Optimized management method and system based on network resource scheduling

Abstract

The invention provides an optimal management method and system based on network resource scheduling. The resource reservation method comprises the following steps: firstly, determining a target resource reservation strategy according to historical service data of user equipment; secondly, analyzing to obtain a slice migration rule according to the network slice information; the slice migration rule and the resource reservation strategy of the corresponding service type are associated and integrated to form a joint scheduling strategy; when a new service request of the user equipment is received, performing adaptive correction on the initial resource reservation parameter based on the corresponding service attribute information and the reflected slice migration state to obtain a target resource reservation parameter; and finally, according to the target resource reservation parameter, executing resource allocation and service migration for the new service request on the target network slice. According to the technical scheme provided by the invention, the dynamic resource scheduling is carried out by fusing the historical service characteristics and the user mobility rule, so that the service continuity and the service quality are effectively guaranteed while the network resource utilization rate is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication network, and particularly relates to an optimization management method and system based on network resource scheduling. BACKGROUND

[0002] With the wide application of 5G network slice technology, the network needs to support diversified services such as enhanced mobile broadband, ultra-reliable low-latency communication and massive machine type communication; when facing different service types with differentiated quality of service requirements, especially in terms of latency, bandwidth and reliability, the user equipment may frequently trigger switching between network slices during movement, which requires the network to have dynamic resource scheduling capability to ensure service continuity and improve resource utilization.

[0003] A current existing scheme is to analyze the real-time service request characteristics of the user equipment to predict its short-term resource demand; based on the current service type and its quality of service level, the scheme dynamically calculates the required resource amount and performs corresponding resource reservation on the target network slice; and when detecting that the user equipment is about to switch slices, resources are pre-allocated to the post-switch slice according to the prediction result to reduce the service interruption probability.

[0004] However, this scheme still has defects, mainly focusing on real-time service characteristics, lacking mining and utilization of historical slice switching patterns of the user equipment; and due to the failure to consider the specific slice access sequence pattern exhibited by the user equipment during movement, the determination of the resource reservation amount often depends on the current instantaneous state, making it difficult to accurately reflect the actual resource demand trend. SUMMARY

[0005] The present application provides an optimization management method and system based on network resource scheduling to solve the problem of inaccurate resource reservation in the prior art, which easily causes excessive resource configuration or insufficient resource configuration, affecting resource utilization efficiency and service experience.

[0006] In a first aspect, the present application provides an optimization management method based on network resource scheduling, comprising: determining a target resource reservation strategy according to historical service data of the user equipment, wherein the historical service data contains service attribute information and accessed network slice information; analyzing the slice migration pattern of the user equipment according to the network slice information in the historical service data; associating and integrating the slice migration pattern with the resource reservation strategy of the corresponding service type to form a joint scheduling strategy; When a new service request is received from the user equipment, the initial resource reservation parameters in the joint scheduling strategy are adaptively modified based on the service attribute information corresponding to the new service request and the slice migration status reflected therein, so as to obtain the target resource reservation parameters. Based on the target resource reservation parameters, resource allocation and service migration are performed on the target network slice for the new service request.

[0007] Optionally, a target resource reservation strategy is determined based on the user equipment's historical service data, wherein the historical service data includes service attribute information and accessed network slice information, including: Extract the value distribution of the business attribute information and the access frequency of the network slice information from the historical business data; Based on the value distribution of the business attribute information, business requests that meet the preset conditions are grouped into the same business type cluster; For each business type cluster, the fluctuation range of resource usage by business requests within that business type cluster during a preset period is statistically analyzed. The basic resource reservation amount for the business type cluster is determined based on the upper bound of the resource fluctuation range. Based on the access frequency of the network slice information, identify the slice access sequence pattern that recurs in continuous service requests of the user equipment. Bind the slice access sequence pattern to the corresponding business type cluster; Based on the basic resource reservation amount and the bound slice access sequence pattern, the target resource reservation strategy is output.

[0008] Optionally, based on the network slice information in the historical service data, the slice migration pattern of the user equipment is analyzed, including: From the historical service data, the network slice identifiers accessed by the user equipment when it initiated the service request are extracted in chronological order to form a slice access sequence. In the slice access sequence, a slice transfer segment composed of at least two different network slice identifiers in chronological order of access timestamps is identified; Count the number of times each slice transfer segment appears in the slice access sequence, and mark the slice transfer segment whose repetition exceeds a set threshold as the target slice transfer mode; Based on the number of network slice identifiers included in the target slice transfer mode, the target slice transfer mode is divided into different levels of migration modes, and the combination conditions of the starting network slice identifier and service attribute information that trigger each level of migration mode are determined. The migration patterns at different levels and their corresponding combination conditions are correlated and integrated to obtain the slice migration rules.

[0009] Optionally, the slice migration pattern is associated and integrated with the resource reservation strategy for the corresponding service type to form a joint scheduling strategy, including: Extract the target business type cluster and the target basic resource reservation amount from the target resource reservation strategy; Extract the target migration pattern and the corresponding combination conditions from the slice migration pattern; The target business type cluster is matched with the target combination conditions. When the match is successful, a mapping relationship is established between the target basic resource reservation amount corresponding to the target business type cluster and the successfully matched target migration mode. Based on the established mapping relationship, generate a strategy entry; Repeatedly extract the target service type cluster and target basic resource reservation amount, extract the target migration mode and the corresponding combination conditions of the target migration mode, establish mapping relationship and generate policy entries, and collect all policy entries to obtain the joint scheduling policy.

[0010] Optionally, when a new service request is received from the user equipment, the initial resource reservation parameters in the joint scheduling strategy are adaptively modified based on the service attribute information corresponding to the new service request and the reflected slice migration status to obtain target resource reservation parameters, including: Parse the new service attribute information and the new starting network slice identifier from the new service request; The new service attribute information is matched with the service type clusters corresponding to each strategy entry in the joint scheduling strategy to determine the new service type clusters; The new starting network slice identifier is matched with the combination conditions corresponding to each policy entry in the joint scheduling policy to determine the new migration mode; Based on the new business type cluster and the new migration mode, find the corresponding target basic resource reservation amount from the joint scheduling strategy; Identify the slice migration path indicated by the new service request, and compare the slice migration path with the new migration mode; Based on the comparison results, the initial resource reservation parameters are adjusted to obtain the target resource reservation parameters.

[0011] Optionally, the initial resource reservation parameters are adjusted based on the comparison results to obtain the target resource reservation parameters, including: Calculate the difference between the number of network slices included in the slice migration path and the number of network slices included in the new migration mode; When the difference is negative, the initial resource reservation amount is reduced according to the first preset ratio to obtain the first adjusted resource amount as the target resource reservation parameter; When the difference is positive, the initial resource reservation amount is increased according to the second preset ratio to obtain the second adjusted resource amount as the target resource reservation parameter; When the difference is zero, the initial resource reservation amount remains unchanged as the target resource reservation parameter.

[0012] Optionally, according to the target resource reservation parameters, resource allocation and service migration are performed on the target network slice for the new service request, including: Based on the target resource reservation parameters, a resource pre-allocation request is sent to the management unit of the target network slice. The resource pre-allocation request includes the type and quantity of resources that need to be reserved. The system receives resource pre-allocation confirmation information returned by the management unit of the target network slice, the confirmation information including the identifier and access parameters of the allocated resources; After receiving the resource pre-allocation confirmation information, a network switching instruction is sent to the user equipment. The switching instruction includes the access information and resource access parameters of the target network slice. Monitor the connection establishment process from the user equipment to the target network slice, and after confirming that the connection is successfully established, route the user equipment's service data flow from the source network slice to the target network slice; After the business data flow switch is completed, release the resources occupied by the user on the source network slice.

[0013] Secondly, this application provides an optimization management system based on network resource scheduling, comprising: The determination module is used to determine the target resource reservation strategy based on the historical service data of the user equipment, wherein the historical service data includes service attribute information and network slice information accessed. The analysis module is used to analyze the network slice information in the historical service data to obtain the slice migration pattern of the user equipment; The integration module is used to associate and integrate the slice migration rules with the resource reservation strategies of the corresponding business types to form a joint scheduling strategy; The correction module is used to adaptively correct the initial resource reservation parameters in the joint scheduling strategy based on the service attribute information corresponding to the new service request and the slice migration status reflected by the new service request when a new service request is received from the user equipment, so as to obtain the target resource reservation parameters. The execution module is used to perform resource allocation and service migration for the new service request on the target network slice according to the target resource reservation parameters.

[0014] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement an optimized management method based on network resource scheduling as described in the first aspect above.

[0015] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements an optimization management method based on network resource scheduling as described in the first aspect.

[0016] This application analyzes historical service data of user equipment to identify stable slice migration patterns exhibited by users in different service scenarios, and forms a joint scheduling strategy based on service type characteristics. When a new service request is received, the initial resource reservation parameters in the strategy are dynamically modified based on real-time service attributes and the current slice migration status, so that resource allocation can reflect the common needs of service types and adapt to the actual mobility characteristics of users.

[0017] Furthermore, by directly applying the modified target resource reservation parameters to the resource pre-allocation and service migration process of the target network slice, a high degree of matching between resource allocation and actual business needs is ensured. This method avoids resource reservation deviations caused by relying solely on real-time status judgments, preventing service quality degradation due to insufficient reservations and reducing resource waste due to excessive reservations. Thus, it achieves synergistic optimization of resource utilization efficiency and service quality in complex and ever-changing network environments. Therefore, this application can significantly improve the accuracy and efficiency of network resource scheduling while meeting diverse service quality requirements.

[0018] These or other aspects of this application will become more apparent from the description of the following embodiments. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of an optimization management method based on network resource scheduling provided in this application is shown; Figure 2 A schematic diagram of the structure of an optimization management system based on network resource scheduling provided in this application is shown; Figure 3A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Figure 1 This application provides a flowchart of an optimization management method based on network resource scheduling, such as... Figure 1 As shown, the method includes: Step 101: Determine the target resource reservation strategy based on the user equipment's historical service data, wherein the historical service data includes service attribute information and accessed network slice information.

[0025] Optionally, step 101 may specifically include: Step 1011: Extract the value distribution of the business attribute information and the access frequency of the network slice information from the historical business data.

[0026] Step 1012: Based on the value distribution of the business attribute information, business requests that meet the preset conditions are grouped into the same business type cluster.

[0027] Step 1013: For each business type cluster, calculate the fluctuation range of resource usage by business requests within the business type cluster during a preset period.

[0028] Step 1014: Determine the basic resource reservation amount for the business type cluster based on the upper bound of the resource quantity fluctuation range.

[0029] Step 1015: Based on the access frequency of the network slice information, identify the slice access sequence pattern that recurs in continuous service requests of the user equipment. Step 1016: Bind the slice access sequence pattern to the corresponding service type cluster; Step 1017: Based on the basic resource reservation amount and the bound slice access sequence mode, output the target resource reservation strategy.

[0030] In this step, historical business data refers to the collection of records generated each time a user device initiates a service over a past period of time. This data is used to analyze user behavior patterns and is obtained by querying and exporting from network operation support.

[0031] Business attribute information refers to data used to describe the characteristics of the business itself, and is used to distinguish the service quality requirements of different types of businesses, such as business latency requirements, business reliability level, business priority, etc.

[0032] Network slice information refers to the identifier of a specific network slice that a user equipment accesses when initiating a service. It is used to identify the network environment carried by the service, such as the identifier of an enhanced mobile broadband slice or an ultra-reliable low-latency communication slice.

[0033] Value distribution refers to the statistical situation of all possible values ​​of a data item and their frequencies. It is used to reflect the central tendency and dispersion of the data item and is obtained through statistical methods.

[0034] Access frequency refers to the number of times a network slice has been accessed in the historical record. It is used to measure the popularity of the slice or user preference, and is obtained through counting statistics.

[0035] Preset conditions refer to data items with similar characteristics that are adjacent in value range and have similar business attribute information. These conditions are used to group data items with similar characteristics into one category and are set by the administrator based on experience or optimization goals.

[0036] A service request refers to a connection establishment request initiated by a user device to the network in order to use a specific service.

[0037] A business type cluster refers to a set of multiple business requests grouped together based on the similarity of their business attribute information. It is used to classify and manage massive amounts of business requests and is obtained through clustering algorithms.

[0038] A preset period refers to a time length set in advance for resource statistics, used to observe the periodic patterns of resource usage, such as one minute, five minutes, or one hour.

[0039] The resource quantity fluctuation range refers to the interval between the minimum and maximum values ​​of the network resources occupied by a service within a statistical period. It is used to describe the stability of resource demand and is obtained through statistical calculation.

[0040] Basic resource reservation refers to the amount of resources pre-allocated to ensure the smooth operation of a certain type of business under normal circumstances, and is used as a benchmark for resource scheduling.

[0041] Slice access sequence pattern refers to a repetitive sequential pattern formed by a user device accessing different network slices when it continuously initiates service requests. This pattern is used to predict the user's future mobile path.

[0042] In this step, firstly, the specific values ​​of the business attribute information and the network slice information identifiers accessed for all business requests are extracted from the stored historical business data. Statistical analysis techniques are then used to calculate the frequency of each value in the business attribute information, thus obtaining its value distribution. Simultaneously, the number of times each network slice information identifier is accessed is counted to obtain the access frequency of the network slice information. Secondly, based on the obtained value distribution of the business attribute information, cluster analysis techniques are used to automatically classify business requests with similar business attribute information values. Specifically, the distance between different business requests along the business attribute dimension is calculated, and requests with a distance less than a predetermined value are grouped together. Service requests with thresholds defined by the conditions are grouped into the same group, which is called a service type cluster. Then, for each service type cluster, a preset period is set, such as five minutes. Then, all service requests within the service type cluster are traversed, and the total network resources consumed by these service requests within each preset period's time window, such as bandwidth or computing resources, are counted. By finding the maximum and minimum values ​​of the total resources within all time windows, the resource fluctuation range of the service type cluster is determined. Then, the upper bound of the resource fluctuation range, that is, the maximum resource consumption value obtained from the statistics, is taken as the basic resource reservation amount for the service type cluster. On another parallel processing line, based on the access frequency of network slice information, the focus is on frequently accessed slices, and the service request records of user devices are scanned in chronological order to identify sequences formed by accessing different slices in continuous requests. Through pattern recognition technology, specific slice access sequences that occur more than a certain threshold are identified and defined as slice access sequence patterns. Finally, a binding operation is performed to associate the identified slice access sequence patterns with the service type clusters obtained through clustering. This association is based on the common occurrence patterns of these clusters in historical data. After binding is completed, the basic resource reservation amount of each service type cluster and its bound slice access sequence pattern are output together to form the target resource reservation strategy.

[0043] For example, based on the user equipment's usage in region A, the historical service data is first analyzed, revealing that the historical service attribute information mainly falls into two categories: one is data with extremely high latency and reliability requirements; the other is data with low latency but extremely high bandwidth requirements. Based on this distribution, historical service requests are categorized into two service type clusters: ultra-low latency service cluster and high bandwidth service cluster. Next, for the ultra-low latency service cluster, it is found that its resource consumption per minute fluctuates between 5Mbps and 8Mbps, so its basic resource reservation is set to 8Mbps. At the same time, it is found that before initiating ultra-low latency services, the user equipment usually follows a fixed sequence of switching from slice B to slice C, so B->C is identified as a slice access sequence pattern. Finally, the ultra-low latency service cluster, the 8Mbps basic resource reservation, and the B->C slice access sequence pattern are bound together and written as a policy into the target resource reservation policy.

[0044] Finally, this step automatically analyzes historical data to scientifically categorize the chaotic business requests and accurately calculate the resource demand baseline for each type of business. It also discovers potential patterns in the migration of user devices between slices. This makes resource reservation no longer a rough estimate based on experience, but rather supported by precise data, laying a reliable foundation for subsequent dynamic adjustments based on real-time conditions. This improves the scientific nature and efficiency of resource planning from the source.

[0045] Step 102: Analyze the slice migration pattern of the user equipment based on the network slice information in the historical service data.

[0046] Optionally, step 102 may specifically include: Step 1021: Extract the network slice identifiers accessed by the user equipment when it initiated the service request from the historical service data in chronological order to form a slice access sequence.

[0047] Step 1022: In the slice access sequence, identify a slice transfer segment consisting of at least two different network slice identifiers in chronological order of access timestamps.

[0048] Step 1023: Count the number of times each slice transfer segment appears in the slice access sequence, and mark the slice transfer segments with a repetition count exceeding a set threshold as target slice transfer modes.

[0049] Step 1024: Based on the number of network slice identifiers included in the target slice transfer mode, divide the target slice transfer mode into different levels of migration modes, and determine the combination conditions of the starting network slice identifier and service attribute information that trigger each level of migration mode.

[0050] Step 1025: Associate and integrate the migration patterns at different levels and their corresponding combination conditions to obtain the slice migration rules.

[0051] In this step, slice migration patterns refer to a systematic description of the habitual paths and triggering conditions for switching between different network slices, summarized from the historical behavior of user devices, and are used to predict the user's future mobility behavior.

[0052] A network slice identifier is a number or code used to uniquely distinguish different network slices. It identifies the specific logical network carried by a service and is assigned by network management and recorded in the service request data.

[0053] A slice access sequence is a sequence of network slice identifiers accessed by a user device arranged in chronological order of service requests, used to reflect the movement trajectory of the user device in the network over time.

[0054] Access timestamps are data that records the exact time when a user device initiates each service request. They are used to determine the order in which service requests occur and are automatically recorded by network devices when a service request is generated.

[0055] A slice transition segment is a short sequence extracted from a slice access sequence, consisting of two or more consecutive network slice identifiers in the order of access. It is used to describe a specific inter-slice switching behavior and is obtained by scanning a sliding window in the complete slice access sequence.

[0056] The repetition count refers to the total number of times a specific slice transfer segment appears in the entire slice access sequence. It is used to measure the frequency and importance of the switching behavior and is obtained by performing pattern matching and counting in the entire sequence.

[0057] The target slice transfer pattern refers to slice transfer segments that are repeated more than a preset threshold and are considered to have significant statistical value. These segments are used to represent the user device's usual switching path and are obtained by filtering segments with high repetition rates.

[0058] The number of network slice identifiers refers to the number of distinct network slice identifiers that constitute a target slice transfer pattern. It is used to measure the length and complexity of the switching path and is obtained by counting the number of unique identifiers in the pattern.

[0059] Different levels of migration modes refer to the classification of target slice transfer modes based on the number of network slice identifiers. The higher the level, the longer the switching path and the more slices involved. It is used to distinguish migration behaviors of different complexities and is divided by setting a range of numbers.

[0060] The starting network slice identifier refers to the identifier of the network slice in which the user equipment is located when the migration begins within a slice transfer segment. It is used to identify the starting point of the migration behavior.

[0061] The combination conditions of business attribute information refer to a set of business characteristic values ​​that frequently co-occur with a specific migration pattern. They are used to describe under what business requirements the migration behavior is likely to be triggered. They are obtained by correlation analysis of business attribute information before and after the migration pattern occurs.

[0062] In this step, firstly, the access timestamp and network slice identifier corresponding to each business record are read from historical business data. Then, according to the access timestamps from earliest to latest, all network slice identifiers are arranged sequentially to form a complete slice access sequence, clearly showing the complete path of the user device jumping between different network slices over time. Secondly, the slice access sequence is analyzed using sliding window technology. A window is set and slides from the beginning of the slice access sequence, capturing several consecutive network slice identifiers in the window each time to form a slice transfer segment. If the window size is 2, two consecutive switches are captured for analysis, and all segments consisting of at least two different network slice identifiers are identified. These segments describe the specific transfer behavior of the user leaving one slice and accessing another slice. Then, the entire slice access sequence is traversed, and a pattern matching algorithm is used to count the number of times each identified slice transfer segment appears, i.e., the repetition count, and a preset importance threshold is set. Segments with a repetition count exceeding this preset threshold are filtered out as representative switching paths frequently used by the user device and marked as target slice transfer patterns. Then, these target slice migration patterns are analyzed in depth. The number of network slice identifiers contained in each target slice migration pattern is calculated, and they are divided into different levels according to the range of the number. For example, the pattern containing 2 slices is the first level, the pattern containing 3 slices is the second level, and so on. At the same time, for each pattern in each level, historical data is reviewed to find the starting network slice identifier of the user equipment and the service attribute information of the service request before each migration of the target slice pattern. Through statistical induction, the starting network slice and service attribute combination that most often appears with the migration pattern is determined, and this combination is defined as the combination condition that triggers the migration pattern of that level. Finally, the analysis results are correlated and integrated. Specifically, a rule base is established to store the migration patterns of different levels and their corresponding combination conditions one by one. This rule base, which contains hierarchical migration patterns and their precise triggering conditions, ultimately constitutes the slice migration rules used to describe the slice migration behavior of user equipment.

[0063] For example, following the specific implementation of the previous step, firstly, a window of size 2 is used to scan the slice access sequence containing slice B and C identifiers to identify frequently occurring slice transfer segments from slice B to slice C. Secondly, it is found that this slice transfer segment appears 50 times in one day, far exceeding the set threshold of 10 times, so it is marked as a target slice transfer pattern. This target slice transfer pattern contains two network slice identifiers, so it is classified as a first-level migration pattern. Next, historical service data is reviewed and it is found that whenever a B->C migration occurs, its starting network slice identifier is always B, and the service attribute information at that time always shows ultra-low latency service. Therefore, the combined condition for triggering this first-level migration pattern is that the starting slice is B and the service type is ultra-low latency service. Finally, this rule, which states that when the starting slice = B and the service = ultra-low latency, the user tends to follow the B->C migration pattern, is added to the slice migration rules of the user equipment.

[0064] Finally, this step, through in-depth analysis of users' historical movement trajectories, abstracts seemingly random slice switching behaviors into regular patterns with different hierarchical structures and clear triggering conditions. This not only reveals users' deep-seated mobility habits, but more importantly, it links migration paths with specific business scenarios, upgrading the prediction of users' future behavior from simple path deduction to accurate inference based on scenarios. This provides a crucial and reliable decision-making basis for subsequent intelligent resource pre-scheduling.

[0065] Step 103: The slice migration pattern is associated and integrated with the resource reservation strategy of the corresponding business type to form a joint scheduling strategy.

[0066] Optionally, step 103 may specifically include: Step 1031: Extract the target business type cluster and the target basic resource reservation amount from the target resource reservation strategy.

[0067] Step 1032: Extract the target migration pattern and the corresponding combination conditions from the slice migration pattern.

[0068] Step 1033: Match the target business type cluster with the target combination conditions. When the match is successful, establish a mapping relationship between the target basic resource reservation amount corresponding to the target business type cluster and the successfully matched target migration mode.

[0069] Step 1034: Generate a strategy entry based on the established mapping relationship.

[0070] Step 1035: Repeat the following steps: extract the target service type cluster and target basic resource reservation amount, extract the target migration mode and the combination conditions corresponding to the target migration mode, establish mapping relationship and generate policy entries, and collect all policy entries to obtain the joint scheduling policy.

[0071] In this step, the joint scheduling strategy refers to a unified set of decision rules formed by combining resource reservation strategies based on business type with slice migration patterns based on user mobility. This set of rules is used to perform collaborative and intelligent resource scheduling when faced with new business requests and is obtained through a correlation and integration process.

[0072] The combination conditions corresponding to the target migration mode refer to the specific value combination of the business attribute information that triggers the occurrence of the mode and the starting network slice identifier, which are closely related to each target migration mode in the slice migration pattern. This combination is used to determine when a specific migration behavior will be triggered.

[0073] The target combination condition refers to the specific combination conditions extracted from the slice migration pattern in the current association and integration step, which are prepared for matching with the resource reservation strategy.

[0074] Mapping relationships refer to the corresponding links established between elements in two different datasets. Here, it refers to business type clusters and migration patterns, which are used to associate resource reservations with migration paths. These links are dynamically established by a matching algorithm when conditions are met.

[0075] A policy entry refers to a basic unit in a joint scheduling policy. It explicitly records the binding relationship between a service type cluster, its corresponding basic resource reservation, and a related migration mode. It is generated by encapsulating the mapping relationship.

[0076] In this step, firstly, the target business type clusters and the target basic resource reservation amount set for each cluster are read from the obtained target resource reservation strategy. Secondly, all identified target migration patterns and the corresponding combination conditions for each target migration pattern are extracted in parallel from the obtained slice migration rules. Next, the core association operation is performed. First, data matching technology is used to compare each target business type cluster in the target resource reservation strategy with the target combination conditions corresponding to each target migration pattern in the slice migration rules. The purpose of this comparison is to find commonalities in business, specifically, to determine whether the business attribute characteristics on which the target business type cluster is based are compatible or consistent with the business attribute information required in the target combination conditions. Then, when it is found that the characteristics of a certain target business type cluster can be successfully matched with the business attribute requirements in a certain target combination condition, the match is considered successful. Once a match is successful, a bidirectional mapping relationship is established between the target basic resource reservation amount corresponding to the target business type cluster and the target migration mode that was successfully matched. This mapping relationship means that when it is predicted that a user will move according to this migration mode, the corresponding amount of resources should be reserved for this type of business. Then, based on the established mapping relationship, a structured policy entry is generated, clearly recording which business type cluster, under which migration mode, and how much target basic resource reservation amount is required. Finally, the process of extracting, matching, establishing mapping, and generating entries is executed cyclically until all potential matchable items are processed. All the generated policy entries are then gathered together to form a complete policy set, which is the final joint scheduling policy.

[0077] For example, following the specific implementation of the previous step, firstly, the target service type cluster is extracted as an ultra-low latency service cluster from the target resource reservation policy, with a target basic resource reservation amount of 8Mbps; simultaneously, the target migration mode is extracted as B->C migration from the slice migration pattern, with the corresponding target combination condition being starting slice = B and service type = ultra-low latency service; then, the service attributes of the ultra-low latency service cluster are matched with the service type = ultra-low latency service in the combination condition, and a perfect match is found, indicating a successful match; thus, a mapping relationship is established: when B->C migration occurs, 8Mbps of resources are reserved for ultra-low latency services; subsequently, a policy entry is generated to record this association; after all similar associations are found and policy entries are generated, the set of these policy entries constitutes the joint scheduling policy for this user equipment.

[0078] Finally, this step organically weaves together the originally independent business resource requirements with user mobility behavior patterns through precise matching rules, forming a global decision-making framework. This allows for simultaneous consideration of the two key dimensions of required business quality and user mobility during scheduling, thereby achieving a leap from static, business type-based resource reservation to dynamic, business and mobility-based joint prediction intelligent scheduling, laying the core rule foundation for ultimately achieving accurate resource allocation.

[0079] Step 104: When a new service request is received from the user equipment, the initial resource reservation parameters in the joint scheduling strategy are adaptively modified based on the service attribute information corresponding to the new service request and the slice migration status reflected therein, so as to obtain the target resource reservation parameters.

[0080] Optionally, step 104 may specifically include: Step 1041: Parse the new service attribute information and the new starting network slice identifier from the new service request.

[0081] Step 1042: Match the new service attribute information with the service type clusters corresponding to each strategy entry in the joint scheduling strategy to determine the new service type clusters.

[0082] Step 1043: Match the new starting network slice identifier with the combination conditions corresponding to each policy entry in the joint scheduling policy to determine the new migration mode.

[0083] Step 1044: Based on the new service type cluster and the new migration mode, find the corresponding target basic resource reservation amount from the joint scheduling strategy.

[0084] Step 1045: Identify the slice migration path indicated by the new service request and compare the slice migration path with the new migration mode.

[0085] Step 1046: Adjust the initial resource reservation parameters according to the comparison results to obtain the target resource reservation parameters.

[0086] Optionally, step 1046 may include the following steps: calculating the difference between the number of network slices included in the slice migration path and the number of network slices included in the new migration mode; when the difference is negative, reducing the initial resource reservation amount according to a first preset ratio to obtain a first adjusted resource amount as the target resource reservation parameter; when the difference is positive, increasing the initial resource reservation amount according to a second preset ratio to obtain a second adjusted resource amount as the target resource reservation parameter; when the difference is zero, keeping the initial resource reservation amount unchanged as the target resource reservation parameter.

[0087] In this step, a new service request refers to a request initiated by the user equipment at the current moment that requires the use of network services. It is used to trigger a real-time resource scheduling process and is actively sent to the network by the user equipment and received.

[0088] Slice migration status refers to the migration status of user equipment between network slices during the current service session, which is implied by new service requests and reflects real-time mobility dynamics. It is obtained by analyzing the context information of new service requests.

[0089] The initial resource reservation parameter refers to the reference value of the initial resource reservation amount matched for new service requests based on historical data in the joint scheduling strategy. It is used as the starting point for resource adjustment and is obtained by querying the joint scheduling strategy.

[0090] The target resource reservation parameter refers to the final resource allocation amount obtained after adjusting the initial resource reservation parameter based on the real-time slice migration status. It is used for actual resource reservation and is obtained through an adaptive correction process.

[0091] New business attribute information refers to data that describes the characteristics of the current business and is directly parsed from the new business request. It is used to identify the business type and is obtained by parsing the message body of the new business request.

[0092] The newly initiated network slice identifier refers to the identifier of the network slice that the user equipment is using when initiating a new service request. It is used to identify the starting point of the current service and is obtained by parsing the signaling message of the new service request.

[0093] The new service type cluster refers to the service type cluster whose service attribute characteristics match the new service attribute information of the new service request in the joint scheduling strategy. It is used to determine the applicable service category for this request and is determined by a matching algorithm.

[0094] The new migration mode refers to the target migration mode in the joint scheduling strategy whose combined conditions require the initial network slice identifier to match the new initial network slice identifier of the new service request. It is used to predict the migration path that this request may follow and is determined by a matching algorithm.

[0095] The slice migration path refers to the specific slice switching sequence that actually occurs or is planned to occur in the current business scenario of the user equipment, inferred from the context information of the new service request, such as the source slice and the target slice. It is used to reflect the current migration status and is identified through signaling analysis.

[0096] The number of network slices refers to the number of distinct network slice identifiers contained in a sequence such as a slice migration path or migration pattern, and is used to measure the complexity of the path.

[0097] The difference in the number of network slices refers to the arithmetic difference between the number of network slices in the actual slice migration path and the number of network slices in the predicted new migration pattern. It is used to quantify the degree of deviation between the actual path and the predicted path and is calculated by subtraction.

[0098] The first preset ratio refers to the coefficient used to reduce the initial resource reservation when the actual path is simpler than the predicted pattern; this ratio is less than 1.

[0099] The first adjusted resource quantity refers to the result obtained by multiplying the initial resource reservation parameter by the first preset ratio when the difference in the number of network slices is negative.

[0100] The second preset ratio refers to a coefficient used to increase the initial resource reservation when the actual path is more complex than the prediction model; this ratio is greater than 1.

[0101] The second adjusted resource quantity refers to the result obtained by multiplying the initial resource reservation parameter by the second preset ratio when the difference in the number of network slices is positive.

[0102] In this step, upon receiving a new service request from a user equipment, the request is immediately parsed to extract new service attribute information describing the characteristics of the current service, as well as a new starting network slice identifier indicating the user's current network location. Next, the parsed new service attribute information is matched against the characteristics of the service type clusters corresponding to each policy entry in the joint scheduling strategy. Using exact matching or similarity matching algorithms, the service type cluster with the closest service attributes is identified, and this cluster is determined as the new service type cluster corresponding to the current request. Simultaneously, the parsed new starting network slice identifier is matched against the combined conditions corresponding to each policy entry in the joint scheduling strategy. Policy entries whose starting network slice requirements match the new starting network slice identifier are identified, and their target migration mode is determined as the possible new migration mode corresponding to the current request. Then, based on the identified new service type cluster and new migration mode, a joint query is performed within the joint scheduling strategy to find the policy entry that satisfies both conditions. The initial resource reservation parameters, also known as the target basic resource reservation amount, are read from this policy entry and used as the initial baseline for this resource allocation. Next, the current real-time situation needs to be analyzed. By analyzing the signaling context of new service requests, the complete slice migration path that has occurred or is about to occur in the current service session of the user equipment is identified. After that, the critical correction stage begins. The identified actual slice migration path is compared with the previously predicted new migration pattern. The core indicator of this comparison is to calculate the difference in the number of network slices contained in the two. Specifically, the number of slices in the actual path is subtracted from the number of slices in the predicted pattern. Finally, based on the calculated difference, the initial resource reservation parameters are corrected using preset adjustment rules. If the difference is negative, it indicates that the actual path is simpler than the predicted pattern. In this case, the initial resource reservation parameters are multiplied by a first preset ratio less than 1 to reduce the initial resource reservation parameters, resulting in the first adjusted resource amount as the target resource reservation parameter. If the difference is positive, it indicates that the actual path is more complex. In this case, the initial resource reservation parameters are multiplied by a second preset ratio greater than 1 to increase the initial resource reservation parameters, resulting in the second adjusted resource amount as the target resource reservation parameter. If the difference is zero, it indicates that the actual path completely matches the prediction. In this case, the initial resource reservation parameters remain unchanged and are directly used as the target resource reservation parameters.

[0103] For example, following the specific implementation of the previous step, firstly, a new service request initiated by the user equipment from slice B is received. The new service attribute information is parsed and found to be an ultra-low latency service, with the new starting network slice identifier being B. Secondly, it is matched with the joint scheduling policy to determine that the new service type cluster is an ultra-low latency service cluster, and the new migration mode is B->C migration. Then, the initial resource reservation parameter is found to be 8Mbps. At the same time, based on the context of the new service request, it is identified that the user's actual slice migration path is directly from B to C and includes 2 slices. This actual slice migration path is compared with the new migration mode B->C, which also includes 2 slices, and the difference in the number of network slices is calculated to be 0. Therefore, it is determined that no adjustment is needed, and the final target resource reservation parameter is 8Mbps. Finally, if it is identified that the user's current path is more complex B->D->C and includes 3 slices, the difference is a positive number 1, and 8Mbps is multiplied by a second preset ratio, such as 1.2, to obtain 9.6Mbps as the target resource reservation parameter.

[0104] Finally, this step obtains an initial baseline for resource allocation by parsing business requests in real time and matching them with pre-defined strategies. Then, by comparing the predicted migration pattern with the actual migration path, the resource reservation is intelligently adjusted. This method dynamically combines historical patterns with real-time status, enabling resource allocation to both follow the common needs of long-term statistics and flexibly adapt to the individual changes of each business session. This effectively improves the accuracy and context awareness of resource scheduling and avoids insufficient or wasted resource allocation.

[0105] Step 105: According to the target resource reservation parameters, perform resource allocation and service migration for the new service request on the target network slice.

[0106] Optionally, step 105 may specifically include: Step 1051: Based on the target resource reservation parameters, send a resource pre-allocation request to the management unit of the target network slice. The resource pre-allocation request includes the type and quantity of resources that need to be reserved.

[0107] Step 1052: Receive resource pre-allocation confirmation information returned by the management unit of the target network slice. The confirmation information includes the identifier and access parameters of the allocated resources.

[0108] Step 1053: After receiving the resource pre-allocation confirmation information, a network switching instruction is sent to the user equipment. The switching instruction includes the access information and resource access parameters of the target network slice.

[0109] Step 1054: Monitor the connection establishment process from the user equipment to the target network slice. After confirming that the connection is successfully established, route the service data flow of the user equipment from the source network slice to the target network slice.

[0110] Step 1055: After the business data flow switch is completed, release the resources occupied by the user on the source network slice.

[0111] In this step, resource allocation refers to the process of allocating a specific quantity and type of network resources to designated users or services to ensure the quality of service.

[0112] Service migration refers to the operation of transferring the service data flow of a user device from one network slice to another to achieve service continuity. It is achieved through changes in control plane signaling and user plane data routing.

[0113] A resource pre-allocation request is a signaling message that requires a target network slice to prepare and lock specific resources in advance to ensure resource availability. It is generated and sent based on the target resource reservation parameters.

[0114] The management unit of a target network slice refers to the control function entity responsible for the internal resource management and allocation of the target network slice. It is used to receive and execute resource allocation instructions and is part of the target network slice.

[0115] The types and quantities of resources that need to be reserved refer to the specific requirements carried in the resource pre-allocation request, which clearly specify what resources need to be reserved, such as bandwidth and computing units, and their specific values, and are directly converted from the target resource reservation parameters.

[0116] Resource pre-allocation confirmation information refers to the response message returned by the management unit of the target network slice after successfully reserving resources. It is used to notify that the resources are ready and is generated by the management unit after successful resource allocation.

[0117] The identifier and access parameters of the allocated resources refer to the data included in the resource pre-allocation confirmation information, which are used to uniquely identify the allocated resource block and its configuration details such as IP address, port, and key, for user equipment access.

[0118] A handover command is a command message sent to a user device that instructs it to begin accessing the target network slice. It is used to trigger the actual handover action and is generated by the scheduling platform after confirming that the resource reservation has been successful.

[0119] Access information refers to the basic network parameters required for a user equipment to connect to the target network slice, such as the frequency and cell identifier of the target slice, which are included in the handover instruction.

[0120] Resource access parameters refer to the specific configuration information included in the handover command that the user equipment needs to access reserved resources, such as the details of the dedicated bearer allocated for this service.

[0121] The source network slice refers to the network slice that the user equipment is using when initiating a new service request; it is the starting point for service migration.

[0122] In this step, the scheduling platform first generates a structured resource pre-allocation request based on the determined target resource reservation parameters, clearly specifying the type of resource to be reserved, such as bandwidth or computing resources, and the specific quantity. This resource pre-allocation request is then sent to the management unit of the target network slice via a communication interface. Next, upon receiving the resource pre-allocation request, the management unit checks availability in its resource pool and reserves resources according to the requirements in the request. After successful reservation, the management unit generates a resource pre-allocation confirmation message containing the unique identifier of the allocated resources and the detailed parameters required to access them. This confirmation message is then received and parsed to confirm that the resources are ready at the target end. After confirming successful resource pre-allocation, the scheduling platform immediately sends a network switching command to the user equipment. This command contains the necessary access information for the user equipment to access the target network slice, as well as resource access parameters for accessing reserved resources. Upon receiving this command, the user equipment begins the switching process. Then, the scheduling platform monitors the connection establishment process from the user equipment to the target network slice by listening to relevant signaling messages to confirm whether the user equipment has successfully established a connection with the target network slice. Once the connection is confirmed to be established successfully, the platform controls the user plane data forwarding function to seamlessly route the user equipment's service data flow from the original source network slice to the target network slice with prepared resources. Finally, after confirming that the service data flow has been completely switched to the target network slice and is running stably, the scheduling platform sends a command to the management unit of the source network slice to release the resources occupied by the user equipment's service on the source network slice, thereby completing the entire resource allocation and service migration process.

[0123] For example, following the specific implementation of the previous step, firstly, based on the finally determined target resource reservation parameter of 8Mbps, a resource pre-allocation request is sent to the management unit of the target network slice C, requesting the reservation of 8Mbps bandwidth; secondly, after the management unit of slice C successfully reserves the bandwidth, it returns confirmation information, which includes the IP address range and QoS parameters allocated for this service; then, after receiving the confirmation, the scheduling platform immediately sends a switching instruction to the user equipment, which includes the carrier frequency information of slice C and the resource access parameters such as the newly allocated IP address; then, the user equipment starts to access slice C according to the switching instruction; subsequently, it is detected that the user equipment has successfully registered on slice C, that is, its video call data stream is routed from slice B to slice C; finally, after the call is stable on slice C, slice B is notified to release the original resources reserved for the user.

[0124] Finally, this step accurately transforms the resource parameters calculated in the early stage into actual network resource allocation and service carrying through standardized signaling interaction and network control operations. The entire process is interconnected, ensuring that resources are in place before service switching is triggered, effectively reducing service interruption time, and realizing automated management of the entire lifecycle of resources from prediction to reservation, and then to final use and release, ensuring the smoothness of service experience and the efficiency of resource utilization.

[0125] Figure 2 This application provides a schematic diagram of the structure of an optimization management system based on network resource scheduling, as shown below. Figure 2 As shown, the system includes: The determination module 21 is used to determine the target resource reservation strategy based on the historical service data of the user equipment, wherein the historical service data includes service attribute information and accessed network slice information. Analysis module 22 is used to analyze and obtain the slice migration pattern of the user equipment based on the network slice information in the historical service data; Integration module 23 is used to associate and integrate the slice migration rules with the resource reservation strategies of the corresponding business types to form a joint scheduling strategy; The correction module 24 is used to adaptively correct the initial resource reservation parameters in the joint scheduling strategy based on the service attribute information corresponding to the new service request and the slice migration status reflected by the new service request when a new service request is received from the user equipment, so as to obtain the target resource reservation parameters. The execution module 25 is used to perform resource allocation and service migration for the new service request on the target network slice according to the target resource reservation parameters.

[0126] Figure 2 The aforementioned optimization management system based on network resource scheduling can execute... Figure 1 The implementation principle and technical effects of the network resource scheduling-based optimization management method described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit performs operations in the network resource scheduling-based optimization management system described in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0127] In one possible design, Figure 2 An optimization management system based on network resource scheduling, as shown in the embodiment, can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0128] The processing component 32 is used for the above Figure 1 The above embodiment is an optimization management method based on network resource scheduling.

[0129] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0130] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0131] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0132] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0133] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0134] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0135] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The illustrated embodiment presents an optimized management method based on network resource scheduling.

[0136] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0137] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0138] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application 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 this application.

Claims

1. An optimization management method based on network resource scheduling, characterized in that, include: Based on the user equipment’s historical service data, a target resource reservation strategy is determined, wherein the historical service data includes service attribute information and accessed network slice information. Based on the network slice information in the historical service data, the slice migration pattern of the user equipment is analyzed. The slice migration rules are associated and integrated with the resource reservation strategies of the corresponding business types to form a joint scheduling strategy; When a new service request is received from the user equipment, the initial resource reservation parameters in the joint scheduling strategy are adaptively modified based on the service attribute information corresponding to the new service request and the slice migration status reflected therein, so as to obtain the target resource reservation parameters. Based on the target resource reservation parameters, resource allocation and service migration are performed on the target network slice for the new service request.

2. The method according to claim 1, characterized in that, Based on the user equipment's historical service data, a target resource reservation strategy is determined, wherein the historical service data includes service attribute information and accessed network slice information, including: Extract the value distribution of the business attribute information and the access frequency of the network slice information from the historical business data; Based on the value distribution of the business attribute information, business requests that meet the preset conditions are grouped into the same business type cluster; For each business type cluster, the fluctuation range of resource usage by business requests within that business type cluster during a preset period is statistically analyzed. The basic resource reservation amount for the business type cluster is determined based on the upper bound of the resource fluctuation range. Based on the access frequency of the network slice information, identify the slice access sequence pattern that recurs in continuous service requests of the user equipment. Bind the slice access sequence pattern to the corresponding business type cluster; Based on the basic resource reservation amount and the bound slice access sequence pattern, the target resource reservation strategy is output.

3. The method according to claim 1, characterized in that, Based on the network slice information in the historical service data, the slice migration pattern of the user equipment is analyzed, including: From the historical service data, the network slice identifiers accessed by the user equipment when it initiated the service request are extracted in chronological order to form a slice access sequence. In the slice access sequence, a slice transfer segment composed of at least two different network slice identifiers in chronological order of access timestamps is identified; Count the number of times each slice transfer segment appears in the slice access sequence, and mark the slice transfer segment whose repetition exceeds a set threshold as the target slice transfer mode; Based on the number of network slice identifiers included in the target slice transfer mode, the target slice transfer mode is divided into different levels of migration modes, and the combination conditions of the starting network slice identifier and service attribute information that trigger each level of migration mode are determined. The migration patterns at different levels and their corresponding combination conditions are correlated and integrated to obtain the slice migration rules.

4. The method according to claim 1, characterized in that, The slice migration rules are correlated and integrated with the resource reservation strategies for corresponding business types to form a joint scheduling strategy, including: Extract the target business type cluster and the target basic resource reservation amount from the target resource reservation strategy; Extract the target migration pattern and the corresponding combination conditions from the slice migration pattern; The target business type cluster is matched with the target combination conditions. When the match is successful, a mapping relationship is established between the target basic resource reservation amount corresponding to the target business type cluster and the successfully matched target migration mode. Based on the established mapping relationship, generate a strategy entry; Repeatedly extract the target service type cluster and target basic resource reservation amount, extract the target migration mode and the corresponding combination conditions of the target migration mode, establish mapping relationship and generate policy entries, and collect all policy entries to obtain the joint scheduling policy.

5. The method according to claim 1, characterized in that, When a new service request is received from the user equipment, based on the service attribute information corresponding to the new service request and the reflected slice migration status, the initial resource reservation parameters in the joint scheduling strategy are adaptively modified to obtain the target resource reservation parameters, including: Parse the new service attribute information and the new starting network slice identifier from the new service request; The new service attribute information is matched with the service type clusters corresponding to each strategy entry in the joint scheduling strategy to determine the new service type clusters; The new starting network slice identifier is matched with the combination conditions corresponding to each policy entry in the joint scheduling policy to determine the new migration mode; Based on the new business type cluster and the new migration mode, find the corresponding target basic resource reservation amount from the joint scheduling strategy; Identify the slice migration path indicated by the new service request, and compare the slice migration path with the new migration mode; Based on the comparison results, the initial resource reservation parameters are adjusted to obtain the target resource reservation parameters.

6. The method according to claim 5, characterized in that, Based on the comparison results, the initial resource reservation parameters are adjusted to obtain the target resource reservation parameters, including: Calculate the difference between the number of network slices included in the slice migration path and the number of network slices included in the new migration mode; When the difference is negative, the initial resource reservation amount is reduced according to the first preset ratio to obtain the first adjusted resource amount as the target resource reservation parameter; When the difference is positive, the initial resource reservation amount is increased according to the second preset ratio to obtain the second adjusted resource amount as the target resource reservation parameter; When the difference is zero, the initial resource reservation amount remains unchanged as the target resource reservation parameter.

7. The method according to claim 1, characterized in that, Based on the target resource reservation parameters, perform resource allocation and service migration for the new service request on the target network slice, including: Based on the target resource reservation parameters, a resource pre-allocation request is sent to the management unit of the target network slice. The resource pre-allocation request includes the type and quantity of resources that need to be reserved. The system receives resource pre-allocation confirmation information returned by the management unit of the target network slice, the confirmation information including the identifier and access parameters of the allocated resources; After receiving the resource pre-allocation confirmation information, a network switching instruction is sent to the user equipment. The switching instruction includes the access information and resource access parameters of the target network slice. Monitor the connection establishment process from the user equipment to the target network slice, and after confirming that the connection is successfully established, route the user equipment's service data flow from the source network slice to the target network slice; After the business data flow switch is completed, release the resources occupied by the user on the source network slice.

8. An optimization management system based on network resource scheduling, characterized in that, include: The determination module is used to determine the target resource reservation strategy based on the historical service data of the user equipment, wherein the historical service data includes service attribute information and network slice information accessed. The analysis module is used to analyze the network slice information in the historical service data to obtain the slice migration pattern of the user equipment; The integration module is used to associate and integrate the slice migration rules with the resource reservation strategies of the corresponding business types to form a joint scheduling strategy; The correction module is used to adaptively correct the initial resource reservation parameters in the joint scheduling strategy based on the service attribute information corresponding to the new service request and the slice migration status reflected therein when a new service request is received from the user equipment, so as to obtain the target resource reservation parameters. The execution module is used to perform resource allocation and service migration for the new service request on the target network slice according to the target resource reservation parameters.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement an optimized management method based on network resource scheduling as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements an optimization management method based on network resource scheduling as described in any one of claims 1 to 7.

Images