Switching system, optical packet transmitter, and optical packet generation method

Abstract

The switching system (10) of the present invention comprises a plurality of optical transmitters (13) that convert input electrical packets into optical packets and transmit them, a plurality of optical receivers (15) that receive the optical packets and convert them into electrical packets, an optical switch (14) that is arranged between the plurality of optical transmitters and the plurality of optical receivers and transmits the optical packets input from the optical transmitters to one of the plurality of optical receivers, and a clock unit (21) that transmits a clock signal having a clock phase to the optical transmitters and the optical receivers, and corrects the clock phase of the optical transmitter based on the clock phase of the optical packet received by the optical receiver and the clock phase of the optical receiver. As a result, the present invention can provide a switching system that suppresses collisions between optical signals.

Description

[Technical Field]

[0001] The present invention relates to a switching system that switches packets while suppressing collisions, an optical packet transmitting device, and a method for generating optical packets. [Background technology]

[0002] To meet the increasing demand for communication in different application domains such as telecommunications and data communications, the bandwidth (bits / sec) of transmitted signals has increased significantly. Optical switching switches optical signals without converting them into electrical signals, so it can accommodate the increase in bandwidth, i.e., communication volume.

[0003] In optical switching, optical signals sent simultaneously to the same destination are subject to collisions. In conventional electrical signal switching, data buffering mechanisms are used to avoid signal collisions. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 3878112 Summary of the Invention [Problem to be solved by the invention]

[0005] However, optical switching has not yet realized a mechanism for buffering optical data to avoid collisions of optical signals. Therefore, there is a need for a switching system that has a mechanism for avoiding collisions of optical signals instead of a buffering mechanism. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems, the switching system of the present invention comprises a plurality of optical transmitters that convert input electrical packets into optical packets and transmit them, a plurality of optical receivers that receive the optical packets and convert them into electrical packets, an optical switch that is arranged between the plurality of optical transmitters and the plurality of optical receivers and transmits the optical packets input from the optical transmitters to one of the plurality of optical receivers, and a clock unit that transmits a clock signal having a clock phase to the optical transmitters and the optical receivers, and is characterized in that the clock phase of the optical transmitters is corrected based on the clock phase of the optical packets received by the optical receivers and the clock phase of the optical receivers.

[0007] Furthermore, an optical packet transmitting device according to the present invention is an optical packet transmitting device that receives a first electrical packet followed by a second electrical packet, converts each of them into an optical packet, and transmits them to an optical receiver based on a clock signal, and includes an optical transmitter that receives the clock signal, stores a clock phase of the clock signal, converts the first electrical packet into a first optical packet, divides the first optical packet by the number of optical receivers to which the first optical packet is to be transmitted, transmits the divided first optical packets at the clock phase, receives from the optical receiver a phase difference between the clock phase of the divided first optical packet received by the optical receiver and the clock phase stored by the optical receiver, converts the second electrical packet into a second optical packet, divides the second optical packet by the number of optical receivers to which the second optical packet is to be transmitted, and transmits the divided second optical packets at a clock phase corrected by the phase difference, and an optical switch that assigns time slots to each of the divided first optical packet and the divided second optical packet, and sets guard times before and after boundaries of the time slots.

[0008] Furthermore, a method for generating an optical packet according to the present invention is a method for generating an optical packet to be transmitted from an optical transmitter to an optical receiver via an optical switch based on a clock signal, and includes the steps of: the optical transmitter receiving the clock signal and storing the clock phase of the clock signal; the optical transmitter dividing a first optical packet and transmitting the divided first optical packets at the clock phase; the optical switch assigning a time slot to each of the divided first optical packets and transmitting them; the optical receiver measuring the phase difference between the clock phase of the divided first optical packet and the clock phase stored in the optical receiver; the optical receiver transmitting the phase difference to the optical transmitter; the optical transmitter correcting the clock phase stored in the optical transmitter using the phase difference; and the optical transmitter dividing a second optical packet and transmitting the divided second optical packets at the corrected clock phase.

[0009] Furthermore, a method for generating optical packets according to the present invention is a method for generating optical packets to be transmitted to an optical receiver from electrical packets input to the optical transmitter using an optical transmitter and an optical switch, and includes the steps of: the optical transmitter converting the electrical packets into optical packets; the optical transmitter dividing the optical packets by the number of optical receivers to which the optical packets are transmitted; the optical switch allocating time slots to each of the divided optical packets; and the optical switch setting guard times between each of the divided optical packets, before and after the boundaries of the time slots. [Effects of the Invention]

[0010] According to the present invention, it is possible to provide a switching system, an optical packet transmitting device, and an optical packet generating method that suppress collisions between optical signals. [Brief explanation of the drawings]

[0011] [Figure 1]FIG. 1 is a block diagram showing the configuration of a switching system according to a first embodiment of the present invention. [Figure 2] FIG. 2 is a diagram for explaining the operation of the switching system according to the first embodiment of the present invention. [Figure 3A] FIG. 3A is a diagram for explaining the operation of the switching system according to the first embodiment of the present invention. [Figure 3B] FIG. 3B is a diagram for explaining the operation of the switching system according to the first embodiment of the present invention. [Figure 3C] FIG. 3C is a diagram for explaining the operation of the switching system according to the first exemplary embodiment of the present invention. [Figure 3D] FIG. 3D is a diagram for explaining the operation of the switching system according to the first embodiment of the present invention. [Figure 4] FIG. 4 is a diagram for explaining the operation of the switching system according to the modified example of the first embodiment of the present invention. [Figure 5] FIG. 5 is a block diagram showing the configuration of a switching system according to the second embodiment of the present invention. [Figure 6] FIG. 6 is a diagram for explaining the operation of the switching system according to the second embodiment of the present invention. [Figure 7] FIG. 7 is a flowchart showing a method for generating optical packets in a switching system according to the second embodiment of the present invention. [Figure 8] FIG. 8 is a diagram for explaining the operation of the switching system according to the modified example of the second embodiment of the present invention. [Figure 9] FIG. 9 is a block diagram showing the configuration of a switching system according to the third embodiment of the present invention. [Figure 10] FIG. 10 is a flowchart showing a method for generating optical packets in a switching system according to the third embodiment of the present invention. [Figure 11]FIG. 11 is a diagram for explaining the operation of the switching system according to the third embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0012] First Embodiment A switching system according to a first embodiment of the present invention will be described with reference to FIGS.

[0013] <Switching system configuration> 1, a switching system (packet switching system) 10 according to this embodiment includes, in order, an input port 11, an input block 12, an optical transmitter 13, an optical switch 14, an optical receiver 15, and an output port 16. The optical switch 14 and the optical receiver 15 are connected by an optical fiber 17. A multiplexer may be provided in front of the optical receiver 15 to multiplex and receive a plurality of optical signals (not shown).

[0014] The input block 12 is an electronic switching unit, a low-radix switching block (chiplet).

[0015] An input port 11 of the switching system 10 is branched into m groups, and each group is connected to an input block 12 .

[0016] The input block 12 processes the incoming packets.

[0017] The optical transmitter 13 converts the electrical signal output from the input block 12 into an optical signal and outputs it.

[0018] The optical switch 14 cross-connects each group of input blocks 12 and output ports 16 based on a time slot operation (described below).

[0019] The optical signal output from the optical switch 14 propagates through an optical fiber 17 and is sent to an optical receiver 15 .

[0020] The optical receiver 15 converts the optical signal output from the optical switch 14 into an electrical signal.

[0021] The output ports 16 of the switching system 10 are each divided into m virtual groups.

[0022] In the switching system 10, the same blocks are connected one by one to each group of different output ports 16 in turn, and each is connected by a time slot (described later), where T is the duration of the packet input to the switching system 10.

[0023] Here, the time slot is Δt=T / m.

[0024] Also, the same output port 16 of an input block 12 always connects to the same output port 16 of a virtual group, where both ports have the same index within the port group.

[0025] <Switching system operation> The operation of the switching system 10 according to this embodiment will be described with reference to FIG.

[0026] The basic operation of a switching system 10 performing non-blocking processing is shown in Figure 2, using a 4x4 switch as an example. This switching system 10 is based on a time slot operation, which will be explained below.

[0027] First, packets are switched by input group, where arbitration is performed only among input packets of the same input group. This arbitration is performed for a small number of ports and low traffic, so it is fast.

[0028] Furthermore, an electrical packet 1 input to the switch has a bandwidth BW (bit / sec) and a duration T, and a desired output port 16 to which it is to be sent is set.

[0029] In switching system 10, a packet switching operation to any of four output ports 16 is completed in time T. This is because if switching a single packet takes longer than T, the next incoming packet will be blocked, and continuous switching delays will accumulate.

[0030] Also, the input packet 1 is compressed by a factor (here 4) equal to the number of ports (i.e., the number of optical receivers to which the packet is sent) at the optical transmitter 13 to fit into the time slot. That is, the duration of the input packet is divided by a factor equal to the number of ports, which becomes T / 4. Also, in order to preserve the packet data content, the bandwidth is multiplied by the same factor, which becomes 4BW.

[0031] In this way, an input packet of light 2 is generated that satisfies these conditions.

[0032] Each optical input packet 2 is then distributed to a desired output port 16 in a periodic time slot by an optical switch 14. Here, the periodic operation of the switch is divided into four time slots.

[0033] Each time slot has a duration Δt of T / 4.

[0034] The distribution (switching) of the optical input packet 2 is repeatedly performed for each time slot according to a sequence made up of steps S1 to S4 (described later).

[0035] Finally, the packets are converted into electrical packets by the optical receiver 15 and output with a fixed duration from the switching system 10. In other words, the data rate of the signals output from the switching system 10 is the same as the data rate of the signals input thereto.

[0036] In this way, packets arriving in different time-reduced time slots will have their data rate changed to the original data rate, in the order of arrival of the packets, or by other arbitration prioritizing the change.

[0037] The switching operation of the optical switch 14 described above will be described with reference to Figures 3A to 3D. Each of Figures 3A to 3D shows an example of a series of switching operations in steps S1 to S4.

[0038] Packets are input to each of four ports 11_1 to 11_4 in the switching system 10. The packet input to port 11_3 (packet C) has the desired output port as port 16_3 and has the highest priority.

[0039] The packets (packets A and D) input to the ports 11_1 and 11_4 have the desired output ports 16_2 and 16_1, respectively, and have the second priority.

[0040] The packet (packet B) input to the port 11_2 has the desired output port as the port 16_4 and has the third priority.

[0041] First, packet C has the highest priority and is therefore transmitted to output port 16_3 for the duration of the first time slot (step S1, FIG. 3A).

[0042] Next, since packets A and D have the second priority, they are transmitted simultaneously to output ports 16_2 and 16_1, respectively, for the duration of the second time slot (step S2, FIG. 3B). Here, packets A and D are transmitted to different output ports, so no collision occurs.

[0043] Next, the packet input to port B (packet B) has the third priority and is therefore transmitted to output port 16_4 with the duration of the third time slot (step S3, FIG. 3C).

[0044] Finally, since the transmission (switching) of packets A to D has been completed in the previous step (step S3), no switching is performed during the duration of the fourth time slot (step S4, FIG. 3D).

[0045] Here, the duration of the first time slot, the duration of the second time slot, the duration of the third time slot, and the duration of the fourth time slot are represented by Δt1, Δt2, Δt3, and Δt4, respectively.

[0046] In this way, when the operation cycle (four steps) is completed, all input packets are switched to their desired output ports simultaneously in a non-blocking manner.

[0047] In this switching operation, in every step, each output port 16 is connected to only one input port 11, as shown in Figures 3A to 3D. Also, the input port 11 is connected to the desired output port 16, and in switching a packet input to the input port 11, the packet is placed in the correct (exact) time slot (with a divided duration).

[0048] Additionally, the optical receiver 15 in the switching system 10 is operable to accommodate such burst mode transmission.

[0049] The switching system 10 can easily implement a high-speed 4×4 optical switch device by being composed of four 1×4 switching units corresponding to different input ports 11. Here, in the 4×4 optical switch device, the time (transition time) required to transition from one switch mode (e.g., FIG. 3A) to another switch mode (e.g., FIG. 3B) is very short compared to the duration of an input packet.

[0050] For example, assuming that the transition time is negligible, with practically available technology the transition time can be reduced to 10 psec, which is extremely short compared to, for example, a 100 Gb / s Ethernet packet which has a duration of 120 nsec.

[0051] Also, if a short guard time is set between packets entering the same input port 11 to avoid data loss during switching, this guard time is less than 1 / 10 of the duration of the input packet. The transition time is short enough to be accommodated within the guard time.

[0052] <Effects> The effects of the switching system 10 according to this embodiment will be described below.

[0053] In a typical electrical switch, an incoming packet passes through an input port of the switch, where it is first inspected for destination and priority, followed by a centralized arbitration to determine which packet should be sent first among all packets destined for the same output port.

[0054] The implementation of a centralized arbitration process becomes more complex as the number of switch ports and throughput increases, resulting in increased communication latency and power consumption.

[0055] On the other hand, the switching system according to this embodiment can switch packets without performing centralized arbitration, which takes a long time, and therefore can reduce communication latency and power consumption.

[0056] Furthermore, because part of the switching process is handled by an optical switch, it is possible to increase the switching capacity with lower power consumption than an ASIC using CMOS transistors.

[0057] Furthermore, because chiplets are used for the input block 12, the area occupied by the input block 12 can be reduced. As a result, even if an optical-electrical interface is implemented, the overall area of the packet switch (chip) does not increase. Therefore, the optical-electrical interface can be implemented without changing the chip area, and the throughput (processing capacity) of the switch can be increased. Furthermore, by using chiplets, power consumption can be reduced.

[0058] It also avoids contention between ports in the same block, allowing non-blocking processing.

[0059] <Variation 1> A switching system according to a first modification of the first embodiment of the present invention will be described with reference to Fig. 4. The configuration of a switching system 10_2 according to this modification is similar to that of the first embodiment.

[0060] <Switching system operation> The operation of the switching system 10_2 according to this modification will be described below.

[0061] In the switching system 10_2, packets (packets A to D) are input to four ports 11_1 to 11_4, respectively. The packets A to D have the same desired output port (16_2), and the packets are prioritized in the order of B, A, D, and C.

[0062] First, packet B has the highest priority and is therefore transmitted to output port 16_2 for the duration of the first time slot (step S1).

[0063] Next, since packet A has the second priority, it is transmitted to the output port 16_2 for the duration of the second time slot (step S2).

[0064] Next, since packet D has the third priority, it is transmitted to the output port 16_2 for the duration of the third time slot (step S3).

[0065] Finally, since packet C has the fourth priority, it is transmitted to output port 16_2 for the duration of the fourth time slot (step S4).

[0066] In this way, when the operation cycle (four steps) is completed, all input packets are simultaneously switched to the desired output ports in a non-blocking manner. Here, packets A to D are transmitted in different time slots, so no collisions occur.

[0067] Thus, in the switching system 10_2, all input packets transmitted to the same output port are correctly (accurately) switched to that port at time T.

[0068] <Effects> The switching system 10_2 according to this modification has the following effects in addition to the effects of the first embodiment.

[0069] In order to send multiple packets simultaneously to the same destination using a conventional packet switch, the same number of parallel optical receivers as the number of packets was required.

[0070] In the switching system 10_2, a compact copy of each input packet is created at a high data rate, and the compact packets are divided into short time slots and transmitted. In this way, transmission of packets to the same destination can be performed in a time shorter than the actual packet input interval using time interleaving.

[0071] According to the switching system of this modification, packets can be sent to the same output port without performing centralized arbitration, which takes a long time, and therefore communication latency can be reduced, and power consumption can be reduced.

[0072] <Second embodiment> A switching system according to a second embodiment of the present invention will be described with reference to FIGS.

[0073] <Switching system configuration> 5, a switching system 20 according to this embodiment includes an optical transmitter 13, an optical switch 14, an optical fiber 17, an optical receiver 15, and a clock unit 21. The basic configuration of the switching system 20 other than the clock unit 21 is the same as that of the first embodiment.

[0074] The packet is input from the host A (3_1) to the optical transmitter 13, output from the optical receiver 15, and transmitted to the host 1 (4_1).

[0075] <Switching system operation> The operation of the switching system 20 according to this embodiment using a shared clock signal will be described with reference to FIG.

[0076] In the switching system 20, a shared clock signal is transmitted from the clock unit 21 to the optical transmitter 13 and the optical receiver 15. It may also be transmitted to the optical switch 14. Here, the transmitted shared clock signal includes a substantially identical copy of the shared clock signal. The substantially identical copy of the shared clock signal includes an identical copy and a range of functions that can be performed by the switching system 20 as described below.

[0077] A single host is connected to each switch port, and, for example, optical transmitter 13 is used to convert 25 Gb / s packets generated by the source host into 100 Gb / s optical packets.

[0078] The packets generated by the source host A (3_1) are transmitted at the optical transmitter 13 within the guard time T grd are separated into two consecutive packets and then output.

[0079] Therefore, the duration of the switched packet, T pkt If the time of the beginning of the first packet is zero, the end of the first packet is T pkt, the start time of the next packet is T pkt +T grd , the end is 2T pkt +T grd This becomes:

[0080] For example, the guard time is set to 2% of the duration of the optical packet. grd The minimum value of will be described later.

[0081] At the optical receiver 15, the duration T of the switched packet is pkt , guard time T grd , where N is the number of packets switched, (T pkt +T grd ) for a period of N times (T pkt +T grd ) is four times larger.

[0082] When the optical receiver 15 receives the data bits of a packet, it requests notification of the timing of the bits. Conventionally, at the receiver side, the process of detecting the exact timing of the incoming bits and recovering the clock of the incoming packet takes a long time compared to the expected short duration of the packet.

[0083] Therefore, by sharing an optical clock between the optical transmitter 13 and the optical receiver 15, this long-time process can be avoided.

[0084] Table 1 shows the setting values etc. in the switching system 20.

[0085] [Table 1]

[0086] FIG. 6 shows the clock phases in the switching system 20. As shown in FIG.

[0087] Normally, even if a clock is shared, the phase 211 of the clock of the input packet does not match the phase 212 of the local copy of the clock shared at the receiving side. This initial clock phase difference (mismatch) can be continuously corrected if the optical path between the optical transmitter 13 and the optical receiver 15 is a time-invariant system.

[0088] Here, the difference in clock phase is represented by Δφ.

[0089] However, for example, if a packet from the optical transmitter 13 can arrive at the same optical receiver 15 via a randomly selected optical path that is not known in advance, phase adjustment is not possible because the optical path between the optical transmitter 13 and the optical receiver 15 is not a time-invariant system.

[0090] In the switching system 20, for example, the clock phase of the input packet is matched to the clock phase of the destination optical receiver 15 (213 in the figure) based on a phase caching method (K.A. Clark et.al., “Synchronous sub-nanosecond clock and data recovery for optically switched data centers using clock phase caching,” in Nature Electronics, vol. 3, July 2020.).

[0091] FIG. 7 shows a flowchart of the transmission and reception of optical packets, including the generation of optical packets using a clock signal in the switching system 20.

[0092] A clock signal is transmitted in advance to the optical transmitter 13 and the optical receiver 15, and the phase of the clock signal (clock phase) is cached (stored) (step S11).

[0093] First, the optical transmitter 13 divides an optical packet (first optical packet) and transmits the divided optical packets (first optical packets) to the optical switch 14 using the cached clock phase (step S12).

[0094] Next, the optical switch 14 assigns a time slot to each of the divided optical packets (first optical packets), and transmits them to the optical receiver 15 (step S13).

[0095] Next, the optical receiver 15 measures the phase difference between the clock phase of the optical packet (first optical packet) received from the optical switch 14 and the clock phase stored in the optical receiver 15 (step S14).

[0096] Next, the optical receiver 15 transmits the measured phase difference to the optical transmitter 13 (step S15).

[0097] Next, the optical transmitter 13 corrects and updates the cached clock phase using the received phase difference (step S16).

[0098] Next, the optical transmitter 13 uses the updated cached clock phase to transmit the next optical packet (second optical packet) to the optical switch 14 (step S17).

[0099] Next, the optical switch 14 allocates a time slot to the optical packet (second optical packet) and transmits it to the optical receiver 15 (step S18).

[0100] Finally, the optical receiver 15 receives the optical packet (second optical packet), resulting in the phase difference becoming zero (step S19).

[0101] In this way, the optical transmitter 13 continues to use the cached clock phase to correct the phase of data sent to a given optical receiver 15, where different phase correction values are used for different destinations within the same optical transmitter 13.

[0102] This embodiment allows for a common time base to be established so that data communication can be coordinated within a set time slot without collisions by sharing a clock signal, and allows for burst mode data reception without long clock data recovery times.

[0103] <Variation 2> In a switching system 20_1 according to the second modification of this embodiment, a space optical fiber with low temperature sensitivity is used as the optical fiber 17. Other configurations are the same as those of the second embodiment.

[0104] The optical fiber 17 is a commercially available optical fiber, which is coated with a predetermined coating and has a transmission coefficient of 3.7 ps / km / k. o The optical fiber 17 has a low temperature sensitivity. The length of the optical fiber 17 is about 10 m.

[0105] In the switching system 20_1, fluctuations in the environmental temperature affect the refractive index of the optical fiber 17. The clock phase already adjusted in a transmitted packet may change at the destination optical receiver 15 after propagating through the fiber 17. As a result, fluctuations occur in the travel time of the packet between hosts.

[0106] Therefore, the validity of the corrected and cached phase value in the switching system 20_1 will be examined below: Here, the frequency usually depends on the fiber length and the temperature fluctuation pattern in the system environment.

[0107] As described above, the switching system 20_1 is intended for interconnection of hosts located at a short distance of about 10 m. Therefore, a space optical fiber having a length of about 10 m and low temperature sensitivity is used as the optical fiber 17 to suppress phase changes.

[0108] In this optical fiber (10 m long), the travel time of the optical signal changes by less than 1.5 psec when the temperature changes by 40°C. This value is sufficient for a high bit rate (T baud This is less than 1 / 10 of the single-bit duration (corresponding to 20 ps), and is an extremely small fluctuation (fluctuation) of a single bit duration, so it can be considered negligible.

[0109] Thus, for example, an initial adjustment of the clock phase at start-up of the switching system can operate for an extended period of time without requiring further correction.

[0110] According to the switching system of this modification, fluctuations in the clock phase due to temperature changes can be suppressed.

[0111] <Variation 3> In a switching system 20_2 according to the third modification of this embodiment, as shown in Fig. 8, the end-to-end optical paths between any pair of an optical transmitter 13 and an optical receiver 15 are equalized. In other words, the lengths of the fibers 17 are equal in all combinations of a sending host and a receiving host (i.e., an optical switch 14 and an optical receiver 15). The other configurations are the same as those of the second embodiment.

[0112] For example, if the lengths LA1, LA2, LA3, and LA4 of the fibers 17 connecting the host A (3_1) and the hosts 1 to 4 (4_1 to 4_4) are about 10 m and include an error of plus or minus 1 mm, the difference in travel time (T trvl_Ai -T trvl_Aj ) is 10 ps, which is extremely small.

[0113] In the switching system 20_2, host units are connected to ports of the optical switching system, and are arranged without any restriction on the distance between hosts.

[0114] In the switching system 20_2 according to this modification, each time slot is occupied only by the target packet without causing other slots to be in an erroneous time slot state. Therefore, even if the host unit is placed without any constraints, the proper operation of the switching system using time slots can be ensured.

[0115] According to the switching system of this modification, host units can be arranged without restrictions, and a switching system using time slots can be operated appropriately.

[0116] In this variant, optical fibers 17 of the same length can be easily adjusted and bundled as needed to connect units that are located close together.

[0117] The length of the optical fiber strand can be adjusted with high resolution using other techniques. However, considering the cost reduction and efficiency of manufacturing the optical fiber strand to be arranged, the resolution may be approximately ±1 mm.

[0118] <Third embodiment> A switching system according to a third embodiment of the present invention will be described with reference to FIGS.

[0119] <Switching system configuration> 9, a switching system 30 according to this embodiment includes, in order, an optical transmitter 13, an optical switch 14, an optical fiber 17, a multiplexer 31, an optical receiver 15, and a clock unit 21. The basic configuration of the switching system 30 other than the clock unit 21 is the same as that of the first embodiment.

[0120] <Optical packet generation method> A method for generating optical packets in the switching system 30 according to this embodiment will be described below.

[0121] FIG. 10 shows a flowchart of a method for generating optical packets in the switching system 30.

[0122] In the switching system 30, for example, as shown in FIG. 9, packets are transmitted from hosts A (3_1) and D (3_4) to a destination host, host 1 (4_1).

[0123] The shared clock signal (master) used here is assumed to have a frequency of 840 MHz (corresponding to a period of 1.2 nsec) as actually used.

[0124] In the optical switch 14, packets sent from the host A (3_1) are separated by guard times T grd As a result, the duration of the switched packet is pkt If the start time of the first packet is zero, the start time of the next packet is T pkt +T grd , the beginning of the next packet is (T pkt +T grd ) is twice as large.

[0125] Similarly, a packet is sent from host D (3_4).

[0126] At this time, the phase of the shared clock in the optical transmitter 13 of the host A (3_1) and the phase of the shared clock in the optical transmitter 13 of the host D (3_4) are usually slightly different.

[0127] This phase difference value ΔT AD_clock is approximately one clock cycle (1.2 nsec) or less.

[0128] Here, phase differences of more than one full clock period can be easily detected (eg, by a time counter) and corrected.

[0129] FIG. 11 shows how the optical receiver 15 of the host 1 (4_1) receives a packet.

[0130] In the optical receiver 15 of the host 1 (4_1), after a time slot is allocated to the reception (packet A) from the host A (3_1), a time slot is allocated to the reception (packet D) from the host D (3_4). Subsequently, a time slot is allocated to the reception (packet C) from the host C (3_3).

[0131] After packet A, there is a signal-free guard time T grd _1, T grd In detail, between the end of packet A and the beginning of packet D, and between the end of packet D and the beginning of packet C, there are T grd In other words, T_1 and Tgrd_2 are set at the beginning of each packet. grd _2, T at the end grd _1 is set.

[0132] If the clock phases at host A (3_1) and host D (3_4) are perfectly aligned, packet D (from host D) will arrive exactly within the guard time T grd At the end of the signal, the signal arrives at the optical receiver 15 of the host 1 (4_1).

[0133] However, since there is usually a phase difference between packets A and D, packet D is grd After _1 is completed or T grd Packet D arrives before packet A completes. Therefore, packet D must arrive as early as possible without colliding with packet A.

[0134] Packet D arrives maximally early when the phase clock at the optical transmitter 13 of host D (3_4) leads the phase clock at the optical transmitter 13 of host A (3_1) by a full shared clock period.

[0135] The time difference ΔT between the end of packet A and the beginning of packet D AD is the difference in travel time between two packets A and D, ΔT AD _ trvl and ΔTAD_clock Here, the difference in travel time between the two packets must also be taken into account. However, with all lightpath adjustments, the maximum difference in travel time is almost negligible (less than 10 ps). Therefore, ΔT AD is ΔT AD_clock is approximately equal to

[0136] Therefore, at least the guard time T between packets A and D grd _2, i.e., T at the beginning of packet D grd If packet_2 is selected to satisfy the condition that it exceeds the duration of the shared clock period, packet D will not arrive within the time slot assigned to packet A, and therefore no collision will occur between packet A and packet D.

[0137] For example, even if packet D arrives early, the beginning of packet D is grd If packets A and D are in _2, no collision occurs between them (dotted box D1 in the figure).

[0138] Similarly, even if packet D arrives as early as possible, it is necessary to prevent collision with packet C. Therefore, at least a guard time T grd _1, i.e., T at the end of packet D grd If packet D_1 is selected to satisfy the condition that it exceeds the duration of the shared clock period, packet D will not arrive within the time slot assigned to packet C, and therefore no collision will occur between packet D and packet C.

[0139] For example, even if packet D arrives late, the end of packet D is grd If packets D and C are within _1, no collision occurs between them (dotted box D2 in the figure).

[0140] In this way, by setting the guard time between packets so that it exceeds the phase difference of the shared clock between the respective packets, collisions between different packets can be avoided.

[0141] According to this embodiment, by sharing a clock signal and setting a guard time, it is possible to further suppress the occurrence of collisions and switch packets for transmission and reception.

[0142] In embodiments of the present invention, other methods may be used to receive burst-mode input data packets without spending a long time performing clock data recovery, such as using a burst-mode receiver (e.g., S. Ibrahim et. al, "Hybrid Optoelectronic Router for Future Optical Packet-Switched Networks," Optoelectronics-Advanced Device Structures, 2017.), where an optical clock pulse is generated synchronously with the burst-mode input packets. This optical clock is used to operate a specially designed optically triggered serial-to-parallel conversion device.

[0143] Additionally, embodiments of the present invention may transmit a separate clock signal along with the data signal for use at the receiving end. By maintaining synchronization between the clock signal and the data signal all the way to the receiving end, incoming data can be received faster without requiring an additional process of clock data recovery.

[0144] In the embodiments of the present invention, examples of the structure, dimensions, materials, etc. of each component in the configuration of the switching system, the optical packet transmitting device, and the optical packet generating method are shown, but the present invention is not limited to these examples. Anything that can demonstrate the functions and effects of the switching system, the optical packet transmitting device, and the optical packet generating method may be used. [Industrial Applicability]

[0145] The present invention relates to a switching system, an optical packet transmitting device, and a method for generating optical packets, and can be applied to telegraph and telephone systems and data communication systems. [Explanation of symbols]

[0146] 10 Switching System 13 Optical transmitter 14 Optical Switch 15 Optical receiver 21 Clock section

Claims

1. a plurality of optical transmitters that convert input electrical packets into optical packets and transmit the optical packets; a plurality of optical receivers that receive and convert the optical packets into electrical packets; an optical switch disposed between the plurality of optical transmitters and the plurality of optical receivers, for transmitting the optical packet input from the optical transmitter to any one of the plurality of optical receivers; a clock unit that transmits a clock signal having a clock phase to the optical transmitter and the optical receiver; Equipped with The clock phase of the optical transmitter is corrected based on the clock phase of the optical packet received by the optical receiver and the clock phase of the optical receiver. A switching system comprising:

2. an optical fiber connecting the optical switch and the optical transmitter; The optical fiber has low temperature sensitivity.

2. The switching system according to claim 1.

3. a plurality of optical fibers connecting the optical switch and the optical transmitter; The plurality of optical fibers are equalized.

2. The switching system according to claim 1.

4. the optical transmitter divides the optical packet by the number of the optical receivers to which the optical packet is transmitted; The optical switch transmits the divided optical packets in the time slots assigned to each of the divided optical packets.

2. The switching system according to claim 1.

5. The optical switch sets guard times before and after the boundaries of the time slot.

5. The switching system according to claim 4.

6. An optical packet transmitting device that receives a first electrical packet and then a second electrical packet, converts each of the input electrical packets into an optical packet, and transmits the optical packet to an optical receiver based on a clock signal, receiving the clock signal and storing a clock phase of the clock signal; converting the first electrical packet into a first optical packet, dividing the first optical packet by the number of optical receivers to which the first optical packet is transmitted, and transmitting the divided first optical packet at the clock phase; receiving, from the optical receiver, a phase difference between a clock phase of the divided first optical packet received by the optical receiver and a clock phase stored by the optical receiver; converting the second electrical packet into a second optical packet, dividing the second optical packet by the number of optical receivers to which the second optical packet is transmitted, and transmitting the divided second optical packet with a clock phase corrected by the phase difference; an optical transmitter; an optical switch that allocates time slots to the divided first optical packet and the divided second optical packet, respectively, and sets guard times before and after boundaries of the time slots; An optical packet transmitting device comprising:

7. 1. A method for generating optical packets to be transmitted from an optical transmitter through an optical switch to an optical receiver based on a clock signal, comprising: the optical transmitter and the optical receiver receiving the clock signal and storing a clock phase of the clock signal; the optical transmitter splitting a first optical packet and transmitting the split first optical packets at the clock phase; a step of the optical switch allocating a time slot to each of the divided first optical packets and transmitting the divided first optical packets; the optical receiver measuring a phase difference between a clock phase of the split first optical packet and a clock phase stored in the optical receiver; the optical receiver transmitting the phase difference to the optical transmitter; the optical transmitter using the phase difference to correct a clock phase stored in the optical transmitter; the optical transmitter splitting a second optical packet and transmitting the split second optical packets at the corrected clock phase; A method for generating an optical packet comprising:

8. A method for generating an optical packet to be transmitted to an optical receiver from an electrical packet input to an optical transmitter using an optical transmitter and an optical switch, comprising: the optical transmitter converting the electrical packets into optical packets; the optical transmitter dividing the optical packet by the number of optical receivers to which the optical packet is transmitted; the optical switch assigning a time slot to each of the divided optical packets; the optical switch setting guard times before and after boundaries of the time slots between each of the divided optical packets; A method for generating an optical packet comprising:

Images