A short message intelligent scheduling system and method based on 5G network slicing

Abstract

The present application belongs to the technical field of short message service intelligent scheduling, and specifically relates to a short message intelligent scheduling system and method based on 5G network slicing. The present application effectively improves the short message service processing efficiency under the 5G network slicing environment through accurate prediction and intelligent scheduling of short message service traffic. Through smooth processing and exponential weighted moving average processing of the traffic change rate time series, the change trend of short message service traffic can be accurately captured, providing reliable data support for subsequent scheduling decisions. At the same time, through confidence evaluation and resource utilization evaluation, the predicted demand and resource utilization of short message service traffic can be comprehensively considered to ensure the rationality and effectiveness of scheduling. In addition, the intelligent scheduling mechanism of the present application can automatically adjust resource allocation according to scheduling priority to meet the sending demand of high-priority short message services, further improving the processing speed and user experience of short message services.

Description

Technical Field

[0001] This invention belongs to the field of intelligent SMS service scheduling technology, specifically relating to an intelligent SMS scheduling system and method based on 5G network slicing. Background Technology

[0002] With the rapid development of 5G communication technology, SMS services, as an important component of mobile communication networks, face higher requirements for transmission efficiency and service quality. Traditional SMS scheduling methods are often based on static resource allocation, which is difficult to adapt to dynamically changing network environments and user needs. Therefore, how to achieve intelligent scheduling of SMS services has become an urgent problem to be solved in the current field of SMS service scheduling. At present, with the rise of 5G network slicing technology, this technology can divide the physical network into multiple virtual network slices to provide customized network resources and services for different types of services, which provides a new solution for intelligent scheduling of SMS services.

[0003] While some SMS scheduling solutions based on 5G network slicing technology have been proposed in the existing technology, some problems still exist. For example, some solutions simply allocate resources based on the size of SMS traffic, ignoring the differences in network resource requirements for different SMS service types, resulting in low resource utilization. Other solutions, although considering the differences in SMS service types, lack flexibility in resource scheduling and are unable to cope with sudden SMS traffic peaks. In addition, existing solutions often rely on manual experience or fixed algorithm models in SMS traffic prediction and scheduling decision-making, lacking intelligent adaptive capabilities and failing to reflect changes in the network environment and user needs in real time and accurately. Therefore, this invention proposes an intelligent SMS scheduling method based on 5G network slicing to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide a smart SMS scheduling system and method based on 5G network slicing, which can dynamically adjust the resource allocation of SMS service network slices according to the real-time network environment and user needs, thereby improving resource utilization and SMS service transmission efficiency.

[0005] The specific technical solution adopted by this invention is as follows:

[0006] A method for intelligent SMS scheduling based on 5G network slicing includes:

[0007] Create various types of SMS service network slices, including low-latency slices, guaranteed slices, and elastic resource slices;

[0008] Real-time monitoring of network slice load information for various types of SMS services, and prediction of expected SMS traffic demand for future periods based on load information;

[0009] Confidence assessment of the projected SMS traffic demand for network slices of various types of SMS services is conducted to determine the first scheduling condition parameters for each SMS service network slice in the future time period.

[0010] Collect the resource utilization rate of network slices for various types of SMS services, and determine the second scheduling condition parameters for each SMS service network slice in the future time period based on the resource utilization rate and the preset resource threshold.

[0011] The scheduling priority of each SMS service network slice is determined by merging the first scheduling condition parameter and the second scheduling condition parameter, and then intelligent scheduling is performed on each type of SMS service network slice according to the scheduling priority.

[0012] In a preferred embodiment, a preemption level matrix is ​​set among the low-latency slices, the guaranteed slices, and the elastic resource slices, wherein the level of the low-latency slices is higher than that of the guaranteed slices, and the level of the guaranteed slices is higher than that of the elastic resource slices.

[0013] When low-latency slices encounter high loads or urgent needs, they can prioritize the use of resources from guaranteed slices and elastic resource slices. When faced with urgent business needs, guaranteed slices can preempt the resources of elastic resource slices.

[0014] In a preferred embodiment, the step of predicting the expected SMS traffic demand for future periods based on load information includes:

[0015] Collect historical load data of network slices for various types of SMS services and summarize them into a slice time-series database containing timestamps, service types, and peak traffic;

[0016] Establish a sliding window and perform time series analysis on historical load data within the sliding window to identify the periodic and non-periodic trends of historical load data;

[0017] Under cyclical trends, the expected demand for SMS traffic in future periods can be predicted directly based on these cyclical trends.

[0018] Under non-periodic trends, historical load data is non-linearly fitted to obtain the SMS traffic adjustment value for future periods. The baseline value of SMS traffic is then superimposed with the adjusted value to obtain the expected demand for SMS traffic in future periods.

[0019] In a preferred embodiment, the step of performing nonlinear fitting on historical load data to obtain SMS service traffic adjustment values ​​for future time periods includes:

[0020] Multiple tracking periods are set within a sliding window, and the rate of change in SMS traffic between adjacent tracking periods is calculated.

[0021] A time series of traffic change rate is established based on the traffic change rate of SMS services, and the time series of traffic change rate is smoothed to remove abnormal fluctuation points;

[0022] An exponentially weighted moving average is applied to the smoothed traffic change rate time series to obtain the predicted SMS traffic adjustment trend for the future period. Then, based on the SMS traffic adjustment trend, the SMS traffic adjustment value for the future period is calculated.

[0023] In a preferred embodiment, the step of assessing the confidence level of the projected SMS traffic demand for each type of SMS service network slice and determining the first scheduling condition parameters for each SMS service network slice in the future time period includes:

[0024] Obtain the historical prediction deviation rate of the expected demand for SMS traffic and record it as the first evaluation feature parameter;

[0025] Collect the fluctuation coefficient of SMS traffic within the current sliding window and record it as the second evaluation feature parameter;

[0026] Obtain the confidence evaluation function, and input the first evaluation feature parameter and the second evaluation feature parameter into the confidence evaluation function together, output the confidence evaluation value of each SMS service network slice in the future time period, and record it as the first scheduling condition parameter;

[0027] After the first scheduling condition parameter is output, a rationality check is immediately performed to determine whether the first scheduling condition parameter is within the preset confidence threshold range.

[0028] If the value exceeds the range, it indicates that the rationality check has failed and the confidence level of the expected SMS traffic demand needs to be reassessed. Conversely, if the value is within the range, it indicates that the rationality check has succeeded and the corresponding first scheduling condition parameter is retained.

[0029] In a preferred embodiment, the step of determining the second scheduling condition parameters for each SMS service network slice in a future time period based on resource utilization and a preset resource threshold includes:

[0030] Obtain resource utilization metrics for various types of SMS network slices within the current sliding window, including CPU utilization, bandwidth utilization, and storage resource utilization.

[0031] The resource utilization rate index is compared with the resources of the corresponding preset type slice to calculate the difference, and a resource saturation coefficient matrix is ​​generated.

[0032] The resource saturation coefficient matrix is ​​normalized, and the elements in the normalized resource saturation coefficient matrix are used as the second scheduling condition parameters.

[0033] Among them, the lower the resource saturation coefficient, the higher the resource redundancy of the corresponding SMS service network slice.

[0034] In a preferred embodiment, the step of performing a fusion calculation on the first scheduling condition parameter and the second scheduling condition parameter to determine the scheduling priority of each SMS service network slice includes:

[0035] Obtain the first scheduling condition parameter and the second scheduling condition parameter, and assign initial weight coefficients to the first scheduling condition parameter and the second scheduling condition parameter;

[0036] The initial weight coefficients of the first scheduling condition parameters are dynamically corrected based on the historical prediction deviation rate, and the corrected weight coefficients are output.

[0037] The initial weight coefficient of the second scheduling condition parameter is dynamically adjusted based on the resource saturation coefficient, and the adjusted weight coefficient is output.

[0038] The first and second corrected weight coefficients are weighted and summed with the corresponding first and second scheduling condition parameters to obtain the comprehensive scheduling evaluation value of each SMS service network slice.

[0039] Based on the comprehensive scheduling evaluation value, each SMS service network slice is ranked, with the SMS service network slice having a higher comprehensive scheduling evaluation value and a higher scheduling priority.

[0040] In a preferred embodiment, the step of intelligently scheduling network slices for various types of SMS services according to scheduling priority includes:

[0041] When the scheduling priority of the SMS service network slice changes, the intelligent scheduling mechanism is automatically triggered.

[0042] Check the current usage of network slice resources to determine if there are any idle or releaseable resources that meet scheduling requirements;

[0043] If there are idle or releaseable resources, the required resources will be allocated to each SMS service network slice in descending order of scheduling priority.

[0044] If the current network slice resources cannot meet the scheduling needs of all SMS service network slices, the resources occupied by low-priority slices will be automatically adjusted according to the preemption level matrix to meet the sending needs of high-priority SMS services.

[0045] The present invention also provides a 5G network slicing-based intelligent SMS scheduling system, which uses the above-mentioned 5G network slicing-based intelligent SMS scheduling method, including:

[0046] The slice construction module is used to create various types of SMS service network slices, including low-latency slices, guaranteed slices, and elastic resource slices.

[0047] The prediction module is used to monitor the load information of network slices for various types of SMS services in real time, and predict the expected demand for SMS service traffic in future periods based on the load information.

[0048] The confidence assessment module is used to assess the confidence of the expected demand for SMS traffic in network slices of various types of SMS services and determine the first scheduling condition parameters for each SMS service network slice in the future time period.

[0049] The resource utilization assessment module is used to collect the resource utilization rate of network slices for various types of SMS services, and determine the second scheduling condition parameters of each SMS service network slice in the future time period based on the resource utilization rate and the preset resource threshold.

[0050] The intelligent scheduling module is used to perform fusion calculations on the first scheduling condition parameter and the second scheduling condition parameter to determine the scheduling priority of each SMS service network slice, and then perform intelligent scheduling on each type of SMS service network slice according to the scheduling priority.

[0051] And, an electronic device, the electronic device comprising:

[0052] At least one processor;

[0053] and a memory communicatively connected to the at least one processor;

[0054] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the above-described intelligent SMS scheduling method based on 5G network slicing.

[0055] The technical effects achieved by this invention are as follows:

[0056] This invention effectively improves the processing efficiency of SMS services in 5G network slicing environments through accurate prediction and intelligent scheduling of SMS traffic. By smoothing the time series of traffic change rates and using exponentially weighted moving averages, it accurately captures the changing trends of SMS traffic, providing reliable data support for subsequent scheduling decisions. Furthermore, through confidence level assessment and resource utilization assessment, it comprehensively considers the expected demand for SMS traffic and resource utilization, ensuring the rationality and effectiveness of scheduling. In addition, the intelligent scheduling mechanism of this invention can automatically adjust resource allocation according to scheduling priorities, meeting the sending needs of high-priority SMS services, further improving the processing speed and user experience of SMS services. Attached Figure Description

[0057] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0058] Figure 2 This is a schematic diagram of the system modules of the present invention;

[0059] Figure 3 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0060] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0061] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0063] Please see Figure 1 As shown, this invention provides a method for intelligent SMS scheduling based on 5G network slicing, including:

[0064] S1. Create various types of SMS service network slices, including low-latency slices, guaranteed slices, and elastic resource slices.

[0065] In step S1, within the 5G network where SMS sending tasks need to be performed, corresponding SMS service network slices are constructed based on different types of SMS service requirements. These SMS service network slices encompass various types, including low-latency slices, guaranteed slices, and elastic resource slices. Multiple slices of each type are configured to achieve precise resource allocation and scheduling for SMS services of different priorities and types. Low-latency slices primarily serve SMS services with extremely high latency requirements, such as financial transaction SMS notifications and emergency security alerts. Guaranteed slices primarily serve SMS services that require guaranteed delivery, such as verification code SMS messages. Important notification SMS messages, etc., are handled by elastic resource slices, which can dynamically adjust resources according to the traffic fluctuations of SMS services to cope with sudden high traffic SMS sending demands. Among them, a preemption level matrix is ​​set between low-latency slices, guaranteed slices, and elastic resource slices. The level of low-latency slices is higher than that of guaranteed slices, and the level of guaranteed slices is higher than that of elastic resource slices. When low-latency slices encounter high load or urgent needs, they can take priority to use the resources of guaranteed slices and elastic resource slices. When facing urgent business needs, guaranteed slices can preempt the resources of elastic resource slices to ensure the timely delivery of critical SMS services.

[0066] S2. Monitor the load information of network slices for various types of SMS services in real time, and predict the expected demand for SMS traffic in future periods based on the load information.

[0067] In step S2, after the SMS service network slice is constructed, the load information of various SMS service network slices is monitored in real time. By collecting and analyzing the load data of the SMS service network slices, the expected demand for SMS service traffic in the future period is predicted, thereby providing data support for subsequent scheduling. The future period is generally taken as 15 minutes to 1 hour in the future, and the specific time length can be adjusted according to actual needs and network conditions to ensure the accuracy and practicality of the prediction results. The step of predicting the expected demand for SMS service traffic in the future period based on load information includes:

[0068] Collect historical load data of network slices for various types of SMS services and summarize them into a slice time-series database containing timestamps, service types, and peak traffic;

[0069] Establish a sliding window and perform time series analysis on historical load data within the sliding window to identify the periodic and non-periodic trends of historical load data;

[0070] Under cyclical trends, the expected demand for SMS traffic in future periods can be predicted directly based on these cyclical trends.

[0071] Under non-periodic trends, historical load data is non-linearly fitted to obtain the SMS traffic adjustment value for future periods. The baseline value of SMS traffic is superimposed with the adjusted value to obtain the expected demand for SMS traffic in future periods.

[0072] Specifically, when predicting the expected SMS traffic demand for future periods based on load information, the first step is to comprehensively collect historical load data from various SMS network slices. This collected historical load data is then aggregated into a slice time-series database containing key information such as timestamps, service types, and peak traffic, ensuring data integrity and accuracy. Next, a sliding window size and step size are preset, and in-depth time-series analysis is performed on the collected historical load data within the sliding window to identify periodic and non-periodic trends. If a periodic trend is identified, the expected SMS traffic demand for future periods can be predicted directly based on this trend. If a non-periodic trend is identified, a more complex non-linear fitting process is required on the historical load data. Based on this process, an adjusted value for SMS traffic in the future period is obtained, and this adjusted value is then superimposed on the baseline value of SMS traffic. In the formula, This indicates the projected demand for SMS traffic. This represents the baseline traffic forecast (obtained based on cyclical trends), ultimately leading to the projected demand for SMS traffic in the future period, ensuring the comprehensiveness and accuracy of the forecast results.

[0073] It should be noted that the steps for performing non-linear fitting on historical load data to obtain adjusted SMS traffic values ​​for future periods include:

[0074] Multiple tracking periods are set within a sliding window, and the rate of change in SMS traffic between adjacent tracking periods is calculated.

[0075] A time series of traffic change rate is established based on the traffic change rate of SMS services, and the time series of traffic change rate is smoothed to remove abnormal fluctuation points;

[0076] The smoothed traffic change rate time series is subjected to exponential weighted moving average processing to obtain the predicted SMS traffic adjustment trend in the future period. Then, based on the SMS traffic adjustment trend, the SMS traffic adjustment value in the future period is calculated.

[0077] In this embodiment, firstly, multiple consecutive tracking periods are set within a sliding window, and SMS traffic within these periods is monitored and recorded. Based on this, the rate of change of SMS traffic between adjacent tracking periods is calculated to capture the dynamic changes in SMS traffic. Then, a time series of traffic change rates is constructed based on the obtained rates. To ensure data stability and reliability, this time series is smoothed to effectively remove abnormal fluctuations, resulting in a smoother time series that reflects the true trend. Next, an exponentially weighted moving average is applied to the smoothed time series, giving higher weight to recent data to make the prediction result closer to the current trend, thus obtaining the predicted future SMS traffic adjustment trend. Finally, based on the predicted SMS traffic adjustment trend, combined with specific business needs and historical data, the adjustment value of SMS traffic in the future period is calculated. In the formula, Indicates future time period SMS service traffic adjustment value, This represents the attenuation factor, with a value of 0 < <1, (This represents the rate of change in traffic). Based on the baseline value of SMS traffic, the expected demand for SMS traffic in the future period can be obtained.

[0078] S3. Assess the confidence level of the expected SMS traffic demand for each type of SMS service network slice and determine the first scheduling condition parameters for each SMS service network slice in the future time period.

[0079] In step S3, after obtaining the projected SMS traffic demand for the future time period, to ensure the rationality and accuracy of the scheduling decision, a confidence assessment is performed on the projected SMS traffic demand for various types of SMS network slices. A scientific method is used to determine the first scheduling condition parameters for each SMS network slice in the future time period. The steps of performing a confidence assessment on the projected SMS traffic demand for each type of SMS network slice and determining the first scheduling condition parameters for each SMS network slice in the future time period include:

[0080] Obtain the historical prediction deviation rate of the expected demand for SMS traffic and record it as the first evaluation feature parameter;

[0081] Collect the fluctuation coefficient of SMS traffic within the current sliding window and record it as the second evaluation feature parameter;

[0082] Obtain the confidence evaluation function, and input the first evaluation feature parameter and the second evaluation feature parameter into the confidence evaluation function together, output the confidence evaluation value of each SMS service network slice in the future time period, and record it as the first scheduling condition parameter;

[0083] After the first scheduling condition parameter is output, a rationality check is immediately performed to determine whether the first scheduling condition parameter is within the preset confidence threshold range.

[0084] If the value is outside the range, it indicates that the rationality check has failed and the confidence level of the expected SMS traffic demand needs to be reassessed. Otherwise, it indicates that the rationality check has succeeded and the corresponding first scheduling condition parameter is retained.

[0085] Specifically, when performing a confidence assessment of the projected demand for SMS traffic, the historical prediction deviation rate data of the projected demand for SMS traffic is first obtained and recorded as the first evaluation feature parameter for subsequent analysis. Then, within the currently set sliding window range, the fluctuation coefficient of SMS traffic is collected (fluctuation coefficient = (maximum SMS traffic value in the current period - minimum SMS traffic value in the current period) / average SMS traffic value in the current period) and this fluctuation coefficient data is accurately recorded as the second evaluation feature parameter, providing preliminary data reference for the confidence assessment. Next, a confidence assessment function suitable for this scenario is obtained, and the previously recorded first and second evaluation feature parameters are input into the confidence assessment function. The confidence assessment function calculates and outputs the confidence assessment value of each SMS network slice in the future period, and this confidence assessment value is recorded as the first scheduling condition parameter. The expression of the confidence assessment function is:

[0086] ;

[0087] In the formula, Indicates the first Confidence assessment value of network slice for SMS-like services (first scheduling condition parameter). Indicates the first Historical prediction bias rate of network slicing for SMS-like services (first evaluation characteristic parameter). Indicates the first Fluctuation coefficient of network slicing for SMS-like services (second evaluation characteristic parameter);

[0088] It is particularly important to note that after the first scheduling condition parameter is output, a reasonableness check will be performed immediately to determine whether the first scheduling condition parameter is within the preset confidence threshold range. If the first scheduling condition parameter exceeds the preset confidence threshold range, it indicates that the reasonableness check has failed. In this case, the confidence of the expected demand for SMS traffic needs to be reassessed to ensure the accuracy of the assessment results. Conversely, if the first scheduling condition parameter is within the preset confidence threshold range, it indicates that the reasonableness check has succeeded, and the corresponding first scheduling condition parameter can be retained as a prerequisite for subsequent scheduling decisions.

[0089] S4. Collect the resource utilization rate of network slices for various types of SMS services, and determine the second scheduling condition parameters for each SMS service network slice in the future time period based on the resource utilization rate and the preset resource threshold.

[0090] In step S4, after the first adjustment condition parameter is output, it is also necessary to collect resource utilization data of various SMS service network slices, and combine it with preset resource thresholds to comprehensively determine the second scheduling condition parameters of each SMS service network slice in the future time period, so as to ensure reasonable allocation and efficient utilization of resources. The step of determining the second scheduling condition parameters of each SMS service network slice in the future time period based on resource utilization and preset resource thresholds includes:

[0091] Obtain resource utilization metrics for various types of SMS network slices within the current sliding window, including CPU utilization, bandwidth utilization, and storage resource utilization.

[0092] The resource utilization rate index is compared with the resources of the corresponding preset type slice to calculate the difference, and a resource saturation coefficient matrix is ​​generated.

[0093] The resource saturation coefficient matrix is ​​normalized, and the elements in the normalized resource saturation coefficient matrix are used as the second scheduling condition parameters.

[0094] Among them, the lower the resource saturation coefficient, the higher the resource redundancy of the corresponding SMS service network slice;

[0095] Specifically, the process first obtains resource utilization metrics for each type of SMS network slice within the current sliding window. These metrics encompass multiple aspects, including CPU utilization, bandwidth utilization, and storage resource utilization, to ensure a comprehensive assessment of resource usage. Then, the difference between the obtained resource utilization metrics and preset resource thresholds for the corresponding slice type is calculated. Based on this process, a resource saturation coefficient matrix is ​​generated. This matrix directly reflects the resource scarcity of each slice. Next, the generated resource saturation coefficient matrix is ​​normalized. Normalization methods can include min-max normalization or Z-score normalization to ensure that all element values ​​are on the same order of magnitude. Finally, each element in the normalized resource saturation coefficient matrix is ​​used as a second scheduling condition parameter for subsequent scheduling decisions. It's important to note that a lower resource saturation coefficient indicates higher resource redundancy for the corresponding SMS service network slice, while a higher coefficient indicates resource scarcity, requiring priority scheduling optimization.

[0096] S5. Perform fusion calculation on the first scheduling condition parameter and the second scheduling condition parameter to determine the scheduling priority of each SMS service network slice, and then perform intelligent scheduling on each type of SMS service network slice according to the scheduling priority.

[0097] In step S5, after both the first scheduling condition parameter and the second scheduling condition parameter are output, the first scheduling condition parameter and the second scheduling condition parameter are fused and calculated. After comprehensive evaluation, the scheduling priority of each SMS service network slice is determined. Then, intelligent scheduling is performed on each type of SMS service network slice according to these scheduling priorities, thereby achieving optimized management and efficient operation of SMS services. The step of fusing and calculating the first scheduling condition parameter and the second scheduling condition parameter to determine the scheduling priority of each SMS service network slice includes:

[0098] Obtain the first scheduling condition parameter and the second scheduling condition parameter, and assign initial weight coefficients to the first scheduling condition parameter and the second scheduling condition parameter;

[0099] The initial weight coefficients of the first scheduling condition parameters are dynamically corrected based on the historical prediction deviation rate, and the corrected weight coefficients are output.

[0100] The initial weight coefficient of the second scheduling condition parameter is dynamically adjusted based on the resource saturation coefficient, and the adjusted weight coefficient is output.

[0101] The first and second corrected weight coefficients are weighted and summed with the corresponding first and second scheduling condition parameters to obtain the comprehensive scheduling evaluation value of each SMS service network slice.

[0102] Based on the comprehensive scheduling evaluation value, each SMS service network slice is sorted. Among them, the SMS service network slice with the higher comprehensive scheduling evaluation value has the higher scheduling priority.

[0103] Specifically, when performing the fusion calculation of the first scheduling condition parameter and the second scheduling condition parameter, firstly, the first scheduling condition parameter and the second scheduling condition parameter are obtained, and initial weight coefficients are assigned to the first scheduling condition parameter and the second scheduling condition parameter respectively. At the same time, the initial weight coefficient of the first scheduling condition parameter is dynamically corrected according to the historical prediction deviation rate. Specifically, by analyzing the prediction deviation in historical data, the weight of the first scheduling condition parameter is adjusted to better reflect the actual situation, and the corrected weight coefficient is output as the first corrected weight coefficient. In the formula, This represents the first corrected weighting coefficient. This represents the initial weight coefficient of the first scheduling condition parameter. (This represents the historical prediction deviation attenuation factor). The higher the historical prediction deviation rate, the more significant the corresponding weight attenuation, and the lower its corresponding first corrected weight coefficient, and vice versa. Then, the initial weight coefficient of the second scheduling condition parameter is dynamically corrected according to the resource saturation coefficient. The resource saturation coefficient reflects the current utilization of network resources. By adjusting the resource saturation coefficient, the weights of the second scheduling condition parameter can be made more reasonable, and the weight coefficient after this process is output as the second corrected weight coefficient. In the formula, This represents the second corrected weighting coefficient. This represents the initial weighting coefficient of the second scheduling condition parameter. Indicates the first Network slicing for SMS-like services in the first The normalized resource saturation coefficient of resource-type suppliers. (This represents a smoothing coefficient to prevent the denominator from being 0). Then, the first and second corrected weighting coefficients are weighted and summed with the corresponding first and second scheduling condition parameters, respectively, to obtain the comprehensive scheduling evaluation value of each SMS service network slice. Finally, the SMS service network slices are sorted according to the magnitude of the comprehensive scheduling evaluation value. Specifically, the SMS service network slice with the higher the comprehensive scheduling evaluation value, the higher its corresponding scheduling priority. This sorting method ensures that SMS services with higher comprehensive evaluation values ​​are processed first, thereby optimizing the overall resource scheduling efficiency.

[0104] Secondly, the steps for intelligent scheduling of network slices for various types of SMS services based on scheduling priorities include:

[0105] When the scheduling priority of the SMS service network slice changes, the intelligent scheduling mechanism is automatically triggered.

[0106] Check the current usage of network slice resources to determine if there are any idle or releaseable resources that meet scheduling requirements;

[0107] If there are idle or releaseable resources, the required resources will be allocated to each SMS service network slice in descending order of scheduling priority.

[0108] If the current network slice resources cannot meet the scheduling needs of all SMS service network slices, the resources occupied by low-priority slices will be automatically adjusted according to the preemption level matrix to meet the sending needs of high-priority SMS services.

[0109] In this implementation, when the scheduling priority of the SMS service network slice changes, an intelligent scheduling mechanism will be automatically triggered to ensure timely response to priority adjustment needs. First, the actual usage of current network slice resources will be comprehensively checked to assess whether there are idle resources that meet scheduling requirements or whether there are resources that can be released for reallocation. If idle or releaseable resources are found, the required resources will be allocated to each SMS service network slice in descending order of the output scheduling priority, ensuring that high-priority services receive priority resource support. However, if the current network slice resources are insufficient to meet the scheduling needs of all SMS service network slices, the resources occupied by low-priority slices will be automatically adjusted according to a pre-set preemption level matrix. This prioritizes the sending needs of high-priority SMS services, ensuring the smooth operation of critical services.

[0110] Please see Figure 2 A 5G network slicing-based intelligent SMS scheduling system, using the aforementioned 5G network slicing-based intelligent SMS scheduling method, includes:

[0111] The slice construction module is used to create various types of SMS service network slices, including low-latency slices, guaranteed slices, and elastic resource slices.

[0112] The prediction module is used to monitor the load information of network slices for various types of SMS services in real time, and predict the expected demand for SMS service traffic in future periods based on the load information.

[0113] The confidence assessment module is used to assess the confidence of the expected demand for SMS traffic in network slices of various types of SMS services and determine the first scheduling condition parameters for each SMS service network slice in the future time period.

[0114] The resource utilization assessment module is used to collect the resource utilization rate of network slices for various types of SMS services, and determine the second scheduling condition parameters of each SMS service network slice in the future time period based on the resource utilization rate and the preset resource threshold.

[0115] The intelligent scheduling module is used to perform fusion calculations on the first scheduling condition parameter and the second scheduling condition parameter to determine the scheduling priority of each SMS service network slice, and then perform intelligent scheduling on each type of SMS service network slice according to the scheduling priority.

[0116] As described above, the main function of the slice construction module is to create and construct various types of SMS service network slices. Specifically, SMS service network slices cover multiple types, including low-latency slices, guaranteed slices, and elastic resource slices, to meet the needs of different SMS service scenarios. The prediction module is responsible for real-time monitoring and collection of load information for each type of SMS service network slice. Based on the real-time load information, the prediction module can predict the expected demand for SMS service traffic in future periods using advanced algorithms and models, thereby providing data support for subsequent scheduling decisions. The confidence assessment module assesses the confidence level of the expected demand for SMS service traffic for each type of SMS service network slice. By comprehensively analyzing various factors, it confirms the confidence level of the expected demand. The first scheduling condition parameter for each SMS service network slice in the future period is determined to ensure the accuracy and reliability of scheduling decisions. The main task of the resource utilization assessment module is to collect and statistically analyze the resource utilization rate data of each type of SMS service network slice. Based on this, and combined with the preset resource threshold, the second scheduling condition parameter for each SMS service network slice in the future period is determined to better optimize resource allocation and utilization. The intelligent scheduling module is responsible for integrating and calculating the first and second scheduling condition parameters. By comprehensively analyzing these two parameters, the scheduling priority of each SMS service network slice is determined, and intelligent scheduling of each type of SMS service network slice is performed according to the scheduling priority, thereby achieving efficient and accurate SMS service management.

[0117] Please see Figure 3 An electronic device, comprising:

[0118] At least one processor;

[0119] and memory that is communicatively connected to at least one processor;

[0120] The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to execute the aforementioned 5G network slicing-based intelligent SMS scheduling method.

[0121] The processor in the aforementioned electronic device can be a central processing unit (CPU), graphics processing unit (GPU), or digital signal processor (DSP), etc., and the memory can include read-only memory (ROM), random access memory (RAM), flash memory, or hard disk, etc. In the electronic device, the processor reads the computer program stored in the memory and executes the aforementioned intelligent SMS scheduling method based on 5G network slicing to achieve intelligent scheduling and management of SMS service network slices. Furthermore, the electronic device may also include an arithmetic logic unit (ALU), input devices, output devices, and a network interface. The ALU provides computational support for various arithmetic and logical operations; input devices, such as keyboards and touchscreens, are used to receive user operation commands and data input; output devices, such as displays and printers, are used to display processing results and output information; and the network interface is used to enable the electronic device to connect and communicate with other devices or networks, facilitating data transmission and sharing.

[0122] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0123] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained in this invention are implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. A method for intelligent SMS scheduling based on 5G network slicing, characterized in that: include: Create various types of SMS service network slices, including low-latency slices, guaranteed slices, and elastic resource slices; Real-time monitoring of network slice load information for various types of SMS services, and prediction of expected SMS traffic demand for future periods based on load information; Confidence assessment of the projected SMS traffic demand for network slices of various types of SMS services is conducted to determine the first scheduling condition parameters for each SMS service network slice in the future time period. Collect the resource utilization rate of network slices for various types of SMS services, and determine the second scheduling condition parameters for each SMS service network slice in the future time period based on the resource utilization rate and the preset resource threshold. The scheduling priority of each SMS service network slice is determined by merging the first scheduling condition parameter and the second scheduling condition parameter, and then intelligent scheduling is performed on each type of SMS service network slice according to the scheduling priority.

2. The SMS intelligent scheduling method based on 5G network slicing according to claim 1, characterized in that: A preemption level matrix is ​​set between the low-latency slices, the guaranteed slices, and the elastic resource slices. The level of the low-latency slices is higher than that of the guaranteed slices, and the level of the guaranteed slices is higher than that of the elastic resource slices. When low-latency slices encounter high loads or urgent demands, they can prioritize the use of resources from guaranteed slices and elastic resource slices. When faced with urgent business demands, guaranteed slices can preempt the resources of elastic resource slices.

3. The SMS intelligent scheduling method based on 5G network slicing according to claim 1, characterized in that: The step of predicting the expected demand for SMS traffic in future periods based on load information includes: Collect historical load data of network slices for various types of SMS services and summarize them into a slice time-series database containing timestamps, service types, and peak traffic; Establish a sliding window and perform time series analysis on historical load data within the sliding window to identify the periodic and non-periodic trends of historical load data; Under cyclical trends, the expected demand for SMS traffic in future periods can be predicted directly based on these cyclical trends. Under non-periodic trends, historical load data is non-linearly fitted to obtain the SMS traffic adjustment value for future periods. The baseline value of SMS traffic is then superimposed with the adjusted value to obtain the expected demand for SMS traffic in future periods.

4. The SMS intelligent scheduling method based on 5G network slicing according to claim 3, characterized in that: The step of performing nonlinear fitting on historical load data to obtain the SMS service traffic adjustment value for future time periods includes: Multiple tracking periods are set within a sliding window, and the rate of change in SMS traffic between adjacent tracking periods is calculated. A time series of traffic change rate is established based on the traffic change rate of SMS services, and the time series of traffic change rate is smoothed to remove abnormal fluctuation points; An exponentially weighted moving average is applied to the smoothed traffic change rate time series to obtain the predicted SMS traffic adjustment trend for the future period. Then, based on the SMS traffic adjustment trend, the SMS traffic adjustment value for the future period is calculated.

5. The SMS intelligent scheduling method based on 5G network slicing according to claim 1, characterized in that: The step of assessing the confidence level of the projected SMS traffic demand for each type of SMS service network slice and determining the first scheduling condition parameters for each SMS service network slice in the future time period includes: Obtain the historical prediction deviation rate of the expected demand for SMS traffic and record it as the first evaluation feature parameter; Collect the fluctuation coefficient of SMS traffic within the current sliding window and record it as the second evaluation feature parameter; Obtain the confidence evaluation function, and input the first evaluation feature parameter and the second evaluation feature parameter into the confidence evaluation function together, output the confidence evaluation value of each SMS service network slice in the future time period, and record it as the first scheduling condition parameter; After the first scheduling condition parameter is output, a rationality check is immediately performed to determine whether the first scheduling condition parameter is within the preset confidence threshold range. If the value exceeds the range, it indicates that the rationality check has failed and the confidence level of the expected SMS traffic demand needs to be reassessed. Conversely, if the value is within the range, it indicates that the rationality check has succeeded and the corresponding first scheduling condition parameter is retained.

6. The SMS intelligent scheduling method based on 5G network slicing according to claim 1, characterized in that: The step of determining the second scheduling condition parameters for each SMS service network slice in a future time period based on resource utilization and a preset resource threshold includes: Obtain resource utilization metrics for various types of SMS network slices within the current sliding window, including CPU utilization, bandwidth utilization, and storage resource utilization. The resource utilization rate index is compared with the resources of the corresponding preset type slice to calculate the difference, and a resource saturation coefficient matrix is ​​generated. The resource saturation coefficient matrix is ​​normalized, and the elements in the normalized resource saturation coefficient matrix are used as the second scheduling condition parameters. Among them, the lower the resource saturation coefficient, the higher the resource redundancy of the corresponding SMS service network slice.

7. The SMS intelligent scheduling method based on 5G network slicing according to claim 1, characterized in that: The step of fusing the first scheduling condition parameter and the second scheduling condition parameter to determine the scheduling priority of each SMS service network slice includes: Obtain the first scheduling condition parameter and the second scheduling condition parameter, and assign initial weight coefficients to the first scheduling condition parameter and the second scheduling condition parameter; The initial weight coefficients of the first scheduling condition parameters are dynamically corrected based on the historical prediction deviation rate, and the corrected weight coefficients are output. The initial weight coefficient of the second scheduling condition parameter is dynamically adjusted based on the resource saturation coefficient, and the adjusted weight coefficient is output. The first and second corrected weight coefficients are weighted and summed with the corresponding first and second scheduling condition parameters to obtain the comprehensive scheduling evaluation value of each SMS service network slice. Based on the comprehensive scheduling evaluation value, each SMS service network slice is ranked, with the SMS service network slice having a higher comprehensive scheduling evaluation value and a higher scheduling priority.

8. The SMS intelligent scheduling method based on 5G network slicing according to claim 1, characterized in that: The step of intelligently scheduling network slices for various types of SMS services according to scheduling priority includes: When the scheduling priority of the SMS service network slice changes, the intelligent scheduling mechanism is automatically triggered. Check the current usage of network slice resources to determine if there are any idle or releaseable resources that meet scheduling requirements; If there are idle or releaseable resources, the required resources will be allocated to each SMS service network slice in descending order of scheduling priority. If the current network slice resources cannot meet the scheduling needs of all SMS service network slices, the resources occupied by low-priority slices will be automatically adjusted according to the preemption level matrix to meet the sending needs of high-priority SMS services.

9. A smart SMS dispatch system based on 5G network slicing, characterized in that: The SMS intelligent scheduling method based on 5G network slicing as described in any one of claims 1 to 8 includes: The slice construction module is used to create various types of SMS service network slices, including low-latency slices, guaranteed slices, and elastic resource slices. The prediction module is used to monitor the load information of network slices for various types of SMS services in real time, and predict the expected demand for SMS service traffic in future periods based on the load information. The confidence assessment module is used to assess the confidence of the expected demand for SMS traffic in network slices of various types of SMS services and determine the first scheduling condition parameters for each SMS service network slice in the future time period. The resource utilization assessment module is used to collect the resource utilization rate of network slices for various types of SMS services, and determine the second scheduling condition parameters of each SMS service network slice in the future time period based on the resource utilization rate and the preset resource threshold. The intelligent scheduling module is used to perform fusion calculations on the first scheduling condition parameter and the second scheduling condition parameter to determine the scheduling priority of each SMS service network slice, and then perform intelligent scheduling on each type of SMS service network slice according to the scheduling priority.

10. An electronic device, characterized in that: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the SMS intelligent scheduling method based on 5G network slicing as described in any one of claims 1 to 8.

Images