Method and device for evaluating availability of link in network, electronic equipment and storage medium

Abstract

The invention relates to a link availability evaluation method and device in a network, electronic equipment and a storage medium. The method comprises the following steps: acquiring network configuration information, traffic demand information and fault scene information of a to-be-evaluated target network; according to the network configuration information, the traffic demand information and the fault scene information, determining a key link non-overload probability in each fault scene, the key link non-overload probability in each fault scene representing a probability that a link through which the key traffic passes is not overloaded in each fault scene; according to the non-overload probability of the key link in each fault scene and the occurrence probability corresponding to each fault scene, a link availability evaluation result corresponding to the target network is determined, and the link availability evaluation result represents the probability that a link through which the key flow passes in the target network is not overloaded in any fault scene. Therefore, the probability that whether the link on the key flow path cannot be overloaded in various fault scenes or not can be scientifically and effectively evaluated.

Description

Technical Field

[0001] The present disclosure relates to the field of computer networks, and in particular to a method and device for evaluating link availability in a network, an electronic device, and a storage medium. Background Art

[0002] With the development of the Internet, Internet service providers are facing a variety of challenges. In the face of users' growing needs and expectations, they need to improve service quality. To this end, service providers have taken a variety of measures, including but not limited to customizing network solutions for different customer groups.

[0003] For users, better and more stable network availability is an important consideration when choosing a service provider. Users need to enjoy stable and fast network services at all times. Therefore, service providers must ensure that their services can meet these needs in order to maintain competitiveness and market share.

[0004] In order to ensure the quality of network services for key customers, network administrators need to monitor the traffic of these customers in real time to ensure that it will not be affected by bottlenecks during network transmission. To this end, administrators need to implement a series of strategies, such as network traffic monitoring, routing strategy optimization, and traffic engineering deployment, to ensure that key traffic paths are unobstructed. In addition, a strict testing and verification process is essential to ensure the effectiveness of the measures taken.

[0005] Service providers and customers usually sign a service level agreement (SLA) to clearly define key indicators such as service level, service quality, and network availability. These agreements not only guarantee the stability and security of the service, but also stipulate important terms such as fault recovery time, providing customers with clear service guarantees. In the industry, the "five nines" standard (i.e. 99.999% operating time) is widely adopted, which means that the annual downtime does not exceed 5.26 minutes. To meet this high standard, network administrators need to evaluate the link availability of key customer traffic paths to ensure that they meet the requirements of the agreement.

[0006] In recent years, many advances have been made in related research to help network administrators evaluate network availability. These studies are mainly concentrated in the data plane and control plane. Data plane verification tools use Boolean variables to determine the reachability of network traffic or link overload, but they are only applicable to single traffic scenarios and simplify the problem into a binary decision (yes or no). They cannot accurately evaluate the possibility and severity of overload, which is obviously difficult to meet the actual application needs. Control plane verification tools extract data plane models from configuration files to actively detect reachability violations. However, such tools cannot accurately simulate traffic load distribution or perform probabilistic analysis of fault scenarios. In addition, some studies use traffic distribution graphs to analyze load attributes, but lack the ability to reason about faults probabilistically. Some other studies evaluate network availability under probabilistic fault scenarios in an attempt to improve existing methods, but most of these solutions are not applicable to multi-flow scenarios, and their brute force-based fault analysis methods limit their application in small networks.

[0007] So far, no research has been able to simultaneously consider link failures and quantitatively evaluate the availability of links on critical traffic paths (i.e., the probability that the link is not overloaded). This reflects that although network administrators and service providers have improved network service quality in many ways, they still lack a reliable method to measure and ensure the availability of links on critical traffic paths. Summary of the invention

[0008] In view of this, the present disclosure proposes a link availability evaluation method and device, an electronic device and a storage medium in a network, which can scientifically and effectively evaluate whether the links on the critical traffic path have the probability of not being overloaded under various failure scenarios, thereby providing more powerful support for ISPs and network administrators to ensure the high availability of network services.

[0009] According to one aspect of the present disclosure, a method for evaluating link availability in a network is provided, comprising: obtaining network configuration information, traffic demand information and fault scenario information of a target network to be evaluated, wherein the network configuration information comprises the capacity and weight of each link in the target network, the traffic demand information comprises a traffic set expected to be generated in the target network and a traffic size corresponding to each traffic in the traffic set, and the fault scenario information comprises a fault scenario set expected to be generated in the target network and a link that fails in each fault scenario in the fault scenario set; determining a probability of no overload of a key link in each fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, wherein the probability of no overload of a key link in each fault scenario represents a probability that a link through which a key traffic passes in each fault scenario is not overloaded, wherein the key traffic is at least one traffic specified in the traffic set; determining a link availability evaluation result corresponding to the target network according to the probability of no overload of a key link in each fault scenario and the corresponding occurrence probability of each fault scenario, wherein the link availability evaluation result represents a probability that a link through which a key traffic passes in the target network is not overloaded in any fault scenario.

[0010] In a possible implementation, the determining of the probability of no overload of a critical link in each fault scenario based on the network configuration information, the traffic demand information, and the fault scenario information includes: for the fth fault scenario in the fault scenario set, judging whether the critical traffic in the fth fault scenario can reach the destination node from the corresponding initiating node in the target network based on the network configuration information, the traffic demand information, and the fault scenario information, the critical traffic being at least one traffic specified in the traffic set; in the case where the critical traffic in the fth fault scenario cannot reach the destination node from the corresponding initiating node in the target network, determining that the probability of no overload of a critical link in the fth fault scenario is 0; When the critical traffic in the f-th fault scenario can reach the destination node from the corresponding initiating node in the target network, determine the critical link set and related traffic set corresponding to the critical traffic in the f-th fault scenario according to the network configuration information, the traffic demand information and the fault scenario information; and, determine the probability of no overload of the critical link in the f-th fault scenario according to the critical link set and related traffic set corresponding to the critical traffic in the f-th fault scenario; wherein the critical link set includes the links through which the critical traffic passes in the f-th fault scenario, and the related traffic set includes the related traffic that shares at least one link with the critical traffic in the f-th fault scenario and the traffic size of the related traffic.

[0011] In a possible implementation, the determining of the probability of no overload of the critical link in each fault scenario according to the network configuration information, the traffic demand information and the fault scenario information also includes: in the case where the critical traffic in the f-th fault scenario can reach the destination node from the corresponding initiating node in the target network, determining the critical endpoint matrix corresponding to the f-th fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, the critical endpoint matrix representing the node information of the head and tail nodes in the network nodes passed by each traffic in the traffic set in the f-th fault scenario that coincide with the network nodes passed by the critical traffic in the f-th fault scenario; the critical endpoint matrix corresponding to the f-th fault scenario and the key endpoint matrix confirmed in the fault scenario set When the key endpoint matrix corresponding to the mth fault scenario in which the probability of no overload of the critical link is determined to be equivalent, the probability of no overload of the critical link corresponding to the fth fault scenario is determined to be the probability of no overload of the critical link corresponding to the mth fault scenario; when the key endpoint matrix corresponding to the fth fault scenario is not equivalent to the key endpoint matrix corresponding to the fault scenario in which the probability of no overload of the critical link has been determined in the fault scenario set, the key link set and the related traffic set corresponding to the key traffic under the fth fault scenario are determined according to the network configuration information, the traffic demand information and the fault scenario information; and, according to the key link set and the related traffic set corresponding to the key traffic under the fth fault scenario, the probability of no overload of the critical link under the fth fault scenario is determined.

[0012] In a possible implementation, the method of determining the probability of no overload of key links in the f-th fault scenario based on the key link set and the related traffic set corresponding to the key traffic in the f-th fault scenario includes: determining the hypervolume of the set of traffic demand values ​​in which the links through which the key traffic passes without overload in the f-th fault scenario based on the key link set and the related traffic set corresponding to the key traffic in the f-th fault scenario; obtaining the hypervolume of the set of total traffic demand values ​​of the links through which the key traffic passes in the f-th fault scenario by calculating the consecutive product of the difference between the upper limit value and the lower limit value of each related traffic in the related traffic set; and determining the ratio between the combined hypervolume of the traffic demand values ​​and the hypervolume of the set of total traffic demand values ​​as the probability of no overload of key links in the f-th fault scenario.

[0013] In a possible implementation, the method of determining the hypervolume of a set of traffic demand values ​​in which links through which the critical traffic passes are not overloaded under the f-th fault scenario according to the set of key links and the set of related traffic corresponding to the critical traffic under the f-th fault scenario comprises: determining the critical link no-overload Lebesgue equation corresponding to the f-th fault scenario according to the set of key links and the set of related traffic corresponding to the critical traffic under the f-th fault scenario, wherein the critical link no-overload Lebesgue equation is expressed as a value of 1 when the link through which the critical traffic passes is not overloaded, and a value of 0 when the link through which the critical traffic passes is overloaded; and obtaining the hypervolume of a set of traffic demand values ​​in which links through which the critical traffic passes are not overloaded under the f-th fault scenario by integrating the critical link no-overload Lebesgue equation over an n-dimensional real number field, wherein n is the number of related traffic in the set of related traffic corresponding to the critical traffic.

[0014] In a possible implementation, the method further includes: estimating the integral value of the non-overload Lebesgue equation of the critical link in the n-dimensional real number domain using a Markov chain Monte Carlo algorithm to obtain a hypervolume of the set of flow demand values.

[0015] In a possible implementation, the sum of the occurrence probabilities corresponding to all fault scenarios in the fault scenario set is 1, wherein the link availability evaluation result corresponding to the target network is determined based on the probability of no overload of the key link under each fault scenario and the occurrence probability corresponding to each fault scenario, including: multiplying the probability of no overload of the key link under each fault scenario by the occurrence probability corresponding to each fault scenario and then adding them up to obtain the link availability evaluation result corresponding to the target network.

[0016] According to another aspect of the present disclosure, a link availability evaluation device in a network is provided, comprising: an acquisition module, used to acquire network configuration information, traffic demand information and fault scenario information of a target network to be evaluated, wherein the network configuration information includes the capacity and weight of each link in the target network, the traffic demand information includes a traffic set expected to be generated in the target network and a traffic size corresponding to each traffic in the traffic set, and the fault scenario information includes a fault scenario set expected to be generated in the target network and a link that fails in each fault scenario in the fault scenario set; a determination module, used to determine a probability of no overload of a key link in each fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, wherein the probability of no overload of a key link in each fault scenario represents a probability that a link through which a key traffic passes in each fault scenario is not overloaded, wherein the key traffic is at least one traffic specified in the traffic set; an evaluation module, used to determine a link availability evaluation result corresponding to the target network according to the probability of no overload of a key link in each fault scenario and the corresponding occurrence probability of each fault scenario, wherein the link availability evaluation result represents a probability that a link through which a key traffic in the target network passes is not overloaded in any fault scenario.

[0017] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0018] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0019] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0020] According to various aspects of the present disclosure, by obtaining the network configuration information, traffic demand information and fault scenario information of the target network to be evaluated, the probability that the link through which the key traffic passes under each fault scenario will not be overloaded can be determined. Combined with the probability of occurrence of each fault scenario, the availability evaluation results of the link non-overload attribute of the target network under various fault scenarios can be effectively determined, that is, an effective quantitative evaluation of the availability of the link through which any key traffic passes in the entire target network is achieved under the consideration of the link failure scenario, or a scientific and effective evaluation of whether the link on the key traffic path will not be overloaded under various fault scenarios is achieved, thereby providing more powerful support for ISPs and network administrators to ensure the high availability of network services.

[0021] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0023] Figure 1a A schematic diagram showing a network topology according to an embodiment of the present disclosure is shown.

[0024] Figure 1b A schematic diagram showing traffic distribution in a fault scenario according to an embodiment of the present disclosure is shown.

[0025] Figure 2 A flow chart of a method for evaluating link availability in a network according to an embodiment of the present disclosure is shown.

[0026] Figure 3 A schematic diagram of a workflow of link availability evaluation according to an embodiment of the present disclosure is shown.

[0027] Figure 4 A block diagram of a link availability evaluation device in a network according to an embodiment of the present disclosure is shown.

[0028] Figure 5 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0029] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0030] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0031] The term "and / or" herein is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent any one or more elements selected from the set consisting of A, B, and C. In the description of the present disclosure, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0032] It should be understood that the terms “include” and “comprising” used in the specification and claims of the present disclosure indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0033] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0034] To facilitate understanding of the evaluation method proposed in the embodiment of the present disclosure, this article first combines Figure 1a and Figure 1b The problems to be solved in the embodiments of the present disclosure and the related concepts involved are explained.

[0035] like Figure 1aA network topology is shown, which expresses the network nodes in a computer network and the connection relationship between different network nodes. A, B, C, D, E, and F represent network nodes (i.e., network devices, such as routers, switches, etc.). There is a link (i.e., network link) between two network nodes directly connected by IP, such as a link between A and C. The traffic demand describes the traffic and traffic size between any two nodes. The traffic can be characterized by the initiating node and the destination node of the traffic. For example, the traffic A→B represents the traffic from the initiating node A to the destination node B. The path can indicate the nodes and links that the traffic passes through from the initiating node to the destination node. For example, the path of the traffic A→B includes the nodes and links that the traffic passes through from A→C→D→B. Each link has a maximum transmission rate (which can be called capacity) and a weight representing its cost (the weight can be used to determine the shortest path that the traffic passes through). The larger the weight, the greater the cost (or resource consumption) consumed by the link. For example, the weight sum of the links in each path that the traffic can pass through can be calculated, and the path with the smallest weight sum can be selected as the shortest path used by the traffic.

[0036] Assumptions Figure 1a There are two traffic demands in the network shown: d1 represents the key customer traffic (i.e., the traffic of key customers) A→B and the traffic size, while d2 represents the common traffic E→G and the traffic size. Assume that the capacity of all links in the network is 10 Gbps. In the absence of link failure, the two traffics A→B and E→G will not share any link during transmission. To ensure that the link on the path through which the key customer traffic passes is not overloaded (overload free), it is only necessary to satisfy d1≤10. However, once a link fails, such as link EF, the path through which the common traffic E→G passes will be rerouted, for example, rerouted to E→C→D→F→G. At this time, this common traffic and the key traffic A→B will share a common link CD. In this case, to determine whether the link through which the key traffic passes is overloaded, it is necessary to conduct a comprehensive and detailed consideration of the traffic demands d1 and d2.

[0037] like Figure 1b As shown in Figure 2, if the traffic size of d1 is evenly distributed in the range of [3,12], and the traffic size of d2 is evenly distributed in the range of [5,8], since the link capacity is 10 Gbps, the probability of overload on the path of key customer traffic A→B is However, when link EF fails, traffic E→G shares a link CD with key customer traffic A→B. In this case, d1+d2≤10 is required to ensure that all key links (i.e., the links through which key customer traffic passes) are not overloaded, i.e., the area indicated by the red triangle in the figure. The blue area in the figure is the feasible area. At this time, the probability of overload on the path of key customer traffic A→B drops to The goal of this paper is to probabilistically verify the availability of the links through which critical traffic passes under different failure scenarios, taking into account the traffic of the entire network.

[0038] In practical applications, the link availability evaluation method in the network of the embodiment of the present disclosure can be deployed on various terminal devices through software or hardware modification. The terminal device involved in the embodiment of the present disclosure may refer to a device with a wireless connection function and / or a wired connection function. The wireless connection function refers to the ability to connect to other devices through wireless connection methods such as wifi and Bluetooth. The terminal device involved in the embodiment of the present disclosure may also communicate with other devices through a wired connection function. The terminal device involved in the embodiment of the present disclosure may be a touch screen, a non-touch screen, or a screenless device. The touch screen can control the terminal device by clicking and sliding on the display screen with a finger or a stylus. The non-touch screen device can be connected to an input device such as a mouse, a keyboard, a touch panel, and the terminal device is controlled by the input device. For example, the device without a screen may be a Bluetooth speaker without a screen. For example, the terminal device of the present application may include but is not limited to a user equipment (UE), a mobile device, a mobile terminal, a handheld device, a tablet computer, a laptop, a PDA, a computing device, etc.

[0039] The link availability evaluation method in the network of the embodiment of the present disclosure can also be deployed on a server, which can be located in the cloud or locally, and can be a physical device or a virtual device, such as a virtual machine, a container, etc., and has a wireless communication function, wherein the wireless communication function can be set in the chip (system) or other parts or components of the server. It can refer to a device with a wireless connection function, and the wireless connection function refers to the ability to connect to other servers or terminal devices through wireless connection methods such as Wi-Fi and Bluetooth. The server involved in the embodiment of the present disclosure may also have the function of communicating through a wired connection. For example, the server of the embodiment of the present disclosure can be located in the cloud, communicate with the terminal device, receive the network configuration information, traffic demand information and fault scenario information sent by the terminal device, and use the evaluation method deployed on the server based on the above network configuration information, traffic demand information and fault scenario information to obtain the link availability evaluation result corresponding to the target network, and return it to the terminal device, so as to display the generated link availability evaluation result to the user in the terminal device.

[0040] Figure 2 FIG. 2 is a flow chart showing a method for evaluating link availability in a network according to an embodiment of the present disclosure. Figure 2 As shown, the method includes: step S11 to step S13.

[0041] In step S11, the network configuration information, traffic demand information and fault scenario information of the target network to be evaluated are obtained, wherein the network configuration information includes the capacity and weight of each link in the target network, the traffic demand information includes the traffic set expected to be generated in the target network and the traffic size corresponding to each traffic in the traffic set, and the fault scenario information includes the fault scenario set expected to be generated in the target network and the link that fails in each fault scenario in the fault scenario set.

[0042] In practical applications, the above network configuration information can be obtained by obtaining the network topology of the target network to be evaluated, and the traffic demand information can be constructed based on historical experience or historical traffic data. For example, let D represent the traffic between every two network nodes in the target network at a certain moment (i.e., a set of traffic sets). For each traffic d in D, an upper limit value u can be defined d and the lower limit l d , and one in [u d ,l d ]A continuous random variable x uniformly distributed in the interval d , x d represents the flow size of flow d. H is a subset of D, representing the subset of key flows. X is the set of all flow sizes. For each x in X d , if d∈D, then x d It represents the flow rate of flow d.

[0043] Among them, the key traffic can be the traffic of key customers. Those skilled in the art can specify at least one traffic in the traffic set D as the key traffic H according to actual needs, that is, the key traffic is at least one traffic specified in the traffic set. For example, the traffic between a specified initiating node and a specified destination node in the target network can be defined as the key traffic. For example, Figure 1a The flow from A to B in the example is designated as the key flow. Figure 1a The flow from A to G in the example is designated as the key flow, etc. This can be customized according to the actual flow requirements of key customers in actual situations, and the embodiments of the present disclosure do not limit this. It should be understood that since the flow size in the network fluctuates, an upper limit and a lower limit can be set for the flow size of each flow to indicate the range of flow variation, and the upper limit and the lower limit of each flow can be set according to historical experience, and the embodiments of the present disclosure do not limit this.

[0044] Among them, the possible fault scenarios in the target network can be estimated according to the links included in the network topology of the target network to obtain a set of fault scenarios. For example, Figure 1a The network topology shown may include the network form when one or more links among AC, CD, BD, CE, CD, DF, EF, and FG in the network fail (i.e., the network form after the link failure), wherein the failure scenario may also include a scenario where no link fails, and the failure scenario may characterize the network form caused by a link failure in the target network.

[0045] In step S12, based on the network configuration information, traffic demand information and fault scenario information, the probability of no overload on the key link in each fault scenario is determined. The probability of no overload on the key link in each fault scenario represents the probability that the link through which the key traffic passes in each fault scenario will not be overloaded.

[0046] In a possible implementation, step S12 determines the probability of no overload of a key link in each fault scenario according to the network configuration information, the traffic demand information, and the fault scenario information, and may include:

[0047] Step S121, for the fth fault scenario in the fault scenario set, judging whether the key traffic under the fth fault scenario can reach the destination node from the corresponding initiating node in the target network according to the network configuration information, the traffic demand information and the fault scenario information, where the key traffic is at least one traffic specified in the traffic set;

[0048] Step S122, when the critical traffic in the fth fault scenario cannot reach the destination node from the corresponding initiating node in the target network, determining that the probability of no overload of the critical link in the fth fault scenario is 0;

[0049] Step S123, when the critical traffic in the fth fault scenario can reach the destination node from the corresponding initiating node in the target network, determine the critical link set and related traffic set corresponding to the critical traffic in the fth fault scenario according to the network configuration information, the traffic demand information and the fault scenario information; and

[0050] Step S124, determining the probability that the key link in the f-th fault scenario is not overloaded according to the key link set corresponding to the key traffic in the f-th fault scenario and the related traffic set;

[0051] Among them, the critical link set includes the links through which the critical traffic passes under the fth fault scenario, and the related traffic set includes the related traffic that shares at least one link with the critical traffic under the fth fault scenario and the traffic size of the related traffic.

[0052] In step S121, the above-mentioned network configuration information, traffic demand information and fault scenario information are known. For each fault scenario, all paths that the key traffic passes through from the initiating node to the destination node in each fault scenario can be obtained. Then, based on the link that causes the fault in the f-th fault scenario, it can be determined whether all paths that the key traffic passes through from the initiating node to the destination node in the f-th fault scenario have no fault links. If there is a path with no fault links between the initiating node and the destination node for the key traffic in the f-th fault scenario, it means that the key traffic can reach the destination node from the corresponding initiating node in the f-th fault scenario. Conversely, if there are fault links in all paths that the key traffic passes through from the initiating node to the destination node in the f-th fault scenario, it means that the key traffic cannot reach the destination node from the corresponding initiating node in the f-th fault scenario. For example, the key traffic A→B can go from the initiating node A to the destination node B through two paths "A→C→D→B" and "A→C→E→F→D→B". If the f-th fault scenario is the link EF or link CD failure scenario, the key traffic can still reach the destination node B from the initiating node A through the path "A→C→D→B" or "A→C→E→F→D→B". This means that the key traffic in the f-th fault scenario can reach the destination node from the corresponding initiating node in the target network. If the f-th fault scenario is any of the link AC failure, link DB failure, and simultaneous failure of link EF and link CD, the key traffic cannot reach the destination node B from the initiating node A through any path. This means that the key traffic in the f-th fault scenario cannot reach the destination node from the corresponding initiating node in the target network.

[0053] In step S122, if the critical traffic in the fth fault scenario cannot reach the destination node from the corresponding initiating node in the target network, it means that there are faulty links in all paths through which the critical traffic in the fth fault scenario can pass. At this time, the critical traffic can no longer be transmitted to the destination node in the target network. In this case, the probability of no overload of the critical link in the fth fault scenario can be directly determined as 0.

[0054] In step S123, as described above, the above-mentioned network configuration information, traffic demand information and fault scenario information are known. For each fault scenario, the link through which the critical traffic passes in each fault scenario can be obtained, that is, the link through which the critical traffic can pass on the path from the initiating node to the destination node in the f-th fault scenario can be obtained. Among them, if there are two or more paths for the critical traffic to reach the destination node from the initiating node in the fault scenario, the shortest path can be selected based on the weight of the link, and the link through which the critical traffic can pass on the shortest path from the initiating node to the destination node in the f-th fault scenario can be determined. For example, for Figure 1a In the network topology shown, when the failure scenario of link EF failure occurs, the links that the key flow A→B can pass through on the path "A→C→D→B" from the initiating node A to the destination node B include AC, CD, and DB; and when the failure scenario of link CD failure occurs, the links that the key flow A→B can pass through on the path "A→C→E→F→D→B" from the initiating node A to the destination node B include AC, CE, EF, FD, and DB, thus obtaining the key link set corresponding to the key flow A→B in this failure scenario.

[0055] It should be understood that, by adopting the same implementation method as determining the associated link set, the links that each other flow in the flow set except the key flow can pass through on the path from the corresponding initiating node to the destination node can be obtained. For example, Figure 1a In the failure scenario where link EF fails, the links that another flow E→G can pass through on the path "E→C→D→F→G" from the initiating node E to the destination node G include EC, CD, DF, and FG; further, given the links that the key flow can pass through on the path from the initiating node to the destination node, and the links that each other flow in the flow set can pass through on the path from the initiating node to the destination node, the related flows that share at least one link with the key flow in the fth failure scenario and the flow size of the related flows can be obtained, wherein sharing at least one link means passing through the same at least one link, for example, Figure 1a In the failure scenario where link EF fails, traffic E→G and critical traffic A→B share the same link CD. Then the traffic E→G is the related traffic of critical traffic A→B. Figure 1a In the fault scenario where link CE fails, the links that traffic E→G passes through include EF and FG. Since traffic E→G does not share any link with key traffic A→B, traffic E→G is not the related traffic of key traffic A→B. For example, if there is another traffic A→G that shares two links AC and CD with key traffic A→B, then this traffic A→G is the related traffic of key traffic A→B, and the related traffic set corresponding to key traffic A→B in this fault scenario is obtained.

[0056] Exemplarily, given the fth failure scenario, F is a set of fault scenarios, where f can represent the set of links that fail in this fault scenario. Then the set of critical links Υ f It can be defined as formula (1):

[0057]

[0058] in, is an indicator when When it is equal to 1, it means that the critical flow h passes through the link e in the fth failure scenario. H represents the critical flow set, and E represents all links in the target network.

[0059] And, the set of critical traffic-related links Θ f It can be defined as formula (2):

[0060]

[0061] in, is an indicator when When it is equal to 1, it means that any flow d in the flow set D of the target network passes through the critical link v (that is, the link through which the critical flow passes) in the fth failure scenario, and υ is the critical link set Υ f For any link in f That is, it is the set of related flows that share at least one link with at least one critical flow in H in the fth failure scenario.

[0062] In step S124, determining the probability that the key link in the f-th fault scenario is not overloaded according to the key link set corresponding to the key traffic in the f-th fault scenario and the related traffic set may include:

[0063] Step S1241, determining the super volume of the set of flow demand values ​​of the links through which the critical flow passes without being overloaded in the f-th fault scenario according to the critical link set corresponding to the critical flow in the f-th fault scenario and the related flow set;

[0064] Step S1242, by calculating the continuous product of the difference between the upper limit value and the lower limit value of each relevant flow in the relevant flow set, the hyper volume of the set of total flow demand values ​​of the links through which the key flow passes in the f-th fault scenario is obtained;

[0065] Step S1243 : Determine the ratio between the excess volume of the set of traffic demand values ​​and the excess volume of the set of total traffic demand values ​​as the probability of no overload of the critical link in the f th fault scenario.

[0066] In step S1241, determining the hypervolume of a set of flow demand values ​​of links through which the critical flow passes without being overloaded in the f-th fault scenario according to the critical link set and the related flow set corresponding to the critical flow in the f-th fault scenario may include:

[0067] Step S12411, according to the key link set and the related flow set corresponding to the key flow in the f-th fault scenario, determine the key link no-overload Lebesgue equation corresponding to the f-th fault scenario, wherein the key link no-overload Lebesgue equation is expressed as a value of 1 when the link through which the key flow passes is not overloaded, and a value of 0 when the link through which the key flow passes is overloaded;

[0068] Step S12412, by integrating the Lebesgue equation for no overload of the critical link over the n-dimensional real number field, the hypervolume of the set of flow demand values ​​of the link through which the critical flow passes without overload in the f-th fault scenario is obtained, where n is the number of related flows in the related flow set corresponding to the critical flow.

[0069] In step S12411, the link through which the critical traffic passes in the f-th fault scenario, as well as the related traffic that shares at least one link with the critical traffic in the f-th fault scenario and the traffic size of the related traffic are known. The total traffic size generated on each critical link (i.e., the link through which the critical traffic passes) in the f-th fault scenario can be calculated, and then the total traffic size generated on each critical link in the f-th fault scenario can be compared with the capacity corresponding to each critical link. If the total traffic size generated on a certain critical link is less than or equal to the capacity corresponding to the critical link, it means that the critical link is not overloaded. Conversely, if the total traffic size generated on a certain critical link is greater than the capacity corresponding to the critical link, it means that the critical link is overloaded. Therefore, the critical link no-overload Lebesgue equation corresponding to the above-mentioned f-th fault scenario can be constructed. For example, let the related traffic set Θ f The relevant traffic in includes the critical traffic itself. Given the fth failure scenario Given the relevant flow d i and flow rate Represents the relevant flow d i The flow size, |Θ f | represents the number of related flows in the related flow set, C υ represents the capacity of the critical link υ, then the Lebesgue equation for the critical link without overload can be expressed as formula (3):

[0070]

[0071] Among them, formula (3) can be understood as given the flow size x of the relevant flow and the fault scenario f, when the critical link is not overloaded, that is, when the link through which the critical flow passes is not overloaded, The value of is 1, otherwise, The value of is 0.

[0072] Furthermore, in step S12412, based on the critical link non-overload Lebesgue equation shown in the above formula (3), the critical link non-overload Lebesgue equation is integrated over the n-dimensional real number field, which can be expressed as: in, Represents |Θ f |-dimensional real number field, n = |Θ f |, n is the relevant flow set Θ corresponding to the key flow f The number of related flows in , that is, the number of related flows that share at least one link with the critical flow in the fth failure scenario.

[0073] Considering that, calculation It is necessary to perform integral operations in high-dimensional space, which is too large to be completed in a limited time. Therefore, in order to improve the efficiency of the operation, a common algorithm known in the art for calculating the volume of high-dimensional space, such as the Markov Chain Monte Carlo (MCMC) algorithm, can be used to calculate the volume of high-dimensional space. Numerical estimation is performed, that is, the integral value of the critical link no-overload Lebesgue equation in the n-dimensional real number domain can be estimated using the Markov chain Monte Carlo algorithm. The estimated integral value is the hypervolume of the set of traffic demand values ​​of the link through which the critical traffic passes without overload in the f-th fault scenario. The embodiment of the present disclosure does not limit the estimation process of the Markov chain Monte Carlo algorithm, as long as the integral value of the critical link no-overload Lebesgue equation in the n-dimensional real number domain can be determined. It should be understood that the above-mentioned use of the Markov chain Monte Carlo algorithm to estimate the integral value is a possible implementation method provided by the embodiment of the present disclosure. In fact, under the inspiration of the embodiment of the present disclosure, those skilled in the art can use other high-dimensional space numerical estimation techniques known in the art to estimate the integral value of the critical link no-overload Lebesgue equation in the n-dimensional real number domain, and the embodiment of the present disclosure does not limit this.

[0074] As mentioned above, the traffic size in the network fluctuates, so for each flow d in the traffic set D, an upper limit value u can be defined d and the lower limit l d , that is, the variation range of each flow is predefined, so in step S1242, the related flows in the related flow set may include the key flow itself, so the hypervolume of the set of total flow demand values ​​of the links through which the key flow passes under the fth fault scenario can be obtained by calculating the continuous product of the difference between the upper limit value and the lower limit value of each related flow in the related flow set. For example, let the related flow set Θ f The relevant traffic in includes the critical traffic itself, so the hypervolume of the set of total traffic demand values ​​of the links through which the critical traffic passes under the fth fault scenario can be expressed as Among them, u d Represents the relevant flow set Θ f The upper limit of the relevant flow d in d Represents u d Represents the relevant flow set Θ f The lower limit of the relevant flow d in .

[0075] The hypervolume based on the above flow demand value set and the hypervolume of the set of total flow demand values In step S1243, the ratio between the super volume of the set of traffic demand values ​​and the super volume of the set of total traffic demand values ​​is determined as the probability of no overload of the critical link in the fth fault scenario, which can be expressed by formula (4):

[0076]

[0077] Among them, ρ f It represents the ratio of the traffic demand range in which the critical link is not overloaded in the f-th fault scenario to the total change range of the traffic demand, that is, the probability that the critical link is not overloaded in the f-th fault scenario.

[0078] As mentioned above, we can use the Markov Chain Monte Carlo algorithm to Based on this, the embodiment of the present disclosure provides a calculation process for calculating the overload probability of a key link based on the Markov chain Monte Carlo algorithm, and the input of the calculation process is the relevant flow set Θ f and the traffic link matrix Γ (that is, the links that each flow in the traffic set can pass through on the path from its corresponding initiating node to the destination node in the fth failure scenario in the form of matrix Γ), the output is the probability of no overload on the critical link ρ f , the calculation process includes:

[0079] 1. Define b as v i ∈Υ f , that is, definition b includes the capacity corresponding to each key link in the key link set;

[0080] 2. Define n as |Θ f |, define N as 400×nlogn, where N represents the number of sampling points;

[0081] 3. Define a polyhedron P f {x|xΓ≤b}, that is, the polyhedron P f It is composed of x that satisfies xΓ≤b, where x represents the traffic on the link;

[0082] 4. Calculate the Chebyshev sphere B(c,r min ) and the external ball B(c,rmax ), where the Chebyshev sphere B(c,r min ) must be in the polyhedron P f Inside, outside ball B (c, r max ) must contain the polyhedron P f , and the centers c of the two balls are the same;

[0083] 5. Calculate α as (ie r min The result of multiplying the logarithm by n and rounding down), and β is calculated as (ie r max The result of multiplying the logarithm value by n and rounding up);

[0084] 6. Calculate the polyhedron P f With the external ball B(c,r max ) β .

[0085] 7. Randomly generate a point p in the intersection Q β , it is used as the initial element of set S, that is, set S is initialized to {p}.

[0086] 8. Initialization And initialize υ i =1;

[0087] 9. Perform the following cycle from β to α+1 to gradually narrow the search space:

[0088] 9.1. Calculating the intersection Q i-1 P f ∩B(c,2 (i-1) / n ), that is, to calculate the polyhedron P f With c as the center and radius 2 (i -1) / n The intersection of the balls Q i-1 ;

[0089] 9.2. Calculate the number of elements in set S that are in Q i-1 The number of points within is recorded as count_prev;

[0090] 9.3. Remove the set S that is not in Q i-1 The point in

[0091] 9.4. Calculate the number of remaining points in the set S, denoted as count;

[0092] 9.5. For j from 1 to N, the loop executes:

[0093] 9.5.1. Generate a random point p, and p∈Q i-1 ;

[0094] 9.5.2. If a random point p is centered at c and has a radius of 2 i / n inside the sphere, that is, if Then update count = count + 1, and add the random point p to the set S;

[0095] 9.6. Update

[0096] 10. Update That is, the ρ calculated in step 9 f Divide by the product of the difference between the upper limit and the lower limit of each relevant flow in the relevant flow set, and get the final calculated probability of no overload on the key link ρ f .

[0097] It should be understood that for each fault scenario in the fault scenario set, the above steps S121 to S124 can be referred to, or the above calculation process can be specifically referred to, to use the Markov chain Monte Carlo algorithm to calculate the corresponding critical link non-overload probability. This method can be used to transform the original #P problem into a #SAT problem, and the critical link non-overload probability value can be accurately estimated within a limited time. Then, based on the critical links of the fault scenario and the probability of occurrence of the fault scenario, the estimated value of the critical link non-overload availability probability is obtained, that is, the link availability evaluation result corresponding to the target network.

[0098] In step S13, based on the probability of no overload on the key links in each fault scenario and the corresponding occurrence probability of each fault scenario, the link availability evaluation result corresponding to the target network is determined, wherein the link availability evaluation result represents the probability that the link through which the key traffic in the target network passes will not be overloaded in any fault scenario.

[0099] In practical applications, given a set of fault scenarios F, the sum of the occurrence probabilities of all fault scenarios in the set can be set to 1, that is, ∑ f∈F Pr(f)=1, Pr(f) represents the occurrence probability corresponding to the fth fault scenario, and the occurrence probability of the fault scenario can be understood as the probability of the fault scenario occurring. It should be understood that those skilled in the art can set the occurrence probability of each fault scenario in the fault scenario set F according to actual conditions and historical experience, etc., as long as the sum of the occurrence probabilities corresponding to all fault scenarios is 1, and the embodiments of the present disclosure are not limited to this.

[0100] Based on this, the link availability evaluation result corresponding to the target network is determined according to the probability of no overload of the key link in each fault scenario and the probability of occurrence of each fault scenario, which may include: multiplying the probability of no overload of the key link in each fault scenario by the probability of occurrence of each fault scenario and then accumulating them to obtain the link availability evaluation result corresponding to the target network. Exemplarily, the link availability evaluation result Ω corresponding to the target network can be expressed as formula (5):

[0101]

[0102] Among them, Ω can be understood as an indicator for evaluating the availability of key links in the entire target network, that is, it can measure the probability that the link through which the key traffic in the target network passes will not be overloaded in any failure scenario.

[0103] In actual applications, after obtaining the link availability evaluation results of the target network, the ISP and network administrator can optimize the network configuration of the target network based on the link availability evaluation results, for example, by adding network equipment to increase links, increase link capacity, etc., to ensure high availability of the links through which key customer traffic passes and improve service levels. The embodiments of the present disclosure are not limited to this.

[0104] According to the evaluation method of the embodiment of the present disclosure, by obtaining the network configuration information, traffic demand information and fault scenario information of the target network to be evaluated, the probability that the link through which the key traffic passes under each fault scenario will not be overloaded can be determined. Combined with the probability of occurrence of each fault scenario, the availability evaluation results of the link non-overload attribute of the target network under various fault scenarios can be effectively determined, that is, an effective quantitative evaluation of the availability of the link through which any key traffic passes in the entire target network is achieved under the consideration of the link failure scenario, or a scientific and effective evaluation of whether the link on the key traffic path will not be overloaded under various fault scenarios is achieved, thereby providing more powerful support for ISPs and network administrators to ensure the high availability of network services.

[0105] Considering that in actual situations, the critical traffic and related traffic may share the same link under different fault scenarios, or pass through the same network nodes. In this case, the probability of no overload on the critical links corresponding to different fault scenarios is actually the same. For example, Figure 1aThe network topology shown in the figure assumes that there are two traffic demands in the network, namely, critical traffic A→B and related traffic A→G (the path of the related traffic A→G is "A→C→D→F→G"). In the failure scenario of link CE failure and the failure scenario of link EF failure, the critical traffic A→B and the related traffic A→G both share links AC and CD, that is, both pass through nodes A, C, and D. The critical link non-overload probabilities in the two failure scenarios calculated by the above-mentioned calculation method of the critical link non-overload probability are actually the same. Therefore, in order to reduce the amount of calculation and improve the calculation efficiency, the two failure scenarios can be merged, or in other words, the critical link non-overload probability of one of the failure scenarios is calculated, and the calculated critical link non-overload probability is directly used as the critical link non-overload probability of the other failure scenario.

[0106] Therefore, in a possible implementation, the above step S12, determining the probability of no overload of the key link in each fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, may include:

[0107] Step S1201, for the fth fault scenario in the fault scenario set, judging whether the key traffic in the fth fault scenario can reach the destination node from the corresponding initiating node in the target network according to the network configuration information, the traffic demand information and the fault scenario information, wherein the key traffic is at least one traffic specified in the traffic set;

[0108] Step S1202, when the critical traffic in the fth fault scenario cannot reach the destination node from the corresponding initiating node in the target network, determining that the probability of no overload of the critical link in the fth fault scenario is 0;

[0109] Step S1203, when the critical traffic in the f-th fault scenario can reach the destination node from the corresponding initiating node in the target network, determine the critical endpoint matrix corresponding to the f-th fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, wherein the critical endpoint matrix represents the node information of the head and tail nodes of the network nodes passed by each traffic in the traffic set in the f-th fault scenario that coincide with the network nodes passed by the critical traffic in the f-th fault scenario;

[0110] Step S1204, when the critical endpoint matrix corresponding to the f-th fault scenario is equivalent to the critical endpoint matrix corresponding to the m-th fault scenario for which the critical link non-overload probability has been determined in the fault scenario set, the critical link non-overload probability corresponding to the f-th fault scenario is determined as the critical link non-overload probability corresponding to the m-th fault scenario;

[0111] Step S1205, when the key endpoint matrix corresponding to the f-th fault scenario is not equivalent to the key endpoint matrix corresponding to the fault scenario in which the key link has been determined to have no overload probability in the fault scenario set, determine the key link set and the related flow set corresponding to the key flow in the f-th fault scenario according to the network configuration information, the flow demand information and the fault scenario information; and

[0112] Step S1206: Determine the probability that the key link in the f-th fault scenario has no overload according to the key link set corresponding to the key traffic in the f-th fault scenario and the related traffic set.

[0113] Among them, steps S1201 to S1202 can refer to the specific implementation methods of steps S121 to S122 of the above-mentioned embodiment of the present disclosure, and are not limited here.

[0114] In step S1203, as described above, it is known that according to the network configuration information, the flow demand information, and the fault scenario information, it is possible to obtain whether each flow in the flow set shares at least one link with the critical flow in the fth fault scenario, and the at least one link shared when there is a shared link. Thus, it is also possible to know the information of the first and last two nodes that coincide with the nodes passed by the critical flow h among the nodes passed by each flow in the fth fault scenario. For example, for Figure 1a In the network topology shown, in the failure scenario of link EF failure, the first network node that the relevant flow A→G (the path passed by the relevant flow A→G is "A→C→D→F→G") passes through and the network node passed by the key flow A→B is A, and the last node is D, that is, the first and last nodes that the two flows overlap are A and D, and the first and last nodes that the relevant flow E→G (at this time, the path passed by the relevant flow E→G is "E→C→D→F→G") overlap with the key flow A→B are C and D nodes. Then, the key endpoint matrix in this failure scenario can record the node information of the first and last nodes A and D that the relevant flow A→G overlaps with the key flow A→B, as well as the node information of the first and last nodes C and D that the relevant flow E→G overlaps with the key flow A→B.

[0115] Among them, the node information can be used to uniquely identify the network node, for example, the unique number of the network node, or the IP address, etc., can be used, and the embodiments of the present disclosure are not limited to this. Of course, the critical endpoint matrix can also use different values ​​to indicate the head and tail nodes that overlap between flows. For example, the critical endpoint matrix (Critical Endnode Matrix) can be defined as a matrix ST of |V|×|V|, where |V| represents the total number of nodes in the target network, and each element in the matrix ST can be defined as formula (6):

[0116]

[0117] Among them, d i,j Represents the slave node v i To node v j of traffic. Defined as formula (7):

[0118]

[0119] in, In the fth fault scenario, the traffic d i,j The set of all the links passed through, represents the set of all links that the critical traffic h passes through in the fth fault scenario, that is, the critical link set; Formula (7) represents When the intersection between is not empty, The value of is (i-1)×|V|+j, otherwise, The value of is -1.

[0120] It should be understood that for each fault scenario, a corresponding key node matrix ST can be calculated. Each element ST[i][j] in the matrix ST can represent the hash value of a pair of nodes, which are from node v i To node v j The first and last nodes in the intersection of the nodes passed by the traffic and the nodes passed by the key traffic, that is, the hash values ​​of the first and last nodes where the two traffic flows overlap (that is, the first and last nodes that overlap) can be used to represent the first and last nodes where the two traffic flows overlap (that is, the first and last nodes that overlap).

[0121] Among them, if the critical endpoint matrix ST of the f-th fault scenario is equivalent (that is, the same) to the critical endpoint matrix of another m-th fault scenario in the fault scenario set, then the two fault scenarios are considered equivalent. At this time, the probability of no overload on the critical link of the f-th fault scenario is the same as the probability of no overload on the critical link of the other m-th fault scenario, that is, ρ f =ρ m, the mth fault scenario can be any fault scenario in the fault scenario set for which the probability of no overload of the critical link has been calculated, m∈F, therefore, the random approximation stage of the fth fault scenario can be skipped (that is, the stage of estimating the probability of no overload of the critical link using the Markov chain Monte Carlo algorithm can be skipped), and the probability of no overload of the critical link corresponding to the fth fault scenario can be determined as the probability of no overload of the critical link corresponding to the mth fault scenario. If the key endpoint matrix ST of the fth fault scenario is not equivalent (that is, not the same) to the key endpoint matrix of each fault scenario in the fault scenario set for which the probability of no overload of the critical link has been determined, the estimation process of the Markov chain Monte Carlo algorithm of the fth fault scenario can be executed, and the value of the key node matrix of the fth fault scenario and the calculated probability of no overload of the critical link h can be recorded. f , that is, executing the above steps S1205 to S1206, wherein steps S1205 to S1206 can refer to the specific implementation method of steps S123 to S124 of the above-mentioned embodiment of the present disclosure. Through this method, the calculation speed of the entire evaluation process can be significantly improved.

[0122] Based on the above fault scenario merging method combined with the Markov chain Monte Carlo algorithm to achieve the evaluation method, the embodiment of the present disclosure also provides Figure 3 A schematic diagram of the workflow of link availability assessment is shown in FIG. Figure 3 As shown, the workflow includes: based on a certain fault scenario of the network topology (i.e., link DF fault, critical flow is A→C, critical link is the link through which critical flow A→C passes, and critical node is the network node through which critical flow A→C passes), input network configuration information and flow demand information, generate a key endpoint matrix under the fault scenario (such as the matrix shown in the figure, in which the elements of the matrix can represent the hash values ​​of the first and last nodes that coincide with the critical flow), merge the fault scenarios (i.e., execute the above steps S1201 to S1204), and execute the Markov chain Monte Carlo algorithm (i.e., execute the above steps S1205 to S1206). 6) Obtain the probability of no overload on the key link of the current fault scenario, continue to calculate the probability of no overload on the key link of the next fault scenario, until the probability of no overload on the key link of all fault scenarios is obtained, and then combine the probability of occurrence of each fault scenario to obtain the link availability evaluation result corresponding to the network topology, that is, by inputting network configuration information, traffic demand information and fault scenario information, the key endpoint matrix of the fault scenario can be obtained, and the fault scenarios are merged based on this, and then the Markov chain Monte Carlo calculation is performed to obtain the result, and the above process is repeated for the next fault scenario to obtain the probability of no overload on the key link under all fault scenarios.

[0123] Based on the above fault scenario merging method combined with the Markov chain Monte Carlo algorithm to achieve the evaluation method, the embodiment of the present disclosure also provides a link availability evaluation process in the network, the evaluation process input is the network configuration information (the network topology of the target network (that is, the node set V = {v1, v2, ..., v |V|}, link set E) and the capacity and weight of each link in the network topology), traffic demand information (including the key traffic set H = {h1,h2,…,h |H|} traffic size), fault scenario information (including the fault scenario set F, and the occurrence probability Pr(f) of each fault scenario in F, f∈F, and the output is the link availability evaluation result Ω of the network; the evaluation process includes:

[0124] 1. Define Ω to be the empty set, and define P to represent a set of arrays.

[0125] 2. For the fth fault scenario in the fault scenario set F, perform the following operations:

[0126] 2.1. Initialize Q to an empty array and set the flag to 0;

[0127] 2.2. Determine the weighted adjacency matrix G under the f-th fault scenario, that is, determine the links and nodes on the path through which each flow passes under the f-th fault scenario;

[0128] 2.3. For each critical flow h in H i , do the following:

[0129] 2.3.1. If h i If the weighted adjacency matrix G is unreachable in the fth failure scenario (that is, the critical traffic cannot reach the destination node from the initiating node), set the flag to 1 and exit the loop;

[0130] 2.3.2. Determine h i The set of nodes passed through, get the key link set L h ;

[0131] 2.3.3. Calculate the set K as {j|v i ∈L h};

[0132] 2.3.4. Based on G and h i Calculate the key endpoint matrix ST with K and add it to Q;

[0133] 2.4. If the flag is 1, it means that at least one critical flow is unreachable, so the critical link in this failure scenario has no overload probability ρ f If it is 0, continue to the next fault scenario.

[0134] 2.4. If Q is already in P (i.e., Q∈P), update Ω to Ω+ζ Q Pr(f), which means merging the failure scenarios and continuing to the next failure scenario;

[0135] 2.5. Otherwise, determine the relevant flow set Θ f and the traffic link matrix Γ;

[0136] 2.6. Using the above Multiphase_MCMC (i.e. the calculation process of the probability of no overload on the key link) based on Θ f and Γ, calculate the probability of no overload on the critical link in the fth fault scenario

[0137] ρ f ;

[0138] 2.7. Update Ω to Ω+ρ f ·Pr(f), which is ρ f Multiply by the probability of occurrence of the fth fault scenario Pr(f) and add to Ω;

[0139] 2.8. Q Assign it to f , and add Q to P.

[0140] The above evaluation process is used to calculate the probability of no overload on the critical link in each fault scenario. f . This probability is calculated by considering the topology of the network and the key traffic demand under the failure scenario. This probability is estimated by adopting a multi-phase MCMC method (Multiphase_MCMC). These probabilities are then multiplied by the probability of occurrence of the corresponding failure scenario Pr(f) and added to Ω to obtain the availability evaluation result of the entire network. This process involves the reachability analysis of the key traffic demand in the network and the simulation of the network performance under different failure scenarios. The link availability of the network considering the key customer traffic demand and failure scenarios can be calculated.

[0141] The above evaluation process evaluates the availability of the network by simulating different failure scenarios. It determines the performance of the network by checking the accessibility of key customer traffic demands under failure scenarios. If all key customer traffic demands are reachable, the Multiphase_MCMC method is used to estimate the probability of no overload on the key links under this failure scenario. This probability is then weighted according to the probability of occurrence of the failure scenario and accumulated into the total availability evaluation result Ω. This above evaluation process is repeated until all failure scenarios have been evaluated. Finally, Ω provides an approximation of the network's availability after considering all failure scenarios.

[0142] The link availability evaluation method in the above network proposed in the embodiment of the present disclosure realizes a method of using Markov chain Monte Carlo technology to evaluate the load attributes of key path links on the network in terms of ensuring network availability, which can be integrated into an efficient and accurate availability probability analysis tool, aiming to verify the non-overload attribute of key traffic in Internet service providers (ISPs). It is also equivalent to building a refined availability probability evaluation model, and by adopting random approximation methods and innovative reasoning algorithms, the computational burden is greatly reduced. This tool is crucial for network management and can be deployed in the network operation centers of various ISPs.

[0143] Figure 4 A block diagram of a link availability evaluation device in a network according to an embodiment of the present disclosure is shown as follows: Figure 4 As shown, the device comprises:

[0144] The acquisition module 401 is used to acquire network configuration information, traffic demand information and fault scenario information of the target network to be evaluated, wherein the network configuration information includes the capacity and weight of each link in the target network, the traffic demand information includes the traffic set expected to be generated in the target network and the traffic size corresponding to each traffic in the traffic set, and the fault scenario information includes the fault scenario set expected to be generated in the target network and the link that fails in each fault scenario in the fault scenario set;

[0145] A determination module 402 is used to determine a probability of no overload of a key link in each fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, wherein the probability of no overload of a key link in each fault scenario represents a probability that a link through which a key flow passes is not overloaded in each fault scenario, wherein the key flow is at least one flow specified in the flow set;

[0146] The evaluation module 403 is used to determine the link availability evaluation result corresponding to the target network based on the probability of no overload of the key link in each fault scenario and the probability of occurrence of each fault scenario. The link availability evaluation result represents the probability that the link through which the key traffic in the target network passes will not be overloaded in any fault scenario.

[0147] In a possible implementation, the determining the probability of no overload of a critical link in each fault scenario according to the network configuration information, the traffic demand information, and the fault scenario information includes: for the fth fault scenario in the fault scenario set, judging whether the critical traffic in the fth fault scenario can reach the destination node from the corresponding initiating node in the target network according to the network configuration information, the traffic demand information, and the fault scenario information; if the critical traffic in the fth fault scenario cannot reach the destination node from the corresponding initiating node in the target network, determining that the probability of no overload of a critical link in the fth fault scenario is 0; When the critical traffic can reach the destination node from the corresponding initiating node in the target network, determine the critical link set and related traffic set corresponding to the critical traffic in the f-th fault scenario according to the network configuration information, the traffic demand information and the fault scenario information; and, determine the probability of no overload of the critical link in the f-th fault scenario according to the critical link set and related traffic set corresponding to the critical traffic in the f-th fault scenario; wherein the critical link set includes the links through which the critical traffic passes in the f-th fault scenario, and the related traffic set includes the related traffic that shares at least one link with the critical traffic in the f-th fault scenario and the traffic size of the related traffic.

[0148] In a possible implementation, the determining of the probability of no overload of the critical link in each fault scenario according to the network configuration information, the traffic demand information and the fault scenario information also includes: in the case where the critical traffic in the f-th fault scenario can reach the destination node from the corresponding initiating node in the target network, determining the critical endpoint matrix corresponding to the f-th fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, the critical endpoint matrix representing the node information of the head and tail nodes in the network nodes passed by each traffic in the traffic set in the f-th fault scenario that coincide with the network nodes passed by the critical traffic in the f-th fault scenario; the critical endpoint matrix corresponding to the f-th fault scenario and the key endpoint matrix confirmed in the fault scenario set When the key endpoint matrix corresponding to the mth fault scenario in which the probability of no overload of the critical link is determined to be equivalent, the probability of no overload of the critical link corresponding to the fth fault scenario is determined to be the probability of no overload of the critical link corresponding to the mth fault scenario; when the key endpoint matrix corresponding to the fth fault scenario is not equivalent to the key endpoint matrix corresponding to the fault scenario in which the probability of no overload of the critical link has been determined in the fault scenario set, the key link set and the related traffic set corresponding to the key traffic under the fth fault scenario are determined according to the network configuration information, the traffic demand information and the fault scenario information; and, according to the key link set and the related traffic set corresponding to the key traffic under the fth fault scenario, the probability of no overload of the critical link under the fth fault scenario is determined.

[0149] In a possible implementation, the method of determining the probability of no overload of key links in the f-th fault scenario based on the key link set and the related traffic set corresponding to the key traffic in the f-th fault scenario includes: determining the hypervolume of the set of traffic demand values ​​in which the links through which the key traffic passes do not become overloaded in the f-th fault scenario based on the key link set and the related traffic set corresponding to the key traffic in the f-th fault scenario; obtaining the hypervolume of the set of total traffic demand values ​​of the links through which the key traffic passes in the f-th fault scenario by calculating the consecutive product of the differences between the upper limit value and the lower limit value of each related traffic in the related traffic set; and determining the ratio between the hypervolume of the set of traffic demand values ​​and the hypervolume of the set of total traffic demand values ​​as the probability of no overload of key links in the f-th fault scenario.

[0150] In a possible implementation, the method of determining the hypervolume of a set of traffic demand values ​​in which links through which the critical traffic passes are not overloaded under the f-th fault scenario according to the set of key links and the set of related traffic corresponding to the critical traffic under the f-th fault scenario comprises: determining the critical link no-overload Lebesgue equation corresponding to the f-th fault scenario according to the set of key links and the set of related traffic corresponding to the critical traffic under the f-th fault scenario, wherein the critical link no-overload Lebesgue equation is expressed as a value of 1 when the link through which the critical traffic passes is not overloaded, and a value of 0 when the link through which the critical traffic passes is overloaded; and obtaining the hypervolume of a set of traffic demand values ​​in which links through which the critical traffic passes are not overloaded under the f-th fault scenario by integrating the critical link no-overload Lebesgue equation over an n-dimensional real number field, wherein n is the number of related traffic in the set of related traffic corresponding to the critical traffic.

[0151] In a possible implementation, the device further includes: an estimation module for estimating the integral value of the non-overloaded Lebesgue equation of the critical link in the n-dimensional real number domain using a Markov chain Monte Carlo algorithm to obtain a hypervolume of the set of flow demand values.

[0152] In a possible implementation, the sum of the occurrence probabilities corresponding to all fault scenarios in the fault scenario set is 1, wherein the link availability evaluation result corresponding to the target network is determined based on the probability of no overload of the critical link in each fault scenario and the probability of occurrence of each fault scenario, including: multiplying the probability of no overload of the critical link in each fault scenario by the probability of occurrence of each fault scenario and adding them up to obtain the link availability evaluation result corresponding to the target network.

[0153] According to the device of the embodiment of the present disclosure, by obtaining the network configuration information, traffic demand information and fault scenario information of the target network to be evaluated, the probability that the link through which the key traffic passes under each fault scenario will not be overloaded can be determined. Combined with the probability of occurrence of each fault scenario, the availability evaluation results of the link non-overload attribute of the target network under various fault scenarios can be effectively determined, that is, under the consideration of the link failure scenario, an effective quantitative evaluation of the availability of the link through which any key traffic passes in the entire target network is achieved, or a scientific and effective evaluation of whether the link on the key traffic path will not be overloaded under various fault scenarios is achieved, thereby providing more powerful support for ISPs and network administrators to ensure the high availability of network services.

[0154] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0155] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0156] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0157] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0158] Figure 5 1 is a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or a terminal device. Figure 5 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions that can be executed by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0159] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0160] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0161] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0162] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0163] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0164] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0165] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0166] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0167] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0168] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0169] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for evaluating link availability in a network, characterized in that: include: Obtaining network configuration information, traffic demand information, and fault scenario information of the target network to be evaluated, wherein the network configuration information includes the capacity and weight of each link in the target network, the traffic demand information includes the traffic set expected to be generated in the target network and the traffic size corresponding to each traffic in the traffic set, and the fault scenario information includes the fault scenario set expected to be generated in the target network and the link that fails in each fault scenario in the fault scenario set; Determine, according to the network configuration information, the traffic demand information and the fault scenario information, a probability of no overload on a key link in each fault scenario, wherein the probability of no overload on a key link in each fault scenario represents a probability that no overload occurs on a link through which a key flow passes in each fault scenario, wherein the key flow is at least one flow specified in the flow set; Based on the probability of no overload on the key links in each fault scenario and the probability of occurrence of each fault scenario, the link availability evaluation result corresponding to the target network is determined. The link availability evaluation result represents the probability that the link through which the key traffic in the target network passes will not be overloaded in any fault scenario.

2. The method according to claim 1, characterized in that: The determining, according to the network configuration information, the traffic demand information, and the fault scenario information, a probability that a key link is not overloaded in each fault scenario includes: For the fth fault scenario in the set of fault scenarios, judging whether the critical traffic under the fth fault scenario can reach the destination node from the corresponding initiating node in the target network according to the network configuration information, the traffic demand information and the fault scenario information; In the case where the critical traffic in the f-th fault scenario cannot reach the destination node from the corresponding initiating node in the target network, determining that the probability of no overload of the critical link in the f-th fault scenario is 0; In the case where the critical traffic in the f-th fault scenario can reach the destination node from the corresponding initiating node in the target network, determining the critical link set and the related traffic set corresponding to the critical traffic in the f-th fault scenario according to the network configuration information, the traffic demand information and the fault scenario information; and Determine, according to the key link set and the related traffic set corresponding to the key traffic in the f-th fault scenario, the probability that the key link in the f-th fault scenario is not overloaded; Among them, the critical link set includes the links through which the critical traffic passes under the f-th fault scenario, and the related traffic set includes the related traffic that shares at least one link with the critical traffic under the f-th fault scenario and the traffic size of the related traffic.

3. The method according to claim 2, characterized in that The determining, according to the network configuration information, the traffic demand information, and the fault scenario information, that there is no overload probability of a key link in each fault scenario further includes: In the case where the critical traffic in the f-th fault scenario can reach the destination node from the corresponding initiating node in the target network, determine the critical endpoint matrix corresponding to the f-th fault scenario according to the network configuration information, the traffic demand information and the fault scenario information, the critical endpoint matrix representing the node information of the head and tail nodes of the network nodes passed by each flow in the traffic set in the f-th fault scenario that coincide with the network nodes passed by the critical traffic in the f-th fault scenario; When the critical endpoint matrix corresponding to the f-th fault scenario is equivalent to the critical endpoint matrix corresponding to the m-th fault scenario in the fault scenario set for which the critical link non-overload probability has been determined, the critical link non-overload probability corresponding to the f-th fault scenario is determined as the critical link non-overload probability corresponding to the m-th fault scenario; When the critical endpoint matrix corresponding to the f-th fault scenario is not equivalent to the critical endpoint matrix corresponding to the fault scenario in which the critical link has been determined to have no overload probability in the fault scenario set, determine the critical link set and related traffic set corresponding to the critical traffic in the f-th fault scenario based on the network configuration information, the traffic demand information and the fault scenario information; and determine the critical link no overload probability in the f-th fault scenario based on the critical link set and related traffic set corresponding to the critical traffic in the f-th fault scenario.

4. The method according to claim 2 or 3, characterized in that: The determining, according to the key link set corresponding to the key traffic in the f-th fault scenario and the related traffic set, that there is no overload probability for the key link in the f-th fault scenario includes: Determine, according to the key link set and the related flow set corresponding to the key flow in the f-th fault scenario, the hypervolume of the set of flow demand values ​​of the links through which the key flow passes without being overloaded in the f-th fault scenario; By calculating the continuous product of the difference between the upper limit value and the lower limit value of each relevant flow in the relevant flow set, a hypervolume of the set of total flow demand values ​​of the links through which the key flow passes under the f-th fault scenario is obtained; The ratio of the super volume of the set of traffic demand values ​​to the super volume of the set of total traffic demand values ​​is determined as the probability of no overload of the critical link in the f-th fault scenario.

5. The method according to claim 4, characterized in that The determining, according to the key link set and the related traffic set corresponding to the key traffic in the f-th fault scenario, a hypervolume of a set of traffic demand values ​​of links through which the key traffic passes without being overloaded in the f-th fault scenario comprises: Determine, according to the critical link set and the related traffic set corresponding to the critical traffic in the f-th fault scenario, a critical link no-overload Lebesgue equation corresponding to the f-th fault scenario, wherein the critical link no-overload Lebesgue equation is expressed as a value of 1 when the link through which the critical traffic passes is not overloaded, and a value of 0 when the link through which the critical traffic passes is overloaded; By integrating the Lebesgue equation for no overload on the critical link over the n-dimensional real number field, the hypervolume of the set of flow demand values ​​for the link through which the critical flow passes without overload in the f-th fault scenario is obtained, where n is the number of related flows in the related flow set corresponding to the critical flow.

6. The method according to claim 5, characterized in that The method further comprises: The integral value of the non-overload Lebesgue equation of the key link in the n-dimensional real number domain is estimated by using the Markov chain Monte Carlo algorithm to obtain the hypervolume of the set of flow demand values.

7. The method according to any one of claims 1 to 3, characterized in that: The sum of the occurrence probabilities corresponding to all the fault scenarios in the fault scenario set is 1, wherein determining the link availability evaluation result corresponding to the target network according to the probability of no overload of the key link under each fault scenario and the occurrence probability of each fault scenario includes: The probability of no overload of the key link in each fault scenario is multiplied by the probability of occurrence of each fault scenario and then added up to obtain the link availability evaluation result corresponding to the target network.

8. A link availability evaluation device in a network, characterized in that: include: An acquisition module, used to acquire network configuration information, traffic demand information, and fault scenario information of a target network to be evaluated, wherein the network configuration information includes the capacity and weight of each link in the target network, the traffic demand information includes a traffic set expected to be generated in the target network and a traffic size corresponding to each traffic in the traffic set, and the fault scenario information includes a fault scenario set expected to be generated in the target network and a link that fails in each fault scenario in the fault scenario set; A determination module, configured to determine a probability of no overload of a key link in each fault scenario according to the network configuration information, the traffic demand information, and the fault scenario information, wherein the probability of no overload of a key link in each fault scenario represents a probability that a link through which a key flow passes in each fault scenario is not overloaded, wherein the key flow is at least one flow specified in the flow set; An evaluation module is used to determine a link availability evaluation result corresponding to the target network based on the probability of no overload of the key link in each fault scenario and the probability of occurrence of each fault scenario. The link availability evaluation result represents the probability that the link through which the key traffic in the target network passes will not be overloaded in any fault scenario.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method described in any one of claims 1 to 7 when executing the instructions stored in the memory.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images