Routing methods, devices, equipment, storage media, and software products for transmission links
By constructing a transmission link state matrix and a two-layer scoring mechanism, and combining business scenario requirements, path delay, and load margin, the target link is dynamically selected, which solves the problem of poor link routing reliability under the static routing strategy and achieves higher transmission stability and resource utilization.
Patent Information
- Application Number
- CN202611451157.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-17
- Publication Date
- 2026-11-17
AI Technical Summary
In existing technologies, static routing strategies cannot adapt to dynamic load changes, resulting in poor link routing reliability. Furthermore, existing dynamic routing methods fail to comprehensively consider multi-dimensional parameters, leading to resource allocation imbalances and decreased transmission stability.
By constructing a state matrix for the transmission link and combining it with business scenario requirements, a two-layer scoring mechanism is adopted to dynamically select the target link by comprehensively considering path delay and load margin.
It improves the reliability and load balancing of link routing, reduces the impact of link anomalies or state fluctuations on transmission stability, and enhances resource utilization.
Smart Images

Figure CN123123243A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data transmission, and in particular to a method, apparatus, device, storage medium, and program product for selecting transmission links. Background Technology
[0002] Multi-controller active-active systems are mainly used in scenarios with extremely high requirements for data transmission reliability, efficiency, and real-time performance, such as large-scale distributed storage clusters and financial-grade data centers.
[0003] In related technologies, a static routing strategy can be adopted, which pre-configures a fixed path for data transmission. The path selection is determined solely based on the fixed path and does not depend on the real-time link status.
[0004] However, in the above methods, static routing strategies cannot adapt to dynamic load changes, resulting in poor reliability of link routing. Summary of the Invention
[0005] This application provides a method, apparatus, device, storage medium, and program product for selecting transmission links, in order to solve the problem of poor reliability in link routing.
[0006] In a first aspect, embodiments of this application provide a routing method for a transmission link, comprising:
[0007] Determine the state matrix corresponding to multiple transmission links. The state matrix includes multiple state parameters corresponding to multiple transmission links.
[0008] Obtain business scenario requirements, which indicate the use cases for link routing.
[0009] Based on the state matrix and business scenario requirements, determine the first score for multiple transmission links;
[0010] Determine the path delay and load margin corresponding to multiple transmission links. The load margin is used to indicate the current remaining carrying capacity of the transmission link.
[0011] Based on the state matrix, path delay, and load margin, determine the second score corresponding to multiple transmission links;
[0012] Based on the first and second scores, the target link for data transmission is determined among multiple transmission links.
[0013] This embodiment organizes link status parameters into a unified state matrix and incorporates business scenario requirements into the scoring process. It then combines path delay and load margin to form a two-layer scoring mechanism, enabling the link routing process to simultaneously reflect the overall link status, business scenario preferences, and real-time link carrying capacity. Compared to methods that rely solely on static priority or a single metric for selection, this method can still output executable target link selection results even when link load distribution is uneven, local link congestion occurs, or some link performance fluctuates.
[0014] In one possible implementation, determining the target link for data transmission among multiple transmission links based on a first score and a second score includes:
[0015] Based on the first score and the second score, target scores are determined for multiple transmission links. The target scores are used to indicate the priority of multiple transmission links during link routing.
[0016] Based on the target score, multiple transmission links are arranged in descending order of target score to obtain the target link table;
[0017] In response to receiving a data transmission instruction, the target link with the highest target score is determined from multiple transmission links according to the target link table.
[0018] This embodiment integrates the first score and the second score into a target score and sorts them. The system can organize the priority relationship of multiple transmission links with a unified quantitative result and quickly locate the link with the highest score when the instruction is triggered. This reduces the processing overhead caused by temporary comparison and thus improves the response speed and result consistency of link routing.
[0019] In one possible implementation, target scores corresponding to multiple transmission links are determined based on a first score and a second score, including:
[0020] Obtain historical load data for multiple transmission links at historical moments;
[0021] Based on historical load data, the predicted load of multiple transmission links is determined;
[0022] Based on the predicted load, determine the first weight corresponding to the first score and the second weight corresponding to the second score;
[0023] Based on the first score, the second score, the first weight, and the second weight, the target scores corresponding to multiple transmission links are determined.
[0024] In this embodiment, historical load data provides a basis for link load evolution, predicted load reflects the subsequent carrying trend of the link, weight adjustment makes the two types of scores change dynamically with the link load, and the target score serves as the input result for subsequent link ranking and routing. Using this method, the target score can dynamically balance the first and second scores in conjunction with historical load trends, making the link score more closely reflect the actual carrying status, thereby improving the consistency between routing results and the actual link capacity.
[0025] In one possible implementation, after determining the target link for data transmission among multiple transmission links based on a first score and a second score, the method further includes:
[0026] Based on the target link table, at least one candidate link is determined from multiple transmission links, and the target score of the candidate link is greater than or equal to a first threshold.
[0027] In response to a fault in the target link, or if the current load of the target link is greater than or equal to a second threshold, an update link is determined from at least one candidate link, and a data transmission instruction is executed through the update link.
[0028] This embodiment enables the target link to maintain its predetermined data transmission path during normal operation. In the event of a fault or overload, it can directly switch from the selected candidate links to the updated link without requiring a full recalculation of all links. Therefore, the link replacement process has clear candidate constraints and threshold control, with a clear switching direction. This allows data transmission tasks to continue executing even when links are abnormal or the load increases, while maintaining the priority information in the target link table for subsequent routing.
[0029] In one possible implementation, based on the state matrix and business scenario requirements, a first score is determined for multiple transmission links, including:
[0030] Based on the business scenario requirements, determine the scale values between multiple state parameters. The scale values are used to indicate the comparison of the importance between any two state parameters under the business scenario requirements.
[0031] Based on the scale value, determine the third weight corresponding to multiple state parameters;
[0032] Based on the state matrix and the third weights corresponding to multiple state parameters, the first score corresponding to multiple transmission links is determined.
[0033] In this embodiment, the first score can simultaneously characterize the relative importance of multiple state parameters in different business scenarios, and transform subjective scenario requirements into calculable weight coefficients. These coefficients are then combined with the state matrix to form a comprehensive link score, thereby making subsequent link routing results more aligned with current business objectives. This approach reduces the bias of a single indicator on routing results, makes the comparison relationship between multiple transmission links more stable, and ultimately improves the consistency between the link score and the actual bearer status.
[0034] In one possible implementation, determining the state matrix corresponding to multiple transmission links includes:
[0035] Collect status values corresponding to multiple transmission links at a preset frequency. The status values include at least one or more of the following: physical status value, transmission status value, and load status value of the transmission link.
[0036] The state values are normalized to obtain the state parameters corresponding to multiple transmission links;
[0037] Based on multiple transmission links and their corresponding state parameters, determine the state matrix corresponding to multiple transmission links.
[0038] This embodiment collects the original link status by frequency, normalizes the values of different dimensions, and constructs a matrix representation. This allows the comprehensive status of multiple transmission links to be described and compared on the same scale, thus providing a consistent input basis for subsequent link scoring and target link selection. This results in a more complete characterization of the link status, reduces bias caused by a single indicator, and improves the matching degree between routing results and actual operating conditions.
[0039] Secondly, embodiments of this application provide a routing device for a transmission link, comprising:
[0040] The first determining module is used to determine the state matrix corresponding to multiple transmission links. The state matrix includes multiple state parameters corresponding to multiple transmission links.
[0041] The acquisition module is used to acquire business scenario requirements, which indicate the usage scenarios for link routing.
[0042] The second determining module is used to determine the first score corresponding to multiple transmission links based on the state matrix and business scenario requirements;
[0043] The third determination module is used to determine the path delay and load margin corresponding to multiple transmission links. The load margin is used to indicate the load that the transmission link can still carry.
[0044] The fourth determination module is used to determine the second score corresponding to multiple transmission links based on the state matrix, path delay, and load margin.
[0045] The fifth determining module is used to determine the target link for data transmission among multiple transmission links based on the first score and the second score.
[0046] In one possible implementation, the fifth determining module is specifically used for,
[0047] Based on the first score and the second score, target scores are determined for multiple transmission links. The target scores are used to indicate the priority of multiple transmission links during link routing.
[0048] Based on the target score, multiple transmission links are arranged in descending order of target score to obtain the target link table;
[0049] In response to receiving a data transmission instruction, the target link with the highest target score is determined from multiple transmission links according to the target link table.
[0050] In one possible implementation, the fifth determining module is specifically used for,
[0051] Obtain historical load data for multiple transmission links at historical moments;
[0052] Based on historical load data, the predicted load of multiple transmission links is determined;
[0053] Based on the predicted load, determine the first weight corresponding to the first score and the second weight corresponding to the second score;
[0054] Based on the first score, the second score, the first weight, and the second weight, the target scores corresponding to multiple transmission links are determined.
[0055] In one possible implementation, the fifth determining module is further configured to,
[0056] Based on the target link table, at least one candidate link is determined from multiple transmission links, and the target score of the candidate link is greater than or equal to a first threshold.
[0057] In response to a fault in the target link, or if the current load of the target link is greater than or equal to a second threshold, an update link is determined from at least one candidate link, and a data transmission instruction is executed through the update link.
[0058] In one possible implementation, the second determining module is specifically used for,
[0059] Based on the business scenario requirements, determine the scale values between multiple state parameters. The scale values are used to indicate the comparison of the importance between any two state parameters under the business scenario requirements.
[0060] Based on the scale value, determine the third weight corresponding to multiple state parameters;
[0061] Based on the state matrix and the third weights corresponding to multiple state parameters, the first score corresponding to multiple transmission links is determined.
[0062] In one possible implementation, the first determining module is specifically used for,
[0063] Collect status values corresponding to multiple transmission links at a preset frequency. The status values include at least one or more of the following: physical status value, transmission status value, and load status value of the transmission link.
[0064] The state values are normalized to obtain the state parameters corresponding to multiple transmission links;
[0065] Based on multiple transmission links and their corresponding state parameters, determine the state matrix corresponding to multiple transmission links.
[0066] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory communicatively connected to the processor;
[0067] The memory stores instructions that the computer executes;
[0068] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.
[0069] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.
[0070] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.
[0071] The transmission link routing method, apparatus, device, storage medium, and program product provided in this application embodiment determine a state matrix corresponding to multiple transmission links, the state matrix including multiple state parameters corresponding to the multiple transmission links; obtain service scenario requirements, which are used to indicate the usage scenario of link routing; determine a first score corresponding to multiple transmission links based on the state matrix and service scenario requirements; determine the path delay and load margin corresponding to multiple transmission links, the load margin indicating the load that the transmission link can currently still bear; determine a second score corresponding to multiple transmission links based on the state matrix, path delay, and load margin; and determine the target link for data transmission among the multiple transmission links based on the first score and the second score. Thus, through the above method, candidate links can be comprehensively evaluated from two dimensions: service adaptability and real-time link carrying capacity, thereby improving the global optimization capability of link routing, improving the reliability of link routing, improving load distribution balance and resource utilization, and reducing the impact of link anomalies or state fluctuations on transmission stability. Attached Figure Description
[0072] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0073] Figure 1 A schematic diagram of the system architecture provided for this application;
[0074] Figure 2 A flowchart illustrating the routing method for the transmission link provided in this application;
[0075] Figure 3 A flowchart illustrating the process of determining a target link for data transmission, provided for an embodiment of this application;
[0076] Figure 4 A flowchart illustrating the process of determining a first score corresponding to multiple transmission links, provided in an embodiment of this application;
[0077] Figure 5 A complete flowchart illustrating the routing method for the transmission link provided in this application embodiment;
[0078] Figure 6 A schematic diagram of the routing device for the transmission link provided in this application;
[0079] Figure 7 A schematic diagram of the structure of the electronic device provided in this application.
[0080] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0081] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0082] First, let me explain the terms used in this application:
[0083] Multi-controller active-active system: A multi-controller active-active system is a high-availability storage architecture consisting of a cluster of two or more controllers and two sets of storage nodes deployed in an equal manner. Multiple controllers in the cluster can handle read and write requests simultaneously to achieve load balancing. Data is synchronized between nodes in real time, and data splitting is avoided by relying on an arbitration mechanism. Both ends of the storage can provide read and write services to the outside world. When any controller, a single storage device, or even a site fails, the business can seamlessly switch to other nodes to continue running, achieving almost no data loss and almost no business interruption. At the same time, it has the high performance of load balancing and the ability to run continuously across devices and sites.
[0084] Analytic Hierarchy Process (AHP): AHP is a decision analysis method that decomposes complex multi-objective decision problems into a multi-level hierarchical structure, such as the objective level, criterion level, and alternative level. It constructs a judgment matrix by comparing each pair of factors, quantitatively calculates the relative weights of factors at each level, and conducts consistency tests to comprehensively derive the ranking of the merits of each alternative. It can transform qualitative experience judgments into quantitative numerical analysis and is suitable for selection and evaluation scenarios with complex indicators that are difficult to directly quantify.
[0085] Dijkstra's Algorithm: Dijkstra's algorithm is a classic greedy algorithm for finding the single-source shortest path in a weighted directed or undirected graph. Starting from a given initial vertex, it continuously selects the node that is closest to the starting point and whose shortest path has not yet been determined. It then uses this node to update the estimated shortest distances of the remaining adjacent nodes, gradually determining the shortest paths from the starting point to all other vertices in the graph. This algorithm requires that the weights of all edges in the graph cannot be negative and is often used in scenarios such as path planning and network routing.
[0086] Transmission link routing technology in multi-controller active-active systems is mainly used in data centers, distributed storage clusters, and business systems with high continuity requirements. In such scenarios, multiple control nodes or storage arrays are typically interconnected through multiple transmission links to undertake tasks such as cross-node data synchronization, service access forwarding, and fault takeover. The link routing result directly affects data transmission efficiency and system availability.
[0087] In existing solutions, the selection of transmission links usually relies on static routing configuration, primary / backup link switching mechanisms, or dynamic selection based on single indicators such as bandwidth and latency.
[0088] Specifically, static routing configuration can pre-configure fixed paths, and path selection does not depend on real-time link status. However, it cannot adapt to dynamic load changes and is prone to overloading some links or wasting resources.
[0089] Delay-based dynamic routing can select the shortest path by monitoring link latency, but it ignores key factors such as bandwidth utilization and load balancing, which may lead to a decline in global performance after local optimization.
[0090] Load balancing-based routing can determine the link load status through simple thresholds, but it lacks a comprehensive evaluation of multi-dimensional parameters (such as bit error rate and number of concurrent connections) and does not introduce a global state awareness mechanism, making it difficult to achieve collaborative optimization across arrays.
[0091] Understandably, most of the above solutions rely solely on local conditions or a limited number of parameters for judgment, lacking a unified characterization of the overall state of multiple transmission links and failing to accurately reflect the current comprehensive carrying capacity of the links. For example, when using only latency or bandwidth as a basis, factors that directly affect transmission quality, such as bit errors, queuing, and instantaneous load, are often ignored, leading to deviations between the routing results and the actual operating conditions.
[0092] Furthermore, in high-concurrency or cross-node synchronization scenarios, some links may become congested due to continuously carrying hot services, while other links are idle or underutilized, resulting in an imbalance in resource allocation. If a link malfunctions or fails, existing solutions often require recalculating the path or implementing a rigid switching strategy, leading to increased recovery latency and consequently affecting service continuity, link utilization, and overall system stability.
[0093] To address the aforementioned issues, the transmission link routing method provided in this application can determine the state matrix corresponding to multiple transmission links and obtain the service scenario requirements. First, a first score is determined for each transmission link based on the state matrix and service scenario requirements. Then, a second score is determined by combining the path delay and load margin of each transmission link. Finally, the target link for data transmission is selected from the multiple transmission links based on the first and second scores. This method comprehensively evaluates candidate links from two dimensions: service adaptability and real-time link carrying capacity. This improves the global optimization capability and reliability of link routing, enhances load distribution balance and resource utilization, and reduces the impact of link anomalies or state fluctuations on transmission stability.
[0094] Figure 1 A schematic diagram of the system architecture provided for this application, such as Figure 1 As shown, it includes a first storage device and a second storage device. The first storage device and the second storage device can be dual-active systems deployed in different geographical locations. For example, the first storage device can be located in region a and the second storage device can be located in region b.
[0095] The first and second storage devices need to maintain complete data consistency. After receiving and writing data in the first storage device, real-time incremental data, cache information, metadata, and log changes need to be pushed to the second storage device on the other end to complete the mirror copy and ensure that the data copies of the two storage devices are synchronized at all times.
[0096] In this way, when either the first or second storage device fails, the other storage device can immediately take over all business read and write operations with complete and consistent data, avoiding data loss and business interruption, thus achieving a disaster recovery effect with near-zero data loss.
[0097] The first and second storage devices can each be equipped with multiple independent controllers, which can handle read and write requests in parallel and manage storage hard disk resources in a unified manner.
[0098] Multiple controllers can interact to cache data, verify metadata, and work together to achieve bidirectional real-time data synchronization. At the same time, the controller will continuously collect operating parameters such as latency, bandwidth utilization, and load margin of all communication links connected to its own port.
[0099] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0100] Figure 2 This is a flowchart illustrating the routing method for a transmission link provided in this application. This method can be executed by a routing device for the transmission link, which can be implemented using a computer program; it can also be implemented using a medium storing the relevant computer program, such as a USB flash drive and / or optical disc; or it can be implemented using a first storage device. The following explanation uses a first storage device as an example. Figure 2 As shown, the method includes the following steps S201-S205.
[0101] S201. Determine the state matrix corresponding to multiple transmission links.
[0102] A transmission link can refer to the data transmission channel between a first storage device and a second storage device, and can be used for data synchronization, business data transmission, heartbeat interaction, etc.
[0103] The first storage device and the second storage device can each be equipped with multiple independent controllers, and the transmission link can be considered as the data transmission channel between the controller of the first storage device and the controller of the second storage device.
[0104] In one possible implementation, multiple transmission links can be parallel interconnect links between multiple controllers, or multiple physical or logical links between storage devices used for data synchronization.
[0105] For example, assuming the first storage device includes controller 1 and controller 2, and the second storage device includes controller 3 and controller 4, the transmission link between the first storage device and the second storage device may include the transmission link between controller 1 and controller 3, the transmission link between controller 1 and controller 4, the transmission link between controller 2 and controller 3, and the transmission link between controller 2 and controller 4.
[0106] A state matrix can include multiple state parameters corresponding to multiple transmission links.
[0107] Understandably, the rows of the state matrix can represent a single transmission link, and the columns of the state matrix can represent the state parameters of the transmission link.
[0108] For example, if the state parameters of any transmission link include bit error rate, bandwidth utilization and queue length, then the row corresponding to that transmission link in the state matrix contains the normalized values of the three state parameters.
[0109] Multiple status parameters can be multi-dimensional data collected by the controller of the first storage device at a preset frequency. The preset frequency can be a value pre-set by the user; for example, the preset frequency can be once every 100ms.
[0110] For example, multiple status parameters may include physical status parameters, transmission performance parameters, and load status parameters. Among them, physical status parameters may include link connectivity, bit error rate, port operating status, etc.; transmission performance parameters may include bandwidth utilization, path delay, throughput, etc.; and load status parameters may include current data transmission volume, queue length, number of concurrent connections, etc.
[0111] In one possible implementation, any one of the multiple controllers mounted in the first storage device can simultaneously act as a global state management node. Understandably, this global state management node can collect the state parameters of its corresponding transmission link, as well as receive the state parameters sent by other controllers, and after normalizing the state parameters, summarize them to obtain a state matrix.
[0112] In this way, by expressing multiple transmission links in a unified structure, subsequent scoring no longer depends on the local indicators of a single transmission link, but rather on the horizontal comparison of different transmission links based on the same state matrix, thereby enabling the current carrying capacity and operating status of the links to be consistently determined.
[0113] In one possible implementation, the state matrix corresponding to multiple transmission links can be determined as follows: collect state values corresponding to multiple transmission links at a preset frequency; normalize the state values to obtain state parameters corresponding to multiple transmission links; and determine the state matrix corresponding to multiple transmission links based on the multiple transmission links and their corresponding state parameters.
[0114] The status values include at least one or more of the following: physical status values of the transmission link, transmission status values, and load status values.
[0115] In practical implementation, the global state management node can periodically poll multiple controllers through a data acquisition thread at a preset frequency. This preset frequency can be set to a fixed time interval or dynamically adjusted based on link fluctuation intensity. The collected raw state values are first processed by removing outliers and filling in missing values, then written to the state buffer and normalized based on a unified value range to obtain the state parameters of each link in each state dimension. Subsequently, the state parameters of each transmission link are organized into a matrix according to link identifier and parameter type, generating a state matrix and storing it in memory or a database. If a link has missing state items in the current acquisition period, it can be supplemented by combining state values from historical moments to ensure the continuity and integrity of the state matrix.
[0116] In this way, by collecting the original state of the links at different frequencies, normalizing the values of different dimensions, and constructing a matrix representation, the comprehensive state of multiple transmission links can be described and compared on the same scale, thus providing a consistent input basis for subsequent link scoring and target link selection. This allows for a more complete characterization of the link state, reduces the bias caused by a single indicator, and improves the matching degree between routing results and actual operating conditions.
[0117] S202. Obtain business scenario requirements.
[0118] Business scenario requirements can be used to indicate the use cases for link routing.
[0119] Understandably, business scenario requirements can be used to limit the focus of link routing, thereby enabling the scoring process to adjust the degree of influence of different state parameters according to the current business objectives.
[0120] In one possible implementation, business scenario requirements can be obtained from external inputs or determined by preset strategies, operating status, or the current business type.
[0121] In one possible implementation, business scenario requirements can include any one or more combinations of low-latency scenarios, high-throughput scenarios, high-reliability scenarios, load balancing scenarios, and fault recovery scenarios. For example, high-reliability scenarios can be applied to financial business scenarios, transaction business scenarios, etc., pursuing low bit error rate and low packet loss rate; high-throughput scenarios can be applied to data backup scenarios, data archiving scenarios, etc., pursuing high bandwidth and high load capacity; low-latency scenarios can be applied to real-time command scenarios, interactive data scenarios, etc., pursuing low jitter and low latency.
[0122] For example, if the current business being executed is the active-active synchronization of core transaction data, the business scenario requirement can be to prioritize link reliability, be highly sensitive to bit errors and packet loss, and tolerate minor bandwidth loss; if the current business being executed is the batch backup and synchronization of data throughout the day, the business scenario requirement can be to prioritize throughput, be insensitive to latency and jitter, and tolerate minor link fluctuations.
[0123] In this way, by incorporating business scenario requirements into the routing process of transmission links, different services can form a differentiated routing basis under the same transmission link. Instead of relying on a fixed unified priority, it changes with the scenario, so that the subsequently calculated link priority corresponds to the actual requirements of data synchronization, service forwarding, or fault takeover.
[0124] S203. Based on the state matrix and business scenario requirements, determine the first score corresponding to multiple transmission links.
[0125] The first score can be used to indicate the scenario adaptation score obtained by combining the state matrix and business scenario requirements of multiple transmission links.
[0126] Understandably, the first score can focus on the long-term steady-state quality of the link and its suitability for services. When the score of the first score of any transmission link is higher, it can be considered that the inherent transmission quality of the transmission link is more suitable for the current business scenario.
[0127] In one possible implementation, the third weights corresponding to multiple state parameters of the state matrix can be obtained according to the needs of the business scenario. The weighted sum can be calculated based on the multiple state parameters and their respective third weights to obtain the first score for each transmission link.
[0128] The third weight can be a preset weight value for multiple state parameters based on business scenario requirements.
[0129] For example, assuming the state parameters include link connectivity, bandwidth utilization, and concurrent connections, if the current business scenario requires high reliability, then the third weight of link connectivity can be 0.4, the third weight of bandwidth utilization can be 0.3, and the third weight of concurrent connections can be 0.3.
[0130] In this way, the scattered multidimensional state parameters in the state matrix can be compressed into a score result that is easy to compare. The score result can reflect the differences in business scenarios. Therefore, a preliminary priority of each link can be formed before further combining path delay and load margin, thereby reducing invalid comparisons in the subsequent comprehensive score.
[0131] S204. Determine the path delay and load margin corresponding to multiple transmission links.
[0132] Path delay can be used to indicate the data transmission delay of a transmission link.
[0133] Understandably, path delay can be related to both the transmission speed of the transmission link and the length of the transmission link path. That is, the greater the path delay, the slower the transmission speed of the transmission link may be, or the longer the transmission link path may be.
[0134] Path delay can be determined based on the state matrix.
[0135] Load margin can be used to indicate the current remaining carrying capacity of a transmission link.
[0136] In one possible implementation, for any transmission link, the load margin can be determined as follows: determine the preset maximum carrying capacity of the transmission link, determine the preset current load of the transmission link according to the state matrix, and determine the difference between the maximum carrying capacity of the link and the current load as the load margin.
[0137] Understandably, a larger load margin indicates that the current transmission link is more idle and can carry more new data transmissions; a smaller load margin indicates that the current transmission link is more congested.
[0138] In this way, by independently extracting path delay and load margin, link evaluation not only focuses on whether the transmission link is in a normal state, but also further identifies whether the transmission link has sufficient transmission timeliness and remaining carrying capacity at the current moment, so that the subsequent comprehensive score can distinguish transmission links with similar states but different real-time carrying capacity.
[0139] S205. Based on the state matrix, path delay, and load margin, determine the second score corresponding to multiple transmission links.
[0140] The second score can be used to score the real-time status of the transmission link. It can focus on instantaneous latency performance and real-time load congestion status, while also taking into account the inherent quality of the link. The higher the score, the better, smoother, and less congested the link's current real-time transmission status.
[0141] In one possible implementation, for any transmission link, the second score can be determined as follows: obtain the fourth weight corresponding to the path delay and the fifth weight corresponding to the load margin; normalize the path delay and load margin of the transmission link to obtain the delay factor and load factor of the transmission link, that is, convert the path delay and load margin into the same quantization range; calculate the weighted sum based on the delay factor, load factor, fourth weight and fifth weight to obtain the second score of the transmission link.
[0142] Understandably, the second rating, compared to the first rating, introduces two more metrics directly related to real-time transmission: path delay and load margin. Therefore, it not only reflects the health of the link but also whether the link is suitable for immediately carrying current service data. When multiple links are similar in the state matrix, the second rating can differentiate them based on differences in path delay and load margin, making the overall routing result closer to the actual carrying capacity of the link.
[0143] S206. Based on the first score and the second score, determine the target link for data transmission among multiple transmission links.
[0144] The target link can be the link that is currently most suitable for data transmission among multiple transmission links.
[0145] Understandably, when the first storage device needs to synchronize data with the second storage device, it can receive a data transmission instruction. Based on the data transmission instruction, the first storage device can select the optimal link from multiple transmission links for data transmission, that is, determine the target link from multiple transmission links for this data transmission.
[0146] In one possible implementation, the target link for data transmission can be determined as follows: based on a first score and a second score, a target score corresponding to multiple transmission links is determined; based on the target score, the multiple transmission links are arranged in descending order of target score to obtain a target link table; in response to receiving a data transmission instruction, the target link with the largest target score is determined from the multiple transmission links according to the target link table.
[0147] The target score can be used to indicate the priority of multiple transmission links during link routing. It can be understood that the target score can be considered as the fusion result of the first score and the second score, that is, a comprehensive representation of the overall transmission priority of the transmission link. When the target score of any transmission link is larger, it can be considered that the transmission link has a higher priority, that is, it is more suitable for transmission. When the target score of any transmission link is smaller, it can be considered that the transmission link has a lower priority, that is, it is less suitable for transmission.
[0148] In one possible implementation, the target score can be obtained by fusing the first weight corresponding to the first score and the second weight corresponding to the second score. The first weight and the second weight can be values preset by the user.
[0149] The target link table can be considered as an ordered list of preferred links generated based on the target score. When it is necessary to select an optimal link for data transmission, the transmission link with the highest target score can be directly queried through the target link table.
[0150] In one possible implementation, when multiple transmission links with the same target score exist simultaneously, or when there is a large amount of data to be transmitted, in order to avoid the data transmission being concentrated on a few transmission links within the update window of the state matrix, thus causing data congestion on the originally optimal transmission link, a random factor can be introduced. This allows multiple transmission data to be randomly distributed across multiple transmission links, avoiding the problem of excessive concentration of transmission and thus ensuring load balancing of the data links.
[0151] In this way, by using both the first and second scores for decision-making, the link routing retains the constraints of the business scenario requirements on the link focus, while also taking into account the link's real-time latency and remaining carrying capacity. This ensures that the finally selected link not only meets the scenario adaptation requirements but also has an operating state that matches the current data transmission task.
[0152] In this embodiment, when routing of transmission links is required, a state matrix corresponding to multiple transmission links can be determined. A transmission link can refer to a data transmission channel between a first storage device and a second storage device, and can be used for data synchronization, business data transmission, heartbeat interaction, etc. The state matrix can include multiple state parameters corresponding to multiple transmission links. Business scenario requirements are obtained, which can indicate the usage scenario for link routing. Business scenario requirements can include low-latency scenarios, high-throughput scenarios, high-reliability scenarios, etc. Based on the state matrix and business scenario requirements, a first score is determined for multiple transmission links. The first score can indicate the scenario adaptation score obtained by combining the state matrix and business scenario requirements. Path delay and load margin are determined for multiple transmission links. Path delay can indicate the data transmission latency of the transmission link, and load margin can indicate the current remaining carrying capacity of the transmission link. Based on the state matrix, path delay, and load margin, a second score is determined for multiple transmission links. The second score can be a real-time status score of the transmission link. Based on the first and second scores, a target link for data transmission is determined among multiple transmission links. The target link can be the link currently most suitable for data transmission among multiple transmission links. In this way, by organizing link status parameters into a unified state matrix and incorporating business scenario requirements into the scoring process, and combining path latency and load margin to form a two-layer scoring mechanism, the link routing process can simultaneously reflect the overall link status, business scenario preferences, and real-time link carrying capacity. Compared to processing methods that rely solely on static priority or a single indicator, this approach can still output executable target link selection results even when there is uneven link load distribution, local link congestion, or performance fluctuations in some links. This improves the reliability of link routing while ensuring link load balancing.
[0153] Below, in conjunction with Figure 3 The process of determining the target link for data transmission is explained.
[0154] Figure 3 This is a flowchart illustrating the process of determining a target link for data transmission, provided as an embodiment of this application. Based on the above embodiments, see also... Figure 3 The method includes:
[0155] S301. Determine the target scores corresponding to multiple transmission links based on the first score and the second score.
[0156] Target scores can be used to indicate the priority of multiple transmission links during link routing.
[0157] In one possible implementation, the target score can be determined as follows: obtain historical load data of multiple transmission links at historical times; determine the predicted load of multiple transmission links based on the historical load data; determine the first weight corresponding to the first score and the second weight corresponding to the second score based on the predicted load; and determine the target score corresponding to multiple transmission links based on the first score, the second score, the first weight, and the second weight.
[0158] For any transmission link, historical load data can be load data collected at multiple historical moments, including bandwidth utilization, traffic volume, and load records during busy and idle periods.
[0159] Predicted load can be calculated from historical load data at a given time, using methods such as moving average, exponential smoothing, or linear regression to obtain future load data. It can be used to predict whether transmission links will experience congestion in the future.
[0160] The first weight can be the weighting coefficient assigned to the first score, which can represent the proportion of link steady-state quality and business adaptation dimension in the final score.
[0161] The second weight can be a weighting coefficient assigned to the second score, which can represent the proportion of link real-time latency and real-time load margin in the final score.
[0162] In one possible implementation, when the predicted load is greater than or equal to the first value, it can be assumed that the current communication link is about to experience a surge in traffic and will soon enter a state of full load and congestion. At this time, the second weight can be increased, that is, focusing on real-time load and instantaneous state, while the first weight is reduced, thereby avoiding the selection of a link that is about to become congested if only the inherent quality of the link is considered.
[0163] When the predicted load is less than or equal to the second value, it indicates that the overall traffic of the transmission link is stable and there will be no congestion fluctuations in the short term. The first weight can be increased, that is, the inherent stability of the link and the service adaptability are emphasized, while the second weight is reduced, so that the transmission link with better transmission quality is selected first to ensure long-term transmission reliability.
[0164] In this way, historical load data provides a basis for the evolution of link load, predicted load reflects the future carrying trend of the link, weight adjustment makes the two types of scores change dynamically with the link load, and the target score serves as the input result for subsequent link ranking and routing. This allows the target score to dynamically balance the first and second scores in conjunction with historical load trends, making the link score more closely reflect the actual carrying capacity, thereby improving the consistency between routing results and the actual link capacity.
[0165] S302. Based on the target score, arrange the multiple transmission links in descending order of target score to obtain the target link table.
[0166] Sorting can refer to sorting according to the target score from largest to smallest.
[0167] The target link table can be an ordered structured list. The table can represent the link transmission priority from high to low from top to bottom. The table header records information such as link number, target score, real-time load, and latency. It can be used as a reference form for subsequent routing and fault switching queries and will be updated in real time along with the link score.
[0168] In practice, each transmission link and its corresponding target score can be extracted and arranged in descending order of the target score value. Transmission links with the same target score can be further sorted according to their real-time load margin, with those having larger margins appearing first. A target link table that can be retrieved and dynamically refreshed at any time is encapsulated and cached in the preset storage space of the first storage device. Whenever the link status, business scenario, or load prediction results are updated, the score is recalculated and the target link table is refreshed to ensure that the data in the target link table is always synchronized with the latest status of the entire network links.
[0169] S303. In response to receiving a data transmission instruction, determine the target link with the highest target score among multiple transmission links according to the target link table.
[0170] Data transmission instructions can be data synchronization task instructions issued by the controller, which can include various cross-device data transmission and reception requests such as storage mirror data, metadata synchronization, cache interaction, and heartbeat message transmission between the first and second storage devices.
[0171] The target link can be the link ranked first in the target link table and with the highest target score, which will serve as the main working link for the current data transmission.
[0172] In one possible implementation, after determining the target link for data transmission among multiple transmission links, the method further includes: determining at least one candidate link among the multiple transmission links according to a target link table, wherein the target score of the candidate link is greater than or equal to a first threshold; in response to a fault in the target link, or the current load of the target link being greater than or equal to a second threshold, determining an update link among the at least one candidate link, and executing a data transmission instruction through the update link.
[0173] The first and second thresholds can be values preset by the user.
[0174] In the specific implementation, after receiving a data transmission command, the control node first reads the candidate link set from the target link table and completes the filtering by combining the target score and a first threshold. When fault information such as link breakage, packet loss anomaly, or port unreachability is detected on the target link, or when the current load of the target link is detected to reach a second threshold, the control node selects an updated link from the candidate links. The selection can be based on the maximum target score, the lowest real-time load, or the fault isolation status. After the updated link is established, the data packets, synchronization frames, or service requests corresponding to the original data transmission command are redirected to this link to continue data transmission.
[0175] This allows the target link to maintain its predetermined data transmission path during normal operation, while in the event of a fault or overload, it can directly switch from the selected candidate links to the updated link without recalculating all links. Therefore, the link replacement process has clear candidate constraints and threshold control, with a clear switching direction, enabling data transmission tasks to continue executing even when links are abnormal or the load increases, while maintaining the priority information in the target link table for subsequent routing.
[0176] exist Figure 3In the illustrated embodiment, when it is necessary to determine the target link with the highest target score, multiple transmission links can be assigned target scores based on the first and second scores. The target scores can indicate the priority of multiple transmission links during link routing. Based on the target scores, the multiple transmission links are arranged in descending order of target scores to obtain a target link table. This arrangement can refer to sorting the links according to their target scores from largest to smallest. The target link table can be an ordered structured list. In response to receiving a data transmission command, the target link with the highest target score is determined from among the multiple transmission links based on the target link table. The data transmission command can be a data synchronization task command issued by the controller, and the target link can be the link ranked first in the target link table with the highest target score. Thus, by merging the first and second scores into a target score and sorting them, the system can organize the priority relationship of multiple transmission links with a unified quantitative result and quickly locate the highest-scoring link when the command is triggered, reducing the processing overhead of temporary comparisons and thereby improving the response speed and consistency of link routing results.
[0177] Below, in conjunction with Figure 4 The process of determining the first score corresponding to multiple transmission links is explained.
[0178] Figure 4 This is a schematic flowchart illustrating the process of determining a first score corresponding to multiple transmission links, as provided in an embodiment of this application. Based on the above embodiment, see [link to relevant documentation]. Figure 4 The method includes:
[0179] S401. Determine the scaling values between multiple state parameters based on business scenario requirements.
[0180] Business scenario requirements can be used to indicate the application scenarios for link routing. They can also be used to limit the focus of link routing, allowing the scoring process to adjust the impact of different state parameters based on current business objectives.
[0181] Scale values can be used to indicate the relative importance of any two state parameters under business scenario requirements.
[0182] In one possible implementation, the scaling value can be determined according to the scaling rules of the Analytic Hierarchy Process (AHP). That is, the scaling value can be a comparative numerical value used to quantify which of two state parameters is more important, and by how much more important. This transforms fuzzy business preferences into precise numerical weights.
[0183] The scaling rules of the Analytic Hierarchy Process (AHP) can include: if state parameter 1 and state parameter 2 are equally important, the scale value is 1; if state parameter 1 is slightly more important than state parameter 2, the scale value is 3; if state parameter 1 is significantly more important than state parameter 2, the scale value is 5; if state parameter 1 is strongly more important than state parameter 2, the scale value is 7; if state parameter 1 is extremely more important than state parameter 2, the scale value is 9; if the relationship between state parameter 1 and state parameter 2 is between equally important and slightly important, the scale value is 2; if the relationship between state parameter 1 and state parameter 2 is between slightly important and significantly important, the scale value is 4; if the relationship between state parameter 1 and state parameter 2 is between significantly important and strongly important, the scale value is 6; if the relationship between state parameter 1 and state parameter 2 is between strongly important and extremely important, the scale value is 8.
[0184] For example, if the business scenario requires high reliability, then the current business logic can be considered to prioritize data correctness, with bit error rate and packet loss being the most critical, followed by jitter, and bandwidth utilization being the least important. If the status parameters include bit error rate, packet loss rate, link jitter, and bandwidth utilization, then the bit error rate can be considered equally important as the packet loss rate (scale value 1), the bit error rate is significantly more important than jitter (scale value 5), the bit error rate is extremely important than bandwidth utilization (scale value 9), the packet loss rate is significantly more important than jitter (scale value 5), the packet loss rate is extremely important than bandwidth utilization (scale value 9), and jitter is strongly more important than bandwidth utilization (scale value 7).
[0185] S402. Determine the third weights corresponding to multiple state parameters based on the scaling values.
[0186] The third weight can be the index dimension weight coefficient corresponding to each state parameter, and the sum of all third weights can be 1.
[0187] In one possible implementation, the third weights corresponding to each state parameter can be obtained through the eigenvalue method and normalization solution, and the sum of each third weight is 1. After obtaining the third weights, a consistency check can be performed on the third weights to prevent logical contradictions between multiple weights, ensure that the weights are scientific and effective, and prevent logical errors.
[0188] S403. Determine the first score corresponding to multiple transmission links based on the state matrix and the third weights corresponding to multiple state parameters.
[0189] The first score can be used to assess the scenario adaptability of the transmission link. It depends only on the inherent quality of the link and the preferences of the business scenario, and does not include real-time latency, real-time load, etc. It can be used to characterize the inherent quality of the link and whether it is suitable for the current business.
[0190] For any transmission link, the first score of the transmission link can be obtained by multiplying and summing all the normalized state parameters of the transmission link with the corresponding third weights (i.e., weighted summation).
[0191] exist Figure 4 In the illustrated embodiment, when it is necessary to determine the first score corresponding to multiple transmission links, a scale value can be determined between multiple state parameters according to the business scenario requirements. The business scenario requirements can be used to indicate the usage scenario of link routing, and the scale value can be used to indicate the comparison relationship of the importance between any two state parameters under the business scenario requirements. Based on the scale value, a third weight corresponding to multiple state parameters is determined. The third weight can be the indicator dimension weight coefficient corresponding to each state parameter, and the sum of all third weights can be 1. Based on the state matrix and the third weights corresponding to multiple state parameters, the first score corresponding to multiple transmission links is determined. The first score can be the scenario adaptation score of the transmission link. In this way, through the above method, the first score can simultaneously characterize the relative importance of multiple state parameters in different business scenarios, and transform subjective scenario requirements into calculable weight coefficients. Combined with the state matrix, a comprehensive link score is formed, thereby making the subsequent link routing results more consistent with the current business objectives. This approach can reduce the bias of a single indicator on the routing results, make the comparison relationship of multiple transmission links more stable, and thus improve the consistency between the link score and the actual bearer status.
[0192] Below, in conjunction with Figure 5 This section explains the complete process of routing in the transmission link.
[0193] Figure 5 This is a complete flowchart illustrating the routing method for the transmission link provided in this application embodiment. Please refer to... Figure 5 ,include:
[0194] S501. Determine the state matrix corresponding to multiple transmission links.
[0195] S502, Obtain business scenario requirements.
[0196] S503. Based on the state matrix and business scenario requirements, determine the first score corresponding to multiple transmission links.
[0197] S504. Determine the path delay and load margin corresponding to multiple transmission links.
[0198] S505. Based on the state matrix, path delay, and load margin, determine the second score corresponding to multiple transmission links.
[0199] S506. Based on the first score and the second score, determine the target score corresponding to multiple transmission links.
[0200] S507. Based on the target score, arrange the multiple transmission links in descending order of target score to obtain the target link table.
[0201] S508. In response to receiving a data transmission instruction, determine the target link with the highest target score among multiple transmission links according to the target link table.
[0202] S509. Based on the target link table, determine at least one candidate link among multiple transmission links.
[0203] S510. In response to a fault in the target link, or if the current load of the target link is greater than or equal to a second threshold, determine an update link among at least one candidate link and execute a data transmission instruction through the update link.
[0204] This application also provides a routing device for a transmission link, which is integrated into an electronic device.
[0205] Figure 6 A schematic diagram of the routing device for the transmission link provided in this application is shown below. Figure 6 As shown, the routing device 60 for the transmission link provided in this embodiment includes:
[0206] The first determining module 61 is used to determine the state matrix corresponding to multiple transmission links, and the state matrix includes multiple state parameters corresponding to multiple transmission links.
[0207] Module 62 is used to acquire business scenario requirements, which are used to indicate the usage scenarios of link routing.
[0208] The second determining module 63 is used to determine the first score corresponding to multiple transmission links based on the state matrix and business scenario requirements;
[0209] The third determining module 64 is used to determine the path delay and load margin corresponding to multiple transmission links. The load margin is used to indicate the load that the transmission link can still carry.
[0210] The fourth determination module 65 is used to determine the second score corresponding to multiple transmission links based on the state matrix, path delay and load margin;
[0211] The fifth determining module 66 is used to determine the target link for data transmission among multiple transmission links based on the first score and the second score.
[0212] In one possible implementation, the fifth determining module 66 is specifically used for,
[0213] Based on the first score and the second score, target scores are determined for multiple transmission links. The target scores are used to indicate the priority of multiple transmission links during link routing.
[0214] Based on the target score, multiple transmission links are arranged in descending order of target score to obtain the target link table;
[0215] In response to receiving a data transmission instruction, the target link with the highest target score is determined from multiple transmission links according to the target link table.
[0216] In one possible implementation, the fifth determining module 66 is specifically used for,
[0217] Obtain historical load data for multiple transmission links at historical moments;
[0218] Based on historical load data, the predicted load of multiple transmission links is determined;
[0219] Based on the predicted load, determine the first weight corresponding to the first score and the second weight corresponding to the second score;
[0220] Based on the first score, the second score, the first weight, and the second weight, the target scores corresponding to multiple transmission links are determined.
[0221] In one possible implementation, the fifth determining module 66 is further configured to,
[0222] Based on the target link table, at least one candidate link is determined from multiple transmission links, and the target score of the candidate link is greater than or equal to a first threshold.
[0223] In response to a fault in the target link, or if the current load of the target link is greater than or equal to a second threshold, an update link is determined from at least one candidate link, and a data transmission instruction is executed through the update link.
[0224] In one possible implementation, the second determining module 63 is specifically used for,
[0225] Based on the business scenario requirements, determine the scale values between multiple state parameters. The scale values are used to indicate the comparison of the importance between any two state parameters under the business scenario requirements.
[0226] Based on the scale value, determine the third weight corresponding to multiple state parameters;
[0227] Based on the state matrix and the third weights corresponding to multiple state parameters, the first score corresponding to multiple transmission links is determined.
[0228] In one possible implementation, the first determining module 61 is specifically used for,
[0229] Collect status values corresponding to multiple transmission links at a preset frequency. The status values include at least one or more of the following: physical status value, transmission status value, and load status value of the transmission link.
[0230] The state values are normalized to obtain the state parameters corresponding to multiple transmission links;
[0231] Based on multiple transmission links and their corresponding state parameters, determine the state matrix corresponding to multiple transmission links.
[0232] The transmission link routing device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0233] Figure 7 A schematic diagram of the structure of the electronic device provided in this application. Figure 7 As shown, the electronic device 70 provided in this embodiment includes: a processor 701 and a memory 702 communicatively connected to the processor 701.
[0234] Optionally, the electronic device 70 also includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus.
[0235] In the specific implementation process, the processor 701 executes the computer execution instructions stored in the memory 702, causing the processor 701 to perform the above-mentioned method.
[0236] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.
[0237] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.
[0238] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.
[0239] Buses can be Industry Standard Architecture (ISA) buses, Peripheral Component Interconnect (PCI) buses, or Extended Industry Standard Architecture (EISA) buses, etc. Buses can be categorized into address buses, data buses, control buses, etc.
[0240] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0241] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.
[0242] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as read-only memory (ROM), static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0243] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in application-specific integrated circuits (ASICs). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.
[0244] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0245] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0246] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0247] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a server to execute all or part of the steps of the methods of the various embodiments of the present invention.
[0248] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.
Claims
1. A routing method for a transmission link, characterized in that, include: Determine a state matrix corresponding to multiple transmission links, wherein the state matrix includes multiple state parameters corresponding to the multiple transmission links; Obtain business scenario requirements, which are used to indicate the usage scenarios for link routing; Based on the state matrix and the business scenario requirements, a first score is determined for each of the multiple transmission links; Determine the path delay and load margin corresponding to the plurality of transmission links, wherein the load margin is used to indicate the current remaining carrying capacity of the transmission links; Based on the state matrix, the path delay, and the load margin, a second score is determined for each of the plurality of transmission links; Based on the first score and the second score, a target link for data transmission is determined among the plurality of transmission links.
2. The method according to claim 1, characterized in that, Based on the first score and the second score, a target link for data transmission is determined among the plurality of transmission links, including: Based on the first score and the second score, a target score is determined for the plurality of transmission links, and the target score is used to indicate the priority of the plurality of transmission links in link routing. Based on the target score, the multiple transmission links are arranged in descending order of the target score to obtain a target link table; In response to receiving a data transmission instruction, the target link with the highest target score is determined from the plurality of transmission links according to the target link table.
3. The method according to claim 2, characterized in that, Based on the first score and the second score, the target score corresponding to the plurality of transmission links is determined, including: Obtain historical load data of the multiple transmission links at historical moments; Based on the historical load data, determine the predicted load of the multiple transmission links; Based on the predicted load, determine the first weight corresponding to the first score and the second weight corresponding to the second score; The target scores corresponding to the plurality of transmission links are determined based on the first score, the second score, the first weight, and the second weight.
4. The method according to any one of claims 2-3, characterized in that, After determining the target link for data transmission among the plurality of transmission links based on the first score and the second score, the method further includes: Based on the target link table, at least one candidate link is determined from the plurality of transmission links, wherein the target score of the candidate link is greater than or equal to a first threshold. In response to a fault in the target link, or if the current load of the target link is greater than or equal to a second threshold, an update link is determined from the at least one candidate link, and the data transmission instruction is executed through the update link.
5. The method according to any one of claims 1-3, characterized in that, Based on the state matrix and the business scenario requirements, a first score is determined for each of the multiple transmission links, including: Based on the business scenario requirements, a scale value is determined among the multiple state parameters. The scale value is used to indicate the comparison relationship of the importance between any two state parameters under the business scenario requirements. Based on the scale value, determine the third weight corresponding to the plurality of state parameters; Based on the state matrix and the third weights corresponding to the multiple state parameters, the first score corresponding to the multiple transmission links is determined.
6. The method according to any one of claims 1-3, characterized in that, Determine the state matrix corresponding to multiple transmission links, including: The status values corresponding to the multiple transmission links are collected at a preset frequency. The status values include at least one or more of the physical status values, transmission status values, and load status values of the transmission links. The state values are normalized to obtain the state parameters corresponding to the multiple transmission links; Based on the multiple transmission links and their corresponding state parameters, a state matrix corresponding to the multiple transmission links is determined.
7. A routing device for a transmission link, characterized in that, include: The first determining module is used to determine a state matrix corresponding to multiple transmission links, the state matrix including multiple state parameters corresponding to the multiple transmission links; The acquisition module is used to acquire business scenario requirements, which are used to indicate the usage scenario of link routing. The second determining module is used to determine the first score corresponding to the multiple transmission links based on the state matrix and the business scenario requirements; The third determining module is used to determine the path delay and load margin corresponding to the plurality of transmission links, wherein the load margin is used to indicate the load that the transmission link can currently still bear; The fourth determining module is used to determine the second score corresponding to the plurality of transmission links based on the state matrix, the path delay, and the load margin. The fifth determining module is used to determine the target link for data transmission among the plurality of transmission links based on the first score and the second score.
8. An electronic device, characterized in that, include: A processor and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.
