A scheduling method and device based on LTE long-distance private network transmission

Abstract

The application is suitable for the technical field of data communication, and provides a scheduling method and device based on LTE long-distance private network transmission.The scheduling method based on LTE long-distance private network transmission comprises the following steps: obtaining a plurality of historical data volumes of a client, matching client service characteristics according to the plurality of historical data volumes; obtaining performance indexes of different links; obtaining a weight set corresponding to the client service characteristics; calculating communication quality scores corresponding to different links respectively according to the performance indexes and the weight set; selecting a main link and a backup link in different links according to the communication quality scores; and scheduling the main link or the backup link to transmit virtual private network data.The virtual private network data refers to data for data communication by using a virtual private network.This scheduling method can balance loads among different links and maximize the utilization rate of network resources, and has a significant advantage in a long-distance transmission scene.

Description

Technical Field

[0001] This invention belongs to the technical field of data communication, and particularly relates to a scheduling method and apparatus based on LTE long-distance private network transmission. Background Technology

[0002] With the continuous development of communication technologies, especially the mature application of LTE (Long Term Evolution) technology, long-distance private network transmission has gradually become the preferred solution for many industries. LTE technology has advantages such as wide coverage, high transmission rate, low latency, and support for high mobility, and has broad application prospects in public safety, energy, transportation, and industrial automation. However, in practical applications, how to efficiently schedule and manage the transmission of long-distance private networks and ensure the stability and reliability of data communication remains a pressing technical challenge.

[0003] Existing LTE long-distance private network transmission scheduling methods typically rely on a single link selection strategy, failing to fully consider the performance indicators of different links and the service characteristics of clients. In dynamic network environments, this approach may lead to inappropriate link selection, impacting data transmission efficiency and reliability. Furthermore, existing methods lack in-depth analysis of historical data volume and service characteristics, making it impossible to effectively differentiate and schedule different types of services.

[0004] Therefore, it is particularly important to propose a scheduling method based on LTE long-distance private network transmission to address the shortcomings of existing technologies. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a scheduling method and apparatus based on LTE long-distance private network transmission to solve the technical problem that existing methods lack in-depth mining of historical data volume and service characteristics, and are unable to effectively distinguish and schedule different types of services.

[0006] A first aspect of this invention provides a scheduling method for long-distance private network transmission based on LTE, the scheduling method for long-distance private network transmission based on LTE includes:

[0007] The system acquires multiple historical data volumes from the client and matches client business characteristics based on these volumes. Each historical data volume refers to the data volume within a historical sub-period, and the historical period includes multiple historical sub-periods. The multiple historical data volumes include the data volumes corresponding to multiple historical periods. The client business characteristics include real-time regular peaks, real-time regular sparse peaks, real-time irregular sparse peaks, real-time regular dense peaks, real-time irregular dense peaks, non-real-time regular peaks, non-real-time regular sparse peaks, non-real-time irregular sparse peaks, non-real-time regular dense peaks, non-real-time irregular dense peaks, and a no-data state.

[0008] Obtain performance metrics for different links; these performance metrics include bandwidth, network latency, jitter, and packet loss rate.

[0009] Obtain the weight set corresponding to the client service characteristics; the weight set includes multiple preset weights;

[0010] Based on the performance metrics and the weight set, calculate the communication quality score corresponding to each link;

[0011] Based on the communication quality score, a primary link and a backup link are selected from different links;

[0012] The primary link or the backup link is scheduled to transmit VPN data; the VPN data refers to data that is used for data communication via VPN.

[0013] Furthermore, the step of obtaining multiple historical data volumes from the client and matching client service characteristics based on the multiple historical data volumes includes:

[0014] Obtain the business tags for the historical data volume; the business tags include real-time data tags and non-real-time data tags;

[0015] Extract the first historical data volume corresponding to multiple first historical sub-periods in the first historical period;

[0016] Calculate a first average among multiple first historical data volumes;

[0017] Extract the first historical sub-period corresponding to the first historical data volume that exceeds the threshold;

[0018] Calculate the first time interval between adjacent first historical sub-cycles;

[0019] Extract the second historical data volume corresponding to multiple previous historical sub-cycles in the previous historical cycle; the previous historical cycle refers to the historical cycle that is preceding and adjacent to the first historical cycle;

[0020] Extract the second historical sub-period corresponding to the second historical data volume that exceeds the threshold;

[0021] Based on the distribution characteristics of multiple first historical sub-cycles and multiple second historical sub-cycles, the degree of agreement of data volume distribution between historical cycles is calculated.

[0022] The current feature vector is constructed based on multiple first time intervals, the first average value, the degree of agreement, and the number of first historical sub-cycles.

[0023] Based on the current feature vector, match the data volume feature;

[0024] The client service characteristics are obtained by combining the business tag with the data volume feature.

[0025] Furthermore, the step of calculating the degree of agreement of data volume distribution between historical periods based on the distribution characteristics of multiple first historical sub-periods and multiple second historical sub-periods includes:

[0026] Match the target historical sub-period that is closest to the second historical sub-period among multiple first historical sub-periods;

[0027] Calculate the second time interval between the target historical sub-period and the corresponding second historical sub-period;

[0028] Calculate the variance of the second time interval corresponding to each of the multiple second historical sub-cycles;

[0029] The variance is used as the degree of fit.

[0030] Further, the step of matching data volume features based on the current feature vector includes:

[0031] Obtain the pre-trained target cluster centers, and calculate the similarity between the target cluster centers and the current feature vector;

[0032] Extract the target cluster center corresponding to the maximum similarity, and use the standard features corresponding to the target cluster center corresponding to the maximum similarity as the data volume features.

[0033] Furthermore, before the steps of obtaining the pre-trained target cluster centers and calculating the similarity between the target cluster centers and the current feature vector, the method further includes:

[0034] Obtain standard feature vectors corresponding to multiple client business features; the standard feature vectors are obtained based on prior knowledge;

[0035] Multiple training feature vectors are obtained, and the multiple standard feature vectors are used as initial cluster centers for clustering operations to obtain multiple clusters and their corresponding current cluster centers;

[0036] Extract sub-clusters from each cluster;

[0037] Calculate the first distance between multiple sub-clusters and multiple clusters;

[0038] The sub-cluster corresponding to the minimum first distance is merged with the cluster to obtain a new cluster and the target cluster center corresponding to the new cluster.

[0039] Furthermore, the step of extracting sub-clusters within each cluster includes:

[0040] Obtain the second distance between each training feature vector in the cluster and the cluster center corresponding to the cluster;

[0041] Arrange the multiple second distances in descending order and extract the first N second distances;

[0042] Calculate the third distance between the training feature vectors corresponding to the first N second distances respectively;

[0043] If the third distance is greater than the threshold, then the two training feature vectors corresponding to the third distance are respectively used as the first current cluster center, and the training feature vectors in the cluster whose distance from the first current cluster center is less than the preset value are respectively used to form the sub-cluster.

[0044] If the third distance is not greater than the threshold, the two training feature vectors corresponding to the third distance are merged into the second current cluster center, and the training feature vectors in the cluster whose distance from the second current cluster center is less than the preset value are formed into the sub-cluster.

[0045] Furthermore, the weight set includes weight values ​​corresponding to various performance indicators;

[0046] The step of calculating the communication quality score corresponding to each link based on the performance index and the weight set includes:

[0047] Obtain multiple numerical ranges for each performance metric type; different numerical ranges correspond to different type scores.

[0048] Match the performance metric to the target value range and obtain the type score corresponding to the target value range;

[0049] Multiply the type score corresponding to each performance indicator by its weight value to obtain the result value;

[0050] The communication quality score is obtained by summing the results corresponding to each of the multiple performance indicators.

[0051] A second aspect of the present invention provides a scheduling device based on LTE long-distance private network transmission, comprising:

[0052] The first acquisition unit is used to acquire multiple historical data volumes from the client and match client business characteristics based on the multiple historical data volumes; each historical data volume refers to the data volume within a historical sub-period, and the historical period includes multiple historical sub-periods, the multiple historical data volumes including the data volumes corresponding to multiple historical periods; the client business characteristics include real-time regular peak, real-time regular sparse peak, real-time irregular sparse peak, real-time regular dense peak, real-time irregular dense peak, non-real-time regular peak, non-real-time regular sparse peak, non-real-time irregular sparse peak, non-real-time regular dense peak, non-real-time irregular dense peak, and no data state;

[0053] The second acquisition unit is used to acquire performance indicators of different links; the performance indicators include bandwidth, network latency, jitter and packet loss rate.

[0054] The third acquisition unit is used to acquire a weight set corresponding to the client service characteristics; the weight set includes multiple preset weights.

[0055] The calculation unit is used to calculate the communication quality score corresponding to each link based on the performance index and the weight set.

[0056] The selection unit is used to select a primary link and a backup link from different links based on the communication quality score.

[0057] A communication unit is used to schedule the transmission of VPN data via the main link or the backup link; the VPN data refers to data that uses a VPN for data communication.

[0058] A third aspect of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the scheduling method based on LTE long-distance private network transmission described in the first aspect.

[0059] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the scheduling method based on LTE long-distance private network transmission described in the first aspect.

[0060] The beneficial effects of this invention compared to existing technologies are as follows: By acquiring multiple historical data sets from clients and matching these historical data sets with the clients' business characteristics, the rational allocation and efficient utilization of network resources are ensured. By acquiring performance indicators of different links, including bandwidth, network latency, jitter, and packet loss rate, and combining them with a preset weight set to evaluate the communication quality of each link, the accuracy and reliability of link selection are further improved. Through intelligent selection and scheduling of primary and backup links, the system can flexibly respond to network fluctuations, ensuring efficient transmission of VPN data, thereby significantly reducing network latency and data packet loss, and improving the stability and reliability of data transmission. This scheduling method can balance the load among different links, maximizing the utilization of network resources, and has significant advantages, especially in long-distance transmission scenarios. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 A schematic flowchart of a scheduling method based on LTE long-distance private network transmission provided by the present invention is shown;

[0063] Figure 2 A schematic diagram of a scheduling device based on LTE long-distance private network transmission according to an embodiment of the present invention is shown;

[0064] Figure 3 A schematic diagram of a terminal device provided in an embodiment of the present invention is shown. Detailed Implementation

[0065] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0066] This invention provides a scheduling method and apparatus for long-distance private network transmission based on LTE, in order to solve the technical problem that existing methods lack in-depth mining of historical data volume and service characteristics, and are unable to effectively distinguish and schedule different types of services.

[0067] First, this invention provides a scheduling method for long-distance private network transmission based on LTE. Please refer to [link / reference]. Figure 1 , Figure 1 A schematic flowchart of a scheduling method based on LTE long-distance private network transmission provided by the present invention is shown. Figure 1 As shown, the scheduling method based on LTE long-distance private network transmission may include the following steps:

[0068] Step 101: Obtain multiple historical data volumes from the client, and match the client's business characteristics based on these multiple historical data volumes; each historical data volume refers to the data volume within a historical sub-period, and the historical period includes multiple historical sub-periods, with the multiple historical data volumes including the data volumes corresponding to multiple historical periods; the client's business characteristics include real-time regular peaks, real-time regular sparse peaks, real-time irregular sparse peaks, real-time regular dense peaks, real-time irregular dense peaks, non-real-time regular peaks, non-real-time regular sparse peaks, non-real-time irregular sparse peaks, non-real-time regular dense peaks, non-real-time irregular dense peaks, and no data state;

[0069] Each historical period includes multiple historical sub-periods. For example, a historical period is 24 hours (days), and a historical sub-period is each hour. The total historical data volume includes the historical data volume corresponding to multiple historical periods (i.e., the historical data volume for N days).

[0070] Matching client business characteristics based on multiple historical data volumes includes, but is not limited to, real-time regular peaks, real-time regular sparse peaks, real-time irregular sparse peaks, real-time regular dense peaks, real-time irregular dense peaks, non-real-time regular peaks, non-real-time regular sparse peaks, non-real-time irregular sparse peaks, non-real-time regular dense peaks, non-real-time irregular dense peaks, and no data state.

[0071] The specific logic for matching client business characteristics based on multiple historical data volumes is as follows:

[0072] Specifically, step 101 includes steps A01 to A11:

[0073] Step A01: Obtain the service tags for the historical data volume; the service tags include real-time data tags and non-real-time data tags;

[0074] Each piece of data has a corresponding business tag, which includes, but is not limited to, real-time data tags and non-real-time data tags. Business tags can be categorized according to business functions. Real-time data tags include communication data generated by functions such as live streaming or video calls, while non-real-time data tags include communication data generated by functions such as downloading or audio / video recording.

[0075] Step A02: Extract the first historical data volume corresponding to multiple first historical sub-periods in the first historical period;

[0076] The first historical period represents the historical period closest to the current moment, making subsequent processing results more aligned with the needs of data changes.

[0077] Step A03: Calculate the first average value among multiple first historical data volumes;

[0078] Step A04: Extract the first historical sub-period corresponding to the first historical data volume that is greater than the threshold;

[0079] The threshold is used to filter the first historical sub-period with a high data volume. Understandably, the first historical data volume exceeding the threshold is considered a data peak.

[0080] Step A05: Calculate the first time interval between adjacent first historical sub-cycles;

[0081] The first time interval can be used to analyze the distribution characteristics between data peaks to identify the density or continuity of data peaks.

[0082] Step A06: Extract the second historical data volume corresponding to multiple previous historical sub-cycles in the previous historical period; the previous historical period refers to the historical period that is adjacent to the first historical period;

[0083] In order to identify whether there is a regularity in the changes of client data volume across multiple historical periods, it is necessary to extract the second historical data volume corresponding to multiple previous historical sub-periods in the previous historical period, so as to further analyze the second historical data volume with the first historical data volume.

[0084] Step A07: Extract the second historical sub-period corresponding to the second historical data volume that is greater than the threshold;

[0085] The threshold is used to filter out the second historical sub-period with a high data volume. Understandably, the second historical data volume exceeding the threshold is considered a data peak.

[0086] Step A08: Calculate the degree of agreement of data volume distribution between historical periods based on the distribution characteristics of multiple first historical sub-periods and multiple second historical sub-periods;

[0087] The consistency can be used to determine the regularity of data peaks between the first and second historical periods. The specific logic is as follows:

[0088] Specifically, step A08 includes steps A081 to A08.

[0089] Step A081: Match the target historical sub-period that is closest to the second historical sub-period among multiple first historical sub-periods;

[0090] Step A082: Calculate the second time interval between the target historical sub-period and the corresponding second historical sub-period;

[0091] Step A083: Calculate the variance of the second time interval corresponding to each of the multiple second historical sub-cycles;

[0092] Step A084: Use the variance as the degree of fit.

[0093] Variance can be used to represent the degree of dispersion between the second time interval, that is, the difference between the target historical sub-period and the second historical sub-period. The smaller the similarity, the smaller the difference between the target historical sub-period and the second historical sub-period, which means that the data peaks between the first and second historical periods have a strong regularity.

[0094] In this embodiment, by accurately matching the distribution characteristics between multiple historical sub-cycles, an innovative approach is proposed to calculate the degree of consistency in data volume distribution between historical cycles using the variance of time intervals. Specifically, the scheme first matches the nearest target historical sub-cycle for each second historical sub-cycle within multiple first historical sub-cycles and calculates the second time interval between them. Statistical analysis is then performed on the time intervals between multiple second historical sub-cycles and their corresponding target historical sub-cycles, and the variance of these time intervals is further calculated as an indicator of the degree of consistency between historical cycles. This calculation method effectively captures the degree of deviation in data distribution between different historical cycles. The smaller the variance, the more consistent the sub-cycle distributions of different historical cycles, and the higher the degree of consistency; conversely, the larger the variance, the greater the differences in the sub-cycle distributions. This method can meticulously characterize the regularity and volatility of historical data distribution, exhibiting high accuracy and stability. Therefore, this technical solution achieves higher accuracy in matching data volume distribution characteristics, effectively reflecting the similarity and periodicity of historical data changes, and providing a reliable data foundation for further analysis and prediction of client-side business characteristics.

[0095] Step A09: Construct the current feature vector based on multiple first time intervals, the first average value, the degree of agreement, and the number of the first historical sub-cycles;

[0096] The current feature vector is obtained by combining multiple first time intervals, first average values, matching degree, and the number of first historical sub-cycles according to preset positions.

[0097] Step A10: Match data volume features based on the current feature vector;

[0098] Specifically, step A10 includes steps A101 to A102:

[0099] Step A101: Obtain the pre-trained target cluster centers and calculate the similarity between the target cluster centers and the current feature vector;

[0100] Step A102: Extract the target cluster center corresponding to the maximum similarity, and use the standard features corresponding to the target cluster center corresponding to the maximum similarity as the data volume features.

[0101] As an optional embodiment of this application, steps B1 to B5 are further included before step A101:

[0102] Step B1: Obtain standard feature vectors corresponding to multiple client business features; the standard feature vectors are obtained based on prior knowledge;

[0103] The standard feature vector is a user-defined prior knowledge based on the client's business characteristics. Understandably, since the manually set standard feature vector differs from the feature vector in the actual application environment, it needs to be corrected and optimized through subsequent clustering.

[0104] Step B2: Obtain multiple training feature vectors, and use the multiple standard feature vectors as initial cluster centers to perform clustering operations, thereby obtaining multiple clusters and their respective current cluster centers;

[0105] The clustering operation uses the traditional K-value clustering method, which will not be elaborated here.

[0106] Step B3: Extract sub-clusters from each cluster;

[0107] To further improve clustering accuracy, it is necessary to refine the clustering process, which requires extracting sub-clusters from the clusters for further optimization. The logic for extracting sub-clusters is as follows:

[0108] Specifically, step B3 includes steps B31 to B35:

[0109] Step B31: Obtain the second distance between each training feature vector in the cluster and the cluster center corresponding to the cluster;

[0110] Step B32: Arrange the multiple second distances in descending order and extract the first N second distances;

[0111] To further improve clustering accuracy, the training feature vectors of the N clusters furthest from the cluster center are obtained for subsequent fusion clustering.

[0112] Step B33: Calculate the third distance between the training feature vectors corresponding to the first N second distances respectively;

[0113] Step B34: If the third distance is greater than the threshold, then the two training feature vectors corresponding to the third distance are respectively used as the first current cluster center, and the training feature vectors in the cluster whose distance from the first current cluster center is less than the preset value are respectively used to form the sub-cluster.

[0114] Step B35: If the third distance is not greater than the threshold, then the two training feature vectors corresponding to the third distance are merged into the second current cluster center, and the training feature vectors in the cluster whose distance from the second current cluster center is less than the preset value are formed into the sub-cluster.

[0115] In this embodiment, by obtaining the second distance between each training feature vector in the cluster and the cluster center, and extracting the N feature vectors with larger distances, local outliers or boundary points in the cluster can be effectively captured. Next, calculating the third distance between these feature vectors can further reveal their inherent similarities or differences. When the third distance exceeds a threshold, two feature vectors can be considered as new cluster centers, thus forming more accurate sub-clusters. This ensures the structural rationality of the sub-clusters and effectively controls redundant information during the clustering process, making the algorithm more efficient in high-dimensional data processing.

[0116] Step B4: Calculate the first distance between the multiple sub-clusters and the multiple clusters;

[0117] Step B5: Merge the sub-cluster corresponding to the minimum first distance with the cluster to obtain a new cluster and the target cluster center corresponding to the new cluster.

[0118] Since the cluster centers of the clusters are obtained by iteratively clustering based on standard feature vectors, the distance between the cluster centers and the corresponding training feature vectors may increase after multiple clustering iterations. Therefore, it is necessary to re-match other clusters for the sub-clusters to further improve the clustering accuracy.

[0119] In this embodiment, using standard feature vectors obtained based on prior knowledge as initial cluster centers effectively utilizes existing business feature information, reduces the randomness of clustering operations, and thus improves clustering accuracy. This introduction of prior knowledge makes the initial cluster centers more representative, avoiding the instability of clustering results caused by randomly selecting initial cluster centers. Using standard feature vectors as initial cluster centers in clustering operations reduces the time it takes for the model to converge to suitable cluster centers, making the clustering process more efficient. Simultaneously, extracting sub-clusters from each cluster and optimizing them by calculating distances further simplifies the computational steps and accelerates convergence. By fusing the sub-clusters and clusters corresponding to the minimum first distance, interference from outliers or noisy data on the clustering results can be effectively avoided, thereby improving the model's robustness. Furthermore, this fusion operation helps ensure more uniform and reasonable clustering even in complex data distributions, enhancing model stability. By calculating the similarity between the current feature vector and the target cluster center, the position of the current business feature within the overall cluster can be more accurately measured. This helps to more accurately find the most similar cluster for each client's business characteristics, improving the accuracy of subsequent business decisions. In summary, this technical solution not only improves the accuracy and efficiency of clustering but also enhances the system's ability to process multi-dimensional feature data, making the clustering of business features more aligned with practical application needs.

[0120] Step A11: Combine the business tag with the data volume feature to obtain the client business characteristics.

[0121] In this embodiment, by acquiring business tags from historical data volumes and combining them with real-time and non-real-time data tags, in-depth analysis and processing of historical data volumes across multiple historical periods are performed, achieving precise matching of client business characteristics. By extracting data volumes from multiple sub-periods within a historical period, calculating the average value of each historical data volume and the time interval between adjacent sub-periods, and filtering out key data volumes exceeding a threshold, the fluctuation trend and periodic characteristics of data volumes can be effectively captured. Furthermore, by analyzing the data distribution consistency across different historical periods, a feature vector reflecting the dynamic changes in data volume is constructed. This feature vector comprehensively considers multiple data statistical indicators, such as time intervals, average data volume, historical period consistency, and the number of sub-periods, ensuring the multi-dimensional expression and completeness of data characteristics. Finally, by combining these feature vectors with business tags, this scheme can not only match data volume characteristics but also accurately identify and distinguish the business characteristics of different clients based on specific business tags. This method improves the accuracy and efficiency of data analysis.

[0122] Step 102: Obtain performance metrics for different links; the performance metrics include bandwidth, network latency, jitter, and packet loss rate;

[0123] Performance metrics include, but are not limited to, bandwidth, network latency, jitter, and packet loss rate.

[0124] Step 103: Obtain the weight set corresponding to the client service characteristics; the weight set includes multiple preset weights;

[0125] Step 104: Calculate the communication quality score corresponding to each link based on the performance indicators and the weight set;

[0126] Specifically, step 104 includes steps 1041 to 1044:

[0127] Step 1041: Obtain multiple numerical ranges for each performance metric type; different numerical ranges correspond to different type scores;

[0128] Step 1042: Match the target value range of the performance indicator and obtain the type score corresponding to the target value range;

[0129] Step 1043: Multiply the type score corresponding to each performance indicator by the weight value to obtain the result value;

[0130] Step 1044: Add the result values ​​corresponding to each of the multiple performance indicators to obtain the communication quality score.

[0131] As an optional embodiment of this application, the communication quality score can also be calculated using the following mathematical formula:

[0132] in, Indicates the communication quality score. This represents the j-th weight value. This represents the j-th performance metric. This represents the lower limit value of the j-th performance metric. This represents the upper limit of the j-th performance metric.

[0133] By converting performance parameters of different units and magnitudes to the same scale, the comparability between different performance indicators is improved, avoiding the excessive influence of certain indicators on the score due to their large magnitude. It is applicable to processing various performance indicator data, such as latency, bandwidth, and packet loss rate, ensuring that these indicators can be compared on the same scale. The formula reflects the importance of different performance indicators and data service characteristics through weights, allowing for flexible adjustment of the influence of each performance indicator and service characteristic according to actual needs, improving the accuracy and applicability of the score. In different application scenarios, such as real-time video transmission, file download, and VoIP calls, the weights can be adjusted according to specific business requirements to obtain the optimal communication link selection.

[0134] This calculation method can fully take into account the comprehensive impact of the multi-dimensional performance indicators of the communication link, and provide a more comprehensive evaluation of communication quality.

[0135] Step 105: Select the primary link and backup link from among the different links based on the communication quality score;

[0136] The first score and the second score will be used as the primary link and the backup link, respectively.

[0137] Step 106: Schedule the primary link or the backup link to transmit VPN data; the VPN data refers to data that uses a VPN for data communication.

[0138] Backup links are used to provide switching when the primary link fails, ensuring communication quality.

[0139] In this embodiment, by acquiring multiple historical data volumes from the client and matching these volumes with the client's business characteristics, the rational allocation and efficient utilization of network resources are ensured. By acquiring performance metrics for different links, including bandwidth, network latency, jitter, and packet loss rate, and combining them with a preset weight set to evaluate the communication quality of each link, the accuracy and reliability of link selection are further improved. Through intelligent selection and scheduling of primary and backup links, the system can flexibly respond to network fluctuations, ensuring efficient transmission of VPN data, thereby significantly reducing network latency and data packet loss, and improving the stability and reliability of data transmission. This scheduling method can balance the load among different links, maximizing the utilization of network resources, and has significant advantages, especially in long-distance transmission scenarios.

[0140] like Figure 2 This invention provides a scheduling device based on LTE long-distance private network transmission. Please refer to [link / reference]. Figure 2 , Figure 2 A schematic diagram of a scheduling device based on LTE long-distance private network transmission provided by the present invention is shown, as follows: Figure 2 The scheduling device shown includes: LTE long-distance private network transmission.

[0141] The first acquisition unit 21 is used to acquire multiple historical data volumes from the client and match client business characteristics based on the multiple historical data volumes; each historical data volume refers to the data volume within a historical sub-period, and the historical period includes multiple historical sub-periods, the multiple historical data volumes including the data volumes corresponding to multiple historical periods; the client business characteristics include real-time regular peak, real-time regular sparse peak, real-time irregular sparse peak, real-time regular dense peak, real-time irregular dense peak, non-real-time regular peak, non-real-time regular sparse peak, non-real-time irregular sparse peak, non-real-time regular dense peak, non-real-time irregular dense peak, and no data state;

[0142] The second acquisition unit 22 is used to acquire performance indicators of different links; the performance indicators include bandwidth, network latency, jitter and packet loss rate;

[0143] The third acquisition unit 23 is used to acquire a weight set corresponding to the client service characteristics; the weight set includes multiple preset weights.

[0144] The calculation unit 24 is used to calculate the communication quality score corresponding to each link based on the performance index and the weight set.

[0145] Selection unit 25 is used to select a primary link and a backup link among different links based on the communication quality score;

[0146] The communication unit 26 is used to schedule the transmission of virtual private network (VPN) data via the main link or the backup link; the VPN data refers to data that uses a VPN for data communication.

[0147] This invention provides a scheduling device for long-distance private network transmission based on LTE. By acquiring multiple historical data volumes from clients and matching these historical data volumes with the clients' service characteristics, it ensures the rational allocation and efficient utilization of network resources. By acquiring performance indicators of different links, including bandwidth, network latency, jitter, and packet loss rate, and combining them with a preset weight set to evaluate the communication quality of each link, it further improves the accuracy and reliability of link selection. Through intelligent selection and scheduling of primary and backup links, the system can flexibly respond to network fluctuations, ensuring efficient transmission of VPN data, thereby significantly reducing network latency and data packet loss, and improving the stability and reliability of data transmission. This scheduling method can balance the load among different links, maximizing the utilization of network resources, and has significant advantages, especially in long-distance transmission scenarios.

[0148] Figure 3 This is a schematic diagram of a terminal device provided in an embodiment of the present invention. Figure 3As shown, a terminal device 3 in this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30, such as a scheduling program for long-distance private network transmission based on LTE. When the processor 30 executes the computer program 32, it implements the steps in the various embodiments of the scheduling method for long-distance private network transmission based on LTE described above, for example... Figure 1 Steps 101 to 105 are shown. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each unit in the above-described device embodiments, for example... Figure 2 The function of the unit shown.

[0149] For example, the computer program 32 can be divided into one or more units, which are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 32 in the terminal device 3. For example, the specific functions of each unit of the computer program 32 can be divided as follows:

[0150] The first acquisition unit is used to acquire multiple historical data volumes from the client and match client business characteristics based on the multiple historical data volumes; each historical data volume refers to the data volume within a historical sub-period, and the historical period includes multiple historical sub-periods, the multiple historical data volumes including the data volumes corresponding to multiple historical periods; the client business characteristics include real-time regular peak, real-time regular sparse peak, real-time irregular sparse peak, real-time regular dense peak, real-time irregular dense peak, non-real-time regular peak, non-real-time regular sparse peak, non-real-time irregular sparse peak, non-real-time regular dense peak, non-real-time irregular dense peak, and no data state;

[0151] The second acquisition unit is used to acquire performance indicators of different links; the performance indicators include bandwidth, network latency, jitter and packet loss rate.

[0152] The third acquisition unit is used to acquire a weight set corresponding to the client service characteristics; the weight set includes multiple preset weights.

[0153] The calculation unit is used to calculate the communication quality score corresponding to each link based on the performance index and the weight set.

[0154] The selection unit is used to select a primary link and a backup link from different links based on the communication quality score.

[0155] A communication unit is used to schedule the transmission of VPN data via the main link or the backup link; the VPN data volume refers to the data used for data communication via VPN.

[0156] The terminal device includes, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of a terminal device 3 and does not constitute a limitation on a terminal device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input / output devices, network access devices, buses, etc.

[0157] The processor 30 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0158] The memory 31 can be an internal storage unit of the terminal device 3, such as a hard disk or memory of the terminal device 3. The memory 31 can also be an external storage device of the terminal device 3, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the terminal device 3. Furthermore, the memory 31 can include both internal and external storage units of the terminal device 3. The memory 31 is used to store the computer program and other programs and data required by the roaming control device. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0159] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0160] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0161] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this invention. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0162] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0163] This invention provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.

[0164] If the integrated unit 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, all or part of the processes in the methods of the above embodiments of the present invention can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0165] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0166] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0167] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and 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 through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0168] 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; they may be located in one place or distributed across multiple network units.

[0169] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0170] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0171] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once [the described condition or event] is detected," or "in response to detection of [the described condition or event]."

[0172] Furthermore, in the description of this invention and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0173] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of the invention include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0174] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A scheduling method based on LTE long-distance private network transmission, characterized in that, The scheduling method based on LTE long-distance private network transmission includes: The system acquires multiple historical data volumes from the client and matches client business characteristics based on these volumes. Each historical data volume refers to the data volume within a historical sub-period, and the historical period includes multiple historical sub-periods. The multiple historical data volumes include the data volumes corresponding to multiple historical periods. The client business characteristics include real-time regular peaks, real-time regular sparse peaks, real-time irregular sparse peaks, real-time regular dense peaks, real-time irregular dense peaks, non-real-time regular peaks, non-real-time regular sparse peaks, non-real-time irregular sparse peaks, non-real-time regular dense peaks, non-real-time irregular dense peaks, and a no-data state. Obtain performance metrics for different links; these performance metrics include bandwidth, network latency, jitter, and packet loss rate. Obtain the weight set corresponding to the client service characteristics; the weight set includes multiple preset weights; Based on the performance metrics and the weight set, calculate the communication quality score corresponding to each link; Based on the communication quality score, a primary link and a backup link are selected from different links; The primary link or the backup link is scheduled to transmit VPN data; the VPN data refers to data used for data communication via a VPN. The step of obtaining multiple historical data volumes from the client and matching client business characteristics based on the multiple historical data volumes includes: Obtain the business tags for the historical data volume; the business tags include real-time data tags and non-real-time data tags; Extract the first historical data volume corresponding to multiple first historical sub-periods in the first historical period; Calculate a first average among multiple first historical data volumes; Extract the first historical sub-period corresponding to the first historical data volume that exceeds the threshold; Calculate the first time interval between adjacent first historical sub-cycles; Extract the second historical data volume corresponding to multiple previous historical sub-cycles in the previous historical cycle; the previous historical cycle refers to the historical cycle that is preceding and adjacent to the first historical cycle; Extract the second historical sub-period corresponding to the second historical data volume that exceeds the threshold; Based on the distribution characteristics of multiple first historical sub-cycles and multiple second historical sub-cycles, the degree of agreement of data volume distribution between historical cycles is calculated. The current feature vector is constructed based on multiple first time intervals, the first average value, the degree of agreement, and the number of first historical sub-cycles. Based on the current feature vector, match the data volume feature; The client service characteristics are obtained by combining the business tag with the data volume feature.

2. The scheduling method based on LTE long-distance private network transmission as described in claim 1, characterized in that, The step of calculating the degree of agreement of data volume distribution between historical periods based on the distribution characteristics of multiple first historical sub-periods and multiple second historical sub-periods includes: Match the target historical sub-period that is closest to the second historical sub-period among multiple first historical sub-periods; Calculate the second time interval between the target historical sub-period and the corresponding second historical sub-period; Calculate the variance of the second time interval corresponding to each of the multiple second historical sub-cycles; The variance is used as the degree of fit.

3. The scheduling method based on LTE long-distance private network transmission as described in claim 1, characterized in that, The step of matching data volume features based on the current feature vector includes: Obtain the pre-trained target cluster centers, and calculate the similarity between the target cluster centers and the current feature vector; Extract the target cluster center corresponding to the maximum similarity, and use the standard features corresponding to the target cluster center corresponding to the maximum similarity as the data volume features.

4. The scheduling method based on LTE long-distance private network transmission as described in claim 3, characterized in that, Before the steps of obtaining the pre-trained target cluster centers and calculating the similarity between the target cluster centers and the current feature vector, the method further includes: Obtain standard feature vectors corresponding to multiple client business features; the standard feature vectors are obtained based on prior knowledge; Multiple training feature vectors are obtained, and the multiple standard feature vectors are used as initial cluster centers for clustering operations to obtain multiple clusters and their corresponding current cluster centers; Extract sub-clusters from each cluster; Calculate the first distance between multiple sub-clusters and multiple clusters; The sub-cluster corresponding to the minimum first distance is merged with the cluster to obtain a new cluster and the target cluster center corresponding to the new cluster.

5. The scheduling method based on LTE long-distance private network transmission as described in claim 4, characterized in that, The step of extracting sub-clusters from each cluster includes: Obtain the second distance between each training feature vector in the cluster and the cluster center corresponding to the cluster; Arrange the multiple second distances in descending order and extract the first N second distances; Calculate the third distance between the training feature vectors corresponding to the first N second distances respectively; If the third distance is greater than the threshold, then the two training feature vectors corresponding to the third distance are respectively used as the first current cluster center, and the training feature vectors in the cluster whose distance from the first current cluster center is less than the preset value are respectively used to form the sub-cluster. If the third distance is not greater than the threshold, the two training feature vectors corresponding to the third distance are merged into the second current cluster center, and the training feature vectors in the cluster whose distance from the second current cluster center is less than the preset value are formed into the sub-cluster.

6. The scheduling method based on LTE long-distance private network transmission as described in claim 1, characterized in that, The step of calculating the communication quality score corresponding to each link based on the performance index and the weight set includes: Obtain multiple numerical ranges for each performance metric type; different numerical ranges correspond to different type scores. Match the performance metric to the target value range and obtain the type score corresponding to the target value range; Multiply the type score corresponding to each performance indicator by its weight value to obtain the result value; The communication quality score is obtained by summing the results corresponding to each of the multiple performance indicators.

7. A scheduling device based on LTE long-distance private network transmission, characterized in that, The scheduling device based on LTE long-distance private network transmission includes: The first acquisition unit is used to acquire multiple historical data volumes from the client and match client business characteristics based on the multiple historical data volumes; each historical data volume refers to the data volume within a historical sub-period, and the historical period includes multiple historical sub-periods, the multiple historical data volumes including the data volumes corresponding to multiple historical periods; the client business characteristics include real-time regular peak, real-time regular sparse peak, real-time irregular sparse peak, real-time regular dense peak, real-time irregular dense peak, non-real-time regular peak, non-real-time regular sparse peak, non-real-time irregular sparse peak, non-real-time regular dense peak, non-real-time irregular dense peak, and no data state; The second acquisition unit is used to acquire performance indicators of different links; the performance indicators include bandwidth, network latency, jitter and packet loss rate. The third acquisition unit is used to acquire a weight set corresponding to the client service characteristics; the weight set includes multiple preset weights. The calculation unit is used to calculate the communication quality score corresponding to each link based on the performance index and the weight set. The selection unit is used to select a primary link and a backup link from different links based on the communication quality score. A communication unit is used to schedule the transmission of VPN data via the primary link or the backup link; the VPN data refers to data communication using a VPN. The step of obtaining multiple historical data volumes from the client and matching client business characteristics based on the multiple historical data volumes includes: Obtain the business tags for the historical data volume; the business tags include real-time data tags and non-real-time data tags; Extract the first historical data volume corresponding to multiple first historical sub-periods in the first historical period; Calculate a first average among multiple first historical data volumes; Extract the first historical sub-period corresponding to the first historical data volume that exceeds the threshold; Calculate the first time interval between adjacent first historical sub-cycles; Extract the second historical data volume corresponding to multiple previous historical sub-cycles in the previous historical cycle; the previous historical cycle refers to the historical cycle that is preceding and adjacent to the first historical cycle; Extract the second historical sub-period corresponding to the second historical data volume that exceeds the threshold; Based on the distribution characteristics of multiple first historical sub-cycles and multiple second historical sub-cycles, the degree of agreement of data volume distribution between historical cycles is calculated. The current feature vector is constructed based on multiple first time intervals, the first average value, the degree of agreement, and the number of first historical sub-cycles. Based on the current feature vector, match the data volume feature; The client service characteristics are obtained by combining the business tag with the data volume feature.

8. A terminal device, characterized in that, The terminal device includes: a memory, a processor, and a scheduler for LTE long-distance private network transmission stored in the memory and executable on the processor, wherein the scheduler for LTE long-distance private network transmission is configured to implement the steps of the scheduling method for LTE long-distance private network transmission as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps in the scheduling method based on LTE long-distance private network transmission as described in any one of claims 1 to 6.

Images