and spectral domains without guardbands. In addition, SDM-based reconfigurable optical add/drop multiplexers (ROADMs) with varying spatial switching granularities and add/drop ports have been developed to support super-channel transmission (e.g., routing and add/drop). Moreover, ROADMs with spatial lane change support, which can further improve the routing flexibility in the network layer, have also been proposed in recent years. Different modes of implementation of the aforementioned technologies have distinct advantages and disadvantages. These technologies can be combined in various ways to support different types of SDM transmission, leading to variable network performance. In this paper, we evaluate the device cost, power consumption, and network performance of SDM transmission systems based on different implementations of these technologies to serve as a reference for future research.

Petascale: A Scalable Buffer-Less All-Optical Network for Cloud Computing Data Center

Optical packet switching is considered as a long-term solution for future data center networks due to their technological strengths, including high throughput, fine switching granularity, and excellent flexibility. However, most prior optical designs are either difficult to scale, costly to solve the packet collision, or inflexible to exploit the multiple wavelengths to increase the end-to-end connectivity. To this end, we present PETASCALE, a scalable, lossless, and high-performance optical data center network. By embedding full-mesh into a bipartite graph, PETASCALE is able to scale beyond 60 000 servers while achieving up to 2.5 and 2 times saving in a number of switches and cables, respectively, compared with fat tree topology. PETASCALE leverages the negative acknowledgment (NACK) and retransmission scheme to solve the packet collision, thus eliminating the complex and costly buffers. Then by leveraging a state retention mechanism, the contention can be notified over multiple hops in near real time. To further improve the bandwidth utilization, a wavelength routing algorithm is proposed to restrict the packet collision domain within the source pod. Moreover, PETASCALE designs a novel switch structure to support both the multi-hop NACK and wavelength routing. Our simulation results show that PETASCALE is able to reduce the end-to-end latency by more than 50% compared with an electrical fat tree network. For throughput, PETASCALE can deliver about 89% bisection bandwidth of a non-blocking network under uniform traffic pattern. While under the local traffic pattern, it can even achieve higher throughput than fat tree and other optical designs.

Compensation of filter cascading effects and non‐linearities in flexible multi‐carrier‐based optical networks using a complex‐kernel‐based support vector machine

Filter cascading effects are identified and compensated in flexible coherent multi-carrier optical networks using, for the first time, a complex-valued support vector machine (C-SVM) non-linear equaliser which is compared to phase-conjugated subcarrier-coding (PC-SC)-based non-linearity compensation. The transmission performance of super-channel-based dual-polarisation coherent multi-band optical OFDM (DP-MB-OFDM) is analysed in a flexible network with two-stage wavelength selective-switch reconfigurable optical add-drop multiplexer for coarse and fine switching granularity. It is shown that filter cascading effects have significant impact only on edge OFDM sub-bands. On the other hand, C-SVM outperforms PC-SC resulting in an extension of the transmission-reach, for instance, by 420 km when employing 32-quadrature amplitude modulation at a targeted bit-error-rate of 10−3. This occurs since C-SVM can compensate more effectively stochastic-induced nonlinear cross-talk effects. Moreover, the interplay between polarisation-mode dispersion (PMD) and fibre non-linearity is also investigated in DP-MB-OFDM, revealing that a high PMD causes time fluctuation on the non-linear interaction affecting the balance of the ‘twin-subcarriers’ in PS-SC.

Adaptability Analysis for IP Switching and Optical Switching in Geographically Distributed Inter-Datacenter Networks

The unexpected growth of cloud services lead to a dramatic increase in the network capital expenditure (CAPEX) and latency in geographically distributed inter-datacenter networks. In this paper, an adaptability analysis is proposed on CAPEX and forwarding delay for IP switching and optical transport network (OTN) switching in distributed inter-datacenter networks. By abstracting the switching behavior of the IP routers and OTN equipment, the IP nodes, and OTN nodes are mapped to the switching matrix of CLOS switching network. A unified network-level connection model is established based on CLOS switching network to meet the needs of connectivity. Then, the hardware costs and the forwarding delay are evaluated to find out the bandwidth threshold (BDT) which decides the most suitable switching mode for a specific switching granularity. The adaptability of IP switching and OTN switching under different switching granularities and port rates is performed based on the simulation platform in terms of hardware cost, optical port cost, and forwarding delay. Simulation results show that the BDT based on hardware cost is 280 Mbps when switching granularity is 1.25 Gb/s. For 2.5 Gb/s switching granularity, when average bandwidth between multiple datacenters is higher than 600 Mbps, OTN switching has more advantages than IP switching on capital expenditure, especially when port rate of the equipment is high. In addition, the simulation results also verify that the forwarding delay is reduced obviously with OTN switching.

Impact of Spatial and Spectral Granularity on the Performance of SDM Networks Based on Spatial Superchannel Switching

Spatially integrated switching architectures have been recently investigated in an attempt to provide switching capability for networks based on spatial division multiplexing (SDM) fibers, as well as to reduce the implementation cost. These architectures rely on the following switching paradigms, furnishing different degrees of spectral and spatial switching granularity: independent switching, which offers full spatial-spectral flexibility; joint-switching, which treats all spatial modes as a single entity; and fractional-joint switching, whereby subgroups of spatial modes are switched together as independent units. The last two paradigms are categorized as spatial group switching solutions since the spatial resources (modes, cores, or single-mode fibers) are switched in groups. In this paper, we compare the performance (in terms of spectral utilization, data occupancy, and network switching infrastructure cost) of the SDM switching paradigms listed above for varying spatial and spectral switching granularities in a network planning scenario. The spatial granularity is related to the grouping of the spatial resources, whereas the spectral granularity depends on the channel baud rate and the spectral resolution supported by wavelength selective switches (WSS). We consider two WSS technologies for handling of the SDM switching paradigms: 1) the current WSS realization, 2) WSS technology with a factor-two resolution improvement. Bundles of single-mode fibers are assumed across all links as a near-term SDM solution. Results show that the performance of all switching paradigms converge as the size of the traffic demands increases, but finer spatial and spectral granularity can lead to significant performance improvement for small traffic demands. Additionally, we demonstrate that spectral switching granularity must be adaptable with respect to the size of the traffic in order to have a globally optimum spectrum utilization in an SDM network. Finally, we calculate the number of required WSSs and their port count for each of the switching architectures under evaluation, and estimate the switching-related cost of an SDM network, assuming the current WSS realization as well as the improved resolution WSS technology.

LCoS-Based Wavelength-Selective Switch for Future Finer-Grid Elastic Optical Networks Capable of All-Optical Wavelength Conversion

A finer-grid wavelength-selective switch (WSS) based on liquid crystal on silicon is proposed, fabricated, and demonstrated. Based on the cost-effective method, namely combined lenses technique, the focal length is increased so that both the bandwidth setting resolution and grid granularity is improved from 12.5 to 6.25 GHz compared with the conventional WSS. To demonstrate its utility, we apply this finer-grid WSS to a reconfigurable optical add/drop multiplexer structure and an all-optical wavelength conversion (AOWC) module. To enable a finer-grid WSS, the performance of a finer-grid elastic optical network (EON) capable of AOWC is also investigated. Different from the conventional AOWC scheme for fixed-grid WDM networks, we propose and experimentally demonstrate a four-wave-mixing-based AOWC module specifically for EON. In addition to physical experiments, an optical network's control and management scheme corresponding to the designed physical scenario is also investigated. Experimental and simulation results show that the proposed method achieves higher spectrum efficiency, lower blocking probability, finer switching granularity, and higher conversion resolution.

Survey of Photonic Switching Architectures and Technologies in Support of Spatially and Spectrally Flexible Optical Networking [Invited

As traffic volumes carried by optical networks continue to grow by tens of percent year over year, we are rapidly approaching the capacity limit of the conventional communication band within a single-mode fiber. New measures such as elastic optical networking, spectral extension to multi-bands, and spatial expansion to additional fiber overlays or new fiber types are all being considered as potential solutions, whether near term or far. In this tutorial paper, we survey the photonic switching hardware solutions in support of evolving optical networking solutions enabling capacity expansion based on the proposed approaches. We also suggest how reconfigurable add/drop multiplexing nodes will evolve under these scenarios and gauge their properties and relative cost scalings. We identify that the switching technologies continue to evolve and offer network operators the required flexibility in routing information channels in both the spectral and spatial domains. New wavelength-selective switch designs can now support greater resolution, increased functionality and packing density, as well as operation with multiple input and output ports. Various switching constraints can be applied, such as routing of complete spatial superchannels, in an effort to reduce the network cost and simplify the routing protocols and managed pathway count. However, such constraints also reduce the transport efficiency when the network is only partially loaded, and may incur fragmentation. System tradeoffs between switching granularity and implementation complexity and cost will have to be carefully considered for future high-capacity SDM–WDM optical networks. In this work, we present the first cost comparisons, to our knowledge, of the different approaches in an effort to quantify such tradeoffs.

Datacenter-Oriented Elastic Optical Networks: Architecture, Operation, and Solutions

With the exponentially increasing Internet traffic and emergence of more versatile and heterogeneous applications, the design of datacenter networks (DCNs) is subject to unprecedented requirements for larger capacity and more flexible switching granularities. Envisioning Optical-Orthogonal Frequency Division Multiplexing (O-OFDM) as a promising candidate for such a scenario, we motivate the use of O-OFDM as the underlying switching technology in order to provide sufficient switching capacity and elastic bandwidth allocation. For this purpose, this article reviews the recent progresses of DCN deployment and assesses the scenario where the O-OFDM transmission and switching technology is employed in the underlying transport plane. We discuss the key issues of the datacenter-oriented O-OFDM optical networks, and in particular, elaborate on a number of open issues and solutions including system interconnection architecture, routing and resource assignment, survivability, and energy-efficiency.

Optical network scaling: roles of spectral and spatial aggregation.

As the bit rates of routed data streams exceed the throughput of single wavelength-division multiplexing channels, spectral and spatial traffic aggregation become essential for optical network scaling. These aggregation techniques reduce network routing complexity by increasing spectral efficiency to decrease the number of fibers, and by increasing switching granularity to decrease the number of switching components. Spectral aggregation yields a modest decrease in the number of fibers but a substantial decrease in the number of switching components. Spatial aggregation yields a substantial decrease in both the number of fibers and the number of switching components. To quantify routing complexity reduction, we analyze the number of multi-cast and wavelength-selective switches required in a colorless, directionless and contentionless reconfigurable optical add-drop multiplexer architecture. Traffic aggregation has two potential drawbacks: reduced routing power and increased switching component size.

Evaluating Availability of Optical Networks Based on Self-Healing Network Function Programmable ROADMs

Due to the large transmission speeds and enormous volume of transferred data, network reliability performance and cost-efficiency are among the key concerns in optical network design. Reducing the number of used optical components with higher failure probability within nodes represents a promising approach for achieving reliable and cost-effective optical network operation as it reduces the correlated risk of connection failures and enables reusing idle components as redundancy for failure recovery. This can result in greater overall network availability and lower loss of data and related revenue. Recently introduced synthetic network function programmable optical nodes implemented by architecture on demand (AoD) support the aforementioned approach by offering high levels of flexibility, modularity, and scalability. In AoD nodes, an optical backplane (i.e., optical switch) hosts optical components and enables arbitrary node configurations by cross-connecting attached modules. As a result, each lightpath passing through the node uses only the components necessary for fulfilling the switching and processing requirements. AoD nodes can perform switching at the wavelength and waveband granularity and also support switching of lightpaths at the fiber level by connecting an input fiber directly to the targeted output, referred to as fiber switching (FS). The latter functionality is particularly beneficial for the availability aspect, as it helps decrease the number of failure-prone components traversed by each lightpath, allowing them to be reused as redundancy. In this paper we demonstrate and evaluate self-healing capabilities of AoD nodes arising from their flexibility and ability to employ idle components for failure recovery. To improve efficiency of self-healing by increasing the number of idle components within nodes, we propose a routing algorithm which obtains a targeted portion of lightpaths switched at the fiber level, called the enforced FS (EFS) algorithm. We study the impact of AoD on network availability at different traffic switching granularities and compare it to traditional hard-wired node architecture via simulation. The results show significant improvements of availability and recovery time due to node-level restoration, with reduced network outage time and operator revenue losses. Finally, to the best of our knowledge, for the first time we experimentally demonstrate two novel hard-wired and synthetic reconfigurable optical add–drop multiplexer architectures with redundancy and all-optical self-healing capabilities.

Impact of the Electronic Architecture of Optical Slot Switching Nodes on Latency in Ring Networks

Optical slot switching has formerly been proposed as a flexible solution for metropolitan ring networks to carry data traffic with a subwavelength switching granularity and with good energy efficiency, which is enabled by optical transparency. In this paper, we propose for the first time, to the best of our knowledge, several architectures for the electronic side of optical slot switching nodes to increase flexibility through the addition of electronic switches, working either at client packet granularity or at slot granularity. Such electronic switches can be located at either the transmitter side or receiver side, or at both sides of a node, thereby decreasing traffic latency, at the expense of increased node cost and/or energy consumption. This paper focuses on the latency aspect. We investigate the impact of a timer that can be used to upper bound the slot insertion time on the medium. We also propose a novel client packet queuing model in an optical slot switching ring and assess and compare the latency of these node architectures analytically and with simulations.

The study of multi-granularity switching based on parallel processing routing technology

A novel parallel processing optical code label-switched paths (PP-OC-LSPs) is proposed to achieve efficient conversion performance for core router and large throughput in optical network, which combines the merits of optical label switching (OLS), optical code-generalized multi-protocol label switching (OC-GMPLS), and optical code division multiplexing-paths (OCDM-paths) technology. In the proposed technology, the smallest switching granularity is an optical code which carries the label information of data packets and would be parallel converted in the core router. In the edge node, the label and payload are separated by using the optical polarity characteristics, and encoded/decoded with two different code series based on OCDM techniques so as to process them in parallel. Compared with the OLS, its switching capability has been extended to support fiber switching, wavelength switching, and OCDM switching. We present simulation results to demonstrate its performance over OCDM-paths technology.