High-speed optical data switching system

• US 5,729,548 A
• Filed: 12/29/1995
• Issued: 03/17/1998
• Est. Priority Date: 12/29/1995
• Status: Expired due to Term

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Telefonaktiebolaget LM Ericsson
• Inventors: Holender, Wlodek
• Primary Examiner(s): Olms, Douglas W.
• Assistant Examiner(s): Patel, Ajit
• Application Number:
  US08/581,159
• Time in Patent Office: 809 Days
• Field of Search: 370/395, 370/396, 370/397, 370/409, 370/389, 370/390, 370/474, 370/465, 370/470, 370/971, 370/476, 359/139, 359/165
• US Class Current: 370/474
• CPC Class Codes: H04L 12/5601 Transfer mode dependent, e.g. ATM
• CPC Class Codes: H04L 2012/5605 Fibre
• CPC Class Codes: H04L 2012/5628 Testing
• CPC Class Codes: H04L 2012/5651 Priority, marking, classes
• CPC Class Codes: H04L 2012/5653 using the ATM adaptation layer [AAL]
• CPC Class Codes: H04L 2012/5672 Multiplexing, e.g. coding, scrambling
• CPC Class Codes: H04L 49/153 ATM switching fabrics having parallel switch planes
• CPC Class Codes: H04L 49/203 ATM switching fabrics with multicast or broadcast capabilities
• CPC Class Codes: H04Q 11/0005 Switch and router aspects
• CPC Class Codes: H04Q 11/0066 Provisions for optical burst or packet networks
• CPC Class Codes: H04Q 2011/0011 using wavelength conversion
• CPC Class Codes: H04Q 2011/0013 using gating amplifiers
• CPC Class Codes: H04Q 2011/0024 using space switching
• CPC Class Codes: H04Q 2011/0039 Electrical control

Abstract

A system and method for high-speed parallel switching of digital data sequences using an all-optical technique is described. Each input digital data sequence is encoded into an optical pattern comprising of several cells. The encoded optical pattern can be of various sizes and shapes depending on cost and quality considerations. A unique modulating pattern is selected for each digital data sequence based on the destination address of that data sequence. Every cell of each encoded optical pattern is modulated using the selected modulating pattern to obtain a modulated-encoded optical pattern. Each modulated-encoded optical pattern corresponds to a specific input data sequence. All of the modulated-encoded optical patterns are superposed to obtain a composite modulated-encoded optical pattern. The composite pattern is optically broadcast to all possible outputs of the parallel switch. All the destination receivers simultaneously demodulate the composite pattern using the unique modulating pattern that corresponds to their destination address and thus extract the encoded data sequence sent to them. The demodulated-encoded data sequences are decoded back from optical to digital form and routed to their destination by conventional techniques.

Claims

1. A method for the high-speed switching of electronic data packets from one of a plurality of input ports of a switch to a selected one of a plurality of output ports, said method comprising the steps of:

separating a signal packet incoming at each port into a first time-domain electronic representation of the data-carrying portion of the signal and second time-domain electronic representation of the address-carrying portion of the signal;

transforming the time-domain electronic representations of each of said data portions and said address portions into separate first and second spatial optical image representations thereof, respectively;

modulating said first spatial optical image representation with said second spatial optical image representation to form a unified image that is associated with a specific packet received at each of said plurality of input ports;

multiplexing each of said unified images associated with an input port into a single composite image;

broadcasting said single composite image to a plurality of target sensors, each sensor being associated with a specific destination address of the incoming signal packet;

demultiplexing said composite image into a plurality of separate unified images each being associated with a specific output port, said demultiplexing being done by filtering said composite image using the address image portion corresponding to each destination data port for the incoming signal packet; and

transforming each of said plurality of separate unified images received at each output port back into time-domain electronic form comprising an address portion and a data portion.

2. A method for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, said method comprising the steps of:

separating the address portion of each digital data sequence from the payload portion of the digital data sequence;

determining the destination output port of each digital data sequence using the address portion of the digital data sequence;

generating a unique modulating optical pattern corresponding to said destination output port for modulating the payload portion of the digital data sequence;

generating an encoded optical pattern comprising a plurality of cells by encoding each of the digital data sequences using a preselected conversion protocol;

modulating each cell of said encoded optical pattern using said unique modulating optical pattern to obtain a corresponding modulated optical pattern;

superposing the modulated optical patterns obtained from each of the digital data sequences to form a unitary composite optical pattern;

broadcasting said unitary composite optical pattern to a plurality of destination receivers;

demodulating said unitary composite optical pattern in each of said destination receivers using the unique modulating optical pattern that corresponds to the destination receiver'"'"'s address; and

decoding said demodulated optical pattern at each output port to obtain a switched time-domain digital data sequence.

3. The method of claim 2 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the digital data sequences are ATM cells.

4. The method of claim 2 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, additionally comprising the step of:

assembling the payload portion of each digital data sequence into one or more frames suitable for optical switching.

5. The method of claim 2 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, additionally comprising the steps of:

repackaging all or a part of the address portion of the original digital data sequence with the payload portion of the original digital data sequence; and

forwarding the repackaged digital data sequence to a downstream processor for onward transmission.

6. The method of claim 2 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the step of generating a unique modulating optical pattern is performed by selecting one of a plurality of symmetric non-overlapping modulating patterns such that each selected modulating pattern is associated with no more than a single destination output port.

7. The method of claim 2 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the step of generating a unique modulating optical pattern is performed by selecting one of a plurality of asymmetric non-overlapping modulating patterns such that each selected modulating pattern is associated with no more than a single destination output port.

8. The method of claim 2 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the step of generating a unique modulating optical pattern is performed by selecting one of a plurality of asymmetric partially-overlapping modulating patterns such that each selected modulating pattern is associated with no more than a single destination output port.

9. The method of claim 2 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the step of generating an encoded optical pattern comprising a plurality of cells further comprises the steps of:

translating the information contained in the payload portion of the digital data sequence into binary form; and

associating each binary value of 0 or 1 with a specific state of a cell in said encoded optical pattern.

10. The method of claim 9 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the encoded optical pattern is a rectangular grid with 384 cells arranged in 16 rows and 24 columns.

11. The method of claim 9 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the encoded optical pattern is a square grid with 384 cells arranged in 20 rows and 20 columns with the central 16 cells remaining unutilized.

12. The method of claim 9 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the encoded optical pattern is a bilaterally symmetric grid with 384 cells, each quadrant of which has a row of 3 columns, a row of 6 columns, a row of 7 columns, a row of 8 columns, a row of 9 columns, a row of 10 columns, and a row of 11 columns.

13. A system for the high-speed switching of electronic data packets from one of a plurality of input ports of a switch to a selected one of a plurality of output ports, said system comprising:

means for separating a signal packet incoming at each port into a first time-domain electronic representation of the data-carrying portion of the signal and second time-domain electronic representation of the address-carrying portion of the signal;

means for transforming the time-domain electronic representations of each of said data portions and said address portions into separate first and second spatial optical image representations thereof, respectively;

means for modulating said first spatial optical image representation with said second spatial optical image representation to form a unified image that is associated with a specific packet received at each of said plurality of input ports;

means for multiplexing each of said unified images associated with an input port into a single composite image;

means for broadcasting said single composite image to a plurality of target sensors, each sensor being associated with a specific destination address of the incoming signal packet;

means for demultiplexing said composite image into a plurality of separate unified images each being associated with a specific output port, said demultiplexing being done by filtering said composite image using the address image portion corresponding to each destination data port for the incoming signal packet; and

means for transforming each of said plurality of separate unified images received at each output port back into time-domain electronic form comprising an address portion and a data portion.

14. A system for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, said system comprising:

means for separating the address portion of each digital data sequence from the payload portion of the digital data sequence;

means for determining the destination output port of each digital data sequence using the address portion of the digital data sequence;

means for generating a unique modulating optical pattern corresponding to said destination output port for modulating the payload portion of the digital data sequence;

means for generating an encoded optical pattern comprising a plurality of cells by encoding each of the digital data sequences using a preselected conversion protocol;

means for modulating each cell of said encoded optical pattern using said unique modulating optical pattern to obtain a corresponding modulated optical pattern;

means for superposing the modulated optical patterns obtained from each of the digital data sequences to form a unitary composite optical pattern;

means for broadcasting said unitary composite optical pattern to a plurality of destination receivers;

means for demodulating said unitary composite optical pattern in each of said destination receivers using the unique modulating optical pattern that corresponds to the destination receiver'"'"'s address; and

means for decoding said demodulated optical pattern at each output port to obtain a switched time-domain digital data sequence.

15. The system of claim 14 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the digital data sequences are ATM cells.

16. The system of claim 14 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, additionally comprising:

means for assembling the payload portion of each digital data sequence into one or more frames suitable for optical switching.

17. The system of claim 14 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, additionally comprising:

means for repackaging all or a part of the address portion of the original digital data sequence with the payload portion of the original digital data sequence; and

means for forwarding the repackaged digital data sequence to a downstream processor for onward transmission.

18. The system of claim 14 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the means for generating a unique modulating optical pattern further comprises means for selecting one of a plurality of symmetric non-overlapping modulating patterns such that each selected modulating pattern is associated with no more than a single destination output port.

19. The system of claim 14 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the means for generating a unique modulating optical pattern further comprises means for selecting one of a plurality of asymmetric non-overlapping modulating patterns such that each selected modulating pattern is associated with no more than a single destination output port.

20. The system of claim 14 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the means for generating a unique modulating optical pattern further comprises means for selecting one of a plurality of asymmetric partially-overlapping modulating patterns such that each selected modulating pattern is associated with no more than a single destination output port.

21. The system of claim 14 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the means for generating an encoded optical pattern comprising a plurality of cells further comprises:

means for translating the information contained in the payload portion of the digital data sequence into binary form; and

means for associating each binary value of 0 or 1 with a specific state of a cell in said encoded optical pattern.

22. The system of claim 21 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the encoded optical pattern is a rectangular grid with 384 cells arranged in 16 rows and 24 columns.

23. The system of claim 21 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the encoded optical pattern is a square grid with 384 cells arranged in 20 rows and 20 columns with the central 16 cells remaining unutilized.

24. The system of claim 21 for the high-speed parallel switching of a plurality of digital data sequences from one of a plurality of input ports to a selected one of a plurality of output ports, wherein the encoded optical pattern is a bilaterally symmetric grid with 384 cells, each quadrant of which has a row of 3 columns, a row of 6 columns, a row of 7 columns, a row of 8 columns, a row of 9 columns, a row of 10 columns, and a row of 11 columns.