Optical interconnection array and networking method therefor, optical signal transmission method, and related device

By dividing the optical interconnect array into multiple networking layers and using optical switches to connect the ports, bypassing irrelevant transmission nodes, and replacing device losses with waveguide losses, the problem of excessive link loss in optical interconnect technology is solved, thereby improving system stability and reliability.

WO2026046121A1PCT designated stage Publication Date: 2026-03-05HUAWEI TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-08-25
Publication Date
2026-03-05

AI Technical Summary

Technical Problem

During the large-scale application of optical interconnect technology in data centers, the channel loss problem of optical interconnect links is serious, leading to communication interruptions and affecting system stability and reliability.

Method used

The optical interconnect array is divided into multiple networking layers, each layer consisting of multiple lower-level arrays. The input and output ports are connected one-to-one by optical switches, bypassing irrelevant transmission nodes and using waveguide loss to replace device loss.

Benefits of technology

It significantly reduces the link loss of the overall optical interconnect array, improves the stability and reliability of the system, and reduces the risk of communication interruption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025116754_05032026_PF_FP_ABST
    Figure CN2025116754_05032026_PF_FP_ABST
Patent Text Reader

Abstract

Disclosed in embodiments of the present application are an optical interconnection array and a networking method therefor, an optical signal transmission method, and a related device. The optical interconnection array comprises at least one networking level; each networking level comprises a networking array composed of a plurality of lower-level arrays, and the lower-level array located at the bottommost level is a basic unit that is a topological structure composed of a plurality of transmission nodes; each lower-level array comprises a plurality of ingress ports and a plurality of egress ports; the plurality of ingress ports of each lower-level array located in the x dimension are respectively connected on a one-to-one basis by means of first optical switches; and the plurality of egress ports of each lower-level array located in the y dimension are respectively connected on a one-to-one basis by means of second optical switches. By dividing the optical interconnection array into a plurality of optical interconnection array units, the link loss caused by interconnection devices in a link is reduced, thereby reducing the link loss of the overall optical interconnection array.
Need to check novelty before this filing date? Find Prior Art

Description

Optical interconnect arrays and their networking methods, optical signal transmission methods and related equipment

[0001] This application claims priority to Chinese Patent Application No. 202411220545.3, filed with the State Intellectual Property Office of China on August 31, 2024, entitled "Optical Interconnect Array and Networking Method Thereof, Optical Signal Transmission Method and Related Equipment", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of optical transmission technology, and in particular to an optical interconnect array and its networking method, an optical signal transmission method, and related equipment. Background Technology

[0003] With the development of information technology, especially the booming development of cloud computing, big data, and artificial intelligence, the requirements for data transmission rates and processing capabilities are gradually increasing. The continuous improvement of signal modulation rates is driving the development of communication technology. Due to its significant advantages such as high bandwidth, long-distance transmission, strong anti-interference capabilities, and low signal attenuation, fiber optic communication has become an ideal choice for solving the problem of high-speed, high-capacity data transmission. Therefore, "fiber-to-the-home" (FTTH) is gradually becoming an important trend for improving data center performance and optimizing network architecture.

[0004] Optical interconnect technology is a technology that enables high-speed data transmission within computers or data centers using optical fibers or other optical transmission media. It has already been applied in data center inter-cabinet interconnects. This technology reduces photoelectric conversion overhead, achieves all-optical switching, lowers data exchange latency, and is compatible with optical modules of different speeds, enabling flexible and configurable interconnects on demand. With continuous technological advancements, the application scenarios of optical interconnects are gradually expanding. From initial inter-cabinet interconnects, the possibilities for interconnects between boards within a cabinet and even between individual chips are now being explored in depth.

[0005] However, in the large-scale application of optical interconnect technology in cabinet scenarios, in addition to basic performance requirements such as interconnect cost, channel bandwidth, and configurability, the channel loss of the optoelectronic interconnect link is particularly critical. Once the link loss exceeds the system's power budget, it will directly lead to communication interruption, affecting the stability and reliability of the entire system. Therefore, how to reduce the link loss of optical interconnect is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] This application provides an optical interconnect array and its networking method, an optical signal transmission method and related equipment. By dividing the optical interconnect array into multiple optical interconnect array units, the link loss caused by interconnect devices in the link is reduced, thereby reducing the overall link loss of the optical interconnect array.

[0007] The first aspect of this application provides an optical interconnect array, including at least one networking layer;

[0008] Each network layer includes a network array composed of multiple lower-level arrays. A lower-level array can be a complete transmission node array or an array composed of multiple transmission node arrays. The lower-level array at the bottom layer is the basic unit, and the basic unit is a topology composed of multiple transmission nodes.

[0009] The lower-level array includes M input ports and N output ports, where M and N are both integers greater than 1;

[0010] The M input ports of the lower-layer array located in the x-dimensional direction are connected one-to-one via a first optical switch;

[0011] The N output ports of the lower-level array located in the y-dimensional plane are connected one-to-one by a second optical switch.

[0012] It is understandable that the array can be viewed as a two-dimensional matrix structure, thus including two dimensions in the same network layer, namely the x dimension and the y dimension. Since each lower-level array includes M input ports, in the x dimension, the M input ports of each lower-level array are connected one-to-one through the first optical switch. Similarly, in the y dimension, the N output ports of each lower-level array are connected one-to-one through the second optical switch.

[0013] In this embodiment, the overall optical interconnect array is divided into multiple networking layers, and optical switches are used to connect the input port in the x-dimensional direction and the output port in the y-dimensional direction of the same networking array. This allows the optical signal to bypass irrelevant transmission nodes when passing through the optical interconnect array, using optical switches and waveguide links. Waveguide loss is used instead of device loss. Since waveguide loss is much smaller than device loss, the link loss of the overall optical interconnect array can be significantly reduced.

[0014] In one possible implementation,

[0015] The M input ports of the lower-level array located in the x-dimensional plane are connected one-to-one via a first optical switch, specifically including:

[0016] The M input ports of the first lower-layer array are respectively connected to the M input ports of the second lower-layer array through M first optical switches. The first lower-layer array and the second lower-layer array are adjacent lower-layer arrays in the x-dimensional direction.

[0017] The N output ports of the lower-level array located in the y-axis are connected one-to-one via a second optical switch, specifically including:

[0018] The N output ports of the third lower-layer array are connected to the N output ports of the fourth lower-layer array through N second optical switches. The third lower-layer array and the fourth lower-layer array are adjacent lower-layer arrays in the y-dimensional direction.

[0019] In this embodiment, two adjacent lower-level arrays located in the x-axis can be defined as a first lower-level array and a second lower-level array. It is understood that both the first and second lower-level arrays include M input ports. Therefore, the M input ports of the first lower-level array can be connected to the M input ports of the second lower-level array through M first optical switches. Similarly, two adjacent lower-level arrays located in the y-axis can be defined as a third lower-level array and a fourth lower-level array. Both the third and fourth lower-level arrays include N output ports. Therefore, the N output ports of the third lower-level array can be connected to the N output ports of the fourth lower-level array through N second optical switches.

[0020] In one possible implementation, the transmission nodes in the basic unit form a torus topology.

[0021] In this embodiment, the basic unit is preferably a torus topology. Due to the directness and ring connection of the torus network, the transmission path of the optical signal between transmission nodes is shorter and the link loss is smaller.

[0022] In one possible implementation, the first optical switch and / or the second optical switch are optical switching devices that control the on / off state of optical signals based on the electrostatic attraction effect.

[0023] In another possible implementation, the first optical switch and / or the second optical switch are optical switching devices that control the on / off state of optical signals based on the mode interference effect.

[0024] In another possible implementation, the first optical switch and / or the second optical switch are optical switching devices that control the on / off state of optical signals based on the mode transmission effect.

[0025] In one possible implementation, in adjacent network layers, the optical signal in the upper waveguide is coupled to the lower waveguide based on an evanescent wave.

[0026] In one possible implementation, the waveguides in the optical interconnect array include horizontal waveguides and vertical waveguides, which are cross-waveguides based on a multilayer silicon nitride structure.

[0027] In another possible implementation, waveguides in adjacent network layers are positioned on different planes.

[0028] One possible implementation also includes a photodetector;

[0029] The photodetector is connected to the first optical switch and / or the second optical switch. The photodetector is used to detect whether an optical signal is input to the optical path of the first optical switch and / or the second optical switch.

[0030] In this embodiment, the photodetector can also be referred to as a photodetector module. The photodetector can be a photodiode (PD). The multiple photodetectors included in the optical interconnect array are used to detect whether the optical signal is transmitted along the transmission path.

[0031] In a further possible implementation, a processing module is also included;

[0032] The processing module is connected to the photodetector, which is also used to send detection information to the processing module. The detection information is used to indicate whether the optical signal is input to the optical path of the first optical switch and / or the second optical switch.

[0033] In this embodiment of the application, the processing module is connected to the photodetector, and the photodetector is also used to send detection information to the processing module. The detection information is used to indicate whether the optical signal is input to the optical path of the first optical switch and / or the second optical switch.

[0034] A second aspect of this application provides an optical transmission device, including K optical transmitting devices, L optical receiving devices, and an optical interconnect array as claimed in any one of claims 1 to 11, wherein the optical interconnect array includes K input ports and L output ports, wherein K and L are both integers greater than 1;

[0035] K optical transmitting devices are connected to K input ports, and L optical receiving devices are connected to L output ports.

[0036] A third aspect of this application provides a networking method for an optical transmission network, comprising:

[0037] Determine the node interconnection scale of the optical transmission network;

[0038] Based on the node interconnection scale, the link loss under different basic units is calculated through traversal. The basic unit includes a topology composed of multiple transmission nodes.

[0039] The basic unit with the minimum link loss is determined as the target unit;

[0040] Based on the topology and node interconnection scale of the target unit, the networking level and the networking array of each level are determined. Each networking array consists of multiple lower-level arrays, with the lowest-level lower-level array being the target unit.

[0041] The optical transmission network is constructed based on the target unit and the networking hierarchy. The lower-layer array includes M input ports and N output ports, where M and N are both integers greater than 1. The M input ports of the lower-layer array located in the x-dimensional direction are connected one-to-one through the first optical switch, and the N output ports of the lower-layer array located in the y-dimensional direction are connected one-to-one through the second optical switch.

[0042] The fourth aspect of this application provides an optical signal transmission method applied to the optical interconnect array described in the first aspect above, wherein the inlet and outlet ports of the optical interconnect array correspond to the coordinate values ​​of the x-axis and y-axis in a two-dimensional coordinate system, respectively. The method includes:

[0043] Determine the target input port and target output port of the optical signal;

[0044] Determine the target coordinates in a two-dimensional coordinate system based on the target inlet and outlet ports.

[0045] The target lower-level array is determined sequentially according to the network hierarchy. The target lower-level array is the lower-level array corresponding to the target coordinates under each network hierarchy.

[0046] The optical transmission links from the target input port and the target output port to the target array unit are connected by controlling the first optical switch and the second optical switch respectively, so that the transmission path of the optical signal bypasses the non-target lower layer array.

[0047] The fifth aspect of this application provides a chip including the optical interconnect array described in the first aspect above.

[0048] The sixth aspect of this application provides an optical communication device, including one or more chips as described in the fifth aspect above.

[0049] The seventh aspect of this application provides a computing device that can be used to execute computer programs or computer instructions stored in memory to perform the methods provided in the third or fourth aspects above.

[0050] The eighth aspect of this application provides a computer program product including instructions that, when run on a computer, cause the computer to perform the method provided in the third or fourth aspect above.

[0051] The ninth aspect of this application provides a chip including a processor for connection to a memory, calling a program stored in the memory to cause the processor to perform the method provided in the third or fourth aspect above.

[0052] The beneficial effects of the technical solutions provided in aspects two through six above can be referred to the beneficial effects of the technical solutions in aspect one, and will not be repeated here. Attached Figure Description

[0053] Figure 1 is a schematic diagram of an application scenario of the optical interconnect array in this application;

[0054] Figure 2 is a schematic diagram of an optical interconnect array in related technologies;

[0055] Figure 3 is a schematic diagram of the structure of an optical interconnect array provided in an embodiment of this application;

[0056] Figure 4 is a schematic diagram of the structure of the lower layer array of the optical interconnect array provided in the embodiment of this application;

[0057] Figure 5 is a schematic diagram of the basic unit of the optical interconnect array provided in the embodiment of this application;

[0058] Figure 6 is a schematic diagram of another optical interconnect array provided in an embodiment of this application;

[0059] Figure 7 is a schematic diagram of another optical interconnect array provided in an embodiment of this application;

[0060] Figure 8 is a schematic diagram of another optical interconnect array provided in an embodiment of this application.

[0061] Figure 9 is a flowchart of the optical signal transmission method provided in an embodiment of this application;

[0062] Figure 10 is a schematic diagram of the optical signal transmission method provided in the embodiment of this application;

[0063] Figure 11 is a flowchart of the networking method of the optical transmission network provided in the embodiment of this application. Detailed Implementation

[0064] This application provides an optical interconnect array and its networking method, optical signal transmission method and related equipment. By splitting the overall optical interconnect array into multiple networking layers, when the optical signal passes through the optical interconnect array, it can bypass irrelevant transmission nodes through optical switches and waveguide links, and replace device loss with waveguide loss. Since waveguide loss is much smaller than device loss, the link loss of the overall optical interconnect array can be significantly reduced.

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application are described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Those skilled in the art will understand that with the emergence of new application scenarios, the technical solutions of this application are also applicable to similar technical problems.

[0066] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules is not necessarily limited to those explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices. The naming or numbering of steps appearing in this application does not imply that the steps in the method flow must be performed in the chronological / logical order indicated by the naming or numbering. The execution order of named or numbered process steps can be changed according to the desired technical purpose, as long as the same or similar technical effect is achieved. The division of units in this application is a logical division. In practical applications, there may be other division methods. For example, multiple units may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the shown or discussed mutual coupling, direct coupling, or communication connection may be through some interface, and the indirect coupling or communication connection between units may be electrical or other similar forms, none of which are limited in this application. Furthermore, the units or sub-units described as separate components may or may not be physically separated, may or may not be physical units, or may be distributed among multiple circuit units. Some or all of the units can be selected to achieve the purpose of the solution in this application according to actual needs.

[0067] The technical solutions of this application can be applied to various optical communication systems. Figure 1 is a schematic diagram of an application scenario of the optical interconnect array in this application. As shown in Figure 1, an optical cross-connect (OXC) device is used. The OXC device has multiple ports at both ends for transmitting optical signals from different sources to a designated destination, thereby achieving routing functionality. The core component of the OXC device is the optical interconnect array. For example, an optical signal is input from port 7, and the transmission path of the optical signal can be changed through the optical interconnect array, allowing the optical signal to be output from the designated port 11 to the destination.

[0068] Figure 2 is a schematic diagram of an optical interconnect array in related technologies. As shown in Figure 2, the optical interconnect array has multiple rows and columns of transmission nodes. Each node is located at the intersection of two transmission paths, and an optical switch can be installed in each node. Optical signals are transmitted between any two adjacent transmission nodes. It is understandable that in the large-scale application of optical interconnect technology in cabinet scenarios, in addition to basic performance requirements such as interconnect cost, channel bandwidth, and configurability, the channel loss of the optoelectronic interconnect link is particularly critical. Once the link loss exceeds the system's power budget, it will directly lead to communication interruption, affecting the stability and reliability of the entire system.

[0069] To ensure the normal operation of the communication link, one solution is to sacrifice some cost and power consumption by introducing polarization-independent optical amplifiers into the optical link. Another solution is to continuously reduce link loss through various technical means, such as reducing the loss of individual interconnect switching devices through device design and process optimization. However, the loss of each device has a theoretical lower limit, so this approach has certain limitations.

[0070] To address the aforementioned issues, this application provides an optical interconnect array. Please refer to Figure 3, which is a schematic diagram of the structure of an optical interconnect array provided in an embodiment of this application.

[0071] In this embodiment of the application, the optical interconnect array includes at least one networking layer, and each networking layer includes a networking array composed of multiple lower-layer arrays, wherein the lower-layer array at the bottom layer is a basic unit, and the basic unit is a topology composed of multiple transmission nodes.

[0072] As shown in Figure 3, the 16 ports on the left are input ports, and the 16 ports at the bottom are output ports. This optical interconnect array comprises two layers; Figure 3 shows the second layer. Taking the second layer as an example, it includes four lower-layer arrays defined by dashed lines: lower-layer array 301, lower-layer array 302, lower-layer array 303, and lower-layer array 304. These four lower-layer arrays form a 2×2 network array.

[0073] When the lower-level array is not the bottom-level array, each lower-level array can be regarded as a network array composed of arrays of the next lower level. Since Figure 3 corresponds to the second level, the lower-level array in the second level is the network array of the first level. For ease of understanding, refer to Figure 4, which is a schematic diagram of the structure of the lower-level array of the optical interconnect array provided in the embodiment of this application.

[0074] As shown in Figure 4, the array in Figure 4 can be any one of the lower arrays 301 to 304 in Figure 3. This array is equivalent to the first-level networking array in the array shown in Figure 3. It also includes a 2×2 array composed of four lower arrays defined by dashed lines. Since the first level is already the lowest level of the networking layer, the array shown in Figure 3 is actually a networking array composed of multiple basic units, namely basic unit 401, basic unit 402, basic unit 403 and basic unit 404.

[0075] For ease of understanding, please refer to Figure 5, which is a schematic diagram of the basic unit of the optical interconnect array provided in the embodiment of this application. Each basic unit is a 4×4 array topology consisting of 16 transmission nodes. This topology describes the connection method and layout between the transmission nodes. An OXC with multiple input ports and multiple output ports can be formed through this topology. The basic unit can be a mesh topology or a torus topology, with a torus topology being preferred. Due to the directness and ring connection of the torus network, the transmission path of the optical signal between the transmission nodes is shorter, and the link loss is lower.

[0076] Each network layer's network array can be viewed as a two-dimensional matrix structure, thus including two dimensions within the same network layer: the x-dimensional dimension and the y-dimensional dimension. Each layer's network array consists of multiple lower-layer arrays, each of which can also be considered a smaller two-dimensional matrix. These lower-layer arrays are connected along the x and y dimensions via optical switches.

[0077] In the x-axis, the M input ports of each lower-level array are connected one-to-one with the corresponding input ports of adjacent or other designated lower-level arrays through a first set of optical switches (first optical switches). This connection allows optical signals to be transmitted in the horizontal direction (i.e., the x-axis). Similarly, in the y-axis, the N output ports of each lower-level array are connected one-to-one with the corresponding output ports of adjacent or other designated lower-level arrays through a second set of optical switches (second optical switches). This connection allows optical signals to be transmitted in the vertical direction (i.e., the y-axis).

[0078] Specifically, two adjacent lower-level arrays located in the x-dimensional direction can be defined as the first lower-level array and the second lower-level array. It can be understood that both the first and second lower-level arrays include M input ports. Therefore, the M input ports of the first lower-level array can be connected to the M input ports of the second lower-level array through M first optical switches. Similarly, two adjacent lower-level arrays located in the y-dimensional direction can be defined as the third lower-level array and the fourth lower-level array. Both the third and fourth lower-level arrays include N output ports. Therefore, the N output ports of the third lower-level array can be connected to the N output ports of the fourth lower-level array through N second optical switches.

[0079] For ease of understanding, please refer to Figure 4. Each lower-level array (basic unit) enclosed by dashed lines in Figure 4 includes 4 input ports and 4 output ports. Lower-level arrays 401 and 402 are equivalent to the first and second adjacent lower-level arrays in the x-axis. The 4 input ports of lower-level array 401 are connected to the 4 input ports of lower-level array 402 through 4 first optical switches 405. Similarly, lower-level arrays 403 and 404 are also equivalent to the first and second adjacent lower-level arrays in the x-axis. Likewise, lower-level arrays 401 and 403 are equivalent to the third and fourth adjacent lower-level arrays in the y-axis. That is, the 4 output ports of lower-level array 401 are connected to the 4 output ports of lower-level array 403 through 4 second optical switches 406. Similarly, lower-level arrays 402 and 404 are also equivalent to the third and fourth adjacent lower-level arrays in the y-axis.

[0080] It is understandable that, in the case of a large-scale optical transmission network, the optical interconnect array shown in Figure 3 can also be extended as a lower-level array of the third layer.

[0081] Similarly, when the scale of the optical transmission network is small, the networking layer can be single-level. Please refer to Figure 6, which is a schematic diagram of another optical interconnect array structure provided in an embodiment of this application.

[0082] As shown in Figure 6, the optical interconnect array includes only one networking layer. The lower array is the basic unit, which is similar to the basic unit shown in Figure 5. This is only an example and is not intended to limit the structure of the basic unit.

[0083] The optical interconnect array is a 3×3 network array composed of 9 lower-level arrays. Each lower-level array (basic unit) includes 4 input ports and 4 output ports. The combined optical interconnect array includes 12 input ports and 12 output ports.

[0084] It is understood that in the embodiments corresponding to Figures 3 and 6, the number of input ports and output ports of the networking array in each networking layer is the same. In addition, the embodiments of this application also provide an optical interconnect array, the number of input ports and output ports of which can be determined according to the combination method of the lower layer array or basic unit.

[0085] Please refer to Figures 7 and 8, which are schematic diagrams of the structures of two other optical interconnect arrays provided in the embodiments of this application.

[0086] As shown in Figure 7, the optical interconnect array includes only one networking layer. The lower array is the basic unit, which is similar to the basic unit shown in Figure 5. This is only an example and is not intended to limit the structure of the basic unit.

[0087] It is understood that the optical interconnect array is a 3×2 networking array composed of 6 lower-level arrays. Each lower-level array includes 4 input ports and 4 output ports, and the combined optical interconnect array includes 8 input ports and 12 output ports.

[0088] As shown in Figure 8, the optical interconnect array includes two networking layers. The area defined by the dashed line is the lower-level array of the second layer, which is a 1×3 networking array composed of three lower-level arrays. Each lower-level array includes four input ports and eight output ports. Any one of the lower-level arrays is a 2×1 networking array composed of two basic units.

[0089] Therefore, based on the structure of the optical interconnect array provided in the embodiments of this application, those skilled in the art can expand the optical interconnect array accordingly based on the lower-layer array or basic unit according to actual networking needs, so as to adapt it to a larger-scale optical transmission network.

[0090] Optical switches can dynamically change the transmission path of optical signals, thereby achieving flexible routing selection. By controlling the on / off state of the optical switch, precise control of the optical signal transmission path can be achieved. Based on this, this application also introduces an optical signal transmission method, the details of which are described in the relevant embodiment corresponding to Figure 9 below, and will not be repeated here.

[0091] In this embodiment, the overall optical interconnect array is divided into multiple networking layers, each consisting of a lower-level array. The ports of each lower-level array are connected via corresponding optical switches. This allows optical signals to bypass unnecessary transmission nodes during transmission within the optical interconnect array via a first and second optical switch, replacing device losses with waveguide loss. Since waveguide loss is much smaller than device loss, the optical interconnect array provided in this embodiment can significantly reduce the link loss of the overall optical interconnect array.

[0092] The loss reduction approach proposed in this application is not limited to reducing the loss of individual devices, but rather optimizes the optical links at the overall architecture level. It adopts a segmented networking approach to avoid the highest loss links and reduces the highest loss links through the idea of ​​amortization. At the same time, the improvement of the lowest loss does not affect the interconnection and communication of the overall architecture.

[0093] To provide a detailed description of the optical interconnect array provided in the embodiments of this application, the following supplementary explanations are provided regarding the details of the optical interconnect array provided in the embodiments of this application:

[0094] In one possible implementation, the first optical switch and / or the second optical switch are optical switching devices that control the on / off state of optical signals based on the electrostatic attraction effect.

[0095] It is understandable that optical switching devices that control the on / off state of optical signals based on the electrostatic attraction effect refer to electromagnetically driven optomechanical switches or electromagnetically actuated fiber optic switches that use electromagnetic force to control the on / off state of the optical path. These devices include movable parts, which may contain magnetic materials that can be attracted or repelled by the magnetic field generated by the electromagnetic actuator, thereby changing their position. In an optical switch, this movable part can directly control the on / off state of the optical path, for example, by moving a mirror, optical fiber, or grating to block or guide the light beam.

[0096] In another possible implementation, the first optical switch and / or the second optical switch are optical switching devices that control the on / off state of optical signals based on the mode interference effect.

[0097] As we can understand, optical switching devices that control the on / off state of optical signals based on the modal interference effect refer to devices that utilize the modal interference phenomenon generated when light propagates in a waveguide or optical fiber to control the switching of the optical signal path. The modal interference effect refers to the phenomenon where, as light propagates in a waveguide or optical fiber, different modes (such as the fundamental mode and higher-order modes) have different propagation constants and phase velocities, resulting in a phase difference after a certain distance, which in turn forms an interference pattern at the output. By controlling the excitation, propagation, and interference processes of these modes, the on / off state of the optical signal can be controlled. This optical switching device typically includes a mode excitation region and a mode interference region. The mode excitation region, through specific structural designs (such as multimode waveguides, gratings, fused abbreviated tapers, etc.), excites multiple modes of the optical signal during transmission; different modes of optical signals interfere in the mode interference region, forming specific interference patterns. By changing certain parameters of the device (such as temperature, stress, voltage, etc.), the intensity and phase of the mode interference can be controlled, thereby achieving control over the on / off state of the optical signal.

[0098] In another possible implementation, the first optical switch and / or the second optical switch are optical switching devices that control the on / off state of optical signals based on the mode propagation effect.

[0099] As is understandable, optical switching devices that control the on / off state of optical signals based on the mode transmission effect refer to switching devices that utilize the coupling effect between different modes when light propagates in a waveguide or optical fiber, thereby changing the transmission characteristics of the optical signal. The mode transmission effect refers to the energy exchange between different modes that were originally propagating independently when light propagates in a waveguide or optical fiber, caused by the inhomogeneity, bending, crossing, or other coupling mechanisms of the waveguide structure. This results in changes to the transmission characteristics of the optical signal (such as power distribution and phase relationship). By controlling these coupling mechanisms, the on / off state of the optical signal can be controlled. This optical switching device typically includes a coupling region, which is the key area where the coupling effect between different modes occurs. Its structural design and material selection have a significant impact on the coupling efficiency. Parameters used to adjust the coupling region (such as temperature, stress, voltage, etc.) control the intensity and phase of mode transmission, thereby controlling the on / off state of the optical signal.

[0100] In one possible implementation, in adjacent network layers, the optical signal in the upper waveguide is coupled to the lower waveguide based on an evanescent wave.

[0101] Understandably, since each network layer is formed by connecting lower-level arrays via optical switches, optical signals will inevitably travel from upper-level waveguides to lower-level waveguides. In optical communication and integrated optics, waveguides are structures used to guide and confine the propagation of optical signals within them. When multiple waveguides are designed to be sufficiently close, optical signal coupling can occur between them. One such coupling mechanism is through evanescent waves. Evanescent waves are a special type of optical wave formed by total internal reflection at the waveguide boundary. When a light wave propagates within a waveguide at an angle greater than the critical angle, most of the light energy propagates along the inside of the waveguide, but a small portion of the light energy penetrates the waveguide boundary, forming an evanescent wave. In adjacent network layers, if upper and lower waveguides are designed to be sufficiently close (typically at the nanometer scale), the evanescent wave of the optical signal in the upper waveguide will extend into the region of the lower waveguide during propagation. Similarly, the optical signal in the lower waveguide may also generate an evanescent wave, which overlaps with the evanescent wave in the upper waveguide. When these two evanescent waves overlap, energy exchange occurs between them, meaning the optical signal is coupled from the upper waveguide to the lower waveguide, or vice versa.

[0102] In one possible implementation, the waveguides in the optical interconnect array include horizontal waveguides and vertical waveguides, which are cross-waveguides based on a multilayer silicon nitride structure.

[0103] As can be understood, as shown in Figures 3 to 8, to construct complex optical networks and achieve efficient transmission and interconnection of optical signals, waveguides in optical interconnect arrays can be divided into two different types: horizontal waveguides and vertical waveguides. When horizontal and vertical waveguides need to intersect at a certain point, a cross-waveguide structure needs to be designed. Multilayer silicon nitride (SiN) structures are multilayer thin-film structures formed by stacking silicon nitride materials in a vertical direction. Silicon nitride is widely used in optical waveguide manufacturing due to its high refractive index, low loss, and good chemical stability. By precisely controlling the thickness and refractive index of each silicon nitride layer, multilayer structures with specific optical properties can be designed. Therefore, the cross-waveguide structure in an optical interconnect array can be based on multilayer silicon nitride.

[0104] In another possible implementation, waveguides in adjacent network layers are placed on different planes.

[0105] Understandably, in optical communication and integrated optics, optical signals of different wavelengths may be transmitted within the same system. If waveguides in adjacent layers are placed on the same plane, optical signals of different wavelengths may interfere with each other, affecting the transmission quality and stability. By employing a multi-layer structure, waveguides can be placed on different planes, reducing interference caused by waveguide intersections through spatial dimension, ensuring independent transmission of optical signals, and improving the stability of optical signal transmission.

[0106] In one possible implementation, the optical interconnect array also includes a photodetector;

[0107] The photodetector is connected to the first optical switch and / or the second optical switch. The photodetector is used to detect whether an optical signal is input to the optical path of the first optical switch and / or the second optical switch.

[0108] It is understandable that this photodetector can also be called a photodetector module. This photodetector can be a photodiode (PD). The multiple photodetectors included in the optical interconnect array are used to detect whether the optical signal is propagating along the transmission path.

[0109] Furthermore, the optical interconnect array also includes a processing module;

[0110] The processing module is connected to the photodetector, which is also used to send detection information to the processing module. The detection information is used to indicate whether the optical signal is input to the optical path of the first optical switch and / or the second optical switch.

[0111] Specifically, the optical interconnect array includes a first photodetector connected to the optical input port of a first optical switch. The first photodetector is also connected to a processing module. The first photodetector generates first detection information based on whether an optical signal has been input to the first optical switch. The first photodetector sends this first detection information to the processing module. The processing module determines whether the optical signal has been successfully input to the first optical switch based on the first detection information.

[0112] The optical interconnect array also includes a second photodetector. This second photodetector is connected to the optical input port of the optical switch of the transmission node used for transmitting optical signals. The second photodetector is also connected to a processing module. The second photodetector generates second detection information based on the state of the optical switch of the transmission node, indicating whether an optical signal has been input. The second photodetector sends this second detection information to the processing module. The processing module determines whether the optical signal has been successfully input to the optical switch of the transmission node based on the second detection information.

[0113] Similarly, each optical switch in the optical interconnect array can be connected to a photodetector via its optical input port and the processing module. Therefore, processing module 2 can determine whether an optical signal can be successfully input to the corresponding optical switch based on the detection information sent by each photodetector. The processing module can also quickly troubleshoot faulty optical switches during optical signal transmission. For example, if the processing module determines that the optical signal needs to be transmitted sequentially through the first optical switch, the optical switch at the transmission node, and the second optical switch, the processing module determines, based on the first detection information from the first photodetector, that the first optical switch is in a normal optical signal transmission state. Based on the second detection information from the second photodetector, the processing module determines that the optical switch at the transmission node is in a state where the optical signal cannot be transmitted normally. The processing module then determines that this optical switch is faulty.

[0114] The optical signal transmission method provided in the embodiments of this application will be described below.

[0115] This application provides an optical signal transmission method applied to the optical interconnect array shown in any one of Figures 3 to 8. In this method, a two-dimensional coordinate system is pre-constructed based on the optical interconnect array. Each input port of the optical interconnect array corresponds to a coordinate value on the x-axis of the two-dimensional coordinate system, and each output port corresponds to a coordinate value on the y-axis of the two-dimensional coordinate system. Please refer to Figure 9, which is a flowchart of the optical signal transmission method provided in this application. The method includes:

[0116] 901. Determine the target input port and target output port of the optical signal.

[0117] 902. Determine the target coordinates in a two-dimensional coordinate system based on the target inlet and outlet ports.

[0118] 903. Determine the target lower-level array according to the network hierarchy. The target lower-level array is the lower-level array corresponding to the target coordinates under each network hierarchy.

[0119] 904. By controlling the first optical switch and the second optical switch respectively, the optical transmission links from the target input port and the target output port to the target array unit are connected, so that the transmission path of the optical signal bypasses the non-target lower layer array.

[0120] In this embodiment, since the input port and output port correspond to the coordinate values ​​on the x-axis and y-axis respectively, after determining the target input port and target output port, the target coordinates on the two-dimensional coordinate system can be determined based on the port number. For example, please refer to Figure 10, which is a schematic diagram of the optical signal transmission method provided in this application embodiment. The structure of the optical interconnect array in Figure 10 is described in the corresponding embodiment of Figure 3, and the structure will not be described again here.

[0121] The optical interconnect array includes 16 input ports and 16 output ports. The target input port is the 3rd input port, and the target output port is the 15th output port, resulting in the target coordinates (3, 15) in the two-dimensional coordinate system.

[0122] Once the target coordinates are determined, the corresponding lower-level array at each network layer can be identified. As shown in Figure 10, based on the target coordinates (3,5), the target lower-level array at the second layer can be identified as lower-level array 302. In the first layer where lower-level array 302 is located, the basic unit is the basic unit in the upper right corner, corresponding to basic unit 402 in Figure 4.

[0123] By controlling the first and second optical switches located on the periphery of each array level, the optical transmission links from the target input port to the target array element and from the target output port to the target array element are connected. As shown in Figure 10, firstly, the first optical switch of the second level is controlled to connect the input port 3 and the lower array 302, and simultaneously, the second optical switch of the second level is controlled to connect the lower array 302 and the output port 15. Then, the first optical switch of the first level is controlled to connect the waveguide connected to the input port 3 to the basic element 402, and simultaneously, the second optical switch of the first level is controlled to connect the basic element 402 to the waveguide corresponding to the output port 15. Inside the basic element, the corresponding input and output ports are connected through transmission nodes.

[0124] As shown in Figure 10, the overall structure of the optical interconnect array is shown in the form of thin dashed lines. The thick solid lines are the waveguides through which the optical signal passes. The arrows indicate the waveguides that the optical signal passes through sequentially from the inlet port 3 to the outlet port 15. The solid rectangles are the transmission nodes through which the optical signal passes. Based on the optical interconnect array provided in this application embodiment, the optical signal can bypass the non-target lower layer array by controlling the first optical switch and the second optical switch. It can be understood that the non-target lower layer array refers to the lower layer array other than the target lower layer array.

[0125] The optical signal transmission method provided in this application embodiment, based on the optical interconnect array of this application embodiment, bypasses unnecessary transmission nodes through a first optical switch and a second optical switch, thereby achieving waveguide loss instead of device loss. Since waveguide loss is much smaller than device loss, the optical interconnect array provided in this application embodiment can significantly reduce the link loss of the overall optical interconnect array.

[0126] This application embodiment also provides a networking method for an optical transmission network. Please refer to Figure 11, which is a flowchart of the networking method for an optical transmission network provided in this application embodiment. The method includes:

[0127] 1101. Determine the node interconnection scale of the optical transmission network;

[0128] 1102. Based on the node interconnection scale, calculate the link loss under different basic units. The basic unit includes a topology composed of multiple transmission nodes.

[0129] 1103. The basic unit with the minimum link loss is determined as the target unit;

[0130] 1104. Based on the topology and node interconnection scale of the target unit, determine the networking level and the networking array of each level. Each networking array consists of multiple lower-level arrays, of which the lowest-level lower-level array is the target unit.

[0131] 1105. Based on target units and networking layers, an optical transmission network is networked. The lower-layer array includes M input ports and N output ports, where M and N are both integers greater than 1. The M input ports of the lower-layer array located in the x-dimensional direction are connected one-to-one through the first optical switch, and the N output ports of the lower-layer array located in the y-dimensional direction are connected one-to-one through the second optical switch.

[0132] In this embodiment, the key to networking an optical transmission network based on an optical interconnect array lies in determining the networking hierarchy of the optical interconnect array and the arrangement rules of the lower-level arrays in each networking hierarchy. Since the basic unit is the lower-level array of the lowest networking hierarchy, the topology of the basic unit must first be determined.

[0133] First, determine the node interconnection scale of the optical transmission network as needed. This node interconnection scale refers to the number of input ports and output ports included in the optical interconnection structure.

[0134] After determining the node interconnection scale, to minimize the link loss of the optical interconnection array, the basic unit with the lowest link loss can be found by traversing and calculating all possible topologies and connection methods of transmission nodes. For example, if the node interconnection scale determined in step 1101 is at least 12 input ports and at least 12 output ports, then the traversal calculation can start from the largest basic unit. That is, first calculate the total link loss from each input port to each output port in a topology composed of transmission nodes in a 12×12 array, then calculate the total link loss in a topology composed of transmission nodes in two 12×6 arrays, then calculate the total link loss in a topology composed of three 12×3 arrays, and so on, until the total link loss in 36 2×2 arrays is calculated. The array with the smallest total link loss among the above calculation results is taken as the target unit.

[0135] After determining the target unit, and combining it with the node interconnection scale, the networking level and the networking array for each level can be determined. For example, according to steps 1102 and 1103, the total link loss is calculated to be the lowest under 9 4×4 arrays. Then, the 4×4 array composed of 16 transmission nodes is taken as the target unit, and the 9 target units are combined into a 3×3 array to obtain the networking array of the first level. At the same time, the networking array of the first level has met the node interconnection scale. This networking array is the final optical interconnection array, as shown in Figure 6.

[0136] After obtaining the optical interconnect array, the connection methods of each lower-layer array or basic unit (target unit) are networked based on the embodiment corresponding to the optical interconnect array shown in any of Figures 3 to 8 above. Please refer to the above for relevant descriptions; the steps are not repeated here.

[0137] The optical transmission network networking method provided in this application decomposes the network from the maximum connection scale downwards. It uses a traversal approach to search all possible optical paths and optimizes the optical switch connections to find the basic unit with the lowest total loss, thereby maximizing the reduction of link loss. Then, this basic unit is used as the smallest functional unit for scale expansion, and multi-layer networking is performed using the smallest functional units. At the same time, the functional units in each layer of the network are connected one-to-one with each input port through a first optical switch and one-to-one with each output port through a second optical switch, allowing the optical signal to bypass irrelevant transmission nodes through waveguides, thereby reducing the overall link loss.

[0138] This application also provides an optical transmission device, including K optical transmitting devices, L optical receiving devices, and an optical interconnect array as described in any of the above embodiments. The optical interconnect array includes K input ports and L output ports, where K and L are both integers greater than 1. The K optical transmitting devices are respectively connected to the K input ports, and the L optical receiving devices are respectively connected to the L output ports.

[0139] This application also provides a chip including an optical interconnect array as described in any of the above embodiments.

[0140] It is understood that the optical interconnect array provided in this application embodiment can be embedded inside a chip, and the layout and interconnection of key components such as optical waveguides, optical switches, and optical couplers can be achieved through nanofabrication technology. The chip can also integrate a photoelectric conversion module, including a photodetector and a light emitter, to achieve the conversion between optical signals and electrical signals.

[0141] This application also provides an optical communication device, including the above-described chip.

[0142] Furthermore, based on the optical signal transmission method in the embodiment corresponding to FIG9, this application also provides a computing device that can be used to execute computer programs or computer instructions in a memory to perform the method in the embodiment corresponding to FIG9.

[0143] In addition, based on the networking method of the optical transmission network in the embodiment corresponding to FIG11, this application also provides a computing device, which can also be used to execute computer programs or computer instructions in memory to execute the method in the embodiment corresponding to FIG11.

[0144] This application also provides a computer program product including instructions that, when run on a computer, cause the computer to perform the method of the embodiment shown in FIG9 or FIG11 above.

[0145] This application also provides a computer-readable storage medium including computer instructions that, when executed on a computer, cause the computer to perform the method of the embodiment shown in FIG9 or FIG11 above.

[0146] This application also provides a chip, including a processor, for being connected to a memory and calling a program stored in the memory, so that the processor executes the method of the embodiment shown in FIG9 or FIG11 above.

[0147] The processor mentioned above can be a general-purpose central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of a program for controlling the methods of the embodiments shown in Figures 9 or 11. The memory mentioned above can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM).

[0148] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0149] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0150] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0151] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0152] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An optical interconnect array, characterized in that, Includes at least one networking layer; Each of the network layers includes a network array composed of multiple lower-layer arrays, wherein the lowest-level lower-layer array is a basic unit, and the basic unit is a topology composed of multiple transmission nodes; The lower-level array includes M input ports and N output ports, where M and N are both integers greater than 1; The M input ports of the lower-layer array located in the x-dimensional direction are connected one-to-one via a first optical switch; The N output ports of the lower-level array located in the y-dimensional plane are connected one-to-one by a second optical switch.

2. The optical interconnect array according to claim 1, characterized in that, The M input ports of the lower-layer array located in the x-dimensional direction are respectively connected one-to-one via a first optical switch, specifically including: The M input ports of the first lower-layer array are respectively connected to the M input ports of the second lower-layer array through M first optical switches. The first lower-layer array and the second lower-layer array are adjacent lower-layer arrays in the x-dimensional direction. The N output ports of the lower-layer array located in the y-dimensional direction are respectively connected one-to-one via a second optical switch, specifically including: The N output ports of the third lower-layer array are respectively connected to the N output ports of the fourth lower-layer array through N second optical switches. The third lower-layer array and the fourth lower-layer array are adjacent lower-layer arrays in the y-dimensional direction.

3. The optical interconnect array according to claim 1 or 2, characterized in that, The transmission nodes in the basic unit form a Torus topology.

4. The optical interconnect array according to any one of claims 1 to 3, characterized in that, The first optical switch and / or the second optical switch are optical switch devices that realize optical signal on / off control based on electrostatic attraction effect.

5. The optical interconnect array according to any one of claims 1 to 3, characterized in that, The first optical switch and / or the second optical switch are optical switch devices that realize optical signal on / off control based on the mode interference effect.

6. The optical interconnect array according to any one of claims 1 to 3, characterized in that, The first optical switch and / or the second optical switch are optical switch devices that realize optical signal on / off control based on mode transmission effect.

7. The optical interconnect array according to any one of claims 1 to 6, characterized in that, In adjacent network layers, the optical signal in the upper waveguide is coupled to the lower waveguide based on evanescent waves.

8. The optical interconnect array according to any one of claims 1 to 7, characterized in that, The waveguides in the optical interconnect array include horizontal waveguides and vertical waveguides, and the horizontal waveguides and the vertical waveguides are based on a multilayer silicon nitride structure to form a cross waveguide.

9. The optical interconnect array according to any one of claims 1 to 8, characterized in that, The waveguides in adjacent network layers are arranged on different planes.

10. The optical interconnect array according to any one of claims 1 to 8, characterized in that, It also includes a light detector; The photodetector is connected to the first optical switch and / or the second optical switch, and the photodetector is used to detect whether an optical signal is input to the optical path of the first optical switch and / or the second optical switch.

11. The optical interconnect array according to claim 10, characterized in that, It also includes a processing module; The processing module is connected to the photodetector, and the photodetector is also used to send detection information to the processing module. The detection information is used to indicate whether the optical signal is input to the optical path of the first optical switch and / or the second optical switch.

12. An optical transmission device, characterized in that, It includes K optical transmitting devices, L optical receiving devices, and an optical interconnect array as described in any one of claims 1 to 11, wherein the optical interconnect array includes K input ports and L output ports, wherein K and L are both integers greater than 1; The K optical transmitting devices are connected to the K input ports respectively, and the L optical receiving devices are connected to the L output ports respectively.

13. A networking method for an optical transmission network, characterized in that, include: Determine the node interconnection scale of the optical transmission network; Based on the node interconnection scale, the link loss under different basic units is calculated through traversal. The basic unit includes a topology composed of multiple transmission nodes. The basic unit with the minimum link loss is identified as the target unit; Based on the topology of the target unit and the interconnection scale of the nodes, the network hierarchy and the network array of each level are determined. Each network array consists of multiple lower-level arrays, with the target unit being the lowest-level lower-level array. The optical transmission network is constructed based on the target unit and the networking layer. The lower-layer array includes M input ports and N output ports, where M and N are both integers greater than 1. The M input ports of the lower-layer array located in the x-dimensional direction are connected one-to-one through a first optical switch, and the N output ports of the lower-layer array located in the y-dimensional direction are connected one-to-one through a second optical switch.

14. A method for transmitting optical signals, characterized in that, Applied to the optical interconnect array according to any one of claims 1 to 11, wherein the inlet and outlet ports of the optical interconnect array correspond to the coordinate values ​​of the x-axis and y-axis in a two-dimensional coordinate system, the method includes: Determine the target input port and target output port of the optical signal; The target coordinates are determined in the two-dimensional coordinate system based on the target inlet port and the target outlet port. The target lower-level array is determined sequentially according to the network hierarchy, wherein the target lower-level array is the lower-level array corresponding to the target coordinates under each network hierarchy; By controlling the first optical switch and the second optical switch respectively to connect the optical transmission links from the target input port and the target output port to the target array unit, the transmission path of the optical signal bypasses the non-target lower layer array.

15. A chip, characterized in that, Includes the optical interconnect array according to any one of claims 1 to 11.

16. An optical communication device, characterized in that, Includes one or more chips as described in claim 15.

Citation Information

Patent Citations

  • Expandable and re-configurable two-dimensional free space optical interconnection system

    CN101813808A

  • Data center optical interconnection structure and communication method based on grid topology structure

    CN108718214A

  • Optical matrix switch and control system therefor

    WO2014155642A1