Design device, design method, and design program

Abstract

A designing device (10) uses a first granularity (for example, a real solution) to optimize the traffic amount allocated to each of the links between adjacent nodes included in a network. The designing device (10) also calculates an approximate solution obtained by using a second granularity (for example, an integer solution) to approximate the traffic amount optimized by use of the first granularity. According to the traffic amount as approximated, the designing device (10) further maps a logic path to each of a plurality of paths constituted by the links.

Description

[Technical field]

[0001] The present invention relates to a design apparatus, a design method, and a design program. [Background technology]

[0002] Network operators need to appropriately design routes to accommodate traffic efficiently while satisfying various carrier-specific policies regarding reliability and quality.

[0003] In order to efficiently accommodate traffic, conventionally, due to constraints on network device implementation, routes between certain end nodes were typically allocated to the same single route, regardless of the users or services accommodated, or randomly assigned to multiple routes.

[0004] On the other hand, in recent years, technologies have emerged that monitor traffic details to identify the users and services being accommodated, and that set up logical paths on a more detailed basis. Utilizing these technologies is expected to further improve traffic accommodation efficiency.

[0005] One method of calculating routes when traffic demand and network topology are given is to use the Dijkstra algorithm or other methods to calculate the route that minimizes the sum of link costs based on the link costs assigned to each link in the topology.

[0006] For example, Non-Patent Document 1 proposes a method for minimizing the maximum link utilization rate in a network and increasing the traffic accommodation efficiency by devising a method for assigning link costs.

[0007] In addition, there is an approach using mathematical programming to calculate a strictly optimal solution when traffic demand and network topology are given.

[0008] For example, non-patent document 2 defines two problems: the Bifurcation Problem (hereinafter referred to as BP), which calculates a real solution that allows for branching and merging of traffic between start and end nodes, and the Non-Bifurcation Problem (hereinafter referred to as NBP), which calculates an integer solution that results in a single route between the start and end nodes. [Prior art documents] [Non-patent literature]

[0009] [Non-Patent Document 1] B. Fortz, M. Thorup, “Internet Traffic Engineering by Optimizing OSPF Weights,” in IEEE INFOCOM 2000. [Non-Patent Document 2] Y. Wang and Z. Wang, "Explicit Routing Algorithms for Internet Traffic Engineering," in Proc. of ICCCN'99, Sep. 1999. Summary of the Invention [Problem to be solved by the invention]

[0010] However, the conventional techniques have a problem in that it is sometimes difficult to design routes with high traffic accommodation efficiency in a communication network using a practical method.

[0011] For example, in the heuristic solution method described in Non-Patent Document 1, a route is indirectly determined by the minimum sum of link costs, and therefore a strictly optimal solution may not be obtained.

[0012] In addition, for example, BP described in Non-Patent Document 2 can be formulated as a linear programming problem, and NBP can be formulated as an integer programming problem, so that strict optimization can be calculated for each.

[0013] On the other hand, BP calculates real solutions quickly, but the calculated real solutions are not solutions that can be set up in real network equipment. Also, NBP is an integer solution, so it can be set up in real network equipment, but because the problem is NP-hard, calculations on a carrier network scale cannot be performed in a practical amount of time. [Means for solving the problem]

[0014] In order to solve the above-mentioned problems and achieve the objective, a design device is characterized by having an optimization unit that optimizes, at a first granularity, a traffic volume assigned to each of the links between adjacent nodes included in a network, and an approximation calculation unit that calculates an approximate solution that approximates, at a second granularity, the traffic volume optimized at the first granularity. Effect of the Invention

[0015] According to the present invention, a route design with high traffic accommodation efficiency in a communication network can be performed by a practical method. [Brief description of the drawings]

[0016] [Figure 1] FIG. 1 is a diagram illustrating BP and NBP. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of a communication system according to the first embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of a design apparatus according to the first embodiment. [Figure 4] FIG. 4 is a diagram for explaining the flow of route calculation. [Diagram 5] FIG. 5 is a diagram for explaining exchange traffic. [Figure 6] FIG. 6 is a diagram showing an example of exchange traffic. [Figure 7] FIG. 7 is a flowchart showing a process flow of the design apparatus according to the first embodiment. [Figure 8] FIG. 8 is a flowchart showing the flow of the mapping process. [Figure 9]FIG. 9 illustrates an example of the mapping process. [Figure 10] FIG. 10 is a diagram for explaining the Subal method. [Figure 11] FIG. 11 is a diagram illustrating an example of a computer that executes a design program. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of a design apparatus, a design method, and a design program according to the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited to the preferred embodiments described below.

[0018] [About BP and NBP] Fig. 1 is a diagram for explaining BP and NBP. As shown in Fig. 1, rigorous optimization in BP and NBP is performed by, for example, wang99.

[0019] In addition, BP allows for mid-stream branching of traffic. As mentioned above, BP is easy (fast) to calculate because it is a real number solution, but it is not suitable for implementation. In addition, NBP is implementable because it is an integer solution, but there is a problem that the problem is NP-hard and the calculation is not practical.

[0020] On the other hand, when considering the scale of a carrier network, the BP approach is effective, but since existing network equipment does not allow for branching or merging of traffic or the setting of logical paths at the granularity of any real number, there is a problem in that the results of optimal calculations using BP cannot be applied.

[0021] One of the objects of this embodiment is to realize a design method that solves the problems of BP and NBP.

[0022] [First embodiment] 2 is a diagram showing an example of the configuration of a communication system according to the first embodiment. As shown in FIG 1, the communication system 1 includes a communication network N, a design device 10, a monitoring device 20, and a control device 30.

[0023] The communication network N is a packet network including a plurality of nodes. For example, the nodes are IP routers and L2 switches. The nodes of the communication network N are connected to each other by links such as optical fibers.

[0024] The design device 10 performs route design for a communication network N. For example, the design device 10 manages a network configuration based on information from a monitoring device 20 and a control device 30, and performs route design (calculation).

[0025] The monitoring device 20 monitors the communication network N. For example, the monitoring device 20 observes the amount of traffic flowing through each link and the exchange traffic information for each logical path (e.g., VPN) set at the start node and the end node. In addition, the monitoring device 20 provides the obtained traffic information to the design device 10 and the control device 30.

[0026] The control device 30 controls the communication network N. For example, the control device 30 sets the path information designed by the design device 10 in each node.

[0027] 3 is a diagram showing an example of the configuration of a design device according to the first embodiment. The design device 10 accepts input of information observed by a monitoring device 20. For example, the design device 10 accepts input of the topology and exchange traffic of a communication network N. In addition, the design device 10 outputs route information to a control device 30.

[0028] As shown in FIG. 3, the design device 10 includes an interface unit 11, a storage unit 12, and a control unit 13.

[0029] The interface unit 11 is an interface for inputting and outputting data. For example, the interface unit 11 is a network interface card (NIC). The interface unit 11 can transmit and receive data to and from other devices.

[0030] The interface unit 11 may also be connected to input devices such as a mouse and a keyboard, and may also be connected to output devices such as a display and a speaker, so that the interface unit 11 functions as an interface with a network operator.

[0031] The storage unit 12 is a storage device such as a hard disk drive (HDD), a solid state drive (SSD), an optical disk, etc. The storage unit 12 may be a semiconductor memory in which data can be rewritten, such as a random access memory (RAM), a flash memory, or a non-volatile static random access memory (NVSRAM). The storage unit 12 stores an operating system (OS) and various programs executed by the design apparatus 10.

[0032] The storage unit 12 stores a route DB 121 , a topology DB 122 , and a traffic DB 123 .

[0033] The route DB 121 holds route information for each logical path set between a start node and an end node. A method for calculating the route information will be described later.

[0034] The topology DB 122 holds connection information between nodes and links, and capacity information of each link, while the traffic DB 123 manages traffic information for each link and exchange traffic information for each logical path.

[0035] The design device 10 calculates route information from the topology DB 122 and the traffic DB 123, and stores the calculated route information in the route DB 121. The design device 10 may also output the calculated route information.

[0036] The control unit 13 controls the entire design apparatus 10. The control unit 13 is, for example, an electronic circuit such as a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 13 also has an internal memory for storing programs that define various processing procedures and control data, and executes each process using the internal memory.

[0037] The control unit 13 functions as various processing units by the operation of various programs. For example, the control unit 13 includes a shortest path calculation unit 131, an optimization unit 132, an approximation calculation unit 133, and a mapping unit .

[0038] The shortest path calculation unit 131 calculates the shortest path between a specified start node and end node.

[0039] The optimization unit 132 optimizes the traffic volume allocated to each of the links between adjacent nodes included in the network with a first granularity. For example, the optimization unit 132 optimizes the exchange traffic volume with a real number solution. For example, the first granularity is a real number.

[0040] The approximation calculation unit 133 calculates an approximation solution by approximating the traffic volume optimized at the first granularity at the second granularity. For example, the approximation calculation unit 133 approximates a real number solution with an integer solution. For example, the second granularity is an integer.

[0041] The mapping unit 134 maps logical paths to each of the routes formed by the links in accordance with the traffic volume approximated by the approximation calculation unit 133 .

[0042] Here, the exchange traffic will be explained using Fig. 5. Fig. 5 is a diagram for explaining the exchange traffic.

[0043] The exchange traffic does not represent the total amount of traffic flowing on the links between adjacent nodes, but represents the amount of traffic on the path (set of links) between the start node and the end node.

[0044] 5, the exchange traffic between node 51 and node 54 is 40 Gbps, and the exchange traffic between node 51 and node 52 is 20 Gbps.

[0045] Fig. 6 is a diagram showing an example of exchange traffic. When two exchange traffic flows as shown in Fig. 5 are generated, the traffic flow is expressed in a matrix as shown in the table of Fig. 6.

[0046] The route calculation by the design device 10 will be described in detail with reference to Fig. 4. Fig. 4 is a diagram for explaining the flow of the route calculation.

[0047] 4, the path resolution, the exchange traffic, and the topology are provided to the design device 10. The path resolution is the minimum granularity (for example, an integer) of the traffic volume that can be set on a route.

[0048] For example, there may be cases where the unit of traffic volume that can be set for a route is determined. This unit corresponds to the minimum granularity. For example, as shown in Figure 4, if the allocatable unit is 1G (bps), the minimum granularity is an integer.

[0049] 4, the optimization unit 132 calculates an optimal route that is a real solution from the exchange traffic and topology. For example, the optimization unit 132 calculates a real solution by the method described in Non-Patent Document 2.

[0050] 4, the optimization unit 132 calculates the traffic volume of the link between the node 51 and the node 53 as a real number, such as 34.77 G. The optimization unit 132 also calculates the traffic volume of the link between the node 53 and the node 54 as 29.84 G.

[0051] Here, the solution calculated by the linear programming method described in Non-Patent Document 2 is a real solution, and therefore the solution has a granularity that cannot be set with the resolution of a given path.

[0052] Therefore, in step S2, the approximation calculation unit 133 approximates the solution calculated by the optimization unit 132 with a value that is a multiple of the path resolution, i.e., with the minimum granularity. For example, the approximation calculation unit 133 rounds up or down digits lower than the path resolution (here, the first decimal place and below).

[0053] 4, the approximation calculation unit 133 approximates the traffic volume of the link between the node 51 and the node 53 from 34.77 G to 35 G. Also, the approximation calculation unit 133 approximates the traffic volume of the link between the node 53 and the node 54 from 29.84 G to 30 G.

[0054] Furthermore, in step S3, the mapping unit 134 maps the traffic to each route. At this time, the mapping unit 134 performs mapping so that the traffic volume assigned to each link is as close as possible to the calculation result of the approximation calculation unit 133.

[0055] In the example of FIG. 4, the mapping unit 134 maps 30 1G logical paths onto a route between the node 51 and the node 54 that passes through the node 53.

[0056] The design process (various calculations and mapping) by the design device 10 of this embodiment may be performed not only when the route of the communication network N is initially designed, but also when the exchange traffic fluctuates.

[0057] When the AC traffic fluctuates, the design device 10 can recalculate the traffic volume and obtain the overall difference from the state before the AC traffic fluctuates. The design device 10 may also calculate a route between specified destinations and obtain the difference only between the specified destinations to obtain a solution for traffic fluctuations during network operation.

[0058] [Processing of the first embodiment] Fig. 7 is a flowchart showing a process flow of the design device according to the first embodiment. As shown in Fig. 7, the design device 10 calculates a real solution of the traffic volume of each link (step S10).

[0059] Next, the design device 10 approximates the real solution at the minimum granularity (for example, integers) (step S20).Then, the design device 10 maps a logical path to each route based on the approximated integer solution (step S30).

[0060] Fig. 8 is a flowchart showing the flow of the mapping process. The process shown in Fig. 8 corresponds to the process of step S30 in Fig. 7. Also, each step in Fig. 7 will be appropriately associated with the example in Fig. 9 for explanation. Fig. 9 is a diagram showing an example of the mapping process.

[0061] First, the mapping unit 134 selects a pair (selected nodes) of a start node and an end node (step S301). In the example of Fig. 9, the mapping unit 134 selects the node 51 in the approximated route information as the start node, and selects the node 54 as the end node. At this time, the selected nodes are the node 51 and the node 54.

[0062] Here, real solutions are calculated for all pairs of start and end nodes, but since the real solutions are calculated for each pair, mapping unit 134 may select pairs in any order.

[0063] Next, the shortest route calculation unit 131 calculates a minimum link cost route using the remaining capacity (approximated traffic volume) as the link cost, and calculates multiple route candidates (step S302). In the example of FIG. 9, the shortest route calculation unit 131 calculates the following route candidates. First route candidate: Node 51 → Node 52 → Node 54 (total link cost: 5 + 10 = 15) Second route candidate: Node 51 → Node 53 → Node 52 → Node 54 (total link cost: 35 + 5 + 10 = 50) Third route candidate: Node 51 → Node 52 → Node 53 → Node 54 (total link cost: 5 + 5 + 30 = 40) Fourth route candidate: Node 51 → Node 53 → Node 54 (total link cost: 35 + 30 = 65)

[0064] The shortest path calculation unit 131 can calculate multiple path candidates by a method of calculating k paths by executing the Dijkstra algorithm and deleting links that have been used once, a method of calculating k paths with overlapping link usage by using the K-shortest path algorithm, a method of calculating K disjoint paths by using the Subal algorithm, etc.

[0065] Fig. 10 is a diagram for explaining the Subal method. As shown in Fig. 10, the Subal method is performed in the following procedure. (1) Calculate the shortest cost route using Dijkstra's algorithm or similar. (2) Reverse the links on the shortest cost route and make the link costs negative. (3) Calculate the shortest cost route using the Bellman-Ford method or similar. (4) The two route calculation results are combined, the common parts are removed, and a redundant path is obtained.

[0066] The Subal method is an algorithm for calculating node / link redundant paths. With the Subal method, it is always possible to discover node / link redundant paths if they exist. The Subal method discovers a pair that minimizes the sum of the costs of the active path and the backup path. On the other hand, the method of applying the Dijkstra method (shortest route search algorithm) twice may not be able to discover node / link redundant paths even if they exist.

[0067] The mapping unit 134 attempts to map the traffic with a given resolution to the route candidates for the selected destination, starting from the route candidate with the smallest total link cost (step S303). In the example of Fig. 9, the mapping unit 134 attempts mapping to the first route candidate with the smallest total link cost in the first round.

[0068] If the mapping is completed (Yes at step S304), the mapping unit 134 proceeds to step S306. Then, the mapping unit 134 updates the remaining capacity (step S306). In the example of Fig. 9, the mapping unit 134 updates the remaining capacity of each link of the first route candidate in the first round.

[0069] The link cost of a link whose remaining capacity has been updated to 0 is regarded as a sufficiently large value (for example, infinity) from the next round onwards.

[0070] If mapping has not been performed for any of the route candidates (step S304, No), the mapping unit 134 proceeds to step S305. Then, the mapping unit 134 attempts to map the traffic to the route with the largest total available capacity (step S305).

[0071] Here, if the mapping unit 134 has allocated all of the requested traffic volume (the volume of the exchange traffic occurring in the selected destination) (step S307, Yes), the mapping unit 134 proceeds to step S308. On the other hand, if the mapping unit 134 has not allocated all of the requested traffic volume (step S307, No), the mapping unit 134 returns to step S302 and repeats the process.

[0072] If the mapping unit 134 has executed the process for all pairs (Yes in step S308), the mapping unit 134 ends the process. On the other hand, if the mapping unit 134 has not executed the process for all pairs (No in step S308), the mapping unit 134 returns to step S301 and repeats the process.

[0073] In this way, the mapping unit 134 prioritizes mapping to a route with a small amount of approximated traffic, and when the amount of approximated traffic is insufficient, the mapping unit 134 prioritizes mapping to a route with the largest amount of approximated traffic.

[0074] In the example of Figure 9, traffic is mapped to routes starting from the route with the least remaining capacity, and when the remaining capacity becomes 0 or less, the link cost is treated as a large value, so traffic is mapped to routes with remaining capacity.

[0075] In addition, since the traffic volume to be mapped is uniform depending on the resolution, there is no performance difference between the method of allocating from routes with little remaining capacity and the method of allocating from traffic volumes with a lot of remaining capacity, since the only difference is the capacity of the mapping destination.

[0076] [Advantages of the First Embodiment] As described above, the optimization unit 132 optimizes the traffic volume allocated to each link between adjacent nodes included in the network with a first granularity. The approximation calculation unit 133 calculates an approximate solution that approximates the traffic volume optimized with the first granularity with a second granularity.

[0077] As described above, the conventional technology has a problem that it is not practical because it is a real number solution and cannot be actually set in the network, or calculations cannot be performed on a carrier network scale. In this embodiment, a solution that can be actually set is calculated while approximating the optimal solution. As a result, according to this embodiment, it is possible to perform a route design with high traffic accommodation efficiency in a communication network by a practical method. Furthermore, the route design with high traffic accommodation efficiency has the effect of reducing equipment costs.

[0078] The optimization unit 132 optimizes the exchange traffic volume with a real solution. The approximation calculation unit 133 approximates the real solution with an integer solution. This makes it possible to map logical paths in units of 1 Gbps.

[0079] Furthermore, the mapping unit 134 maps logical paths to each of the routes formed by the links according to the traffic volume approximated by the approximation calculation unit 133. This allows the design device 10 to reflect the result of the approximation calculation in the actual communication network.

[0080] Furthermore, the mapping unit 134 prioritizes mapping to a route with a small approximated traffic volume, and when the approximated traffic volume is insufficient, prioritizes mapping to a route with the largest approximated traffic volume. This allows the design device 10 to realize efficient mapping.

[0081] [System configuration, etc.] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or a part of it can be functionally or physically distributed or integrated in any unit depending on various loads, usage conditions, etc. Furthermore, each processing function performed by each device can be realized in whole or in any part by a CPU and a program analyzed and executed by the CPU, or can be realized as hardware by wired logic. Note that the program may be executed not only by the CPU but also by other processors such as a GPU.

[0082] Furthermore, among the processes described in this embodiment, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0083] [program] As an embodiment, the design device 10 can be implemented by installing a design program that executes the above design processing as package software or online software on a desired computer. For example, the above design program can be executed by an information processing device, causing the information processing device to function as the design device 10. The information processing device here includes desktop or notebook personal computers. In addition, the information processing device also includes mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone System), and even slate terminals such as PDA (Personal Digital Assistant), etc.

[0084] The design device 10 can also be implemented as a design server device that provides services related to the above design processing to a client, the client being a terminal device used by a user. For example, the design server device is implemented as a server device that provides a design service that receives the exchange traffic and topology of a communication network as input and outputs the mapping result of a logical path. In this case, the design server device may be implemented as a Web server or as a cloud that provides services related to the above design processing by outsourcing.

[0085] 11 is a diagram showing an example of a computer that executes a design program. The computer 1000 includes, for example, a memory 1010 and a CPU 1020. The computer 1000 also includes a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0086] The memory 1010 includes a read only memory (ROM) 1011 and a random access memory (RAM) 1012. The ROM 1011 stores a boot program such as a basic input output system (BIOS). The hard disk drive interface 1030 is connected to a hard disk drive 1090. The disk drive interface 1040 is connected to a disk drive 1100. A removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to a mouse 1110 and a keyboard 1120, for example. The video adapter 1060 is connected to a display 1130, for example.

[0087] The hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, a program that defines each process of the design device 10 is implemented as a program module 1093 in which computer-executable code is written. The program module 1093 is stored, for example, in the hard disk drive 1090. For example, a program module 1093 for executing the same process as the functional configuration of the design device 10 is stored in the hard disk drive 1090. The hard disk drive 1090 may be replaced by an SSD (Solid State Drive).

[0088] Furthermore, setting data used in the processing of the above-described embodiment is stored as program data 1094, for example, in the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads out the program module 1093 or the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes the processing of the above-described embodiment.

[0089] Note that the program module 1093 and the program data 1094 are not limited to being stored in the hard disk drive 1090, but may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1100 or the like. Alternatively, the program module 1093 and the program data 1094 may be stored in another computer connected via a network (such as a local area network (LAN) or wide area network (WAN)). The program module 1093 and the program data 1094 may then be read by the CPU 1020 from the other computer via the network interface 1070. [Explanation of symbols]

[0090] N Communication Network 1. Communication Systems 10 Design equipment 11 Interface section 12 Storage section 13 Control section 20 Monitoring equipment 30 Control device 121 Route DB 122 Topology DB 123 Traffic DB 131 Shortest Path Calculation Unit 132 Optimization Department 133 Approximate calculation section 134 Mapping Section

Claims

1. an optimization unit that optimizes, with a first granularity, a traffic volume allocated to each of links between adjacent nodes included in the network; an approximation calculation unit that calculates an approximation solution obtained by approximating the traffic volume optimized at the first granularity at a second granularity as a remaining capacity; a mapping unit that maps logical paths with priority to a path having the smallest total remaining capacity, and when the total remaining capacity of the path is insufficient, maps logical paths with priority to a path having the largest total remaining capacity; A design device comprising:

2. The optimization unit optimizes the exchange traffic with a real solution, 2. The design apparatus according to claim 1, wherein the approximation calculation unit approximates the real solution with an integer solution.

3. A design method executed by a design device, comprising: an optimization step of optimizing, with a first granularity, a traffic volume allocated to each of links between adjacent nodes included in the network; an approximation calculation step of approximating the traffic volume optimized at the first granularity at a second granularity to calculate an approximation solution as a remaining capacity; a mapping step of mapping a logical path with priority to a path having the smallest total remaining capacity, and, when the total remaining capacity of the path is insufficient, mapping with priority to a path having the largest total remaining capacity; A design method comprising:

4. A design program for causing a computer to function as the design device according to claim 1 or 2.

Images