CN107509126A - Logical topology reconfiguration method, reconfigurable controller and the optical network system of optical-fiber network - Google Patents

Logical topology reconfiguration method, reconfigurable controller and the optical network system of optical-fiber network Download PDF

Info

Publication number
CN107509126A
CN107509126A CN201710598765.3A CN201710598765A CN107509126A CN 107509126 A CN107509126 A CN 107509126A CN 201710598765 A CN201710598765 A CN 201710598765A CN 107509126 A CN107509126 A CN 107509126A
Authority
CN
China
Prior art keywords
network
optical
subnet
wavelength
subnets
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201710598765.3A
Other languages
Chinese (zh)
Other versions
CN107509126B (en
Inventor
元国军
曹政
潘玮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
XFusion Digital Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of CN107509126A publication Critical patent/CN107509126A/en
Application granted granted Critical
Publication of CN107509126B publication Critical patent/CN107509126B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04Q—SELECTING
    • H04Q11/00—Selecting arrangements for multiplex systems
    • H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
    • H04Q11/0005—Switch and router aspects

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The embodiment of the present invention proposes a kind of logic light path reconstructing method of optical-fiber network, the optical-fiber network includes first network, second network, 3rd network and reconfigurable controller, the first network includes multiple first subnets, second network is the optical interconnection network exchanged based on optical wavelength, including multiple second subnets, 3rd network is the optical interconnection network exchanged based on space, the reconfigurable controller determines the target logic light path annexation of the 3rd network according to the target resource configuration of the target logic topological structure and the optical-fiber network of the optical-fiber network, and the light path configuration information of the 3rd network is sent to the light path control device of the 3rd network；The reconfigurable controller determines the target logic light path annexation of second network according to the target resource configuration of the target logic topological structure and the optical-fiber network of the optical-fiber network, and the wavelength configuration information of each first subnet in the first network is determined, and it is sent to corresponding first subnet.

Description

Logical topology reconstruction method of optical network, reconstruction controller and optical network system
The present application claims priority of chinese patent application entitled "logical topology reconfiguration method of optical network, reconfiguration controller and optical network system" filed by chinese patent office on 10/11/2016 under the application number of 201610988995.6, which is incorporated herein by reference in its entirety.
Technical Field
The embodiment of the invention relates to the field of computer networks, in particular to a logical topology reconstruction method, a reconstruction controller and an optical network system of an optical network.
Background
The rapid development of the internet and cloud computing has led to an exponential increase in data storage and interaction. This poses a serious challenge to the design of interconnected networks for data centers, and especially the diversity of applications makes it a big challenge how to efficiently utilize data center resources.
The data center simultaneously bears a plurality of applications such as mass data processing, network video, games, intelligent hardware, biological computation and the like, the communication modes of different applications are greatly different, and the high-efficiency operation efficiency can be ensured by adopting different topological structures according to the communication characteristics of the applications. The existing data center fixes a single interconnection network structure, and the requirement of various communication characteristics is difficult to be met efficiently.
Disclosure of Invention
Embodiments of the present invention provide a method for reconstructing a logical topology of an optical network, a reconstruction controller, and an optical network system, which can complete logical topology reconstruction to match communication characteristics of an application without changing physical wiring, and improve resource utilization and power consumption of the system.
In a first aspect, a logical topology reconfiguration method for an optical network is provided, where the optical network is applied to an optical network, the optical network includes a first network, a second network, a third network, and a reconfiguration controller, the first network includes a plurality of first subnets, the second network is an optical interconnection network based on optical wavelength switching, and includes a plurality of second subnets, and the third network is an optical interconnection network based on spatial switching, where the third network establishes optical path connections between the second subnets in the second network based on spatial switching; the second network establishes optical path connection of the first subnets in the first network based on optical wavelength switching, an uplink optical port of each first subnet is accessed to a downlink optical port of one second subnet, and two first subnets configure specified optical signal wavelength according to the accessed downlink optical port of the second subnet to establish optical path connection, wherein the two first subnets belong to the same second subnet or respectively belong to two different second subnets establishing optical path connection; each first sub-network in the first network is further used for realizing the electrical signal connection of different electrical domain units in the first sub-network, and a downlink port in each first sub-network is connected to an electrical domain unit; the reconfiguration controller is in communication connection with the optical path control device of the third network, the optical path control device is used for reconfiguring and configuring the logical optical path of the third network, and the reconfiguration controller is in communication connection with each first subnet; the method comprises the following steps: the reconfiguration controller determines a target logical optical path connection relationship of the third network according to a target logical topology structure of the optical network and a target resource configuration of the optical network, determines optical path configuration information of the third network according to the target logical optical path connection relationship of the third network, and sends the optical path configuration information to the optical path control device of the third network, wherein the optical path configuration information is used for indicating the optical path control device to reconfigure and configure the logical optical path connection of the third network so as to form the target logical optical path connection relationship of the third network; the reconfiguration controller determines a target logical lightpath connection relationship of the second network according to a target logical topology of the optical network and a target resource configuration of the optical network, determines wavelength configuration information of each first subnet in the first network according to the target logical lightpath connection relationship of the second network, and sends the wavelength configuration information to the corresponding first subnet, wherein the wavelength configuration information of each first subnet in the first network is used for configuring optical signal wavelengths of each corresponding first subnet in the first network, so as to form the target logical lightpath connection relationship of the second network.
Optionally, each second subnetwork is connected to the downstream optical port of the third network respectively through the same number of upstream optical ports.
In the embodiment of the invention, the reconfiguration controller dynamically determines and configures the optical path connection of the third network and the second network according to the target logic topology structure and the target resource configuration of the optical network, so that the logic topology reconfiguration can be completed without changing physical wiring to match the applied communication characteristics, and the improvement of the resource utilization rate and the power consumption of the system is realized.
With reference to the first aspect, in a first possible implementation manner, the method specifically includes: each of the second subnets includes an optical wavelength switch, an upstream optical port of any one of the optical wavelength switches is connected to at most one downstream optical port of the third network, a downstream optical port of the third network is connected to at most one upstream optical port of the optical wavelength switch, and each downstream optical port of the optical wavelength switch is connected to at most one upstream optical port of the first subnet.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the method is specifically implemented as: at most one optical link passing through the third network is configured between any two second subnets in the second network, and in the optical path configuration information of the third network, the optical wavelength exchangers of the two second subnets performing optical path connection configure the same uplink optical port number.
In the embodiment of the present invention, by specifying that at most one optical link passing through the third network is configured between any two second subnets in the second network, and the uplink optical port numbers of the two second subnets used for the optical connection are the same, based on the connection manner, the second network and the third network in the optical network can complete topology reconfiguration without any wavelength switching device and photoelectric conversion device, and a logical optical path connection relationship meeting the condition can be always found by a greedy algorithm.
With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner of the first aspect, the method is specifically implemented as: the third network is r 1 Network of D-Torus structure, the r 1 With n per dimension in a network of D-Torus architectures 1 A second network, the third network having n 1 r1 A second network, each of the second networks being r 2 Network of D-Torus structure, the r 1 With n for each dimension in a network of D-Torus structures 2 A first network, each of the second networks having n 2 r2 A first subnet, the optical path configuration information being expressed by the following formula:
wherein k is a value satisfyingK is all values of odd numbers, and the value of d satisfies the condition that d is more than or equal to 1 and less than or equal to r 1 D is all values of a positive integer, f (d) is a function related to d, taking the value of the integer, N is the number of first subnets connected to each second subnet, and N = N is satisfied 2 r2 ，LM[i][j]= x denotes that the xth optical port of the ith second subnet and the xth optical port of the jth second subnet are connected by an optical space switch.
With reference to the third possible implementation manner of the first aspect, in a fourth possible implementation manner of the first aspect, the method is specifically implemented as: the function f (d) is expressed as f (d) = n 1 (d-1) 。
With reference to the second possible implementation manner of the first aspect, in a fifth possible implementation manner of the first aspect, the method is specifically implemented as: the third network is a network with a 1-layer HyperX structure, and each dimension in the network with the 1-layer HyperX structure has s 1 A second network, the third network having s in common 1 A second network, each of the second networks being a network of a 2-layer HyperX structure, each dimension of the network of the 2-layer HyperX structure having s 2× s 3 A first network, each of the second networks having s in common 2× s 3 A first subnet, the optical path configuration information being expressed by the following formula:
LM [ i ] [ j ] = maxval (i, j), wherein
LM[i][j]= x denotes that a maxval (i, j) th optical port of the ith second subnet and a maxval (i, j) th optical port of the jth second subnet are connected through the optical space switch, maxval (i, j) denotes prob i,j The value of val is the maximum value, where val is N +1 or more and N + s or less 1 A positive integer of-1, prob i,j (val) represents the ratio of the number of optical paths to be constructed which can be completed by the optical port val to the number of all optical paths to be constructed, and the value of i, j includes 1to s 1 N is the number of the first subnets connected to each of the second subnets, and N takes the value s 2× s 3 。
With reference to the second possible implementation manner of the first aspect, in a sixth possible implementation manner of the first aspect, the determining, according to the target logical lightpath connection relationship of the second network, the wavelength configuration information of each first subnet in the first network is specifically implemented as: determining wavelength configuration information of each first subnet in the first network according to the target logical optical path connection relationship of the second network and the optical wavelength switching rule of the optical wavelength exchanger corresponding to each second subnet in the second network; wherein, the optical wavelength switch corresponding to each second sub-network in the second network adopts the same optical wavelength switching rule.
With reference to the sixth possible implementation manner of the first aspect, in a seventh possible implementation manner of the first aspect, determining, according to the target logical optical path connection relationship of the second network and the optical wavelength switching rule of the optical wavelength exchanger corresponding to each second subnet in the second network, wavelength configuration information of each first subnet in the first network is specifically implemented as:
if the first subnet N 1,1 And a first subnetwork N 1,2 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,1 And a first subnetwork N 1,2 The optical port x and the optical port y of the optical wavelength switch respectively connected to the second network configure the first subnet N respectively 1,1 And a first subnetwork N 1,2 Wherein one path of optical wavelength is lambda [x+y]％p To establish a first subnet N 1,1 And a first subnetwork N 1,2 The logic optical path connection between the two; or
If the first subnet N 1,3 And a first subnetwork N 1,4 The logical optical path connection relationship is to establish connection, and the first subnet N 1,3 Accessing to a second network N 2,1 Optical port x of an optical wavelength switch in (1), a first subnetwork N 1,4 Accessing to a second network N 2,2 Optical port x of the optical wavelength switch in (1), and a second network N 2,1 And a second network N 2,2 Establishing a second network N by configuring the same optical port z 2,1 And a second network N 2,2 Configuring the first sub-network N respectively in the logical light path connection of the third network 1,3 And a first subnetwork N 1,4 Wherein one path of optical wavelength is lambda [x+y]％p To establish a first subnet N 1,3 And a first subnetwork N 1,4 The logic optical path connection between the two; or alternatively
If the first subnet N 1,5 And a first subnetwork N 1,6 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,5 Accessing to a second network N 2,3 Optical port x of the optical wavelength switch in (1), first subnetwork N 1,6 Accessing to a second network N 2,3 Optical port y of the optical wavelength switch in (1), and a second network N 2,3 And a second network N 2,4 Establishing a second network N by configuring the same optical port z 2,3 And a second network N 2,4 A logical lightpath connection in a third network, and a first subnetwork N 1,7 Accessing to a second network N 2,3 The optical port y of the optical wavelength switch in (1) is configured with the first subnet N 1,5 Wherein one path of light has a wavelength of lambda [x+y]％p Configuring a first subnet N 1,7 Wherein one path of optical wavelength is lambda [x+y]％p To establish a first subnet N 1,5 And a first subnetwork N 1,7 And configuring a first subnet N 1,7 Wherein the other light wavelength is lambda [x+y]％p Configuring a first subnet N 1,6 Wherein one path of optical wavelength is lambda [x+y]％p To establish a first subnet N 1,7 And a first subnetwork N 1,6 To establish a logical lightpath connection between them, thereby establishing a first subnetwork N 1,5 And a first subnetwork N 1,6 The logic optical path connection between the two;
wherein p is the number of ports of the optical wavelength switch,% represents the modulus, optical ports x and y are optical ports used for establishing logical optical path connection in the second subnet among all optical ports of the optical wavelength switch in the second subnet, and optical port z is an optical port used for establishing logical optical path connection with other second subnets among all optical ports of the optical wavelength switch in the second subnet.
With reference to the seventh possible implementation manner of the first aspect, in an eighth possible implementation manner of the first aspect, the method is specifically implemented as: the third network is r 1 Network of D-Torus structure, the r 1 With n per dimension in a network of D-Torus architectures 1 A second network, the third network having n 1 r1 A second network, each of the second networks being r 2 Network of D-Torus structure, the r 1 With n for each dimension in a network of D-Torus structures 2 A first network, each of the second networks having n 2 r2 A first sub-network, the wavelength configuration information of each first sub-network in the first network is expressed by the following formula:
if ((i-1)% n) 2 (j+1)/2 <n 2 (j-1)/2 )&&(j％2＝＝1)&&(j≤2r 2 ) Then, then
Otherwise, if ((i-1)% n) 2 (j+1)/2 ≥(n 2 -1)n 2 (j-1)/2 )&&(j％2＝＝0)&&(j≤2r 2 ) Then, then
Otherwise, if (j ≦ 2r 2 ) Then, then
Otherwise, if (2 r) 2 <j≤2r 1 +2r 2 ) Then, then
Wherein λ is i j b represents the wavelength of the ith first subnet accessing the jth optical port, P represents the number of optical ports of the optical wavelength switch corresponding to the second subnet,% represents the modular operation, i and j satisfy the condition 1 ≦ i ≦ n 2 r2 ,1≤j≤2r 1 +2r 2 N is the number of first subnets connected to each of the second subnets, and N = N is satisfied 2 r2 。
With reference to the seventh possible implementation manner of the first aspect, in a ninth possible implementation manner of the first aspect, the method is specifically implemented as: the third network is a network with a 1-layer HyperX structure, and each dimension in the network with the 1-layer HyperX structure has s 1 A second network, the third network having s in common 1 A second network, each of the second networks being a network of a 2-layer HyperX structure, each dimension of the network of the 2-layer HyperX structure having s 2× s 3 A first network, each of the second networks having s in common 2× s 3 A first sub-network, the wavelength configuration information of each first sub-network in the first network is expressed by the following formula:
if (1. Ltoreq. J. Ltoreq. I-1)% s 3 ) Then, then
Otherwise, if ((i-1)% s) 3 <j≤s 3 -1) then
Otherwise, if(s) 3 ≤j≤s 2 +s 3 -2)&&(j-s 3 <(i-1)/s 3 ) Then, then
Otherwise, if(s) 3 ≤j≤s 2 +s 3 -2)&&(j-s 3 ≥(i-1)/s 3 ) Then, then
Otherwise, if(s) 2 +s 3 -1≤j≤s 1 +s 2 +s 3 -3) then
Wherein the content of the first and second substances,showing the wavelength of the ith first sub-network accessed to the jth optical port, and P tableIndicating the number of optical ports of the optical wavelength switch corresponding to the second subnet,% indicates the modulus operation, i satisfies 1 ≦ i ≦ s 2 ×s 3 ,1≤j≤s 1 +s 2 +s 3 -3,N is the number of first subnets connected to each of the second subnets, with a value s 2× s 3 。
With reference to the first aspect and the foregoing implementation manner of the first aspect, in a tenth possible implementation manner of the first aspect, the method further includes: the reconfiguration controller determines a target logic topological structure of the optical network according to the communication characteristics of the optical network; the reconfiguration controller determines a target resource configuration of the optical network according to the communication characteristics of the optical network and a target logical topology of the optical network.
With reference to the first aspect and the foregoing implementation manner of the first aspect, in an eleventh possible implementation manner of the first aspect, the implementation manner is specifically that: the target resource configuration of the optical network comprises the use mode configuration of optical link resources and optical port resources.
With reference to the first aspect and the foregoing implementation manner of the first aspect, in a twelfth possible implementation manner of the first aspect, the implementation manner is specifically that: the first subnet includes a complex function unit and a plurality of wavelength tunable transceivers, where the complex function unit is configured to aggregate multiple paths of optical signals with different wavelengths of the plurality of wavelength tunable transceivers into one path of optical signal through wavelength division multiplexing and send the optical signal to a downstream optical port of the second subnet connected to the first subnet, or demultiplex one path of optical signal with multiple wavelengths of the downstream optical port of the second subnet connected to the first subnet into multiple paths of optical signals with different wavelengths, and send the optical signals to the wavelength tunable transceivers with the same wavelength in the plurality of wavelength tunable transceivers.
With reference to the first aspect and the foregoing implementation manner of the first aspect, in a thirteenth possible implementation manner of the first aspect, the implementation manner is specifically that: the electric domain unit comprises a Central Processing Unit (CPU), a computing node, a cabinet Rack and an electric domain switch.
With reference to the first aspect and the foregoing implementation manner of the first aspect, in a fourteenth possible implementation manner of the first aspect, the implementation manner is specifically that: the third network comprises one optical space switch or the third network comprises a cascade of a plurality of optical space switches.
With reference to the first aspect and the foregoing implementation manner of the first aspect, in a fifteenth possible implementation manner of the first aspect, the method further includes: the reconfiguration controller determines a first node and a second node having a load flow greater than a predetermined threshold; the reconfiguration controller establishes a fast link between the first node and the second node from the unconfigured resources of the optical network; wherein the first node and the second node are both the first subnet, or the first node and the second node are both the second subnet.
In the embodiment of the invention, network congestion can be relieved by establishing the quick link between hotspot communication.
In a second aspect, a reconstruction controller is presented for performing the method of the first aspect or any of its possible implementations.
In particular, the apparatus may comprise means for performing the method of the first aspect or any possible implementation manner of the first aspect.
In a third aspect, there is provided another reconstruction controller comprising a processor configured to perform the method of the first aspect or any possible implementation manner of the first aspect.
In a fourth aspect, a computer-readable storage medium is presented for storing a computer program comprising instructions for performing the method of the first aspect or any possible implementation manner of the first aspect.
In a fifth aspect, an optical network system is provided, including a first network, a second network, a third network, and a reconfiguration controller, where the first network includes a plurality of first subnets, the second network is an optical interconnection network based on optical wavelength switching, and includes a plurality of second subnets, and the third network is an optical interconnection network based on spatial switching, where the third network establishes optical path connections between the second subnets in the second network based on spatial switching, and each of the second subnets is connected to a downstream optical port of the third network through the same number of upstream optical ports, respectively; the second network establishes optical path connection of the first subnets in the first network based on optical wavelength switching, an uplink optical port of each first subnet is accessed to a downlink optical port of one second subnet, and two first subnets configure specified optical signal wavelength according to the accessed downlink optical port of the second subnet to establish optical path connection, wherein the two first subnets belong to the same second subnet or respectively belong to two different second subnets establishing optical path connection; each first sub-network in the first network is further used for realizing the electrical signal connection of different electrical domain units in the first sub-network, and a downlink port in each first sub-network is connected to an electrical domain unit; the reconfiguration controller is in communication connection with the optical path control device of the third network, the optical path control device is used for reconfiguring and configuring the logical optical path of the third network, and the reconfiguration controller is in communication connection with each first subnet; the reconstruction controller is the reconstruction controller of the second aspect or the third aspect.
Based on the above scheme, the optical network includes a third network of an optical interconnection network based on space switching, a second network of the optical interconnection network based on optical wavelength switching, and a third network connected to an electric domain unit, and the reconfiguration controller dynamically determines and configures optical path connections of the third network and the second network according to a target logical topology structure and a target resource configuration of the optical network, so that logical topology reconfiguration can be completed without changing physical wiring to match communication characteristics of applications, and improvement of system resource utilization rate and power consumption is achieved.
Drawings
Fig. 1 is a flowchart of a logical topology reconfiguration method of an optical network according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of an interaction flow of an optical network according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of an L1 subnet.
Fig. 4 is a schematic diagram of an example of a logical topology of an optical network according to an embodiment of the present invention.
Fig. 5 is a schematic diagram of another example of a logical topology of an optical network according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of a logical lightpath connection configuration of two first subnets accessing the same second subnet according to an embodiment of the present invention.
Fig. 7 is a schematic diagram of a logical optical connection configuration of two first subnets accessing different second subnets and having the same optical port number according to an embodiment of the present invention.
Fig. 8 is a schematic diagram of a logical lightpath connection configuration accessing two different second subnets and accessing two first subnets with different optical port numbers according to an embodiment of the present invention.
Figure 9 is a schematic flow diagram of an embodiment of the present invention for constructing a Torus network topology.
Fig. 10 is a schematic flow chart of constructing a HyperX network topology according to an embodiment of the present invention.
Fig. 11 is a schematic structural diagram of a reconfiguration controller according to an embodiment of the present invention.
Detailed Description
Fig. 1 is a flowchart of a topology reconfiguration method of an optical network according to an embodiment of the present invention, which is applied to an optical network that includes, from bottom to top, a first Layer network (Layer 1, also referred to as a first network), a second Layer network (Layer 2, also referred to as a second network), a third Layer network (Layer 3, also referred to as a third network), and a reconfiguration controller. The first layer network is connected with the second layer network, the second layer network is connected with the third layer network, and the reconstruction controller is connected with the first layer network and the third layer network. It should be noted that each layer of the network in this embodiment is an abstraction and generalization of some devices, and does not represent a specific device. In a specific implementation, each layer includes some devices, and if two layers of networks are connected, the devices of the two layers are connected. The first layer network, the second layer network and the third layer network from bottom to top are represented on a data exchange layer, the first layer network is connected with the second layer network, and the second layer network is connected with the third layer network.
Next, a connection structure of an optical network according to an embodiment of the present invention will be described as an example.
Referring to fig. 2, a schematic diagram of an optical network is shown, in which the first Layer network (Layer 1) may also be referred to as a photoelectric conversion Layer, and is denoted by symbol L1 in the figure. The first layer network comprises a plurality of optical-to-electrical conversion devices, each of which may be considered a subnet of the first layer network, hereinafter referred to as "first subnet", see fig. 3, each optical-to-electrical conversion device (first subnet) comprising a multiplexing/demultiplexing unit and one or more (typically a plurality of) optical wavelength tunable transceivers (hereinafter referred to as transceivers). In an embodiment of the present invention, the first layer network is used to convert the electrical signal into an optical signal with a specific wavelength, and specifically, the optical-to-electrical conversion device may receive the electrical signal from, for example, a router or a switch, and convert the electrical signal into an optical signal according to the requirements of the reconstruction controller.
The transceiver is used for completing photoelectric conversion, namely converting an optical signal into an electric signal or converting the electric signal into an optical signal. The devices of the electric domain unit are connected to one end of each transceiver, and usually, the router or the switch is connected first, and then other electric domain devices (such as various devices for computing) are connected through the router or the switch. The other end of the transceiver is connected with the multiplexing/demultiplexing unit through an optical fiber. Any two nodes (for example, photoelectric conversion devices) in the first network may communicate with each other via a second network (for example, an arrayed waveguide grating router described later) and a third network, and the nodes in the first network and the second network may communicate with each other based on optical signals.
The multiplexing/demultiplexing unit is used for multiplexing or demultiplexing optical signals, so that the utilization degree of light can be improved. The multiplexing/demultiplexing units, in addition to being connected to the transceivers, are also connected to devices in the layer two network via optical fibers.
Through the transceiver and the multiplexing/demultiplexing unit, the electrical signals from the devices in the electrical domain can be converted into optical signals, and the optical signals are multiplexed by the multiplexing/demultiplexing unit and then output to the devices in the second-layer network. Conversely, the optical signal from the second device can be converted into an electrical signal to the device outputting to the electrical domain through demultiplexing and photoelectric conversion.
The second layer network, which may also be referred to as an optical wavelength interconnect layer, is indicated by the symbol L2 in fig. 2, may also comprise one or more subnetworks (hereinafter "second subnetworks"), each of which may comprise one or more Arrayed Waveguide Grating Routers (AWGR), e.g., model savg-G-100G-32-32-C-FCA-ITC manufactured by Enablence corporation. Each AWGR includes a plurality of downstream ports (unless otherwise specified, the ports hereinafter refer to optical ports to which optical fibers can be inserted for optical communication via the optical fibers) and a plurality of upstream ports. Each downstream port is connected to one of the photoelectric conversion devices, and specifically, to a multiplexing/demultiplexing unit in the photoelectric conversion device. Each uplink port is connected with a downlink port in the third-layer network equipment through an optical fiber. Each second subnetwork is connected to the downstream port of the third network via the same number of upstream ports, respectively.
Specifically, in this embodiment of the present invention, each second subnet may communicate with the third network (specifically, one or more downstream ports of the third network) through one or more upstream ports.
Optionally, the number of upstream ports of each second sub-network is the same.
And, optionally, the number of the downstream ports may be the same as the number of the upstream ports.
Therefore, the same bandwidth of the second sub-networks can be ensured, and the compatibility and the expandability of the system are improved.
Furthermore, by making the number of upstream ports of each second sub-network the same, the design complexity of the downstream ports of the third network can be simplified.
It should be noted that the above listed relationship between the upstream ports of the second subnets is only an example and not a limitation, the present invention is not particularly limited, and the number of the upstream ports of the second subnets may be different.
The above-mentioned relationship between the upstream ports of the second subnet and the downstream ports of the third network is only an example and not a limitation, and the present invention is not particularly limited.
The AWGR is an optical device for optical interconnection, and when the wavelength of light input to two ports in the AWGR is a specific wavelength, the two ports can be interconnected.
For example, assuming, as a simple example, that an AWGR device includes three ports 1, 2, and 3, then the wavelength λ of the port1 and 2 is 1 In the case of interconnection, ports 2 and 3 have a wavelength of λ 2 In the case of interconnection, ports No. 1 and 3 have a wavelength of λ 3 Are interconnected.
For another example, suppose AWGR1 and AWGR2 have No. 1, no. 2, no. 3 downlink ports and No. 4 uplink ports, respectively, and AWGR1 and AWGR2 are connected to devices in the layer three network through respective No. 4 ports. Wherein, for each AWGR, the number 1 and 2 ports are defined to pass through lambda 1 Establishing optical connection with 1, 3 ports through lambda 2 Establishing optical connection with 2, 3 ports passing through lambda 3 Establishing optical connection with number 1, 4 ports passing through lambda 4 An optical connection is established. Assuming that the two first subnetworks A1 and A2 access ports AWGR1 and 2, respectively, A3 accesses port1 of AWGR2, and AWGR1 and AWGR2 establish optical connection through devices in the third layer network, if a wavelength λ is used by A1 and A3 configurable to implement A1 connection with A3 4 Thus, A1 can be connected to devices in the layer three network via ports 1 and 4 of AWGR1, and A3 can also be connected to devices in the layer three network via ports 1 and 4 of AWGR2, thereby establishing an optical connection between A1 and A3.
It should be noted that, the rule for connecting a specific wavelength to a specific port is usually fixed when the product is shipped from the factory, and the user cannot change the rule.
The third layer network, which may also be referred to as an optical spatial switching layer, is indicated by the symbol L3 in fig. 2. The third network may also include one or more sub-networks (hereinafter referred to as third sub-networks), and in particular, the third sub-network may include one or more Optical space switches (or Optical space switching devices), for example, micro-Electro-Mechanical-System-based Optical switches (MBOS), or Optical Cross-connects (OXCs), etc. based on Micro-electromechanical systems. The downstream ports of devices in the layer three network are connected to the upstream ports of devices in the layer two network (e.g., AWGR) by optical fibers. The devices in the layer three network may also be connected to higher layer devices (for example, if the optical network in this embodiment forms a data center, the optical network may be a device for exchanging data between the data centers), which is not described in detail herein.
MBOS or OXC are devices for optical-space interaction, comprising a plurality of ports (ports for plugging and unplugging optical fibers for optical transmission) and an interface for receiving control instructions, which can be adjusted according to the received instructions for interconnecting the two ports. For example, an MBOS includes ports 1, 2, and 3, and the ports 1 and 2, the ports 1 and 3, and the ports 2 and 3 may be interconnected by a specific instruction.
In addition, in the embodiment of the present invention, an optical path control device may be configured in the optical space switch, where the optical path control device refers to a unit or a component used for optical path setting in the optical space switch, and may be centralized or distributed control, and the embodiment of the present invention is not limited to a specific control module structure.
By way of example and not limitation, for example, when the optically controlled gold switching device is MBOS, the optical path controller may be a device for controlling micro-electromechanical operation (e.g., micro-electromechanical rotation angle).
Next, determination of the logical topology of the optical network according to the embodiment of the present invention based on the above-described connection structure will be described.
In the embodiment of the present invention, the logical topology of the optical network refers to a topology mainly formed based on the first subnet, that is, each node included in the topology is mainly the first subnet, and the second and third subnets are used as intermediate handover nodes to perform data exchange on a plurality of first subnets.
Without loss of generality, taking the example that the first subnet # a needs to transmit an optical signal with the first subnet # B, if the first subnet # a is connected to the second subnet # C in the second network, and the first subnet # B is connected to the second subnet # D in the second network, the logical topology structure of the optical network according to the embodiment of the present invention can implement: the optical signal that the first subnet # a needs to transmit to the first subnet # B can reach the first subnet # B via the second subnet # C, the third network, and the second subnet # D in this order.
For example, but not by way of limitation, the topology of the optical network according to the embodiment of the present invention may be a Mesh (Mesh) topology, and fig. 4 is a schematic diagram illustrating an example of the Mesh topology according to the embodiment of the present invention, as shown in fig. 4, different first subnets may be connected through a second network, and different second subnets may be connected through a third network. For example, as shown in fig. 4, three first subnets located in the same row constitute one second subnet, and different second subnets (in fig. 4, networks constituted by first subnets connected by solid lines of different rows) are connected via a third network (a network constituted by logical lines shown by dotted lines). It should be understood that the Mesh topology shown in fig. 4 is only an exemplary topology, and the present invention is not limited thereto, for example, in the embodiment of the present invention, the third network may also be represented as a vertical logical connection.
For another example, the topology of the optical network according to the embodiment of the present invention may be a HyperX topology, and fig. 5 illustrates an example schematic diagram of the HyperX topology, as shown in fig. 5, different first subnets may be connected through a second network, and different second subnets may be connected through a third network. For example, as shown in fig. 5, four first subnets constituting four vertices of a quadrangle constitute one second subnet, and different second subnets (in fig. 5, a network constituted by first subnets connected by solid lines constituting sides of the quadrangle) are connected via a third network (a network constituted by logical lines shown by broken lines).
For another example, the topology of the optical network according to the embodiment of the present invention may be a ring (Torus) topology, and fig. 9 shows an example schematic diagram of the Torus topology, as shown in fig. 9, each first subnet (e.g., node) in the same second subnet (i.e., the same Rack) is formed as a ring connection, and different second subnets (i.e., different racks) are connected by a ring third network.
It should be understood that the above-listed topologies are only illustrative examples of the logical topologies of the optical network according to the embodiment of the present invention, and the present invention is not limited thereto, and topologies capable of implementing the above transmission paths all fall within the scope of the present invention. For example, when the topology structure of the optical network according to the embodiment of the present invention may also use a Torus structure, the third network may be constructed as rD-Torus topology, and the third network is made r 1 D-Torus structure having n 1 A dimension, each dimension having r 1 A second sub-network; let the second network be r 2 D-Torus structure having n 2 A dimension, each dimension having r 2 A first sub-network, and a second sub-networkA second sub-network, which is shared by the first networkA first sub-network.
Next, a method for reconstructing a logical topology of an optical network according to an embodiment of the present invention is described in detail.
As an example and not by way of limitation, the logical topology of the optical network according to the embodiment of the present invention may be adjusted through reconfiguration, and the finally adjusted logical topology is the logical topology of the optical network according to the embodiment of the present invention (hereinafter, for convenience of understanding and distinction, it is referred to as a target logical topology), and fig. 1 shows a schematic flow of the reconstructor performing the reconfiguration.
First, the reconfiguration controller may determine the logical topology of the optical network that currently needs to be used (i.e., the target logical topology).
By way of example and not limitation, in an embodiment of the present invention, the logical topology of the optical network may be stored in the reconfiguration controller in the form of, for example, an entry, each row in the entry may represent one second subnet, and each element in each row represents the first subnet to which the second subnet is connected. For example, as shown in FIG. 4, each second subnet (the first node in the same row in FIG. 4) may be a row in the entry, and each second subnet may have an index. Table 1 below shows an example of a corresponding memory structure of the logical topology shown in fig. 4.
TABLE 1
It should be understood that the storage form of the above-listed logical topology is only an exemplary illustration, and the present invention is not limited thereto, and any other form of data structure can be used to store the logical topology of the embodiment of the present invention.
For example, in the embodiment of the present invention, a plurality of logical topologies may be stored in the reconfiguration controller, and a user may select one of the logical topologies as a currently desired logical topology.
It should be understood that the above listed method and process for determining the logical topology by the reconfiguration controller are only exemplary, and the present invention is not limited thereto, for example, the reconfiguration controller may also store the mapping relationship between the plurality of logical topologies and the plurality of usage manners (e.g., usage time, usage place, service object, etc.), so that the reconfiguration controller may select the corresponding logical topology as the logical topology that is currently desired to be used based on the usage manner that is currently desired to be used.
And, the reconfiguration controller may also determine a resource configuration of the optical network.
The resource allocation of the optical network refers to physical resources required by the optical network to complete a topology (or necessary to complete functions of the optical network), and includes the number of ports of the second and third networks, the number of transceivers in the first network, and the like. The target resource configuration represents the resource configuration required by the target logical topology.
By way of example and not limitation, in the embodiment of the present invention, the resource configuration of the optical network may be input to the reconfiguration controller by a network operator or an administrator, for example, in the embodiment of the present invention, a plurality of resource configurations may be stored in the reconfiguration controller, and a user may select one from the plurality of resource configurations as a resource configuration which is currently desired to be used.
It should be understood that the above-listed method and process for determining resource configuration by the reconfiguration controller are only exemplary, and the present invention is not limited thereto, for example, the reconfiguration controller may also store mapping relationships between various resource configurations and various usage manners (e.g., usage time, usage place, service object, etc.), so that the reconfiguration controller may select the corresponding resource configuration as the resource configuration currently desired to be used based on the usage manner currently desired to be used.
Optionally, as an embodiment, the reconfiguration controller may determine the target logical topology of the optical network according to a communication characteristic of the optical network. The target logical topology of the optical network may include target logical topologies of the second network and the third network.
Optionally, as an embodiment, after the target logical topology configuration of the optical network is completed, the reconfiguration controller may further determine the target resource configuration of the optical network according to the communication characteristic of the optical network and the target logical topology.
Or, optionally, as another embodiment, the target resource configuration of the optical network is manually configured by a network administrator.
Optionally, the method further comprises: the reconfiguration controller determines a first node and a second node with load flow larger than a preset threshold; the reconfiguration controller establishes a fast link between the first node and the second node from the unconfigured resources of the optical network; wherein the first node and the second node are both the first subnet, or the first node and the second node are both the second subnet.
In the embodiment of the invention, network congestion can be relieved by establishing the quick link between hotspot communication.
Optionally, the method further comprises: the reconfiguration controller turns off unused resources in the optical network. In the embodiment of the invention, the power consumption of the system can be reduced by closing the redundant resources.
Further, at S110, the reconfiguration controller may determine a target logical lightpath connection relationship of the third network according to the target logical topology of the optical network and the target resource configuration of the optical network.
In the embodiment of the present invention, the plurality of ports included in the third network for performing optical signal communication with the second network may constitute a plurality of port groups, each port group includes two ports, and the target logical optical path connection relationship of the third network may refer to a connection relationship between two ports in each port group (or an optical signal transmission path between two ports in each port group).
Preferably, when determining the target logical optical path connection relationship of the third network according to the target logical topology of the optical network and the target resource configuration of the optical network, in order to solve the problem of cascade connection among the plurality of switches without introducing an optical-electrical/electrical-optical conversion device or a wavelength switcher between the second network and the third network, the following configuration may be performed in the optical path configuration information of the third network: at most one optical link passing through the third network is configured between any two second subnets in the second network, and the uplink optical port numbers of the two second subnets used for the optical connection are the same.
Therefore, any two second subnets connected through the third subnetwork have the same optical port number and contain the same wavelength distribution, and according to the mode, the second network and the third network can complete topology reconstruction without any wavelength switching device and photoelectric conversion device, and a logical light path connection relation meeting the conditions can be always found through a greedy algorithm.
That is, in the embodiment of the present invention, optionally, within a specified time period, there may be a one-to-one mapping relationship between the multiple wavelengths and the multiple port groups, and the logical lightpath connection relationship of the third network may refer to the mapping relationship.
Optionally, in this embodiment of the present invention, the third network may include a plurality of downstream ports (or sending ports), and the wavelength used by each downstream port may be different in a specified period.
Or, in the embodiment of the present invention, each second network may have a plurality of upstream ports, where the plurality of upstream ports respectively use different wavelengths, that is, between any two second subnets, there are a plurality of port groups, each port group includes two ports respectively belonging to the two second subnets, and the wavelengths used by the same port group are the same.
Then, the reconfiguration controller may determine the optical path configuration information of the third network according to the target logical optical path connection relationship of the third network, and send the optical path configuration information to the optical path control apparatus of the third network.
The optical path configuration information is used to instruct the optical path control device to reconfigure and configure the logical optical path connection of the third network, so as to form an optical path that satisfies the target logical optical path connection relationship of the third network.
Of course, it should be understood that the optical path configuration information of the third network may not follow the above configuration, but the wavelength switching device is introduced to convert the optical path therein. For specific implementation, reference may be made to the working principles of the optical space converter and the optical wavelength converter, and the embodiments of the present invention are not described herein again.
At 120, the reconfiguration controller determines a target logical lightpath connection relationship of the second network according to the target logical topology of the optical network and the target resource configuration of the optical network.
The target logical lightpath connection relationship of the second network may refer to a mapping relationship between each uplink port and each wavelength in each second subnet of the second network.
Then, the reconfiguration controller may determine the wavelength configuration information of each first subnet in the first network according to the target logical lightpath connection relationship of the second network and send the wavelength configuration information to the corresponding first subnet.
Specifically, the case when the first subnet # a needs to transmit a signal to the first subnet # B is taken as an example without loss of generality. The reconfiguration controller may determine a second subnet (i.e., the second subnet # D) connected to the first subnet # B, further, the reconfiguration controller may determine a port (hereinafter, referred to as port # B for easy understanding) of the third network for optical signal transmission with the second subnet # D, and the reconfiguration controller may determine a wavelength used by the port # B, wherein the wavelength used by the port # B may be a wavelength used by the first subnet # B (or a port of the second subnet # D communicating with the first subnet # B) (hereinafter, referred to as wavelength # B for easy understanding and distinction).
Also, the reconfiguration controller may determine the port in the second subnet # C using the wavelength # B (hereinafter, for ease of understanding and distinction, referred to as port # a).
Thus, since port # a and port # B use the same wavelength (or, belong to the same port group), the optical path inter-actor of the third network can forward the optical signal from port # a to port # B.
Thus, the reconfiguration controller can inform the first subnet # a to generate an optical signal using the wavelength # B, and thus, it can be ensured that the generated optical signal can be transmitted to the port # a of the second subnet # C, and thus, the optical signal can be transmitted to the second subnet # D (specifically, the port # B) via the forwarding of the third network, and thus, the optical signal can be transmitted to the first subnet # B through the port # B. The wavelength configuration information of each first subnet in the first network is used for configuring the optical signal wavelength of the corresponding first subnet in the first network to form a target logical optical path connection relationship of the second network. In particular, the wavelength configuration information of the first subnet may include wavelength configurations of the respective wavelength tunable transceivers in the first subnet.
It should be understood that the wavelength configuration information for each sub-network may include the optical signal wavelength, the number of the first sub-network, the number of the wavelength tunable transceiver of the first sub-network, and the like. For example, the reconfiguration controller sends wavelength configuration information carrying λ (representing wavelength), N1 (representing the first subnet), and port1 (representing the wavelength tunable transceiver) to the first subnet N1, N1 transmits the message to port1 of the wavelength tunable transceiver, and port1 can adjust the wavelength of the optical signal to λ after receiving the wavelength configuration information.
In the embodiment of the invention, the third network and the second network are respectively an optical interconnection network based on space switching and an optical interconnection network based on optical wavelength switching, and the reconfiguration controller dynamically determines and configures the logic light path connection of the third network and the second network according to the target logic topological structure and the target resource configuration of the optical network, so that the logic topological reconfiguration can be completed without changing physical wiring to match the applied communication characteristics, and the improvement of the resource utilization rate and the power consumption of the system is realized.
As shown in fig. 2, a specific interaction flow of the optical network is as follows:
step1: and the topology matching unit of the reconfiguration controller finds a matched target logic topology structure according to the communication characteristics of the optical network and sends the matched target logic topology structure to the resource configuration unit and the logic light path configuration unit of the reconfiguration controller. Of course, it should be understood that the target logical topology of the optical network may also be manually configured by a network administrator.
Step2: and the resource configuration unit of the reconfiguration controller determines the target resource configuration of the optical network according to the communication characteristics of the optical network and the target logical topology structure and sends the target resource configuration to the logical light path configuration unit and the wavelength configuration unit.
And Step3, a logic light path configuration unit of the reconfiguration controller receives the target logic topological structure and the target resource configuration, solves the logic light path connection relation of the L3 layer optical network according to the target logic topological structure and the target resource configuration, and sends light path configuration information for specifying the logic light path connection relation among all ports of all the space exchangers in the L3 layer network to a light path control device of the L3 layer network.
Step4: and after receiving the light path configuration information of Step3, the light path control device of the L3 layer network adjusts the connection relation of the MEMS-based Optical Switch to complete the reconstruction of the L3 layer network. The optical path control device in the embodiment of the present invention refers to a unit or component for optical path setting in a space switching device of an L3 network, and the optical path control device may be centralized or distributed control, and may be specifically implemented with reference to the prior art.
Step5: and the wavelength configuration unit of the reconfiguration controller receives the target logic topological structure and the target resource configuration, solves the logic light path connection relation of the L2-layer optical network according to the target logic topological structure and the target resource configuration, and sends specific wavelength configuration information to the tunable transceiver module of the L1 subnet.
Step6: the tunable transceiver module of the L1 subnet, such as a wavelength tunable transceiver or a wavelength tunable laser, adjusts its own optical wavelength according to the received wavelength configuration information. Of course, if one or some of the tunable transceiver modules does not have corresponding wavelength configuration information, indicating that the tunable transceiver module is not enabled, the tunable transceiver module may be temporarily turned off to reduce power consumption.
For ease of understanding, fig. 3 shows a schematic diagram of the structure of the L1 subnet. As shown in fig. 3, the L1 subnet may be composed of Mux/Demux, several wavelength tunable TRXs, and Switch/Router. The downstream port of Switch/Router is connected with the electric domain unit, the upstream port is connected with the wavelength-tunable TRXs and the Mux/Demux, all optical signals are converged to 1 WDM optical fiber by the Mux/Demux and are connected to the optical wavelength switching device of the L2 subnet, and the control signal of the L1 subnet is connected to the reconstruction controller. The TRXs with adjustable wavelength in fig. 3 is the tunable transceiver module in Step 6. The Mux/Demux in fig. 3 is a wavelength multiplexing/demultiplexing unit, and is responsible for aggregating multiple beams of laser with different wavelengths onto 1 WDM optical fiber by wavelength division multiplexing technology or demultiplexing multiple wavelengths of optical waves transmitted simultaneously in 1 WDM optical fiber onto multiple single-mode optical fibers, and can be implemented based on a wavelength selective switch, an optical circulator, a coupler, or other optical devices. It should be understood that the embodiments of the present invention do not limit the electrical domain units of the L1 network connection, including but not limited to a Central Processing Unit (CPU), a computing node, a Rack (Rack), an electrical domain switch (ToR), and other electrical domain computing or network nodes. In addition, the specific physical structure of the Mux/Demux is not limited by the embodiments of the present invention.
At this point, the reconfiguration controller completes the topology reconfiguration of the optical network.
Of course, it should be understood that the reconfiguration controller may also optimize the optical network after the reconfiguration controller completes the topology reconfiguration of the optical network. The reconfiguration controller may determine whether to perform optimization according to a load flow on an optical link corresponding to the logical optical path connection.
Specifically, the reconfiguration controller may determine a first node and a second node having a load flow greater than a predetermined threshold, and then establish a fast link between the first node and the second node from the unconfigured resources of the optical network; wherein the first node and the second node are both a first subnet, or the first node and the second node are both a second subnet. The reconfiguration controller can configure link resources through the resource configuration unit, and establish a fast link according to the link resources configured by the resource configuration unit through the logic light path configuration unit and the wavelength configuration unit.
The "establishing a fast link" may refer to, after the link establishment between the first subnets (or the logical topology of the optical network) is completed as described above, if resources of the current optical network are left (for example, port resources of the third network or wavelength resources of each second subnet), establishing a logical topology relationship for one or more nodes that need to communicate and are outside the logical topology structure (or modifying an original logical topology relationship so that the modified logical topology relationship covers the one or more nodes), where the specific process may be similar to the above process of establishing the logical topology relationship, and a detailed description thereof is omitted here to avoid redundant description.
In the embodiment of the invention, network congestion can be relieved by establishing the quick link between hotspot communications.
Alternatively, the reconfiguration controller may also shut down unused resources in the optical network.
In the embodiment of the invention, the power consumption of the system can be reduced by closing unused resources (or residual resources or redundant resources).
It should be understood, of course, that fig. 2 is only one specific implementation scenario of the optical network according to the embodiment of the present invention. In a specific application, other implementation manners may exist in the optical network according to the embodiment of the present invention, and the embodiment of the present invention is not particularly limited.
Optionally, as an embodiment, each of the second subnets includes an optical wavelength switch, one uplink optical port of any one of the optical wavelength switches is connected to at most one downlink optical port of the third network, one downlink optical port of the third network is connected to at most one uplink optical port of one optical wavelength switch, and each downlink optical port of the optical wavelength switch is connected to at most one uplink optical port of the first subnet.
For example, in the embodiment shown in fig. 2, the L2 sub-network may be formed by 1 AWGR (Arrayed Waveguide Grating Router), and each optical port of the AWGR is connected to 1 WDM optical fiber. Each AWGR of a L2-level network is connected to the L3-level network by the same number of optical ports (WDM fibers), and each of the remaining optical ports is connected to 1L 1 subnet by 1 WDM fiber (of course, there may also be free optical ports). It is to be understood that the embodiments of the present invention do not limit the variety of optical wavelength exchangers.
Furthermore, at most one optical link passing through the third network is configured between any two second subnets in the second network, and in the optical path configuration information of the third network, the optical wavelength exchangers of the two second subnets performing optical path connection are configured with the same uplink optical port number.
In order to solve the problem of cascade connection among a plurality of second subnets on the premise that no photoelectric/electro-optical conversion device or wavelength switcher is introduced between the second network and the third network, the following configuration may be performed in the optical path configuration information of the third network: at most one optical link passing through the third network is configured between any two second subnets in the second network, and the uplink optical port numbers of the two second subnets used for the optical connection are the same. According to the mode, the second network and the third network can complete topology reconstruction without any wavelength switching device and photoelectric conversion device, and a qualified logic light path connection relation can be always found through a greedy algorithm. Based on the connection relationship, a connection relationship matrix between the optical port numbers of the third network can be derived. The third network is realized based on the space switching device, so that the configuration of the optical path connection relationship of the third network can be completed by controlling the connection relationship of the ports. For example, most MEMS-based space switches support configuration of connections through an open flow (OpenFlow) protocol interface.
The procedure of the above method will be further exemplified below by taking the case where the above logical topology is a Torus structure as an example.
That is, optionally, in a specific implementation manner of this embodiment, the third network is r 1 Network of D-Torus structure, the r 1 With n per dimension in a network of D-Torus architectures 1 A second network, the third network having n 1 r1 A second network, each of the second networks being r 2 Network of D-Torus structure, r 1 With n per dimension in a network of D-Torus architectures 2 A first network, each of the second networks having n 2 r2 A first subnet, the optical path configuration information being expressed by the following formula:
LM[k][(k+f(d))％n 1 r1 ]＝LM[(k+f(d))％n 1 r1 ][k]＝2d－1+N；
LM[k][(k－f(d))％n 1 r1 ]＝LM[(k－f(d))％n 1 r1 ][k]＝2d+N；
wherein k is equal to or greater than 1 and equal to or less than n 1 r1 And k is an odd integer, and d is equal to or greater than 1 and equal to or less than r 1 D is all values of a positive integer, f (d) is a function related to d, taking the value of the integer, N is the number of first subnets connected to each second subnet, and N = N is satisfied 2 r2 ，LM[i][j]= x tableThe xth optical port of the ith second subnetwork and the xth optical port of the jth second subnetwork are shown as being connected by an optical space switch.
It should be understood that there may be multiple expressions for the function f (d) in this implementation. Preferably, the function f (d) is expressed as f (d) = n 1 d-1 。
Optionally, in a specific implementation manner of this embodiment, the third network is a network with a 1-layer HyperX structure, and each dimension in the network with the 1-layer HyperX structure has s 1 A second network, the third network having s in common 1 A second network, each of the second networks being a network of a 2-layer HyperX structure, each dimension of the network of the 2-layer HyperX structure having s 2× s 3 A first network, each of the second networks having s in common 2× s 3 A first subnet, the optical path configuration information is expressed by the following formula:
LM [ i ] [ j ] = maxval (i, j), wherein
LM[i][j]= x denotes that a maxval (i, j) th optical port of the ith second subnet and a maxval (i, j) th optical port of the jth second subnet are connected through the optical space switch, maxval (i, j) denotes prob i,j A value of (val) when the value is the maximum, wherein val is not less than N +1 and not more than N + s 1 A positive integer of-1, prob i,j (val) represents the ratio of the number of optical paths to be constructed which can be completed by the optical port val to the number of all optical paths to be constructed, and the value of i, j includes 1to s 1 N is the number of the first subnets connected to each of the second subnets, and N takes the value s 2× s 3 。
After the topology connection between the second subnets is completed, the wavelengths of the first subnets of the second subnets need to be configured, so as to implement the logical lightpath connection of the entire optical network.
It should be understood that, among the optical ports of the optical wavelength switch of each second subnet, part of the optical ports are used for the logical optical circuit connection in the second subnet, and part of the optical ports are used for the logical optical circuit connection of the second subnet with other second subnets. Each first sub-network may comprise a plurality of tunable transceiver modules, which are multiplexed/demultiplexed and connected to a port of the second sub-network via 1 WDM fiber. The tunable transceiver module is used for the logical light path connection between two first subnets in the same second subnet, and the tunable transceiver module is used for the logical light path connection between two first subnets in different subnets. For example, in the embodiment shown in fig. 3, L2TRXs may be used for logical lightpath connections between two first subnets within the same second subnet, L3TRXs may be used for logical lightpath connections between two first subnets within different subnets, and so on.
In step 110 of fig. 1, determining the wavelength configuration information of each first subnet in the first network according to the target logical lightpath connection relationship of the second network may specifically be implemented as follows: determining wavelength configuration information of each first subnet in the first network according to the target logical optical path connection relationship of the second network and the optical wavelength switching rule of the optical wavelength exchanger corresponding to each second subnet in the second network; and the optical wavelength exchangers corresponding to each second subnet in the second network adopt the same optical wavelength switching rule.
It is not assumed that a first subnetwork N1 is connected to t other first subnetworks, wherein t are the total of the first subnetworks to which the first subnetwork N1 is connected 1 Several first subnets are located in the same second subnet, t 2 The first subnets are located within other second subnets. Each first sub-network comprises t tunable transceiver modules, and the tunable transceiver modules are connected to one port of the second sub-network through 1 WDM optical fiber after multiplexing/demultiplexing. t tunable transceiver modules are sequentially named as numbers 1-t, wherein 1-t 1 The number tunable transceiver module is used for the logical light path connection between two first subnets in the same second subnet; t is t 1 +1～t 1 +t 2 The number tunable transceiver module is used for logical light path connection between two first subnets in different subnets. According to the conditions of the second subnets and the optical ports to which the two first subnets to be connected are accessed, the connection conditions of the two second subnets can be divided into three scenes, namely scene 1, wherein the two first subnets belong to the same second subnet; in a scene 2, the two first subnets belong to two different second subnets, and the numbers of the accessed optical ports are the same; scenario 3, the two first subnets belonging to two different second subnets,and the number of the accessed optical ports is different.
The following shows an optical wavelength switching rule adopted by an optical wavelength switch, which respectively corresponds to the connection relationship between two first subnets under three different scenarios.
Scene 1:
if the first subnet N 1,1 And a first subnetwork N 1,2 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,1 And a first subnetwork N 1,2 The optical port x and the optical port y of the optical wavelength switch respectively connected to the second network configure the first subnet N respectively 1,1 And a first subnetwork N 1,2 Wherein one path of light has a wavelength of lambda [x+y]％p To establish a first subnetwork N 1,1 And a first subnetwork N 1,2 Wherein p is the number of ports of the optical wavelength switch,% represents modulo, and the optical ports x and y are respectively one of the optical ports of the optical wavelength switch of the second subnet used for establishing the logical optical path connection in the second subnet.
In the embodiment of the invention, the first subnet N on the optical port x is accessed 1,1 Wherein one path of optical wavelength is lambda [x+y]％p And will access the first subnet N on optical port y 1,2 Wherein one path of light has a wavelength of lambda [x+y]％p Thereby enabling establishment of the first subnet N 1,1 And a first subnetwork N 1,2 The logical optical path connection between them.
Fig. 6 is a schematic diagram of a logical lightpath connection configuration of two first subnets accessing the same second subnet according to an embodiment of the present invention. In fig. 6, the first subnet 1, the first subnet 2, the first subnet 3 and the first subnet 4 all belong to the same second subnet, the first subnet 2 and the first subnet 3to be connected are respectively connected to the x port and the y port of the second subnet, and the optical wavelength for establishing the logical lightpath connection of the x port and the y port is λ [x+y]％p . In this case, 1to t of the first subnet 2 can be set 1 The wavelength of one tunable transceiver module in the number tunable transceiver modules is configured to be lambda [x+y]％p 1-t of the first subnetwork 3 1 One tunable receiving and transmitting module in number tunable receiving and transmitting moduleThe block wavelengths are all configured as lambda [x+y]％p A logical lightpath connection of the first subnetwork 2 and the second subnetwork 3 can be established.
Scene 2:
if the first subnet N 1,3 And a first subnetwork N 1,4 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,3 Accessing to a second network N 2,1 Optical port x of an optical wavelength switch in (1), a first subnetwork N 1,4 Accessing to a second network N 2,2 Optical port x of the optical wavelength switch in (1), and a second network N 2,1 And a second network N 2,2 Establishing a second network N by configuring identical optical ports z 2,1 And a second network N 2,2 Configuring the first sub-network N respectively in the logical light path connection of the third network 1,3 And a first subnetwork N 1,4 Wherein one path of light has a wavelength of lambda [x+z]％p To establish a first subnet N 1,3 And a first subnetwork N 1,4 The logic optical path connection between the two; wherein p is the number of ports of the optical wavelength switch,% represents a modulus, the optical port x is one of the optical ports of the optical wavelength switch of the second subnet used for establishing logical optical path connection in the second subnet, and the optical port z is one of the optical ports of the optical wavelength switch of the second subnet used for establishing logical optical path connection with other second subnets.
In the embodiment of the invention, the first subnet N is connected with the first port 1,3 Wherein one path of light has a wavelength of lambda [x+z]％p Thereby establishing a second network N 2,1 A logical lightpath connection between the x port and the z port of (a); will connect to the first subnet N 1,4 Wherein one path of light has a wavelength of lambda [x+z]％p Thereby establishing a second network N 2,2 Is connected to the logical optical path between the x port and the z port. Due to the second network N 2,1 And a second network N 2,2 Has established a logical lightpath connection, while the first subnetwork N is in the process 1,3 It is possible to establish a first subnet N 1,4 Is connected with the logic optical circuit.
FIG. 7 is a logical lightpath connection of two first subnets accessing different second subnets and having the same optical port number according to an embodiment of the present inventionSchematic illustration of the configuration. In fig. 7, the first subnet 1 and the first subnet 2 both belong to the second subnet 1, the first subnet 3 and the first subnet 4 both belong to the second subnet 2, and the second subnet 1 and the second subnet 2 establish a logical lightpath connection through the optical port z. The first subnet 1 and the first subnet 3to be connected are respectively connected to the optical port x of the second subnet 1 and the second subnet 2, and the optical wavelength for establishing the logical optical path connection of the optical port x and the optical port z is λ [x+z]％p . At this time, t of the first subnet 1 may be set 1 The wavelength of one tunable transceiver module in the + 1-t tunable transceiver modules is configured as lambda [x+z]％p T of the first subnetwork 3 1 The wavelength of one tunable transceiver module in the + 1-t tunable transceiver modules is configured as lambda [x+z]％p A logical lightpath connection of the first subnetwork 2 and the second subnetwork 3 can be established.
Scene 3:
if the first subnet N 1,5 And a first subnetwork N 1,6 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,5 Accessing to a second network N 2,3 Optical port x of the optical wavelength switch in (1), first subnetwork N 1,6 Accessing to a second network N 2,3 Optical port y of the optical wavelength switch in (1), second network N 2,3 And a second network N 2,4 Establishing a second network N by configuring identical optical ports z 2,3 And a second network N 2,4 In the logical lightpath connection of the third network, the first subnetwork N 1,7 Accessing to a second network N 2,3 The optical port x of the optical wavelength switch in the optical network, then the first subnet N is configured 1,5 Wherein one path of light has a wavelength of lambda [x+z]％p Configuring a first subnet N 1,7 Wherein one path of light has a wavelength of lambda [x+z]％p To establish a first subnet N 1,5 And a first subnetwork N 1,7 A logical lightpath connection between them, and configure a first subnet N 1,7 Wherein the other path of light has a wavelength of λ [x+y]％p Configuring a first subnet N 1,6 Wherein one path of light has a wavelength of lambda [x+y]％p To establish a first subnet N 1,7 And a first subnetwork N 1,6 To establish a logical lightpath connection between them, thereby establishing a first subnetwork N 1,5 And a first subnetwork N 1,6 The logic optical path connection between the two; wherein p is the number of ports of the optical wavelength switch,% represents a modulus, the optical port x and the optical port y are respectively one of the optical ports of the optical wavelength switch of the second subnet for establishing a logical optical path connection in the second subnet, and the optical port z is one of the optical ports of the optical wavelength switch of the second subnet for establishing a logical optical path connection with other second subnets.
In the embodiment of the invention, the first subnet N is connected with the second subnet N 1,5 Wherein one path of light wavelength is configured as lambda [x+z]％p The first subnet N 1,7 Wherein one path of light wavelength is configured as lambda [x+z]％p Then, a first subnet N is established 1,5 And a first subnetwork N 1,7 The logic optical path connection between the two; by connecting the first subnetwork N 1,7 Wherein the other light wavelength is configured as lambda [x+y]％p The first subnet N 1,6 Wherein one path of light wavelength is configured as lambda [x+y]％p Then the first subnet N can be established 1,7 And a first subnetwork N 1,6 The logic optical path connection between the two; first subnetwork N 1,5 And a first subnetwork N 1,7 A logical light path connection is established between them, a first subnet N 1,7 And a first subnetwork N 1,6 A logical lightpath connection is established between them, so that a first subnetwork N can be connected 1,5 And a first subnetwork N 1,6 A logical lightpath connection is established between them.
Fig. 8 is a schematic diagram of a logical lightpath connection configuration accessing two different second subnets and accessing two first subnets with different optical port numbers according to an embodiment of the present invention. In fig. 8, the first subnet 1 and the first subnet 2 both belong to the second subnet 1, the first subnet 3 and the first subnet 4 both belong to the second subnet 2, and the second subnet 1 and the second subnet 2 establish a logical lightpath connection through the optical port z. The first subnet 1 and the first subnet 2 are respectively connected to the optical port x and the optical port y of the second subnet 1, the first subnet 3 and the first subnet 4 are respectively connected to the optical port x and the optical port y of the second subnet 2, and the optical wavelength for establishing the logical optical path connection of the optical port x and the optical port y is λ [x+y]％p Optical wavelength used to establish logical lightpath connection of optical port x and optical port zIs λ [x+z]％p The first subnet 1 and the first subnet 4 are the first subnets to be connected.
At this time, as shown in fig. 8, first, in step1, by applying t of the first subnet 1 1 The wavelength of one tunable transceiver module in the + 1-t tunable transceiver modules is configured as lambda [x+z]％p T of the first subnetwork 3 1 The wavelength of one tunable transceiver module in the + 1-t tunable transceiver modules is configured as lambda [x+z]％p Thereby establishing a logical lightpath connection of the first subnetwork 2 and the second subnetwork 3; then, in step2, 1to t of the first subnetwork 3 are combined 1 The wavelength of the other tunable transceiver module in the number tunable transceiver modules is configured as lambda [x+y]％p 1to t of the first subnet 4 1 The wavelength of one tunable transceiver module in the number tunable transceiver modules is configured as lambda [x+y]％p Thereby establishing a logical lightpath connection of the first subnetwork 3 and the second subnetwork 4; at this time, the first subnet 1 can establish a logical lightpath connection with the first subnet 4 through the first subnet 3. Of course, it should be understood that, in the scenario shown in fig. 8, a logical lightpath connection between the first subnet 1 and the first subnet 2 may also be established, and a logical lightpath connection between the first subnet 2 and the first subnet 4 may also be established, at this time, the first subnet 1 may establish a logical lightpath connection with the first subnet 4 through the first subnet 2.
In order to describe the content of the present invention more intuitively, the embodiment of the present invention further provides a specific wavelength solving formula and a logical light path constructing algorithm required when Torus and HyperX logical topologies are constructed. For convenience of description, λ is used in the present embodiment i j Indicating the ith first subnet Node i Middle j optical port TRX j Represents the Optical path connection relationship of the MEMS-based Optical Switch by a LinkMatrix (LM) matrix, wherein the wavelength configuration in all the second sub-networks (AWGR) is the same, and LM [ i [ [ i ] is][j]= P stands for Rack i P port and Rack of j Is connected through a MEMS-based Optical Switch.
Based on the wavelength configuration rule for the connection of the two first subnets in the 3 scenarios shown in fig. 6 to 8, the reconfiguration controller may configure the wavelength configuration information of each first subnet according to the topology structure and the logical lightpath connection relationship of the optical network.
Optionally, as an embodiment, the third network is r 1 Network of D-Torus structure, r 1 With n for each dimension in a network of D-Torus structures 1 A second network, the third network having n 1 r1 A second network, each of the second networks being r 2 Network of D-Torus structure, the r 1 With n per dimension in a network of D-Torus architectures 2 A first network, each of the second networks having n 2 r2 A first sub-network, the wavelength configuration information of each first sub-network in the first network is expressed by the following formula:
if ((i-1)% n) 2 (j+1)/2 <n 2 (j-1)/2 )&&(j％2＝＝1)&&(j≤2r 2 ) Then the
Otherwise, if ((i-1)% n 2 (j+1)/2 ≥(n 2 -1)n 2 (j-1)/2 )&&(j％2＝＝0)&&(j≤2r 2 ) Then, then
Otherwise, if (j ≦ 2r 2 ) Then, then
Otherwise, if (2 r) 2 <j≤2r 1 +2r 2 ) Then, then
Wherein λ is i j The wavelength of the ith first subnet accessing the jth optical port is represented, P represents the number of optical ports of the optical wavelength switch corresponding to the second subnet,% represents the modular operation, i and j respectively satisfy the condition that i is more than or equal to 1 and is less than or equal to n 2 r2 ,1≤j≤2r 1 +2r 2 N is the number of first subnets connected to each of the second subnets, and N = N is satisfied 2 r2 。
Or, optionally, as another embodiment, the third network is a network of a 1-layer HyperX structure, and each dimension in the network of the 1-layer HyperX structure has s 1 A second network, the third network having s in common 1 A second network, each of the second networks being a network of a 2-layer HyperX structure, each dimension of the network of the 2-layer HyperX structure having s 2× s 3 A first network, each of the second networks having s in common 2× s 3 A first sub-network, the wavelength configuration information of each first sub-network in the first network is expressed by the following formula:
if (1. Ltoreq. J. Ltoreq. I-1)% s 3 ) Then, then
Otherwise, if ((i-1)% s) 3 <j≤s 3 -1)
Otherwise, if(s) 3 ≤j≤s 2 +s 3 -2)&&(j-s 3 <(i-1)/s 3 ) Then, then
Otherwise, if(s) 3 ≤j≤s 2 +s 3 -2)&&(j-s 3 ≥(i-1)/s 3 ) Then, then
Otherwise, if(s) 2 +s 3 -1≤j≤s 1 +s 2 +s 3 -3) then
Wherein λ is i j The wavelength of the ith first subnet accessing the jth optical port is represented, P represents the number of optical ports of the optical wavelength switch corresponding to the second subnet,% represents the modular operation, i satisfies 1 ≦ i ≦ s 2 ×s 3 ,1≤j≤s 1 +s 2 +s 3 -3,N is the number of first subnets connected to each of the second subnets, with a value s 2× s 3 。
In order to facilitate understanding of the optical path configuration information of the third network and the wavelength configuration information of the first subnet in the first network in the embodiment of the present invention, the following description is made with reference to fig. 9 and 10.
FIG. 9 is a schematic flow chart of an embodiment of the present invention for constructing a Torus logical topology. In fig. 9, the Pod interconnect is based on an optical network implementation. As shown in fig. 9, the Network topology of the Inter-Rack Network (i.e. the third Network in the embodiment shown in fig. 1, or the L3 Network in the embodiment shown in fig. 2) is r 1 D-Torus structure with n per dimension 1 A Rack; the Network topology of the Intra-Rack Network (i.e., the second Network in the embodiment shown in FIG. 1, or the L2 Network in the embodiment shown in FIG. 2) is r 2 D-Torus structure with n per dimension 2 Node, r = r 1 +r 2 . Therefore, the optical network Pod contains n 1 r1 A Rack, denoted as Rack 1 ～Rackn 1 r1 Each Rack contains n 2 r2 Each Node, marked as Node 1 ～Noden 2 r2 。
For rD-Torus topology, a MEMS-based Optical Switch's Optical path connection rule: when any two racks are optically connected through the MEMS-based Optical Switch, the ports used by the racks must be consistent, and the LM matrix is a symmetric matrix. The LM matrix solving method based on greedy algorithm is shown in Table 2:
TABLE 2Torus topology LM matrix solving algorithm
Wherein k is 1 The value is (k + f (d))% n 1 r ,k 2 The value is (k-f (d))% n 1 r K is equal to or more than 1 and equal to or less than n 1 r1 And k is all values of odd number, and the value of d satisfies the condition that d is more than or equal to 1 and less than or equal to r 1 D is all values of positive integer, f (d) is function related to d, value is integer, N is number of first sub-network connected to each second sub-network, N = N 2 r2 ，LM[i][j]= x denotes that the xth optical port of the ith second subnet and the xth optical port of the jth second subnet are connected through the optical space switch.
For rD-Torus topology, each Node needs at least (2 r) 1+ 2r 2 ) Each TRXs, denoted as TRX 1 ～TRX (2r1+2r2) One wavelength assignment algorithm is: TRX 1 ～TRX 2r2 For an Intra-Rack Network (i.e., the second Network of the embodiment shown in FIG. 1, or the L2 Network of the embodiment shown in FIG. 2), TRX 2r2+1 ～TRX (2r1+2r2) For an Inter-Rack Network (i.e., the third Network in the embodiment shown in fig. 1, or the L3 Network in the embodiment shown in fig. 2), the corresponding wavelength calculation formula is shown in table 3:
TABLE 3Torus topology wavelength allocation formula
Wherein λ is i j The wavelength of the ith first subnet accessing the jth optical port is represented, P represents the number of optical ports of the optical wavelength switch corresponding to the second subnet,% represents the modular operation, i and j respectively satisfy the condition that i is more than or equal to 1 and is less than or equal to n 2 r2 ,1≤j≤2r 1 +2r 2 N is the number of the first sub-networks connected to each of the second sub-networks, and N = N is satisfied 2 r2 。
The logical topology of the Optical network can be reconstructed to rD-Torus according to the method shown in the pseudo code of the above table 1 and table 2, for example, the Optical interconnection structure is composed of 1 16-port MEMS-based Optical Switch and 4 8-port AWGR, and then the logical topology can be reconstructed to 4 × 4 2D-Torus according to the equations (1) - (4) and the algorithm of table 2, and the specific reconstruction process is shown in fig. 9, wherein r is 1 ＝r 2 ＝1,n 1 ＝n 2 ＝4：
Pod can be mapped into a1 × 4Tours structure of 4 racks, each Rack can be mapped into a 4 × 1Torus structure of 4 nodes, and the mapping process is shown in fig. 9 (a).
The 4 Rack in the Pod are connected through the MEMS-based Optical Switch, the Optical port and the connection information are shown in FIG. 9 (B), and the corresponding LM connection matrix is shown in FIG. 9 (C), such as LM [1 ]][2]=6, then Rack 1 And Rack 2 Connected through respective 6 ports.
The ports 1-4 of the AWGR in each Rack are connected with the Node in turn 1 ～Node 4 Ports 5 and 6 are connected to MEMS-based Optical Switch, ports 7 and 8 can be used to build fast links or shut down to reduce power consumption, and the wavelength of TRXs in a Node can be derived from a formula, such as for a Node 1 λ is obtained from i =1, n =4, p =8 according to equation (1) in table 2 1 1 ＝λ 5 λ is obtained according to equation (3) in Table 2 3 1 ＝λ 6 λ is obtained according to the formula (4) of Table 2 3 1 ＝λ 6 ,λ 4 1 ＝λ 7 In this way all wavelength settings can be derived, see fig. 9 (D).
Fig. 10 is a schematic flowchart of constructing a HyperX network topology according to an embodiment of the present invention. In fig. 10, pod is the optical network. As shown in fig. 10, the network topology of the third network (L3-layer network) is a HyperX (L = 1) structure, and each dimension has s 1 A Rack; the network topology of the second network (L2 layer network) is a HyperX (L = 2) structure with s for each dimension 2× s 3 And each Node. Thus having s in common within the Pod 1 A Rack, denoted as Rack 1 ～Racks 1 Each Rack contains s 2× s 3 Each Node, marked as Node 1 ～Nodes 2 s 3 。
For the HyperX topology, a MEMS-based Optical Switch Optical path connection rule: when any two racks are optically connected through the MEMS-based Optical Switch, the ports used by the racks must be consistent, and the LM matrix is a symmetric matrix. The corresponding algorithm to solve the LM matrix is shown in table 4:
TABLE 4HyperX topology LM matrix solving algorithm
Wherein, LM [ i ]][j]= x denotes that a maxval (i, j) th optical port of the ith second subnet and a maxval (i, j) th optical port of the jth second subnet are connected through the optical space switch, maxval (i, j) denotes prob i,j The value of val is the maximum value, where val is N +1 or more and N + s or less 1 A positive integer of-1, prob i,j (val) represents the ratio of the number of optical paths to be constructed which can be completed by the optical port val to the number of all optical paths to be constructed, and the value of i, j includes 1to s 1 N is a positive integer connected to each of the second sub-unitsThe number of the first sub-network of the network, N being s 2× s 3 。
For the HyperX topology, each Node needs at least(s) 1+ s 2+ s 3 -3) TRXs, noted TRX 1 ～TRX s1+s2+s3-3 One wavelength assignment algorithm is: TRX 1 ～TRX s2+s3-2 For an Intra-Rack Network (i.e., the second Network of the embodiment shown in FIG. 1, or the L2 Network of the embodiment shown in FIG. 2), TRX s2+s3-1 ～TRX s1+s2+s3-3 For an Inter-Rack Network (i.e., the third Network in the embodiment shown in fig. 1, or the L3 Network in the embodiment shown in fig. 2), the corresponding wavelength calculation formula is shown in table 5:
TABLE 5HyperX topology wavelength assignment equation
Wherein λ is i j The wavelength of the ith first subnet accessing the jth optical port is represented, P represents the number of optical ports of the optical wavelength switch corresponding to the second subnet,% represents the modular operation, i satisfies 1 ≦ i ≦ s 2 ×s 3 ,1≤j≤s 1 +s 2 +s 3 -3,N is the number of first subnets connected to each of the second subnets, with a value s 2× s 3 。
The Optical network can be reconfigured into a HyperX topology according to the methods shown in the pseudo codes of table 3 and table 4, and taking the physical structure exactly the same as that in embodiment 1 as an example, an Optical interconnection structure is formed by 1 16-port MEMS-based Optical Switch and 4 8-port AWGR, and Pod can be reconfigured into a HyperX (L = 3) topology according to the formulas (5) - (9) in table 4 and the algorithm in table 3, where s =3 1 ＝4,s 2 ＝s 3 =2, the detailed reconstruction process is shown in fig. 10:
the Pod can be mapped to a Hyper (L = 1) structure composed of 4 racks, and each Rack can be mapped to a Hyper (L = 2) structure composed of 4 nodes, and the mapping process is shown in fig. 10.
4 Rack in Pod passes through MEMS-based OThe logical Switch connection, optical port and connection information is shown in FIG. 10, and the corresponding LM connection matrix is shown in FIG. 10, e.g., LM [1 ]][2]=5, then Rack 1 And Rack 2 Connected through respective 5 ports.
The ports 1-4 of the AWGR in each Rack are connected with the Node in turn 1 ～Node 4 Ports 5-7 are connected to MEMS-based Optical Switch, port 8 can be used to build fast links or shut down to reduce power consumption, and the wavelength of TRXs in a Node can be derived from a formula, such as for a Node 1 λ is obtained by i =1,n =4,p =8 according to equation (6) 1 1 ＝λ 3 Obtaining λ according to equation (8) 2 1 ＝λ 4 Obtaining λ according to equation (9) 3 1 ＝λ 6 ,λ 4 1 ＝λ 7 ，λ 5 1 ＝λ 8 In this way all wavelength settings can be derived, see fig. 10.
Based on the foregoing embodiments, an embodiment of the present invention discloses a reconfiguration controller, where the reconfiguration controller is a device for controlling devices in the first and third layers. The reconfiguration controller is also an abstract, generalized term and does not represent a real hardware device. In practical implementation, the hardware device may generally include only one hardware device, and the hardware device may mainly include a general-purpose processor or an FPGA, and at the same time, the hardware device needs to include corresponding interfaces to connect with the devices in the first and third layers to control the devices in the first and third layers. In particular, the wavelength control module is used for controlling the wavelength of each optical wavelength tunable transceiver in the first layer network and controlling which two ports in the MBOS or the OXC in the third layer network are interconnected.
In other embodiments, the reconfiguration controller may also include two or more physical hardware devices that are connected to one or more of the first and third layers of devices, respectively, to effect control. Meanwhile, the hardware devices can communicate with each other and cooperate with each other in a unified manner to realize the control of the whole optical network.
By way of example and not limitation, the reconstruction controller may include: the device comprises a target logic topological structure determining unit, a resource configuration determining unit, a logic light path configuration unit and a wavelength configuration unit.
The target logic topology structure determining unit is used for finding the matched target logic topology structure according to the communication characteristics of the optical network.
Specifically, for example, a mapping relationship table of the communication characteristics and the network topology structure may be stored in the reconfiguration controller, and the topology matching unit may search the corresponding target logical topology structure by searching the mapping relationship table according to the communication characteristics of the current optical network. Furthermore, the topology matching unit does not exclude the use of other ways than table look-up to determine the target logical topology. For example, the topology matching unit may determine the target logical topology (or determine relevant parameters of the target logical topology) through a predetermined calculation rule, and so on.
Of course, the topology matching unit may also select the target logical topology based on more information. For example, the topology matching unit may determine the target logical topology according to communication characteristics, the number of nodes, hardware resources, and the like. At this time, the mapping relationship table may further include a mapping relationship between input information such as communication characteristics, the number of nodes, and hardware resources, and a corresponding network topology, and the like.
The resource allocation determining unit is used for determining the target resource allocation of the optical network according to the communication characteristics and the target logic topological structure (or the target logic topological structure manually configured by the network manager) determined by the topology matching unit. The target resource allocation of the optical network according to the embodiment of the present invention may include allocation of usage modes of optical link resources and optical port resources. Specifically, the usage of the optical link resource and the optical port resource may refer to whether the optical link resource and the optical port resource are used.
In addition, the resource configuration unit in the embodiment of the present invention may further determine whether to establish a fast link according to the load traffic of each node (L2 subnet or L1 subnet) in the topology network.
If the resource configuration unit determines that the load traffic between two nodes (which may be two L2 subnets or two L1 subnets) is greater than a predetermined threshold, the resource configuration unit may also establish a fast link (including an optical link and an optical port resource) between the two nodes, thereby alleviating network congestion. In addition, the resource configuration unit can also close unused redundant resources to reduce the system power consumption.
The logical light path configuration unit is used for receiving the target logical topological structure and the target resource configuration, solving the logical light path connection relation of the L3 layer optical network according to the target logical topological structure and the target resource configuration, and sending light path configuration information used for specifying the connection relation among all ports of all the space exchangers in the L3 layer network to the light path control device of the L3 layer network.
The wavelength configuration unit is used for receiving the target logic topological structure and the target resource configuration, solving the logic light path connection relation of the L2 layer optical network according to the target logic topological structure and the target resource configuration, and sending specific wavelength configuration information to the tunable transceiving module of the L1 subnet. In particular, the tunable transceiver module may include a wavelength tunable transceiver, a wavelength tunable laser, or the like.
Of course, it should be understood that the reconfiguration controller may also include a topology manual matching unit and/or a resource manual configuration unit. The topology manual matching unit is used for a network manager to manually configure a target logic topology structure of the optical network; and the resource manual configuration unit is used for manually configuring the target resource configuration of the optical network by network management personnel.
Fig. 11 is a schematic structural diagram of a reconfiguration controller 900 according to an embodiment of the present invention. The reconfiguration controller 900 may include a processor 902, a channel interface 901.
Optionally, the reconstruction controller 900 may also include a memory 903 for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory 903 may include both read-only memory and random access memory, and provides instructions and data to the processor 902. The memory 903 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The channel interface 901, the processor 902 and the memory 903 are interconnected by a bus 904 system. Bus 904 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 11, but that does not indicate only one bus or one type of bus.
The method performed by the reconstruction controller according to the embodiment of the present invention shown in fig. 1 and 2 can be applied to the processor 902 or implemented by the processor 902. The processor 902 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 902. The Processor 902 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete valve or transistor logic, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 903, and the processor 902 reads the information in the memory 903 and performs the steps of the above method in combination with the hardware thereof.
Optionally, the processor 902 may also be configured to execute the method executed by the reconfiguration controller according to the embodiment shown in fig. 1 and fig. 2, and for specific implementation, reference may be made to the embodiment shown in fig. 1 and fig. 2, which is not described herein again in this embodiment of the present invention.
The embodiment of the invention also discloses an optical network system, which comprises a first network, a second network, a third network and a reconfiguration controller, wherein the first network comprises a plurality of first subnets, the second network is an optical interconnection network based on optical wavelength switching and comprises a plurality of second subnets, and the third network is an optical interconnection network based on space switching,
the third network establishes optical path connection between the second subnets in the second network based on space switching, and each second subnet is respectively connected to the downlink optical ports of the third network through the same number of uplink optical ports;
the second network establishes optical path connection of the first subnets in the first network based on optical wavelength switching, an uplink optical port of each first subnet is accessed to a downlink optical port of one second subnet, and two first subnets configure specified optical signal wavelength according to the accessed downlink optical port of the second subnet to establish optical path connection, wherein the two first subnets belong to the same second subnet or respectively belong to two different second subnets establishing optical path connection;
each first sub-network in the first network is further used for realizing the electrical signal connection of different electrical domain units in the first sub-network, and a downlink port in each first sub-network is connected to an electrical domain unit;
the reconstruction controller may be the reconstruction controller in the embodiments shown in fig. 1, 2, 11.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (19)

1. A logical lightpath reconfiguration method of an optical network is applied to the optical network, the optical network comprises a first network, a second network, a third network and a reconfiguration controller, the first network comprises a plurality of first subnets, the second network is an optical interconnection network based on optical wavelength switching and comprises a plurality of second subnets, the third network is an optical interconnection network based on space switching, wherein,
the third network establishes optical path connection between the second subnets in the second network based on spatial switching, and each second subnet is respectively connected to the downlink optical ports of the third network through the same number of uplink optical ports;
the second network establishes optical path connection of the first subnets in the first network based on optical wavelength switching, an uplink optical port of each first subnet is accessed to a downlink optical port of one second subnet, and the two first subnets configure a designated optical signal wavelength according to the accessed downlink optical port of the second subnet to establish optical path connection, wherein the two first subnets belong to the same second subnet or respectively belong to two different second subnets establishing optical path connection;
each first sub-network in the first network is further used for realizing the electrical signal connection of different electrical domain units in the first sub-network, and a downlink port in each first sub-network is connected to an electrical domain unit;
the reconfiguration controller is in communication connection with the optical path control device of the third network, the optical path control device is used for reconfiguring and configuring the logical optical path of the third network, and the reconfiguration controller is in communication connection with each first subnet;
the method comprises the following steps:
the reconfiguration controller determines a target logical light path connection relation of the third network according to a target logical topology structure of the optical network and a target resource configuration of the optical network, determines light path configuration information of the third network according to the target logical light path connection relation of the third network, and sends the light path configuration information to a light path control device of the third network, wherein the light path configuration information is used for instructing the light path control device to reconfigure and configure the logical light path connection of the third network to form the target logical light path connection relation of the third network;
the reconfiguration controller determines a target logical lightpath connection relationship of the second network according to a target logical topology structure of the optical network and a target resource configuration of the optical network, determines wavelength configuration information of each first subnet in the first network according to the target logical lightpath connection relationship of the second network, and sends the wavelength configuration information to the corresponding first subnet, where the wavelength configuration information of each first subnet in the first network is used to configure an optical signal wavelength of each corresponding first subnet in the first network, so as to form the target logical lightpath connection relationship of the second network.
2. The method of claim 1,
each of the second subnets includes an optical wavelength switch, one uplink optical port of any one of the optical wavelength switches is connected to at most one downlink optical port of the third network, one downlink optical port of the third network is connected to at most one uplink optical port of one optical wavelength switch, and each downlink optical port of the optical wavelength switch is connected to at most one uplink optical port of the first subnet.
3. The method of claim 2,
at most one optical link passing through the third network is configured between any two second subnets in the second network, and in the optical path configuration information of the third network, the optical wavelength exchangers of the two second subnets performing optical path connection configure the same uplink optical port number.
4. The method of claim 3, wherein the third network is r 1 Network of D-Torus structures, said r 1 With n per dimension in a network of D-Torus architectures 1 A second network, said third network having n in total 1 r1 A second network, each of said second networks being r 2 Network of D-Torus structure, said r 1 With n per dimension in a network of D-Torus architectures 2 A first network, each of said second networks having n 2 r2 A first subnet, said lightpath configuration information being represented by the following formula:
wherein k is a value satisfyingK is all values of odd numbers, and the value of d satisfies the condition that d is more than or equal to 1 and less than or equal to r 1 D is all values of a positive integer, f (d) is a function related to d, taking the value as an integer, N is the number of first subnets connected to each of the second subnets, and N = N is satisfied 2 r2 ，LM[i][j]= x denotes that the xth optical port of the ith second subnet and the xth optical port of the jth second subnet are connected by an optical space switch.
5. The method of claim 4, wherein the function f (d) is expressed as f (d) = n 1 (d-1) 。
6. The method of claim 3, wherein the third network is a network of a 1-layer HyperX architecture, each dimension in the network of the 1-layer HyperX architecture having s 1 A second network, said third network having s in common 1 Each second network is a network with a 2-layer HyperX structure, and each dimension in the network with the 2-layer HyperX structure has s 2 ×s 3 A first network, each of said second networks having s in common 2 ×s 3 A first subnet, said lightpath configuration information being represented by the following formula:
LM [ i ] [ j ] = maxval (i, j), wherein
LM[i][j]= x denotes that a maxval (i, j) th optical port of the ith second subnet and a maxval (i, j) th optical port of the jth second subnet are connected through the optical space switch, maxval (i, j) denotes prob i,j A value of (val) when the value is the maximum, wherein val is not less than N +1 and not more than N + s 1 A positive integer of-1, prob i,j (val) represents the ratio of the number of optical paths to be constructed which can be completed by the optical port val to the number of all optical paths to be constructed, and the value of i, j includes 1to s 1 N is the number of first subnets connected to each of said second subnets, N taking the value s 2 ×s 3 。
7. The method of claim 3,
the determining the wavelength configuration information of each first subnet in the first network according to the target logical lightpath connection relationship of the second network includes:
determining wavelength configuration information of each first subnet in the first network according to a target logical light path connection relationship of the second network and an optical wavelength switching rule of an optical wavelength exchanger corresponding to each second subnet in the second network;
and the optical wavelength exchangers corresponding to each second subnet in the second network adopt the same optical wavelength switching rule.
8. The method of claim 7, wherein the determining the wavelength configuration information of each first subnet in the first network according to the target logical lightpath connection relationship of the second network and the optical wavelength switching rule of the optical wavelength switch corresponding to each second subnet in the second network comprises:
if the first subnet N 1,1 And a first subnetwork N 1,2 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,1 And a first subnetwork N 1,2 The optical port x and the optical port y of the optical wavelength switch respectively connected to the second network configure the first subnet N respectively 1,1 And a first subnetwork N 1,2 Wherein one path of light has a wavelength of lambda [x+y]％p To establish a first subnet N 1,1 And a first subnetwork N 1,2 The logic optical path connection between the two; or
If the first subnet N 1,3 And a first subnetwork N 1,4 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,3 Accessing to a second network N 2,1 Optical port x of an optical wavelength switch in (1), a first subnetwork N 1,4 Accessing to a second network N 2,2 Optical port x of an optical wavelength switch in the network, and a second network N 2,1 And a second network N 2,2 Establishing a second network N by configuring identical optical ports z 2,1 And a second network N 2,2 Configuring the first sub-network N respectively in the logical light path connection of the third network 1,3 And a first subnetwork N 1,4 Wherein one path of light has a wavelength of lambda [x+z]％p To establish a first subnet N 1,3 And a first subnetwork N 1,4 The logic optical path connection between the two; or
If the first subnet N 1,5 And a first subnetwork N 1,6 The logical lightpath connection relationship is to establish connection, and the first subnet N 1,5 Accessing to a second network N 2,3 Optical port x of the optical wavelength switch in (1), first subnetwork N 1,6 Accessing to a second network N 2,3 Light of the optical wavelength converter in (1)Port y, and a second network N 2,3 And a second network N 2,4 Establishing a second network N by configuring the same optical port z 2,3 And a second network N 2,4 A logical lightpath connection in a third network, and a first subnetwork N 1,7 Accessing to a second network N 2,3 The optical port y of the optical wavelength switch in (1) is configured with the first subnet N 1,5 Wherein one path of light has a wavelength of lambda [x+z]％p Configuring a first subnet N 1,7 Wherein one path of light has a wavelength of lambda [x+z]％p To establish a first subnet N 1,5 And a first subnetwork N 1,7 And configuring a first subnet N 1,7 Wherein the other light wavelength is lambda [x+y]％p Configuring the first subnet N 1,6 Wherein one path of light has a wavelength of lambda [x+y]％p To establish a first subnet N 1,7 And a first subnetwork N 1,6 To establish a logical lightpath connection between them, thereby establishing a first subnetwork N 1,5 And a first subnetwork N 1,6 The logic optical path connection between the two;
wherein p is the number of ports of the optical wavelength switch,% represents the modulus, optical ports x and y are the optical ports used for establishing logical optical path connection in the second subnet among all the optical ports of the optical wavelength switch in the second subnet, and optical port z is the optical port used for establishing logical optical path connection with other second subnets among all the optical ports of the optical wavelength switch in the second subnet.
9. The method of claim 8,
the third network is r 1 Network of D-Torus structures, said r 1 With n per dimension in a network of D-Torus architectures 1 A second network, said third network having n in total 1 r1 A second network, each of said second networks being r 2 Network of D-Torus structure, said r 1 With n for each dimension in a network of D-Torus structures 2 A first network, each of said second networks having n 2 r2 A first sub-network, wherein the wavelength configuration information of each first sub-network in the first network is expressed by the following formula:
if ((i-1)% n) 2 (j+1)/2 <n 2 (j-1)/2 )&&(j％2＝＝1)&&(j≤2r 2 ) Then, then
Otherwise, if ((i-1)% n) 2 (j+1)/2 ≥(n 2 -1)n 2 (j-1)/2 )&&(j％2＝＝0)&&(j≤2r 2 ) Then, then
Otherwise, if (j ≦ 2r 2 ) Then, then
Otherwise, if (2 r) 2 <j≤2r 1 +2r 2 ) Then, then
Wherein the content of the first and second substances,the wavelength of the ith first subnet accessing the jth optical port is represented, P represents the number of optical ports of the optical wavelength switch corresponding to the second subnet,% represents the modular operation, i and j respectively satisfy the condition that i is more than or equal to 1 and is less than or equal to n 2 r2 ,1≤j≤2r 1 +2r 2 N is the number of first subnets connected to each of the second subnets, and N = N is satisfied 2 r2 。
10. The method of claim 8, wherein the third network is a network of a 1-layer HyperX architecture,each dimension in the network of the 1-layer HyperX structure has s 1 A second network, said third network having s in common 1 Each second network is a network with a 2-layer HyperX structure, and each dimension in the network with the 2-layer HyperX structure has s 2 ×s 3 A first network, each of said second networks having s in common 2 ×s 3 A first sub-network, wherein the wavelength configuration information of each first sub-network in the first network is expressed by the following formula:
if (1. Ltoreq. J. Ltoreq. I-1)% s 3 ) Then, then
Otherwise, if ((i-1)% s) 3 <j≤s 3 -1) then
Otherwise, if(s) 3 ≤j≤s 2 +s 3 -2)&&(j-s 3 <(i-1)/s 3 ) Then, then
Otherwise, if(s) 3 ≤j≤s 2 +s 3 -2)&&(j-s 3 ≥(i-1)/s 3 ) Then, then
Otherwise, if(s) 2 +s 3 -1≤j≤s 1 +s 2 +s 3 -3) then
Wherein the content of the first and second substances,the wavelength of the ith first subnet accessing the jth optical port is represented, P represents the number of optical ports of the optical wavelength switch corresponding to the second subnet,% represents the modular operation, i satisfies 1 ≦ i ≦ s 2 ×s 3 ,1≤j≤s 1 +s 2 +s 3 -3,N is the number of first subnets connected to each of said second subnets, with a value s 2 ×s 3 。
11. The method of any of claims 1to 10, further comprising:
the reconfiguration controller determines a target logic topological structure of the optical network according to the communication characteristics of the optical network;
and the reconfiguration controller determines the target resource configuration of the optical network according to the communication characteristics of the optical network and the target logic topological structure of the optical network.
12. The method according to claims 1to 11, wherein the target resource configuration of the optical network comprises a usage pattern configuration of optical link resources and optical port resources.
13. The method according to any one of claims 1to 12, wherein the first subnet includes a complex function unit and a plurality of wavelength tunable transceivers, and the complex function unit is configured to aggregate, by wavelength division multiplexing, the plurality of optical signals with different wavelengths of the plurality of wavelength tunable transceivers into one optical signal to be sent to the downstream optical port of the second subnet connected to the first subnet, or demultiplex one optical signal with a plurality of wavelengths of the downstream optical port of the second subnet connected to the first subnet into a plurality of optical signals with different wavelengths to be sent to the wavelength tunable transceivers with the same wavelength among the plurality of wavelength tunable transceivers, respectively.
14. The method of any of claims 1to 13, wherein the electrical domain unit comprises a Central Processing Unit (CPU), a compute node, a Rack, an electrical domain switch.
15. The method of any of claims 1to 14, wherein the third network comprises one optical space switch or the third network comprises a cascade of a plurality of optical space switches.
16. The method of any one of claims 1to 15, further comprising:
the reconfiguration controller determines a first node and a second node with load flow greater than a predetermined threshold;
the reconfiguration controller establishes a fast link between the first node and the second node from the unconfigured resources of the optical network;
wherein the first node and the second node are both the first subnet, or the first node and the second node are both the second subnet.
17. The method of any one of claims 1to 16, further comprising:
the reconfiguration controller shuts down unused resources in the optical network.
18. A reconstruction controller comprising a processing module for performing the method of any one of claims 1to 17.
19. An optical network system comprising a first network comprising a plurality of first subnetworks, a second network, being an optical wavelength switching based optical interconnect network, comprising a plurality of second subnetworks, a third network, being a spatial switching based optical interconnect network, and a reconfiguration controller, wherein,
the third network establishes optical path connection between the second subnets in the second network based on spatial switching, and each second subnet is respectively connected to the downlink optical ports of the third network through the same number of uplink optical ports;
the second network establishes optical path connection of the first subnets in the first network based on optical wavelength switching, an uplink optical port of each first subnet is accessed to a downlink optical port of one second subnet, and the two first subnets configure specified optical signal wavelength according to the accessed downlink optical port of the second subnet to establish optical path connection, wherein the two first subnets belong to the same second subnet or respectively belong to two different second subnets establishing optical path connection;
each first sub-network in the first network is further used for realizing the electric signal connection of different electric domain units in the first sub-network, and a downlink port in each first sub-network is connected to an electric domain unit;
the reconfiguration controller is in communication connection with the optical path control device of the third network, the optical path control device is used for reconfiguring and configuring the logical optical path of the third network, and the reconfiguration controller is in communication connection with each first subnet;
the reconstruction controller is the reconstruction controller of claim 18.
CN201710598765.3A 2016-11-10 2017-07-21 Logical topology reconstruction method of optical network, reconstruction controller and optical network system Active CN107509126B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610988995 2016-11-10
CN2016109889956 2016-11-10

Publications (2)

Publication Number Publication Date
CN107509126A true CN107509126A (en) 2017-12-22
CN107509126B CN107509126B (en) 2020-03-10

Family

ID=60688769

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710598765.3A Active CN107509126B (en) 2016-11-10 2017-07-21 Logical topology reconstruction method of optical network, reconstruction controller and optical network system

Country Status (1)

Country Link
CN (1) CN107509126B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109640196A (en) * 2018-11-26 2019-04-16 中国人民解放军国防科技大学 Wireless optical communication link reconfigurable system for data center
CN111954099A (en) * 2019-05-17 2020-11-17 华为技术有限公司 Data center system and data center control method
CN114070286A (en) * 2021-10-25 2022-02-18 中国电子科技集团公司第二十九研究所 Arbitrary routing radio frequency switch matrix
CN115499271A (en) * 2022-08-30 2022-12-20 西北工业大学 Hybrid network topology structure and routing method thereof

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101895463A (en) * 2010-04-20 2010-11-24 上海大学 System and method for achieving network reconfigurability of mixed WDM (Wavelength Division Multiplexing)/TDM (Time Division Multiplexing) PON (Passive Optical Network)
US8571415B1 (en) * 2001-07-19 2013-10-29 Alcatel Lucent Regenerators placement mechanism for wavelength switched optical networks
CN105430538A (en) * 2015-10-28 2016-03-23 河北工程大学 Inter-domain routing method based on optical network sub-topological graph

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8571415B1 (en) * 2001-07-19 2013-10-29 Alcatel Lucent Regenerators placement mechanism for wavelength switched optical networks
CN101895463A (en) * 2010-04-20 2010-11-24 上海大学 System and method for achieving network reconfigurability of mixed WDM (Wavelength Division Multiplexing)/TDM (Time Division Multiplexing) PON (Passive Optical Network)
CN105430538A (en) * 2015-10-28 2016-03-23 河北工程大学 Inter-domain routing method based on optical network sub-topological graph

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109640196A (en) * 2018-11-26 2019-04-16 中国人民解放军国防科技大学 Wireless optical communication link reconfigurable system for data center
CN111954099A (en) * 2019-05-17 2020-11-17 华为技术有限公司 Data center system and data center control method
CN111954099B (en) * 2019-05-17 2021-09-14 华为技术有限公司 Data center system and data center control method
CN114070286A (en) * 2021-10-25 2022-02-18 中国电子科技集团公司第二十九研究所 Arbitrary routing radio frequency switch matrix
CN114070286B (en) * 2021-10-25 2023-05-26 中国电子科技集团公司第二十九研究所 Arbitrary route radio frequency switch matrix
CN115499271A (en) * 2022-08-30 2022-12-20 西北工业大学 Hybrid network topology structure and routing method thereof
CN115499271B (en) * 2022-08-30 2023-10-13 西北工业大学 Hybrid network topology structure and routing method thereof

Also Published As

Publication number Publication date
CN107509126B (en) 2020-03-10

Similar Documents

Publication Publication Date Title
US10454585B2 (en) Data center network system and signal transmission system
US9654852B2 (en) Scalable hybrid packet/circuit switching network architecture
CN107509126B (en) Logical topology reconstruction method of optical network, reconstruction controller and optical network system
Chen et al. WaveCube: A scalable, fault-tolerant, high-performance optical data center architecture
Skubic et al. Rethinking optical transport to pave the way for 5G and the networked society
CN103441942B (en) Based on data centre network system and the data communications method of software definition
Ji et al. Prospects and research issues in multi-dimensional all optical networks
Lu et al. Flexible and scalable optical interconnects for data centers: Trends and challenges
Zhu et al. Fully programmable and scalable optical switching fabric for petabyte data center
JP6271757B2 (en) Optical network on chip, and method and apparatus for dynamically adjusting optical link bandwidth
CN102202005B (en) Reconfigurable network on mating plate and configuration method
RU2569323C1 (en) Network node and method in node, which provides first unit with possibility of connection to or being connected to second unit in mode of self-organising network
CN108604940B (en) Optoelectronic switch
Christodoulopoulos et al. Performance evaluation of a hybrid optical/electrical interconnect
Kamchevska et al. Experimental demonstration of multidimensional switching nodes for all-optical data center networks
US11791926B2 (en) Efficiently interconnecting a plurality of computing nodes to form a circuit-switched network
Alvizu et al. Can open flow make transport networks smarter and dynamic? An overview on transport SDN
US20160301495A1 (en) Power Efficient Multi-Degree ROADM Using Variable Optical Splitter
US20200162373A1 (en) Data Center Network (DCN) Architecture and Communication
Le et al. AgileDCN: An agile reconfigurable optical data center network architecture
Chen et al. Toward a scalable, fault-tolerant, high-performance optical data center architecture
CN104618026A (en) Design method of optical fiber interconnection system
Zhao et al. Time-aware software defined networking (Ta-SDN) for flexi-grid optical networks supporting data center application
Barry et al. Optical switching in datacenters: architectures based on optical circuit switching
Qin et al. TIO: a VLC-enabled hybrid data center network architecture

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20211221

Address after: 450046 Floor 9, building 1, Zhengshang Boya Plaza, Longzihu wisdom Island, Zhengdong New Area, Zhengzhou City, Henan Province

Patentee after: Super fusion Digital Technology Co.,Ltd.

Address before: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen

Patentee before: HUAWEI TECHNOLOGIES Co.,Ltd.