Router region division method and device, storage medium and processor
By dynamically adjusting the partition of router areas in the 2.5D integrated circuit system, the problem of traffic imbalance caused by vertical link failure is solved, and faster failure recovery and higher network service quality is achieved.
Patent Information
- Application Number
- CN202510469422.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-15
- Publication Date
- 2025-06-27
AI Technical Summary
In the 2.5D system of integrated circuits, when problems occur in vertical links, the prior art is difficult to effectively re-dividing the router area, resulting in unbalanced traffic, high pressure on the border router, and prone to blockage and failure.
By obtaining the faulty boundary router area, repartitioning based on the distance between the non-boundary router and other boundary routers, multiple router areas are obtained, and the vertical traffic data of these areas are compared with the threshold of the boundary router, and the range of the router area is dynamically adjusted to achieve a more balanced distribution of traffic.
This method can quickly restore network connections in affected areas, shorten failure recovery time, enhance network risk resistance, reduce cross-region communication costs, and improve the overall service quality of the network.
Smart Images
Figure CN120223605A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of integrated circuit technology, and in particular to a method, device, storage medium and processor for dividing router areas. Background Art
[0002] 2.5D integrated circuits integrate advanced concepts such as prefabricated assembly and wafer integration. By taking advantage of the high bandwidth, low latency, and low power consumption of wafer-level interconnects, a large number of prefabricated particles such as computing, storage, and sensing can be integrated on a single wafer. Rewiring layers, through-silicon vias, and networks on substrates are implemented on the wafer substrate. The prefabricated parts can be IP cores provided by a third party or custom chips. If the IP core is provided by a third party, the internal structure cannot be changed, and the construction on the wafer can be abstracted as a traditional two-dimensional on-chip network. Existing research has been very complete, but for custom chips, there is currently less research because it involves the interconnection of units inside the chip and the interconnection between the chip and the wafer substrate.
[0003] For the wafer system interconnection network with integrated custom chips, if a vertical link has a problem, the traditional method is to redivide the router area according to the distance. The router includes border routers and ordinary routers. The border router is responsible for the downward transmission task within the router area. The ordinary router does not have the downward transmission function. The traffic within a router area is mainly borne by the border router. After the router area is redivided according to the distance, it is still easy to have a situation where the traffic in the router area is very unbalanced, which makes the border router of a certain area with large traffic volume under great pressure and prone to blockage. At the same time, the micro-bumps at the physical connection of the vertical link will also fail if the traffic volume is too large.
[0004] Therefore, when a problem occurs in a vertical link, how to redivide the router area to improve the balance of regional traffic is a technical problem that needs to be solved urgently. Summary of the invention
[0005] Based on the above problems, the present application provides a method, device, storage medium and processor for dividing router areas, the purpose of which is to improve the balance of regional traffic.
[0006] The embodiments of the present application disclose the following technical solutions:
[0007] A first aspect of the present application provides a method for dividing router areas, the method comprising:
[0008] Acquire a fault border router area; the fault border router area includes a fault border router and a plurality of non-border routers;
[0009] Re-partition the multiple non-border routers based on the distances between the multiple non-border routers and other border routers to obtain multiple router regions;
[0010] Compare the vertical traffic data of the multiple router regions with the thresholds of the border routers in the multiple router regions one by one, and adjust the ranges of the multiple router regions to obtain the adjusted multiple router regions.
[0011] Optionally, the step of comparing the vertical traffic data of the multiple router regions with the thresholds of the border routers in the multiple router regions one by one, adjusting the ranges of the multiple router regions, and obtaining the adjusted multiple router regions includes:
[0012] Obtain the vertical traffic data of the multiple router regions; the vertical traffic data of a router region includes the sum of the border router traffic and the non-border router traffic;
[0013] Compare the vertical traffic data of the multiple router regions with the thresholds of the border routers in the multiple router regions one by one to obtain multiple comparison results;
[0014] Based on the multiple comparison results, adjust the ranges of the multiple router regions to obtain the adjusted multiple router regions.
[0015] Optionally, the step of adjusting the ranges of the multiple router regions based on the multiple comparison results to obtain the adjusted multiple router regions includes:
[0016] If the comparison result shows that the vertical traffic data of a router region is greater than or equal to the threshold of the border router in the router region, re-partition the non-border routers in the faulty border router region included in the router region, adjust the range of the router region, and obtain the adjusted router region;
[0017] If the comparison result shows that the vertical traffic data of a router region is less than the threshold of the border router in the router region, obtain the range of the router region.
[0018] Optionally, the step of, if the comparison result shows that the vertical traffic data of a router region is greater than or equal to the threshold of the border router in the router region, re-partitioning the non-border routers in the faulty border router region included in the router region, adjusting the range of the router region, and obtaining the adjusted router region includes:
[0019] Based on the distances between the non-border routers in the faulty border router region included in the router region and other border routers, re-partition the non-border routers to obtain multiple new router regions;
[0020] Let the value of k be 1; use the multiple new router regions as the initial data for the k-th iteration;
[0021] Based on the multiple boundary router thresholds in the multiple new router regions, judge the vertical traffic data of the multiple new router regions in the k-th iteration one by one to obtain multiple judgment results;
[0022] If the judgment result is yes, adjust the initial data of the k-th iteration to obtain the initial data of the (k + 1)-th iteration, increment the value of k by 1, and return to the step of judging the vertical traffic data of the multiple new router regions in the k-th iteration one by one based on the multiple boundary router thresholds in the multiple new router regions to obtain multiple judgment results;
[0023] If the judgment result is no, end the iteration and output the initial data of the k-th iteration as the range of the adjusted multiple router regions.
[0024] Optionally, the step of if the judgment result is yes, adjusting the initial data of the k-th iteration to obtain the initial data of the (k + 1)-th iteration, incrementing the value of k by 1, and returning to the step of judging the vertical traffic data of the multiple new router regions in the k-th iteration one by one based on the multiple boundary router thresholds in the multiple new router regions to obtain multiple judgment results includes:
[0025] If the judgment result is yes, based on the distances between the non-boundary routers and other boundary routers in the faulty boundary router regions included in the router region, determine the boundary routers whose distances from the non-boundary routers are within a preset distance range;
[0026] Assign the non-boundary routers to the router regions to which the boundary routers belong to obtain the initial data of the (k + 1)-th iteration.
[0027] Optionally, the step of if the judgment result is yes, based on the distances between the non-boundary routers and other boundary routers in the faulty boundary router regions included in the router region, determining the boundary routers whose distances from the non-boundary routers are within a preset distance range includes:
[0028] When it is determined that there is more than one boundary router whose distance from the non-boundary router is within the preset distance range, make a selection by calculating the cost; the cost includes distance cost and traffic cost;
[0029] The formula for calculating the cost is:
[0030]
[0031] Among them, C is the overall cost of the router area, and C j is the traffic cost of a single border router, and D i is the distance cost between non-border routers and border routers. j is the number of border routers in the router area, r is the total number of border routers and non-border routers in the router area, and m and n are weighting coefficients that satisfy m + n = 1.
[0032] The second aspect of this application provides a router area division device, which includes:
[0033] An acquisition module, configured to acquire a faulty border router area; the faulty border router area includes a faulty border router and multiple non-border routers;
[0034] A router area division module, configured to re-partition the multiple non-border routers based on the distances between the multiple non-border routers and other border routers to obtain multiple router areas;
[0035] A router area adjustment module, configured to compare the vertical traffic data of the multiple router areas with the thresholds of the border routers in the multiple router areas one by one, and adjust the ranges of the multiple router areas to obtain the adjusted multiple router areas.
[0036] The router area adjustment module is specifically configured to:
[0037] Acquire the vertical traffic data of the multiple router areas; the vertical traffic data of a router area includes the sum of the border router traffic and the non-border router traffic;
[0038] Compare the vertical traffic data of the multiple router areas with the thresholds of the border routers in the multiple router areas one by one to obtain multiple comparison results;
[0039] Based on the multiple comparison results, adjust the ranges of the multiple router areas to obtain the adjusted multiple router areas.
[0040] The third aspect of this application provides a computer-readable storage medium, in which a computer program is stored. When the program is run by a processor, it implements the router area division method provided in any implementation manner of the first aspect.
[0041] The fourth aspect of this application provides a processor, which is used to run a computer program. When the program runs, it executes the router area division method provided in any implementation manner of the first aspect.
[0042] Compared with the prior art, this application has the following beneficial effects:
[0043] The router area division method provided by this application can immediately reassign the non-border routers under the responsibility of a faulty border router once it is detected. This can quickly restore the network connection in the affected area, shorten the fault recovery time, and enhance the overall risk resistance ability of the network. By reassigning the affiliated areas according to the distances between non-border routers and other border routers, the network topology becomes more reasonable, reducing the cost of cross-area communication. Judging the router area traffic based on the border router threshold and adjusting the scope of the router area accordingly helps to balance the network load, prevent some border routers from being overloaded, and thus improve the service quality of the entire network. Therefore, when a border router fails on the vertical link, this application fully considers the distance factor and traffic balance, optimizes the traffic distribution in the router area by dynamically adjusting the division of the router area, and avoids network performance degradation or congestion caused by border router failures. Description of the Drawings
[0044] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0045] Figure 1 It is a flowchart of a router area division method provided by an embodiment of this application;
[0046] Figure 2 It is a schematic diagram of a network topology structure provided by an embodiment of this application;
[0047] Figure 3 It is a flowchart of another router area division method provided by an embodiment of this application;
[0048] Figure 4 It is a schematic diagram of another network topology structure provided by an embodiment of this application;
[0049] Figure 5 It is a schematic diagram of yet another network topology structure provided by an embodiment of this application;
[0050] Figure 6 It is a schematic diagram of the structure of a router area division device provided by an embodiment of this application. Detailed Embodiments
[0051] As described above, the current method is to re-partition the area of the router according to the distance. The router includes a border router and ordinary routers. The border router is responsible for the downward transmission task within the router area. Ordinary routers do not have the function of downward transmission. The traffic within a certain router area is mainly borne by the border router. After re-partitioning the router area according to the distance, it is still easy to have a very unbalanced situation of router area traffic, which makes the border router in a certain area with a large traffic under great pressure and prone to congestion. At the same time, problems such as failure will also occur when the traffic of the microbumps at the physical connection of the vertical link is too large.
[0052] In view of the above problems, through research, the inventor has proposed a router area partitioning method, device, storage medium and processor, which acquires a faulty border router area; the faulty border router area includes a faulty border router and a plurality of non-border routers; based on the distances between the plurality of non-border routers and other border routers, the plurality of non-border routers are re-partitioned to obtain a plurality of router areas; the vertical traffic data of the plurality of router areas are respectively compared with the thresholds of the border routers in the plurality of router areas one by one, and the ranges of the plurality of router areas are adjusted to obtain the adjusted plurality of router areas.
[0053] In order to enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.
[0054] See Figure 1 , which is a flowchart of a router area partitioning method provided by an embodiment of this application. As Figure 1 shown, the method includes the following steps:
[0055] S101. Acquire a faulty border router area.
[0056] Among them, the faulty border router area includes a faulty border router and a plurality of non-border routers.
[0057] The faulty border router area refers to the area directly controlled or affected by the faulty border router. This area not only includes the faulty border router itself, but also all non-border routers connected to the border router. The border router is responsible for cross-region communication and usually connects multiple subnets. The non-border router is an ordinary router and is mainly responsible for internal communication. As Figure 2 shown, Figure 2It shows a network topology. The dark dots represent border routers, and the light dots represent non-border routers. Each dot is connected by a straight line, indicating that there is a direct communication link between these dots. The entire grid is divided into four regions by dashed lines, and the four regions are labeled 1, 2, 3, and 4 respectively. The dots within each region belong to the same subnet or administrative domain.
[0058] S102. Re-partition the multiple non-border routers based on the distances between the multiple non-border routers and other border routers to obtain multiple router regions.
[0059] The distance can be physical distance, hop count, or latency, etc. Which distance metric to choose depends on the specific application scenario and network requirements. For example, according to the calculated distances, each non-border router is assigned to the border router with the closest distance to it. Here, the closest can be the minimum latency, the fewest hop counts, or other criteria.
[0060] Re-partition the non-border routers within the faulty border router region based on distance. For example, according to the distance priority mechanism, select the border router with the closest distance. When the distances to multiple border routers are equal, further decisions can be made according to strategies such as random selection, historical performance, priority, or redundant paths.
[0061] Re-partitioning the multiple non-border routers based on the distances between the multiple non-border routers and other border routers can avoid large-scale network service interruptions caused by the failure of a single border router.
[0062] S103. Compare the vertical traffic data of the multiple router regions with the thresholds of the border routers in the multiple router regions one by one, and adjust the ranges of the multiple router regions to obtain the adjusted multiple router regions.
[0063] The border router threshold refers to the maximum traffic or load upper limit that a border router can handle, which is usually set by the hardware performance of the border router, bandwidth limitations, or network design requirements. In an implementable embodiment, for each router region, the collected vertical traffic data is compared with the border router threshold. If the traffic within the region is less than the border router threshold, it means that the traffic in the region is within the carrying capacity of the border router and the status is normal; if the traffic within the region is equal to or greater than the border router threshold, it means that the traffic in the region has approached or exceeded the carrying capacity of the border router and the status is overloaded.
[0064] Judging the traffic in multiple router regions based on the boundary router threshold is an important step in network management and optimization. This method can be used to evaluate whether the traffic load in each region exceeds the processing capacity of the boundary router, and provide a basis for determining the scope of the router region in the subsequent stage according to the evaluation result.
[0065] By judging whether the traffic in each router region exceeds the boundary router threshold to determine the scope of multiple router regions, this way of dynamically adjusting the network topology enables the network to adapt to the demand changes in different scenarios, such as traffic fluctuations, equipment failures, etc.
[0066] In an implementable embodiment, if the traffic in a certain router region is overloaded after re-partitioning, the non-boundary routers are transferred from the overloaded router region to other normal router regions, where the non-boundary routers are the non-boundary routers in the faulty boundary router region. When transferring, based on the distance between the non-boundary routers and other boundary routers, the router region with the closest distance is selected. After the transfer of the non-boundary routers is completed, the traffic in each router region is recalculated and compared with the boundary router threshold again until the traffic in all router regions meets the carrying capacity of the boundary router, then this process ends and the adjusted scope of the router region is obtained.
[0067] The router region division method provided by the embodiments of the present application can immediately reallocate the non-boundary routers responsible for a faulty boundary router once it is detected, quickly restore the network connection in the affected area, shorten the fault recovery time, and enhance the overall risk resistance ability of the network; reallocating the affiliated regions according to the distance between the non-boundary routers and other boundary routers makes the network topology more reasonable and reduces the cost of cross-region communication; judging the traffic in the router region based on the boundary router threshold and adjusting the scope of the router region accordingly helps to balance the network load, prevent some boundary routers from being overloaded, and thus improve the service quality of the entire network. Therefore, when a boundary router fails on the vertical link, the present application fully considers the distance factor and traffic balance, optimizes the traffic distribution in the router region by dynamically adjusting the division of the router region, and avoids the network performance degradation or congestion caused by the boundary router failure.
[0068] On the basis of the above embodiments, in order to further improve the router region division method, the step of judging the traffic in the multiple router regions based on the boundary router threshold to obtain multiple first judgment results in this method is refined.
[0069] See Figure 3 , this figure is a flowchart of another router region division method provided by the embodiments of the present application. As Figure 3 shown, this method includes the following steps:
[0070] S301. Obtain the faulty boundary router area.
[0071] Wherein, the faulty boundary router area includes a faulty boundary router and multiple non-boundary routers.
[0072] When a certain boundary router fails, the area within its influence range is called the faulty boundary router area, and it is necessary to re-partition the non-boundary routers within the faulty boundary router area to optimize the traffic distribution.
[0073] S302. Based on the distances between the multiple non-boundary routers and other boundary routers, re-partition the multiple non-boundary routers to obtain multiple router areas.
[0074] As Figure 4 shown, Figure 4 shows a network topology. The dark dots represent boundary routers, and the light dots represent non-boundary routers. Each dot is connected by a straight line, indicating that there is a direct communication link between these dots. The dark grid-like dot is the faulty boundary router. After re-partitioning the non-boundary routers within the faulty router area, the entire grid is divided into three areas by dashed lines, and these three areas are respectively labeled 1, 2, and 3. The vertical traffic T in area 1 is 0.9, the vertical traffic T in area 2 is 0.2, and the vertical traffic T in area 3 is 0.5. It can be seen that the vertical traffic in the three areas is unbalanced. The pressure on the boundary router in area 1 is relatively large and is prone to congestion. At the same time, when the traffic of the microbumps at the physical connection of the vertical link is too large, failures will also occur.
[0075] When re-partitioning, the distance between the non-boundary router and the boundary router is given priority, which can shorten the data transmission path, optimize the network topology, and reduce the influence range of a single failure point.
[0076] S303. Obtain the vertical traffic data of the multiple router areas.
[0077] Wherein, the vertical traffic data of the router area includes the sum of the boundary router traffic and the non-boundary router traffic.
[0078] S304. Compare the vertical traffic data of the multiple router areas with the thresholds of the boundary routers in the multiple router areas one by one to obtain multiple comparison results.
[0079] In an implementable embodiment:
[0080] If the comparison result shows that the vertical traffic data of the router area is greater than or equal to the threshold of the border router in the router area, re-partition the non-border routers in the faulty border router area included in the router area, adjust the scope of the router area, and obtain the adjusted router area;
[0081] If the comparison result shows that the vertical traffic data of the router area is less than the threshold of the border router in the router area, obtain the scope of the router area.
[0082] Based on the multiple comparison results, adjust the scopes of the multiple router areas to obtain the adjusted multiple router areas. Traffic overload may be caused by a single border router carrying too much traffic or unreasonable area division. Based on the distances between the non-border routers in the area and other border routers, re-divide the areas to which the non-border routers in the faulty border router area belong. The goal is to disperse the traffic to other border routers, thereby reducing the pressure on the original border router. If the vertical traffic of the router area does not exceed the threshold, there is no need to re-divide the area, and the scope of the router area divided in the previous step can be used.
[0083] By comparing the vertical traffic of the router area with the border router threshold, it is possible to detect and solve the traffic overload problem in a timely manner, quickly re-allocate the traffic, reduce the impact on the overall network, and ensure the stability of the network.
[0084] S305. Based on the multiple comparison results, adjust the scopes of the multiple router areas to obtain the adjusted multiple router areas.
[0085] In an achievable implementation, if the comparison result shows that the vertical traffic data of the router area is greater than or equal to the threshold of the border router in the router area, re-partition the non-border routers in the faulty border router area included in the router area, adjust the scope of the router area, and obtain the adjusted router area, including:
[0086] Based on the distances between the non-border routers in the faulty border router area included in the router area and other border routers, re-partition the non-border routers to obtain multiple new router areas;
[0087] Let the value of k be 1; use the multiple new router areas as the initial data for the k-th iteration;
[0088] Based on the multiple border router thresholds in the multiple new router areas, judge the vertical traffic data of the multiple new router areas in the k-th iteration one by one to obtain multiple judgment results;
[0089] If the judgment result is yes, adjust the initial data of the k-th iteration to obtain the initial data of the (k + 1)-th iteration, increment the value of k by 1, and return the step of judging the vertical traffic data of the multiple new router regions in the k-th iteration one by one based on the multiple border router thresholds in the multiple new router regions to obtain multiple judgment results;
[0090] If the judgment result is no, end the iteration and output the initial data of the k-th iteration as the range of the adjusted multiple router regions.
[0091] In an implementable embodiment, if the judgment result is yes, adjusting the initial data of the k-th iteration to obtain the initial data of the (k + 1)-th iteration, incrementing the value of k by 1, and returning the step of judging the vertical traffic data of the multiple new router regions in the k-th iteration one by one based on the multiple border router thresholds in the multiple new router regions to obtain multiple judgment results includes:
[0092] If the judgment result is yes, based on the distances between the non-border routers and other border routers in the faulty border router regions included in the router region, determine the border routers whose distances from the non-border routers are within a preset distance range;
[0093] Assign the non-border routers to the router regions to which the border routers belong to obtain the initial data of the (k + 1)-th iteration.
[0094] Among them, the step of, if the judgment result is yes, based on the distances between the non-border routers and other border routers in the faulty border router regions included in the router region, determining the border routers whose distances from the non-border routers are within a preset distance range includes:
[0095] When it is determined that there is more than one border router whose distance from the non-border router is within the preset distance range, make a selection by calculating the cost; the cost includes distance cost and traffic cost;
[0096] The formula for calculating the cost is:
[0097]
[0098] Among them, C is the overall cost of the router region, C j is the traffic cost of a single border router, D i is the distance cost between the non-border router and the border router, j is the number of border routers in the router region, r is the total number of border routers and non-border routers in the router region, and m and n are weighting coefficients satisfying m + n = 1.
[0099] By adjusting the values of m and n, the degree of emphasis on traffic balance and distance can be flexibly adjusted. If more attention is paid to traffic balance (such as avoiding overload of certain border routers), m can be increased. If more attention is paid to reducing communication latency or optimizing the network topology, n can be increased. This method takes into account the requirements of both traffic and distance and is applicable to cost assessment and optimization decisions in complex network environments.
[0100] Calculate C j The formula for it is:
[0101] C j = T j / V;
[0102] Among them, T j is the traffic of the border router, which is the sum of the traffic of non-border routers in the router area to which the border router belongs, and V is the threshold of the border router.
[0103] Calculate D i The formula for it is:
[0104] D i = |x r - x b | + |y r - y b |;
[0105] Among them, (x r , y r ) are the coordinates of the non-border router, and (x b , y b ) are the coordinates of the border router.
[0106] As Figure 5 shown, Figure 5 shows a network topology. The dark dots represent border routers, and the light dots represent non-border routers. Each dot is connected by a straight line, indicating that there is a direct communication link between these dots. The dark grid-like dots are faulty border routers. After adjusting the scope of multiple router areas based on the first judgment result, the entire grid is divided into three areas by a dotted line, and these three areas are marked as 1, 2, and 3 respectively. The vertical traffic T in area 1 is 0.5, the vertical traffic T in area 2 is 0.6, and the vertical traffic T in area 3 is 0.5. It can be seen that the vertical traffic in the three areas is relatively balanced.
[0107] Another router area division method provided by the embodiments of the present application can immediately reassign the non-border routers responsible for a faulty border router once the faulty border router is detected, quickly restore the network connection in the affected area, shorten the fault recovery time, and enhance the overall risk resistance of the network; reassign the affiliated areas according to the distances between non-border routers and other border routers, making the network topology more reasonable and reducing the cost of cross-area communication; judge the router area traffic based on the border router threshold and adjust the scope of the router area accordingly, which helps to balance the network load, prevent some border routers from being overloaded, and thus improve the service quality of the entire network. Therefore, when a border router fails on the vertical link, this method fully considers the distance factor and traffic balance, optimizes the traffic distribution in the router area by dynamically adjusting the scope of the router area, enhances the fault tolerance of the network, and improves the traffic balance of the network.
[0108] Based on the router area division method introduced in the foregoing embodiments, correspondingly, the present application further provides a router area division device. Figure 6 The following is a schematic structural diagram of the device. As Figure 6 shown, the router area division device includes:
[0109] An obtaining module 601, configured to obtain a faulty border router area; the faulty border router area includes a faulty border router and multiple non-border routers;
[0110] A router area division module 602, configured to re-partition the multiple non-border routers based on the distances between the multiple non-border routers and other border routers, to obtain multiple router areas;
[0111] A router area adjustment module 603, configured to compare the vertical traffic data of the multiple router areas with the thresholds of the border routers in the multiple router areas one by one, and adjust the scopes of the multiple router areas to obtain the adjusted multiple router areas.
[0112] Optionally, the router area adjustment module is specifically configured to:
[0113] Obtain the vertical traffic data of the multiple router areas; the vertical traffic data of a router area includes the sum of the border router traffic and the non-border router traffic;
[0114] Compare the vertical traffic data of the multiple router areas with the thresholds of the border routers in the multiple router areas one by one, to obtain multiple comparison results;
[0115] Based on the multiple comparison results, adjust the scopes of the multiple router areas to obtain the adjusted multiple router areas.
[0116] Optionally, adjusting the ranges of the multiple router areas based on the multiple comparison results to obtain adjusted multiple router areas includes:
[0117] If the comparison result shows that the vertical traffic data of a router area is greater than or equal to the threshold of the border router in the router area, repartition the non-border routers in the faulty border router area included in the router area, adjust the range of the router area, and obtain an adjusted router area;
[0118] If the comparison result shows that the vertical traffic data of a router area is less than the threshold of the border router in the router area, obtain the range of the router area.
[0119] Optionally, if the comparison result shows that the vertical traffic data of a router area is greater than or equal to the threshold of the border router in the router area, repartition the non-border routers in the faulty border router area included in the router area, adjust the range of the router area, and obtain an adjusted router area, including:
[0120] Based on the distances between the non-border routers in the faulty border router area included in the router area and other border routers, repartition the non-border routers to obtain multiple new router areas;
[0121] Let the value of k be 1; use the multiple new router areas as the initial data for the k-th iteration;
[0122] Based on the multiple border router thresholds in the multiple new router areas, judge the vertical traffic data of the multiple new router areas in the k-th iteration one by one to obtain multiple judgment results;
[0123] If the judgment result is yes, adjust the initial data of the k-th iteration to obtain the initial data of the (k + 1)-th iteration, increment the value of k by 1, and return to the step of judging the vertical traffic data of the multiple new router areas in the k-th iteration one by one based on the multiple border router thresholds in the multiple new router areas to obtain multiple judgment results;
[0124] If the judgment result is no, end the iteration and output the initial data of the k-th iteration as the ranges of the adjusted multiple router areas.
[0125] Optionally, if the judgment result is yes, adjust the initial data of the k-th iteration to obtain the initial data of the (k + 1)-th iteration, increment the value of k by 1, and return the step of judging the vertical traffic data of the multiple new router regions in the k-th iteration one by one based on the multiple border router thresholds in the multiple new router regions to obtain multiple judgment results, including:
[0126] If the judgment result is yes, based on the distances between the non-border routers and other border routers in the faulty border router region included in the router region, determine the border routers whose distances from the non-border routers are within a preset distance range;
[0127] Assign the non-border routers to the router region to which the border routers belong to obtain the initial data of the (k + 1)-th iteration.
[0128] Optionally, the step of, if the judgment result is yes, based on the distances between the non-border routers and other border routers in the faulty border router region included in the router region, determining the border routers whose distances from the non-border routers are within a preset distance range, includes:
[0129] When it is determined that there is more than one border router whose distance from the non-border router is within the preset distance range, make a selection by calculating the cost; the cost includes distance cost and traffic cost;
[0130] The formula for calculating the cost is:
[0131]
[0132] where C is the overall cost of the router region, C j is the traffic cost of a single border router, D i is the distance cost between the non-border router and the border router, j is the number of border routers in the router region, r is the total number of border routers and non-border routers in the router region, and m and n are weighting coefficients satisfying m + n = 1.
[0133] In addition, an embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored. When the program is run by a processor, the router region partitioning method introduced in any manner of the method embodiment is implemented.
[0134] In addition, an embodiment of the present application further provides a processor for running a computer program, and when the program runs, it executes the router region partitioning method introduced in any implementation manner of the foregoing method embodiment.
[0135] It should be noted that the various embodiments in this specification are described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for the relevant content. The device embodiments described above are only illustrative. The units described as separate components may or may not be physically separated, and the components referred to as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.
[0136] As described above, it is only a specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in this application should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.
Claims
1. A method for dividing a router area, characterized in that: include: Get the faulty border router area; The fault boundary router area includes a fault boundary router and a plurality of non-boundary routers; Based on the distances between the multiple non-border routers and other border routers, the multiple non-border routers are re-partitioned to obtain multiple router areas; The vertical flow data of the multiple router areas are compared one by one with the thresholds of the border routers in the multiple router areas respectively, and the ranges of the multiple router areas are adjusted to obtain the adjusted multiple router areas.
2. The method according to claim 1, characterized in that The vertical flow data of the plurality of router areas are compared one by one with the thresholds of the border routers in the plurality of router areas respectively, and the ranges of the plurality of router areas are adjusted to obtain the plurality of adjusted router areas, including: Acquire vertical traffic data of the plurality of router areas; the vertical traffic data of the router area includes the sum of the border router traffic and the non-border router traffic; Comparing the vertical flow data of the plurality of router areas with the thresholds of the border routers in the plurality of router areas one by one, respectively, to obtain a plurality of comparison results; Based on the multiple comparison results, the ranges of the multiple router areas are adjusted to obtain multiple adjusted router areas.
3. The method according to claim 2, characterized in that The step of adjusting the ranges of the plurality of router areas based on the plurality of comparison results to obtain the plurality of adjusted router areas comprises: If the comparison result shows that the vertical flow data of the router area is greater than or equal to the threshold of the border router in the router area, the non-border routers of the faulty border router area contained in the router area are re-partitioned, and the range of the router area is adjusted to obtain an adjusted router area; If the comparison result shows that the vertical flow data of the router area is less than the threshold of the border router in the router area, the range of the router area is obtained.
4. The method according to claim 3, characterized in that If the comparison result shows that the vertical flow data of the router area is greater than or equal to the threshold of the border router in the router area, the non-border routers of the faulty border router area contained in the router area are repartitioned, and the range of the router area is adjusted to obtain the adjusted router area, including: Based on the distance between the non-border routers in the faulty border router area and other border routers contained in the router area, the non-border routers are re-partitioned to obtain a plurality of new router areas; Let the value of k be 1; use the multiple new router areas as initial data for the kth iteration; Based on multiple border router thresholds in the multiple new router areas, vertical flow data of multiple new router areas of the kth iteration are judged one by one to obtain multiple judgment results; If the judgment result is yes, the initial data of the kth iteration is adjusted to obtain the initial data of the k+1th iteration, the value of k is increased by 1, and the vertical flow data of the multiple new router areas of the kth iteration are judged one by one based on the multiple border router thresholds in the multiple new router areas to obtain multiple judgment results; If the judgment result is no, the iteration ends, and the initial data of the kth iteration is output as the adjusted range of the multiple router areas.
5. The method according to claim 4, characterized in that If the judgment result is yes, the initial data of the kth iteration is adjusted to obtain the initial data of the k+1th iteration, the value of k is increased by 1, and the vertical flow data of the multiple new router areas of the kth iteration are judged one by one based on the multiple border router thresholds in the multiple new router areas to obtain multiple judgment results, including: If the judgment result is yes, based on the distances between the non-border routers in the faulty border router area and other border routers included in the router area, determine a border router whose distance to the non-border router is within a preset distance range; The non-border router is divided into the router area to which the border router belongs, and initial data of the k+1th iteration is obtained.
6. The method according to claim 5, characterized in that If the judgment result is yes, based on the distances between the non-border routers in the faulty border router area and other border routers included in the router area, determining the border routers within a preset distance range from the non-border routers, including: When it is determined that there is more than one border router within a preset distance range from the non-border router, a selection is made by calculating the cost; the cost includes a distance cost and a flow cost; The formula for calculating the cost is: Where C is the overall cost of the router area, C j is the traffic cost of a single border router, D i is the distance cost between the non-border router and the border router, j is the number of border routers in the router area, r is the total number of border routers and non-border routers in the router area, m and n are weighted coefficients, satisfying m+n=1.
7. A router area division device, characterized in that: include: An acquisition module, used for acquiring a faulty border router area; The fault boundary router area includes a fault boundary router and a plurality of non-boundary routers; A router area partitioning module, configured to re-partition the plurality of non-border routers based on the distances between the plurality of non-border routers and other border routers to obtain a plurality of router areas; The router area adjustment module is used to adjust the ranges of the multiple router areas based on comparing the vertical flow data of the multiple router areas with the thresholds of the border routers in the multiple router areas one by one to obtain the multiple adjusted router areas.
8. The device according to claim 7, characterized in that The router area adjustment module is specifically used for: Acquire vertical traffic data of the plurality of router areas; the vertical traffic data of the router area includes the sum of the border router traffic and the non-border router traffic; Comparing the vertical flow data of the plurality of router areas with the thresholds of the border routers in the plurality of router areas one by one, respectively, to obtain a plurality of comparison results; Based on the multiple comparison results, the ranges of the multiple router areas are adjusted to obtain multiple adjusted router areas.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the program is executed by a processor, the method for dividing router areas according to any one of claims 1 to 6 is implemented.
10. A processor, characterized in that: Used to run a computer program, which executes the router area division method according to any one of claims 1 to 6 when running.