System and method for improving the efficiency of routers on the Internet and/or cellular networks and/or other networks and alleviating bottlenecks and overloads on the network

• US 20080145050A1
• Filed: 10/30/2007
• Published: 06/19/2008
• Est. Priority Date: 11/08/2000
• Status: Active Grant

• Current Assignee: Batya Barhon Mayer
• Original Assignee: Batya Barhon Mayer
• Inventors: Mayer, Yaron, Baur, Al J.C.
• Granted Patent: US 8,073,327 B2
• Time in Patent Office: Days
• US Class Current: 398/49
• CPC Class Codes: H04J 14/0227 Operation, administration, maintenance or provisioning [OAMP] of WDM networks, e.g. media access, routing or wavelength allocation
• CPC Class Codes: H04J 14/0232 for downstream transmission
• CPC Class Codes: H04J 14/0238 Wavelength allocation for communications one-to-many, e.g. multicasting wavelengths
• CPC Class Codes: H04J 14/0282 WDM tree architectures
• CPC Class Codes: H04J 14/0284 WDM mesh architectures
• 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 2011/002 using optical delay lines or optical buffers or optical recirculation
• CPC Class Codes: H04Q 2011/0039 Electrical control

Abstract

The biggest bottleneck in the Internet today is caused by the slow speed of routers, compared to the speeds that are achieved by optic fibers with DWDM (Dense Wave Division Multiplexing). Packet switching or something similar to it is needed not just for better utilization of the lines, but also because it is superior to circuit switching in many ways, such as better scalability as the Internet grows, better handling of traffic congestions, and better routing flexibility. But optical routers are currently unable to do packet switching except by translating the data to electronic data and then back, which is very inefficient. The present invention solves this problem by optically marking and detecting the packet headers or parts of them, translating at most only the headers or parts of them to electronics for making packet switching decisions, and keeping the rest of the packets in optical delay lines, and solving response-time problems in the router, so that the crude optical switches can execute the packet switching decisions at fast bit rates. This solution has very high scalability and becomes even more efficient when physical addresses are used. Another optimization described in this invention is improving routing efficiency and bandwidth utilization by grouping together identical data packets from the same source going to the same general area with a multiple list of targets connected to each copy of the data and sent together to the general target area. These grouped packets are then preferably broken down into smaller groups by the routers in the general target area and finally broken down to individual data packets for delivering to the final actual destinations. This optimization works best with Physical addresses, and can be very useful for example for optimizing the access to very popular sites such as for example Yahoo or CNN, and can be used also for example for more efficiently transferring streaming data, such as for example from Internet radio stations, or Internet TV stations which will probably exist in the next years. Another important optimization is a new architecture and principles for routing based on physical geographical IP addresses (such as for example based on GPS), in a way much more efficient than has been previously discussed in the literature that suggested using physical (geographical) addresses. This is preferably based on a hierarchy similar to a hierarchical road system, so that preferably the MAIN routers (and/or intermediary-level routers) are preferably also connected directly and preferably with high-bandwidth as peers between each other, without having to go through lower-level routers in order to reach their peers, so that once a higher-level router (and especially if it'"'"'s one of the MAIN routers) decides to forward a packet (or a group of packets) to a higher-level peer, preferably the packets don'"'"'t have to go through lower level routers. However, conversion from the current architecture to the new one can be done very easy, as shown in the description below.

Claims

1. A system for improving the performance of routers on the Internet and/or cellular networks and/or other networks wherein packets with headers are used, comprising at least one of:

a. A System for fast packet switching in optical routers, by dealing only with the headers, without having to convert the packets themselves to electronics and back, and using a device for compensating for the margin of error that occurs when the response time of the router is too slow for the bit rate, and wherein said compensation is done by at least one of;

1. Optically duplicating the bit stream and using one copy of the bit stream to route the even packets, so that the odd packets are used as a slack area, and another copy of the bit stream to route the odd packets, so that the even packets are used as a slack area, 2. Using a long mark at the beginning of the packet which is sufficiently larger than the margin of error, and making sure the size of this mark remains long enough for the next router;

b. A hierarchical system that uses geographical IP addresses, in which routers that are higher on the hierarchy usually have sufficient direct links between themselves so that they can reach their peers without having to go through lower level routers;

c. A system for grouping together at least one of identical and non-identical packets going to the same general area or direction, wherein the system is adapted so that packets that are identical can be grouped together and condensed into a single packet with a list of multiple target addresses.

2. The system of claim 1 wherein optical marks are used for fast locating of the headers of optical data packets, further comprising:

A device for creating said optical marks;

A device at the router for optically detecting and extracting at least part of the packet header before delaying the light bits;

A device for delaying the light bits at the router for the time needed for making packet switching decisions without having to convert said light bits to electricity;

A computer for comparing said target addresses to the required database and making packet switching decisions;

A fast optical router for carrying out said packet switching decisions after the light has passed through the delaying device, without having to convert the light bits to electricity;

A device for compensating for the margin of error that occurs when the response time of said fast optical router is too slow for the bit rate and enabling at least one of addition and deletion of data if required.

10. The system of claim 1 comprising a system for grouping together at least one of identical and non-identical packets going to the same general area or direction, wherein the system is adapted so that packets that are identical can be also condensed into a single packet with a list of multiple target addresses, and wherein at least one of:

a. Identical data packets from the same source going to the same general area can be grouped together and condensed by sending in each group the identical data only once, with a multiple list of targets connected to each copy of the data and sent together to the general target area;

b. Non-identical Packets from the same source or form different sources going to the same general target area can be grouped together without condensing, so that they can be routed together more efficiently and later similarly broken down according to physical proximity to the target area;

c. The grouped packets are broken down into smaller groups by the routers in the general target area and finally broken down to individual data packets for delivering to the final actual destinations;

d. Said grouped packets are broken down directly by the routers in the general target area into individual data packets for delivering to the final actual destinations;

e. Said grouping of the packets is done as a pre-processing by routers;

f. Said grouping of the packets is done by the servers themselves, which can be at least one of the original site, a mirror site, and a proxy;

g. A short time window is used on the server for collecting requests for data in order to group the packets together;

h. When downloading at least one of large video files, MP3 files, popular software files, and other large files, the server can combine together in the united packets also requests that came after the original time window, so that new requests can be combined with older requests and thus get first a later part of the file and then get earlier parts of the file later.

15. The system of claim 1 further comprising a hierarchical system that uses geographical IP addresses, in which routers that are higher on the hierarchy usually have sufficient direct links between themselves so that they can reach their peers without having to go through lower level routers and wherein at least one of the following features exist:

a. Each IP address contains also geographical coordinates and the routers are aware of their own coordinates and the coordinates of at least other main routers;

b. Stationary Internet-connected devices have exact coordinates that are updated globally in the Internet when they change location;

c. Mobile devices have more general coordinates and their more exact coordinates are updated only locally when they move;

d. Routers make their routing decisions mainly by choosing the router whose physical coordinates are closest to the target;

e. The routers can also take into consideration at least one of connectivity data and bandwidth data and current load data when such additional data is needed;

f. The physical addresses can also be combined with some additional non-physical codes, so that if there are more than one network-connected devices with exactly the same physical coordinates, the additional code can distinguish between them and only the nearest local devices need to carry local tables for choosing between them;

g. The physical addresses are combined with additional non-physical addresses, so that network-connected devices are grouped together into small areas, and within each small area non-physical routing tables are used locally.

17. The system of claim 15 wherein a hierarchical system of geographical addresses is used and at least one of the following features exist:

a. Each router tries to choose one of the routers directly connected to it that are closest to the physical direction of the target area;

b. Unless the target is within its own area, each router tries to choose one of the neighboring MAIN routers (routers that are highest on the hierarchy) that are closest to the physical direction of the target area;

c. Each router has already a list of preferable next best hops or best routes for reaching the chosen MAIN router;

d. Each MAIN router has the list of locations of all the MAIN routers on the net and tries to choose one of the MAIN routers that are closest to the target area;

e. Typically each MAIN router has the list of locations of the MAIN routers on the net and tries to choose one of the MAIN routers that are closest to the target area;

f. Each MAIN router has already a list of preferable next best hops or best routes for reaching the chosen MAIN router;

g. A hierarchy of at least two-levels of routers is used;

h. The higher a router is on the hierarchy, it also has more bandwidth associated with it;

i. Higher-level routers are also connected directly with high-bandwidth as peers between each other, at least each one to its more close neighbors, without having to go through lower-level routers in order to reach their peers, so that once a higher-level router decides to forward a packet or group of packets to a higher-level peer the packets don'"'"'t have to go through lower level routers;

j. Lower level routers are used locally, and in order to get to other areas a lower level router forwards packets to a nearby MAIN router, which then forwards the data through direct connections to other MAIN routers, and only at the target area lower level routers are used again, in order to reach the final target;

k. At least one of load distribution systems and caching systems are optimized by placing at least one of mirror servers and proxies especially at close proximity to at least higher-level central routers on the hierarchies;

l. When updates are initiated from the source of the data to mirror sites, they are distributed to all of them at the same time, thus automatically utilizing the optimization of routing together packets going to the same general areas;

m. When updates are initiated from the source of the data to mirror sites, they are distributed to them at the same time, thus automatically utilizing the optimization of routing together packets going to the same general areas;

n. Data such as streaming audio and streaming video can also be constantly updated this way between the origin of the data to the main centers and/or sub-centers even before any user asks for them.

3. (canceled)

4. A method for improving the performance of routers on the Internet and/or cellular networks and/or other networks wherein packets with headers are used, comprising at least one of the following steps:

a. Using fast packet switching in optical routers, by dealing only with the headers, without having to convert the packets themselves to electronics and back, and using a device for compensating for the margin of error that occurs when the response time of the router is too slow for the bit rate, and wherein said compensation is done by at least one of;

1. Optically duplicating the bit stream and using one copy of the bit stream to route the even packets, so that the odd packets are used as a slack area, and another copy of the bit stream to route the odd packets, so that the even packets are used as a slack area, 2. Using a long mark at the beginning of the packet which is sufficiently larger than the margin of error, and making sure the size of this mark remains long enough for the next router;

b. Using a hierarchical system that uses geographical IP addresses, in which routers that are higher on the hierarchy usually have sufficient direct links between themselves so that they can reach their peers without having to go through lower level routers;

c. Grouping together at least one of identical and non-identical packets going to the same general area or direction, wherein the system is adapted so that packets that are identical can be grouped together and condensed into a single packet with a list of multiple target addresses;

5. The method of claim 4 wherein optical marks are used for fast locating of the headers of optical data packets, further comprising:

A method for creating said optical marks;

A method at the router for optically detecting and extracting at least part of the packet header before delaying the light bits;

A method for delaying the light bits at the router for the time needed for making packet switching decisions without having to convert said light bits to electricity;

A computer for comparing said target addresses to the required database and making packet switching decisions;

A fast optical router for carrying out said packet switching decisions after the light has passed through the delaying device, without having to convert the light bits to electricity;

A method for compensating for the margin of error that occurs when the response time of said fast optical router is too slow for the bit rate and enabling at least one of addition and deletion of data if required.

6. The method of claim 5 wherein at least one of the following features exist:

a. The light bits are delayed at the router by means of an optic delay circuit that the light has to run through;

b. The light bits are delayed at the router by at least one of Holographic memory, Stopping and storing the light in gas, Letting the light pass through chilled Sodium gas or another medium that considerably slows it down, and Other types of optical memory;

c. Some address processing is done in advance, so that the packet has also a destination label that helps said computer make faster packet switching decisions;

d. Said target addresses are converted into electrical data and said packet switching decisions are made by an electronic computer;

e. Said packet switching decisions are made by a photonic computer;

f. For adding data or changing data the router can route the packet bit stream into a short delay circuit, insert the new data into the output channel, and route the packet bit stream into the output channel;

g. A group of lambdas can be regarded as a single channel for packet switching, so that the group is routed together with the same routing decisions;

h. All the lambdas can be regarded as a single channel for packet switching, so that the entire group is routed together with the same routing decisions;

i. Groups of fibers can be regarded as a single channel for packet switching, so that each group is routed together with the same routing decisions.

7. The method of claim 4 wherein Said compensation for the margin of error is done by at least one of:

a. Optically duplicating the bit stream and using one copy of the bit stream to route the even packets, so that the odd packets are used as a slack area, and another copy of the bit stream to route the odd packets, so that the even packets are used as a slack area, and arrangements are made in advance to make sure that all the packets are of at least the minimum required size;

b. Using a long mark at the beginning of the packet which is sufficiently larger than the margin of error, and making sure the size of this mark remains long enough for the next router by at least one of;

Adding again a similar long mark after every cut, Adding again a similar long mark after the cutting only if the existing mark is not long enough, and Staring in advance with a mark long enough for multiple routers.

8. The method of claim 5 wherein said marks are done by at least 1 of:

a. A change in frequency, and said optical detector of marks looks for a change in frequency;

b. A change in amplitude, and said optical detector of marks looks for a change in amplitude;

c. An easily detectable period of no light, and said optical detector of marks looks for a period of no light;

d. An easily detectable period of consecutive light, and said optical detector of marks looks for a period of consecutive light;

e. An easily detectable period of consecutive light that is also marked by significantly increased intensity of the light, and said optical detector of marks also looks for a period of more intense light;

f. A change in polarization, and said optical detector of marks looks for a change in polarization;

g. An easily detectable period of fat bits that can also carry data, and said optical detector of marks looks for a period of fat bits;

h. A relative time shifting of the waves of the different lambdas, and said optical detector of marks looks for a change in wave phases;

i. An easily detectable period of no light before the beginning of the packet, and said optical detector of marks looks for a period of no light, and said period is always kept long enough to compensate for the margin of error caused by the response time of the router;

j. An easily detectable period consecutive light before the beginning of the packet and said optical detector of marks looks for a period of consecutive light, and said period is always kept long enough to compensate for the margin of error caused by the response time of the router;

k. An easily detectable period of fat bits that can also carry data and said optical detector of marks looks for a period of fat bits and said period is always kept long enough to compensate for the margin of error caused by the response time of the router.

9. The method of claim 5 wherein more than one input fibers are sharing the same output fibers, and additional mechanisms are used for handling problems when more than one packet with the conflicting wavelengths need to enter the same exit fiber before the other one finished passing, wherein at least one of the following features exist:

a. Said mechanisms are based on using at least a few fibers for each destination route, so that there is more flexibility in choosing alternative output fibers in such cases of collision;

b. Each lambda is used as a separate channel and said mechanisms are based on optical conversion of at least one of the colliding bit streams into another lambda;

c. Subsets of lambdas are used each as a single channel and said mechanisms are based on optical conversion of at least one of the colliding bit streams into another non-conflicting group of lambdas;

d. Said mechanisms are based on using at least two different polarizations in such cases by letting the colliding bit streams pass though appropriate polarization filters;

e. Said mechanisms are based on routing at least one of the colliding bit streams into at least one additional delay circuit, hoping that by the time it comes out the collision problem will no longer exist, and, if the collision is not solved, problematic packets can be dropped;

f. Said mechanisms are based on routing at least one of the colliding bit streams for temporary storage in optical memory, hoping that by the time it comes out the collision problem will no longer exist, and, if the collision is not solved, problematic packets can be dropped.

11. The method of claim 4 further comprising using a system for grouping together at least one of identical and non-identical packets going to the same general area or direction, wherein the system is adapted so that packets that are identical can be also condensed into a single packet with a list of multiple target addresses, and wherein at least one of:

a. Identical data packets from the same source going to the same general area can be grouped together and condensed by sending in each group the identical data only once, with a multiple list of targets connected to each copy of the data and sent together to the general target area;

b. Non-identical Packets from the same source or form different sources going to the same general target area can be grouped together without condensing, so that they can be routed together more efficiently and later similarly broken down according to physical proximity to the target area;

c. The grouped packets are broken down into smaller groups by the routers in the general target area and finally broken down to individual data packets for delivering to the final actual destinations;

d. Said grouped packets are broken down directly by the routers in the general target area into individual data packets for delivering to the final actual destinations;

e. Said grouping of the packets is done as a pre-processing by routers;

f. Said grouping of the packets is done by the servers themselves, which can be at least one of the original site, a mirror site, and a proxy;

g. A short time window is used on the server for collecting requests for data in order to group the packets together;

h. When downloading at least one of large video files, MP3 files, popular software files, and other large files, the server can combine together in the united packets also requests that came after the original time window, so that new requests can be combined with older requests and thus get first a later part of the file and then get earlier parts of the file later.

12. The method of claim 11 wherein said grouping is used for at least one of:

a. Transmitting much more efficiently at least one of data from Internet TV stations and Other heavy streaming data, so that even huge overloads of users accessing the site at the same time can be handled very efficiently;

b. For many purposes in many servers, so that even huge overloads of users accessing popular sites at the same time can be handled very efficiently;

c. Pushing data to a large group of subscribers at the same time;

d. Pushing updates of the DNS tables among the servers;

e. Constantly pushing at least one of streaming audio and streaming video to the proxies or centers that distribute it.

16. The method of claim 4 further comprising using a hierarchical system that uses geographical IP addresses, in which routers that are higher on the hierarchy usually have sufficient direct links between themselves so that they can reach their peers without having to go through lower level routers and wherein at least one of the following features exist:

a. Each IP address contains also geographical coordinates and the routers are aware of their own coordinates and the coordinates of at least other main routers;

b. Stationary Internet-connected devices have exact coordinates that are updated globally in the Internet when they change location;

c. Mobile devices have more general coordinates and their more exact coordinates are updated only locally when they move;

d. Routers make their routing decisions mainly by choosing the router whose physical coordinates are closest to the target;

e. The routers can also take into consideration at least one of connectivity data and bandwidth data and current load data when such additional data is needed;

f. The physical addresses can also be combined with some additional non-physical codes, so that if there are more than one network-connected devices with exactly the same physical coordinates, the additional code can distinguish between them and only the nearest local devices need to carry local tables for choosing between them;

g. The physical addresses are combined with additional non-physical addresses, so that network-connected devices are grouped together into small areas, and within each small area non-physical routing tables are used locally.

18. The method of claim 16 wherein a hierarchical system of geographical addresses is used and at least one of the following features exist:

a. Each router tries to choose one of the routers directly connected to it that are closest to the physical direction of the target area;

b. Unless the target is within its own area, each router tries to choose one of the neighboring MAIN routers (routers that are highest on the hierarchy) that are closest to the physical direction of the target area;

c. Each router has already a list of preferable next best hops or best routes for reaching the chosen MAIN router;

d. Each MAIN router has the list of locations of all the MAIN routers on the net and tries to choose one of the MAIN routers that are closest to the target area;

e. Typically each MAIN router has the list of locations of the MAIN routers on the net and tries to choose one of the MAIN routers that are closest to the target area;

f. Each MAIN router has already a list of preferable next best hops or best routes for reaching the chosen MAIN router;

g. A hierarchy of at least two-levels of routers is used;

h. The higher a router is on the hierarchy, it also has more bandwidth associated with it;

i. Higher-level routers are also connected directly with high-bandwidth as peers between each other, at least each one to its more close neighbors, without having to go through lower-level routers in order to reach their peers, so that once a higher-level router decides to forward a packet or group of packets to a higher-level peer the packets don'"'"'t have to go through lower level routers;

j. Lower level routers are used locally, and in order to get to other areas a lower level router forwards packets to a nearby MAIN router, which then forwards the data through direct connections to other MAIN routers, and only at the target area lower level routers are used again, in order to reach the final target;

k. At least one of load distribution systems and caching systems are optimized by placing at least one of mirror servers and proxies especially at close proximity to at least higher-level central routers on the hierarchies;

l. When updates are initiated from the source of the data to mirror sites, they are distributed to all of them at the same time, thus automatically utilizing the optimization of routing together packets going to the same general areas;

m. When updates are initiated from the source of the data to mirror sites, they are distributed to them at the same time, thus automatically utilizing the optimization of routing together packets going to the same general areas;

n. Data such as streaming audio and streaming video can also be constantly updated this way between the origin of the data to the main centers and/or sub-centers even before any user asks for them.

19. The method of claim 18 wherein for making the transition to this hierarchical architecture more efficient, the current structure of backbones and higher bandwidth connections is analyzed for automatically defining at least part of the hierarchy structure.

20. The method of claim 19 wherein at least one of the following things are done:

a. Said analysis is done by automatic statistical analysis, and after this initial structure is analyzed and the geographical position of at least the more significant routers is specified, the basic geographical hierarchy can be automatically defined according to this, and then later improved for achieving better optimizations;

b. The further optimizations are achieved at least by finding where at least one of more connections and more bandwidth are needed, and adding them accordingly

c. The further optimizations are achieved at least by deciding where more MAIN routers are needed, and adding bandwidth and more direct connections to routers that are chosen to become MAIN routers;

d. This analysis is automatically repeated often, for getting constant follow-ups over the growth of the net and the connectivity of various parts of it and for locating and fixing at least one of weak links and vulnerable junctions in advance;

e. In order to further facilitate the conversion into the above described hierarchies, and since the net currently contains many interconnected independent networks that are connected between them on borders called NAPs (Network Access Points), which are problematic junctures, at least one MAIN router with high broadband direct contacts to their peers at other networks are added at the center or centers of each important network;

f. More direct links are added along the borders between such networks, which is much easier, since there is no more need for complex routing tables at these borders.

21. The method of claim 4 wherein at least some proxies keep streaming data in at least one temporary buffer for a specified time window that enables users also to request at least one of instant replay and retroactive recording even if the user hasn'"'"'t been tuned in to at least one of that streaming data or that source before, and at least one of the following features exist:

a. Said proxies are at least near at least one of MAIN routers, and lower-level central routers on the hierarchies;

b. At least one of the instant replay and retroactive recoding can be used with at least one of Internet Radio, Internet TV, video-conferences, and e-learning sessions;

c. Different time windows can be used for different events;

d. At least some events carry also a code specifying the requested time window for that event, so that proxies can be requested by the source of the streaming data to allow a longer retroactive time window;

e. Replay is allowed in a few discrete time shifts, so that many users can view it at the same time, thus saving bandwidth when multiple packets going to the same physical direction are combined;

f. Requests for data can be combined even if some users start at a later point, and then only the missing starting parts are transferred separately to each user, while at the same time the common parts are transferred simultaneously in condensed packets to many users in the same general area.

13. A method of improving routing efficiency and bandwidth utilization efficiency in the Internet and/or cellular networks and/or other networks of interconnected devices, wherein proxies are used which can work also with streaming data by using short time windows to combine requests for data together.

14. The method of claim 13 wherein at least one of the following exists:

a. After getting the data, said proxies can also group together identical data packets from the same source going to the same general area by sending in each group the identical data only once, with a multiple list of targets connected to each copy of the data and sent together to the general target area;

b. At least some of the routers function also as said proxies.