Adjustment method and system for 5G network slice

Abstract

The invention discloses an adjustment method and system for 5G network slices, and relates to the field of 5G networks, and the method comprises the steps: obtaining historical demand information of a target service; determining an initial network slicing strategy based on the historical demand information; determining an initial network slice based on the initial network slice strategy; monitoring performance data of each initial network slice; obtaining priority information of a target service corresponding to each network slice; the initial network slice is adjusted based on the performance data and the priority information to determine an optimized network slice.

Description

Technical Field

[0001] This specification relates to the field of 5G networks. More specifically, the present application relates to an adjustment method and system for 5G network slicing. Background Art

[0002] With the rapid development of 5G technology, network slicing, as a key technology, allows operators to create multiple independent virtual networks on a shared physical network infrastructure. Each network slice can independently allocate resources and set quality of service (QoS) parameters according to different service requirements. This flexible network resource management method greatly improves network utilization and service quality. However, existing network slicing management solutions usually rely on preset strategies and cannot flexibly respond to dynamically changing network environments and service requirements, resulting in low resource utilization efficiency and inability to effectively guarantee the priority of key services. Summary of the invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0004] In a first aspect, the present application proposes a method for adjusting 5G network slicing, including:

[0005] Obtain historical demand information for target services;

[0006] Determine the initial network slicing strategy based on the above historical demand information;

[0007] Based on the above initial network slicing strategy, determine the initial network slice;

[0008] Monitor the performance data of each of the above initial network slices;

[0009] Obtain the priority information of the target service corresponding to each network slice;

[0010] Adjustments are made to the initial network slice based on the performance data and the priority information to determine an optimized network slice.

[0011] In a feasible implementation manner, determining the initial network slicing strategy based on the historical demand information includes:

[0012] A preset network slicing strategy is obtained by using a genetic algorithm based on the historical demand information, wherein the historical demand information includes bandwidth usage information, latency requirement information, and connection density information of the target service, the bandwidth usage information is obtained from a network log, the latency requirement information is obtained from a user usage record, and the connection density information is obtained from service load data;

[0013] The initial network slicing strategy is determined based on the above preset network slicing strategy through the reinforcement learning algorithm.

[0014] In a feasible implementation manner, the method of obtaining a preset network slicing strategy by using a genetic algorithm based on the historical demand information includes:

[0015] Define the encoding method of the network slicing strategy, encode the bandwidth usage information, latency requirement information and connection density information of each of the above target services, and represent them as genes in the chromosome;

[0016] Randomly extract typical resource allocation patterns from historical demand information and randomly generate an initial population;

[0017] Design a fitness function to evaluate the quality of each chromosome;

[0018] Based on the above fitness function, selection operation, crossover operation and mutation operation are performed, and iterative operation is continuously performed until the fitness function improvement rate is less than a preset threshold or the number of iterations reaches a preset number, and the above preset network slicing strategy is output.

[0019] In a feasible implementation manner, the above-mentioned determining the initial network slicing strategy according to the above-mentioned preset network slicing strategy by using the reinforcement learning algorithm includes:

[0020] The network environment is modeled as the environment state in reinforcement learning, and the above-mentioned preset network slicing strategy is modeled as the behavior of the agent, where the above-mentioned environment state includes the current network state, resource utilization and service demand:

[0021] Design a reward function to evaluate the quality of each action;

[0022] Adopt Q-learning reinforcement learning algorithm, aiming to maximize the cumulative reward, and update the strategy through repeated interaction with the environment;

[0023] At each time step, the agent observes the current state, selects an action to adjust the network slicing strategy, and updates the network slicing strategy based on the above reward function;

[0024] When the preset number of iterations and / or strategy convergence is reached, the above initial network slicing strategy is output.

[0025] In a feasible implementation manner, adjusting the initial network slice based on the performance data and the priority information to determine an optimized network slice includes:

[0026] Defining multiple objective functions according to the performance data and the priority information, wherein the performance data includes delay data, bandwidth utilization data, energy consumption data, and service quality data; the multiple objective functions include a delay objective function, a bandwidth utilization objective function, an energy consumption objective function, and a service quality objective function, each objective function includes a priority information, and the priority information is used to adjust the weight of the objective function;

[0027] The NSGA-II algorithm is used to perform multi-objective optimization on all objective functions to adjust the above-mentioned initial network slices and determine the optimized network slices, wherein the above-mentioned optimized network slices include resource allocation slices, service quality slices, bandwidth slices, delay optimization slices and energy consumption optimization slices.

[0028] In a feasible implementation manner, the above-mentioned optimized network slice also includes a resource isolation slice and a resource protection slice.

[0029] The above method further includes:

[0030] Obtain performance bottleneck information and exception information;

[0031] Determine the resource isolation slice and resource protection slice based on the above performance bottleneck information, the above exception information and the above priority information.

[0032] In a feasible implementation manner, the determining of the resource isolation slice and the resource protection slice based on the performance bottleneck information, the exception information and the priority information includes:

[0033] Analyze the above performance bottleneck information and the above abnormal information based on a hierarchical clustering algorithm to obtain multiple categories of candidate areas;

[0034] Calculate the priority score of each category of candidate areas according to the priority information corresponding to all target services in each category of candidate areas;

[0035] The resource isolation slice and resource protection slice are determined based on the priority score and priority score threshold of each category of candidate areas.

[0036] In a feasible implementation manner, the above-mentioned calculation of the priority score of each category of the candidate area according to the priority information corresponding to all target services in each category of the candidate area includes:

[0037] The priority score S(Ci) is calculated according to the following formula:

[0038]

[0039] Among them, p ij Indicates the priority of the target service, w ij For C i The weight coefficient corresponding to the jth target service in the category to be selected area is, i is the index of the category to be selected area, and j is the index of a target service in the category to be selected area.

[0040] In a feasible implementation manner, the specific steps of determining the weight coefficients corresponding to the target services in each category of the to-be-selected area include:

[0041] Determine the service importance basic weight coefficient corresponding to the target service in each category of the candidate area based on the number of service users, business revenue contribution and business continuity requirements of each target service in each category of the candidate area;

[0042] Determine the resource occupancy basic weight coefficient corresponding to the target service in each category of the to-be-selected area based on the bandwidth information, CPU utilization information and storage space information of each target service in each category of the to-be-selected area;

[0043] The weight coefficients corresponding to the target services in the above-mentioned categories of selected areas are determined based on the above-mentioned service importance basic weight coefficients, the above-mentioned resource occupancy basic weight coefficients, the first weight coefficients and the second weight coefficients corresponding to the above-mentioned target services in the above-mentioned categories of selected areas, wherein the above-mentioned first weight coefficient is the weight coefficient corresponding to the above-mentioned service importance basic weight coefficient, and the above-mentioned second weight coefficient is the weight coefficient corresponding to the above-mentioned resource occupancy basic weight coefficient.

[0044] In a second aspect, the present application provides a 5G network slice adjustment system, including:

[0045] A first acquisition unit, used to acquire historical demand information of a target service;

[0046] A first determining unit, configured to determine an initial network slicing strategy based on the historical demand information;

[0047] A second determining unit is used to determine an initial network slice based on the initial network slicing strategy;

[0048] A monitoring unit, configured to monitor the performance data of each of the initial network slices;

[0049] A second acquisition unit is used to obtain priority information of a target service corresponding to each network slice;

[0050] An adjustment unit is used to adjust the above-mentioned initial network slice based on the above-mentioned performance data and the above-mentioned priority information to determine an optimized network slice.

[0051] In summary, the adjustment method for 5G network slicing in the embodiment of the present application includes: obtaining historical demand information of the target service; determining the initial network slicing strategy based on the above historical demand information; determining the initial network slice based on the above initial network slicing strategy; monitoring the performance data of each of the above initial network slices; obtaining the priority information of the target service corresponding to each network slice; adjusting the above initial network slice based on the above performance data and the above priority information to determine the optimized network slice. In the prior art, the network slicing strategy is usually based on static configuration, which is difficult to cope with the dynamically changing network environment. The present application can dynamically adjust the network slicing strategy by real-time monitoring of the performance data of the network slice and combining the priority information of the target service, so that the network resource allocation is more flexible and can quickly respond to changes in network conditions. In the existing scheme, the preset network slicing strategy may cause over-allocation or under-allocation of resources, affecting the overall efficiency of the network. The present application analyzes the historical demand information of the target service, formulates the initial network slicing strategy, and optimizes it based on real-time data to ensure that resources can be more reasonably allocated and used, and maximize the utilization of network resources. The present application pays special attention to the priority management of the target service. After obtaining the service priority information corresponding to each network slice, the system can give priority to the performance requirements of high-priority services when resources are limited. This is of great significance for ensuring the service quality of key businesses, especially when multiple services are running concurrently, and can effectively avoid service performance degradation caused by resource competition. This application is applicable to various complex network environments and diversified service needs. Whether in mobile network scenarios where user needs fluctuate frequently, or in enterprise private networks with strict service quality requirements, this solution can provide an effective network slicing adjustment method to ensure network stability and service quality. Through these improvements, this application can better meet the diverse and complex service needs in 5G networks, achieve efficient management of network resources and stable guarantee of high-quality services, and has significant technical advancement and practical application value.

[0052] The adjustment method for 5G network slicing proposed in this application and other advantages, objectives and features of the application will be reflected in part through the following description, and in part will be understood by technical personnel in this field through research and practice of the application. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0054] Figure 1A schematic diagram of a process for adjusting a 5G network slice provided in an embodiment of the present application;

[0055] Figure 2 A video transmission system for live vocal music teaching is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0057] See also Figure 1 , which is a flow diagram of a method for adjusting 5G network slicing provided in an embodiment of the present application, including:

[0058] S110, obtaining historical demand information of the target service;

[0059] S120. Determine an initial network slicing strategy based on the historical demand information.

[0060] S130. Determine an initial network slice based on the initial network slicing strategy.

[0061] S140. Monitor the performance data of each of the initial network slices.

[0062] S150. Obtain priority information of the target service corresponding to each network slice;

[0063] S160. Adjust the initial network slice based on the performance data and the priority information to determine the optimized network slice.

[0064] Exemplarily, the system collects historical demand information related to the target service. This information includes but is not limited to bandwidth usage information, latency requirement information, and connection density information of the target service in the past period of time. This data provides a basis for the formulation of network slicing strategies in subsequent steps.

[0065] After collecting historical demand information, the system will determine an initial network slicing strategy based on this information. This strategy will define how to allocate resources for target services in the network to ensure service quality and efficiency.

[0066] According to the previously determined initial network slicing strategy, the system will generate specific initial network slices. Each network slice corresponds to a certain resource allocation method to ensure that specific target services can get resources that meet their needs.

[0067] After the initial network slice configuration is completed, the system will monitor the performance data of each network slice in real time. These performance data may include bandwidth utilization, latency, packet loss rate, etc., in order to evaluate the actual operation effect of the network slice.

[0068] The system also obtains the priority information of the target service corresponding to each network slice. The priority information determines the order and importance of resource allocation between different services. For example, some critical services may have a higher priority and their performance needs to be guaranteed first.

[0069] Finally, the system will adjust the initial network slice based on the collected performance data and priority information. These adjustments are designed to optimize the allocation of network resources, ensure that high-priority target services can obtain sufficient resources in the network, and improve the efficiency and performance of the overall network slice. Finally, the optimized network slice configuration is determined.

[0070] In summary, in the prior art, network slicing strategies are usually based on static configurations, which are difficult to cope with dynamically changing network environments. The present application can dynamically adjust the network slicing strategy by real-time monitoring of the performance data of network slices and combining the priority information of the target service, so that network resource allocation is more flexible and can quickly respond to changes in network conditions. In the existing scheme, the preset network slicing strategy may lead to over-allocation or under-allocation of resources, affecting the overall efficiency of the network. The present application analyzes the historical demand information of the target service, formulates the initial network slicing strategy, and optimizes it based on real-time data to ensure that resources can be more reasonably allocated and used, and maximize the utilization of network resources. The present application pays special attention to the priority management of the target service. After obtaining the service priority information corresponding to each network slice, the system can give priority to guaranteeing the performance requirements of high-priority services when resources are limited. This is of great significance for the service quality assurance of key businesses, especially when multiple services are running concurrently, it can effectively avoid the degradation of service performance caused by resource competition. The present application is applicable to various complex network environments and diversified service requirements. Whether in mobile network scenarios where user demand fluctuates frequently or in enterprise private networks with strict service quality requirements, the solution can provide an effective network slicing adjustment method to ensure network stability and service quality. Through these improvements, this application can better meet the diversified and complex service needs in 5G networks, achieve efficient management of network resources and stable guarantee of high-quality services, and has significant technological advancement and practical application value.

[0071] In some examples, determining the initial network slicing strategy based on the historical demand information includes:

[0072] A preset network slicing strategy is obtained by using a genetic algorithm based on the historical demand information, wherein the historical demand information includes bandwidth usage information, latency requirement information and connection density information of the target service, the bandwidth usage information is obtained from a network log, the latency requirement information is obtained from a user usage record, and the connection density information is obtained from service load data;

[0073] The initial network slicing strategy is determined based on the above preset network slicing strategy through the reinforcement learning algorithm.

[0074] Exemplarily, historical demand information is obtained from a variety of data sources, including network logs, user usage records, business load data, etc. These data sources provide key performance indicator information of the target service, such as bandwidth usage information, latency requirement information, and connection density information. This information describes the target service's demand for network resources in different time periods, providing data support for subsequent steps.

[0075] After collecting historical demand information, the system will use genetic algorithms to obtain a preset network slicing strategy based on this information. The strategy will predefine how to allocate resources for target services in the network to get as close to the best service quality as possible. Based on the preset network slicing strategy obtained by the genetic algorithm, the system further determines the initial network slicing strategy through a reinforcement learning algorithm.

[0076] The embodiment of the present application combines genetic algorithms and reinforcement learning algorithms to form a network slicing strategy formulation process that can not only consider historical demand information but also continuously optimize in a dynamic environment. This method can achieve more efficient resource management and better service guarantee in complex 5G networks.

[0077] In some examples, the method of obtaining a preset network slicing strategy based on the historical demand information by using a genetic algorithm includes:

[0078] Define the encoding method of the network slicing strategy, encode the bandwidth usage information, latency requirement information and connection density information of each of the above target services, and represent them as genes in the chromosome;

[0079] Randomly extract typical resource allocation patterns from historical demand information and randomly generate an initial population;

[0080] Design a fitness function to evaluate the quality of each chromosome;

[0081] Based on the above fitness function, selection operation, crossover operation and mutation operation are performed, and iterative operation is continuously performed until the fitness function improvement rate is less than a preset threshold or the number of iterations reaches a preset number, and the above preset network slicing strategy is output.

[0082] For example, before starting the optimization, it is necessary to first define the encoding method of the network slicing strategy. In this scheme, the encoding method is to represent the bandwidth usage information, latency requirement information, and connection density information of each target service as genes in the chromosome. Each gene represents a specific resource allocation strategy, and the entire chromosome represents a complete network slicing strategy.

[0083] To start the optimization process of the genetic algorithm, typical resource allocation patterns are first randomly extracted from historical demand information, and an initial population is randomly generated based on these patterns. Each individual in this initial population is a possible network slicing strategy, which is generated in a random manner to ensure that the population has diversity so that there are more possibilities to find the optimal solution in subsequent iterations.

[0084] In order to evaluate the pros and cons of each individual (i.e. each network slicing strategy), a fitness function is designed. This fitness function is used to measure the effectiveness of the strategy, which is specifically expressed as:

[0085] F(x)=α·U(x)+β·Q(x)-γ·C(x)

[0086] Among them, U(x) represents resource utilization, Q(x) represents service quality, C(x) represents cost, and α, β, and γ are weight parameters; these three indicators jointly determine the pros and cons of the network slicing strategy. The higher the resource utilization, the better the service quality, and the lower the cost, the higher the adaptability of the strategy.

[0087] In each iteration, individuals in the population are selected based on the fitness function, and individuals with higher fitness are retained first. Then, two chromosomes (i.e., two network slicing strategies) are combined through a crossover operation to generate new individuals. At the same time, mutation operations are applied to randomly modify certain gene values ​​to increase the diversity of the population and prevent falling into a local optimal solution.

[0088] The genetic algorithm continuously performs selection, crossover and mutation operations, and gradually optimizes the individuals in the population through iterative operations. When the improvement rate of the fitness function is less than the preset threshold, or the number of iterations reaches the preset number, the algorithm terminates and outputs the final preset network slicing strategy.

[0089] Through the method proposed in this embodiment, the system can extract an optimized preset network slicing strategy from historical demand information, laying the foundation for the formulation of subsequent initial network slicing strategies. This method ensures efficient use of network resources, improves service quality, and provides a better network slicing solution while meeting certain cost constraints.

[0090] In some examples, the determining of the initial network slicing strategy according to the preset network slicing strategy by the reinforcement learning algorithm includes:

[0091] The network environment is modeled as the environment state in reinforcement learning, and the above-mentioned preset network slicing strategy is modeled as the behavior of the agent, where the above-mentioned environment state includes the current network state, resource utilization and service demand:

[0092] Design a reward function to evaluate the quality of each action;

[0093] Adopt Q-learning reinforcement learning algorithm, aiming to maximize the cumulative reward, and update the strategy through repeated interaction with the environment;

[0094] At each time step, the agent observes the current state, selects an action to adjust the network slicing strategy, and updates the network slicing strategy based on the above reward function;

[0095] When the preset number of iterations and / or strategy convergence is reached, the above initial network slicing strategy is output.

[0096] Exemplarily, the network environment is modeled as the environment state in reinforcement learning. Specifically, the environment state includes the current network state, resource utilization, and service demand. This state information provides the context of the current network slicing strategy, allowing the agent to make reasonable decisions based on this information.

[0097] The above preset network slicing strategy is modeled as the behavior of the intelligent agent. The behavior of the intelligent agent is to select a specific network slicing strategy or adjust the existing strategy under a given environmental state. Through this modeling, each action of the intelligent agent corresponds to an adjustment of the network slicing strategy.

[0098] Design a reward function to evaluate the quality of each action. The above reward function is:

[0099] R(s,a)=δ·Q(s,a)-∈·D(s,a)

[0100] Among them, Q(s,a) represents the service quality improvement obtained after taking action a in state s, D(s,a) represents the cost of resource use, and δ,∈ are the corresponding weight information; the goal of the reward function is to maximize the improvement of service quality while minimizing the cost of resource use.

[0101] The Q-learning reinforcement learning algorithm is used to continuously interact with the environment and update the strategy to maximize the cumulative reward. At each time step, the agent observes the current state and selects an optimal action to adjust the network slicing strategy. The agent will use the Q-learning algorithm to update its strategy based on the reward obtained after executing the action, so that the strategy is gradually optimized and can better cope with different network states and service requirements.

[0102] At each time step, the agent observes the current state and selects an action based on the Q-learning algorithm, which corresponds to the adjustment of the network slicing strategy. The agent then calculates the quality of the action based on the above reward function and uses this information to update the strategy. Through continuous strategy updates, the agent can learn which network slicing strategies can bring the greatest cumulative rewards under different environmental conditions.

[0103] When the preset number of iterations and / or policy convergence is reached, the algorithm stops and outputs the final initial network slicing policy. At this point, the policy has been iterated and optimized many times and can better balance the relationship between service quality improvement and resource usage cost.

[0104] Through the method provided in this embodiment, the system can continuously optimize the network slicing strategy based on the reinforcement learning algorithm in a dynamic and complex network environment, thereby effectively improving the utilization rate and service quality of network resources. The final determined initial network slicing strategy can adapt to diverse service requirements and perform well in various environments.

[0105] In some examples, adjusting the initial network slice based on the performance data and the priority information to determine an optimized network slice includes:

[0106] Defining multiple objective functions according to the performance data and the priority information, wherein the performance data includes delay data, bandwidth utilization data, energy consumption data, and service quality data; the multiple objective functions include a delay objective function, a bandwidth utilization objective function, an energy consumption objective function, and a service quality objective function, each objective function includes a priority information, and the priority information is used to adjust the weight of the objective function;

[0107] The NSGA-II algorithm is used to perform multi-objective optimization on all objective functions to adjust the above-mentioned initial network slices and determine the optimized network slices, wherein the above-mentioned optimized network slices include resource allocation slices, service quality slices, bandwidth slices, delay optimization slices and energy consumption optimization slices.

[0108] Exemplary performance data include:

[0109] Latency data: indicates the response time of services in the network slice, which directly affects the user experience.

[0110] Bandwidth utilization data: Indicates the actual usage of network bandwidth as a percentage of available bandwidth.

[0111] Energy consumption data: represents the energy consumed during the operation of network slicing, which is related to the energy efficiency of the network.

[0112] Service quality data: indicates the overall quality of services provided by the network slice to users, which may include multiple indicators such as packet loss rate and jitter.

[0113] In the process of adjusting the initial network slice, multiple objective functions are defined based on the above-mentioned delay data, bandwidth utilization data, energy consumption data, service quality data and priority information. Each objective function corresponds to one of the above-mentioned performance data, and includes priority information for adjusting the weight of the objective function.

[0114] Delay objective function: reflects the impact of network delay on overall performance. Priority information is used for weighted calculation so that high-priority services receive more attention in terms of delay.

[0115] Bandwidth utilization objective function: reflects the impact of bandwidth utilization on network resources. Priority information is used to adjust the weight of bandwidth utilization to ensure the bandwidth requirements of high-priority services.

[0116] Energy consumption objective function: reflects the energy consumption during network operation. Priority information is used to adjust the weight of the energy consumption target to ensure that energy consumption is optimized in the case of high priority services.

[0117] Service quality objective function: reflects the impact of network service quality on user experience. Priority information is used to adjust the weight of service quality to ensure that the quality requirements of high-priority services are met.

[0118] After defining the objective functions, the NSGA-II algorithm is used to perform multi-objective optimization on all objective functions. NSGA-II is an advanced evolutionary algorithm that can effectively handle multiple conflicting objectives and generate a set of Pareto optimal solutions.

[0119] Initial population generation: Generate an initial population containing multiple candidate network slicing strategies, each of which is an individual and represents a possible network slicing adjustment solution.

[0120] Fitness evaluation: For each individual in the population, the fitness is evaluated according to the defined objective function. Since each objective function contains priority information, more optimization weights will be automatically given to high-priority services during the evaluation process.

[0121] Non-dominated sorting and selection: NSGA-II sorts individuals by non-dominated sorting and retains those individuals that perform well on each objective function.

[0122] Crossover and mutation operations: Generate new individuals through crossover and mutation operations to maintain the diversity of the population and explore new network slicing strategies.

[0123] Iterative optimization: fitness evaluation, non-dominated sorting, selection, crossover, and mutation operations are performed repeatedly until the preset number of iterations or convergence conditions are reached.

[0124] Resource allocation slicing: used to manage the dynamic allocation of network resources, adjusting them based on real-time demand and performance data.

[0125] Quality of Service Slicing (QoS Slicing): Ensures that the quality requirements of specific services are met and provides different resource guarantees for services of different priorities.

[0126] Bandwidth slicing: used to ensure bandwidth requirements between different applications and adjust according to network load.

[0127] Latency-optimized slicing: specifically used for low-latency services, such as autonomous driving, telemedicine, and other application scenarios that require extremely low latency.

[0128] Energy-optimized slices: Slices designed for energy-saving optimization and suitable for energy-sensitive network scenarios.

[0129] Finally, a set of Pareto optimal solutions generated by the NSGA-II algorithm represent different optimized network slicing strategies. These strategies make trade-offs between different objective functions, taking into account multiple performance indicators such as latency, bandwidth utilization, energy consumption, and service quality, while fully considering the impact of priority information. The system can select an optimal solution as the final optimized network slice according to specific needs.

[0130] In some examples, the above-mentioned optimized network slice also includes resource isolation slice and resource protection slice.

[0131] The above method further includes:

[0132] Obtain performance bottleneck information and exception information;

[0133] Determine the resource isolation slice and resource protection slice based on the above performance bottleneck information, the above exception information and the above priority information.

[0134] Exemplarily, the optimization of network slices includes not only general network slicing strategies, but also resource isolation slices and resource protection slices. The method obtains performance bottleneck information and exception information, and determines resource isolation slices and resource protection slices in combination with priority information, thereby further optimizing the allocation and utilization of network resources.

[0135] First, by monitoring the network operation status, obtain performance bottleneck information and abnormal information. This information includes but is not limited to:

[0136] Performance bottleneck information: reflects areas in the network where there are resource shortages or service quality degradation, such as insufficient bandwidth, high latency, or overloaded computing resources.

[0137] Abnormal information: reflects abnormal events or emergencies that occur in the network, such as network congestion, link failure, or service interruption.

[0138] After obtaining performance bottleneck information and exception information, combined with priority information, the system begins to determine resource isolation slices and resource protection slices. Priority information indicates the importance of different services, ensuring that high-priority services are given priority in resource allocation.

[0139] Resource isolation slices: Resource isolation slices are used to isolate resource areas affected by performance bottleneck information and exception information to prevent these problems from spreading to other network slices and affecting overall network performance. By analyzing performance bottleneck information and exception information, determine which resource areas may need to be isolated based on this information. Combined with priority information, if some low-priority services occupy resources that may be required by high-priority services, these low-priority services are isolated through resource isolation slices to ensure the resource requirements of high-priority services.

[0140] Resource protection slices are used to ensure that high-priority services can obtain sufficient resource support and maintain service quality in resource-constrained or abnormal situations. Combined with priority information, the resource requirements corresponding to high-priority services are identified, and resource protection slices are set up in possible resource areas based on these requirements. Resource protection slices ensure that when performance bottleneck information and abnormal information appear, the resources of high-priority services will not be occupied or interfered with by low-priority services.

[0141] In some examples, determining the resource isolation slice and the resource protection slice based on the performance bottleneck information, the exception information, and the priority information includes:

[0142] Analyze the above performance bottleneck information and the above abnormal information based on a hierarchical clustering algorithm to obtain multiple categories of candidate areas;

[0143] Calculate the priority score of each category of candidate areas according to the priority information corresponding to all target services in each category of candidate areas;

[0144] The resource isolation slice and resource protection slice are determined based on the priority score and priority score threshold of each category of candidate areas.

[0145] Exemplarily, a hierarchical clustering algorithm is used to analyze the acquired performance bottleneck information and abnormal information. The hierarchical clustering algorithm is an unsupervised learning algorithm that gradually aggregates similar data points into clusters by calculating the similarity or distance between data points.

[0146] The performance bottleneck information and anomaly information are used as input data to construct a data matrix. Each data point represents a specific performance bottleneck or anomaly, and the similarity between data points is calculated based on this information.

[0147] A hierarchical clustering algorithm is used to gradually aggregate similar performance bottleneck information and abnormal information into clusters. Through the clustering operation of the algorithm, the system can identify multiple categories of candidate areas, each of which represents a group of resource areas with similar performance bottlenecks and abnormal situations.

[0148] After obtaining multiple categories of candidate areas, the system will calculate the priority score of each category of candidate areas based on the priority information corresponding to all target services in each category of candidate areas. The specific steps are as follows:

[0149] Priority information integration: collects the priority information of all target services included in each category of the candidate area. The priority information of each target service indicates the importance of the service and is usually pre-defined by the service provider or network operator.

[0150] Priority score calculation: According to the formula, the priority information p of all target services in each category of the selected area is calculated. ij and the corresponding weight coefficient w ij Perform weighted summation to calculate the priority score S(C i ). The priority score reflects the overall importance of the candidate area in that category and the urgency of the resource needs.

[0151] After calculating the priority score for each category candidate area, the system determines the resource isolation slice and resource protection slice based on these scores and the preset priority score threshold. The priority score of each category candidate area is compared with the preset priority score threshold. The threshold is used to distinguish between high-priority areas and low-priority areas. For category candidate areas with priority scores below the threshold, the system identifies them as resource isolation slices. The resources in these slices will be isolated to prevent them from negatively affecting the overall network performance, especially in the event of performance bottlenecks or anomalies. For category candidate areas with priority scores above the threshold, the system identifies them as resource protection slices. The resources in these slices will be protected and allocated preferentially to ensure that high-priority services can maintain good performance and service quality when resources are tight.

[0152] In some examples, the above-mentioned calculating the priority score of each category of candidate areas according to the priority information corresponding to all target services in each category of candidate areas includes:

[0153] The priority score S(Ci) is calculated according to the following formula:

[0154]

[0155] Among them, p ij Indicates the priority of the target service, w ij For C i The weight coefficient corresponding to the jth target service in the category to be selected area is, i is the index of the category to be selected area, and j is the index of a target service in the category to be selected area.

[0156] For example, P ij Indicates category candidate area C iThe priority of the target service j in the network. The priority reflects the importance of the target service in the entire network and is usually determined by pre-set business requirements or policies. High-priority target services are crucial to ensure service quality and user experience.

[0157] w ij Represents the weight coefficient of the target service j in the category candidate area Ci. This weight coefficient reflects the proportion or importance of the target service j in the category candidate area. The weight coefficient is usually determined by the resource requirements of the service, the number of users of the service, or other key indicators. It helps to further refine the evaluation of the importance of the target service to the entire category candidate area.

[0158] Priority score S(C i ) is through the category candidate area C i The priority of all target services in ij And its corresponding weight coefficient w ij Specifically, the priority P of each target service is ij The corresponding weight coefficient w ij Therefore, the result represents the importance contribution of the target service to the category candidate area. Then, the contribution values ​​of all target services are added together to obtain the overall priority score S(C i ).

[0159] The calculated priority score S(C i ) represents the category candidate area C i The overall priority of a resource. The higher the score, the more high-priority services are included in the candidate area of ​​this category, or the greater the demand for network resources for these services. Therefore, the priority score is an important basis for determining resource isolation areas and resource protection areas. According to the score, the system can reasonably allocate resources to ensure that high-priority target services are given priority when resources are tight, while low-priority services may be isolated or restricted to avoid affecting key services.

[0160] In some examples, the specific steps of determining the total weight coefficient of the target service in the category to be selected area include:

[0161] Determine the basic weight coefficient of service importance based on the number of service users, business revenue contribution and business continuity requirements of the target service;

[0162] Determine a resource occupancy basic weight coefficient based on bandwidth information, CPU utilization information, and storage space information of the target service;

[0163] The above-mentioned resource occupancy basic weight coefficient is determined based on the above-mentioned service importance basic weight coefficient, the above-mentioned resource occupancy basic weight coefficient, the first weight coefficient and the second weight coefficient, wherein the above-mentioned first weight coefficient is the weight coefficient corresponding to the above-mentioned service importance basic weight coefficient, and the above-mentioned second weight coefficient is the weight coefficient corresponding to the above-mentioned resource occupancy basic weight coefficient.

[0164] Exemplarily, the service importance basic weight coefficient is determined by analyzing three key indicators of the target service:

[0165] Number of service users: The number of service users directly reflects the user coverage of the service. The more users there are, the more important the service is.

[0166] Business revenue contribution: refers to the proportion of the service's contribution to the overall business revenue. Services with high business revenue contribution are usually considered strategically critical services and therefore have a higher importance.

[0167] Business continuity requirements: Some services may have extremely high requirements for business continuity, such as mission-critical or real-time services. The higher the business continuity requirements, the more important the service is.

[0168] By combining these three indicators, the basic weight coefficient of service importance is calculated, which reflects the relative importance of the target service in the entire business system.

[0169] It can be determined by the following formula:

[0170]

[0171] Wi mportance : The basic weight coefficient of service importance reflects the relative importance of the target service in the entire business system.

[0172] U i： The number of users of the target service.

[0173] R i :Business revenue contribution of target services.

[0174] C i :Business continuity requirements for target services.

[0175] U max : The maximum number of users in all services, used for normalization.

[0176] R max : The maximum value of business revenue contribution among all services, used for normalization.

[0177] C max : The maximum value of business continuity requirements among all services, used for normalization.

[0178] α, β, and γ are weight coefficients for the number of users, business revenue contribution, and business continuity requirements, respectively, and are used to adjust the impact of each indicator on the overall weight. These weights can be set according to actual business needs to reflect the importance of each indicator.

[0179] Next, the resource usage basic weight coefficient is determined based on the bandwidth information, CPU utilization information, and storage space information of the target service:

[0180] Bandwidth information: indicates the amount of bandwidth occupied by the target service in the network. The larger the bandwidth occupied, the higher the resource demand.

[0181] CPU utilization information: reflects the computing resource (CPU) usage of the target service during processing. High CPU utilization indicates that the service requires more computing resources.

[0182] Storage space information: The amount of storage space required by a service is also an important factor in measuring its resource usage. The larger the storage space required, the higher the resource usage.

[0183] Based on the above resource occupancy indicators, the basic weight coefficient of resource occupancy is calculated, which quantifies the intensity of the target service's demand for network and computing resources.

[0184] Finally, the total weight coefficient of the target service is determined by combining the service importance basic weight coefficient and resource occupancy basic weight coefficient obtained above and applying the two weight coefficients:

[0185] First weighting factor: related to the service importance basic weighting factor, reflecting the proportion of service importance in the total weight. For example, if the importance of the service is critical to the business, the first weighting factor will be larger, indicating that the service importance weight is higher when calculating the total weight.

[0186] Second weight coefficient: related to the basic weight coefficient of resource usage, reflecting the proportion of resource usage in the total weight. If a service consumes a large amount of resources, the second weight coefficient will be larger, indicating that the resource usage contributes more to the total weight.

[0187] Calculate the total weight coefficient: Combine the service importance basic weight coefficient and resource occupancy basic weight coefficient by weighted average. The specific formula is:

[0188] Total weight coefficient = (first weight coefficient × service importance basic weight coefficient) + (second weight coefficient × resource occupancy basic weight coefficient)

[0189] This total weight coefficient will serve as the final weight of the target service in the category candidate area and determine the priority of the service in resource allocation and optimization strategy.

[0190] The method provided in this embodiment can scientifically and reasonably determine the total weight coefficient of the target service in the category selection area. First, the importance of the service is analyzed and the basic weight coefficient of the service importance is calculated; then, the resource occupancy is evaluated to obtain the basic weight coefficient of resource occupancy; finally, the total weight coefficient is calculated by combining the proportion coefficient. This weight coefficient provides an important basis for subsequent resource allocation and optimization, ensuring that key services can be given priority and optimal resource allocation.

[0191] In a second aspect, the present application provides a 5G network slice adjustment system, including:

[0192] A first acquisition unit 21 is used to acquire historical demand information of a target service;

[0193] A first determining unit 22 is used to determine an initial network slicing strategy based on the above historical demand information;

[0194] A second determining unit 23 is used to determine an initial network slice based on the initial network slicing strategy;

[0195] A monitoring unit 24, configured to monitor the performance data of each of the above initial network slices;

[0196] A second acquisition unit 25 is used to obtain priority information of a target service corresponding to each network slice;

[0197] The adjustment unit 26 is used to adjust the above-mentioned initial network slice based on the above-mentioned performance data and the above-mentioned priority information to determine the optimized network slice.

[0198] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for adjusting 5G network slices, characterized in that: include: Obtain historical demand information for target services; Determine an initial network slicing strategy based on the historical demand information; Based on the initial network slicing strategy, determine an initial network slice; Monitoring performance data of each of the initial network slices; Obtain the priority information of the target service corresponding to each network slice; Adjust the initial network slice based on the performance data and the priority information to determine an optimized network slice.

2. The adjustment method for 5G network slicing according to claim 1, characterized in that: The determining of the initial network slicing strategy based on the historical demand information includes: A preset network slicing strategy is obtained by using a genetic algorithm based on the historical demand information, wherein the historical demand information includes bandwidth usage information, delay requirement information, and connection density information of a target service, the bandwidth usage information is obtained from a network log, the delay requirement information is obtained from a user usage record, and the connection density information is obtained from service load data; An initial network slicing strategy is determined based on the preset network slicing strategy through a reinforcement learning algorithm.

3. The adjustment method for 5G network slicing according to claim 2, characterized in that: The obtaining a preset network slicing strategy by using a genetic algorithm based on the historical demand information includes: Define an encoding method for the network slicing strategy, encode the bandwidth usage information, latency requirement information, and connection density information of each target service, and represent them as genes in the chromosome; Randomly extract typical resource allocation patterns from historical demand information and randomly generate an initial population; Design a fitness function to evaluate the quality of each chromosome; Based on the fitness function, selection operations, crossover operations and mutation operations are performed, and iterative operations are continuously performed until the fitness function improvement rate is less than a preset threshold or the number of iterations reaches a preset number, and the preset network slicing strategy is output.

4. The adjustment method for 5G network slicing according to claim 2, characterized in that: The determining the initial network slicing strategy according to the preset network slicing strategy by using a reinforcement learning algorithm includes: The network environment is modeled as an environmental state in reinforcement learning, and the preset network slicing strategy is modeled as the behavior of an intelligent agent, wherein the environmental state includes the current network state, resource utilization, and service demand: Design a reward function to evaluate the quality of each action; Adopt Q-learning reinforcement learning algorithm, aiming to maximize the cumulative reward, and update the strategy through repeated interaction with the environment; At each time step, the agent observes the current state, selects an action to adjust the network slicing strategy, and updates the network slicing strategy according to the reward function; When the preset number of iterations and / or the strategy converges, the initial network slicing strategy is output.

5. The adjustment method for 5G network slicing according to claim 1, characterized in that: The adjusting the initial network slice based on the performance data and the priority information to determine an optimized network slice includes: Defining a plurality of objective functions according to the performance data and the priority information, wherein the performance data includes delay data, bandwidth utilization data, energy consumption data, and service quality data; the plurality of objective functions include a delay objective function, a bandwidth utilization objective function, an energy consumption objective function, and a service quality objective function, each objective function includes a priority information, and the priority information is used to adjust the weight of the objective function; The NSGA-II algorithm is used to perform multi-objective optimization on all objective functions to adjust the initial network slice and determine the optimized network slice, wherein the optimized network slice includes resource allocation slice, quality of service slice, bandwidth slice, delay optimization slice and energy consumption optimization slice.

6. The adjustment method for 5G network slicing according to claim 5, characterized in that: The optimized network slice also includes a resource isolation slice and a resource protection slice; The method further comprises: Obtain performance bottleneck information and exception information; Resource isolation slices and resource protection slices are determined based on the performance bottleneck information, the exception information and the priority information.

7. The adjustment method for 5G network slicing according to claim 6, characterized in that: The determining of the resource isolation slice and the resource protection slice based on the performance bottleneck information, the exception information and the priority information includes: Analyzing the performance bottleneck information and the abnormal information based on a hierarchical clustering algorithm to obtain multiple categories of candidate areas; Calculate the priority score of each category of the to-be-selected area according to the priority information corresponding to all target services in each category of the to-be-selected area; The resource isolation slice and resource protection slice are determined based on the priority score and priority score threshold of each category of candidate areas.

8. The adjustment method for 5G network slicing according to claim 7, characterized in that: The step of calculating the priority score of each category of the to-be-selected area according to the priority information corresponding to all target services in each category of the to-be-selected area comprises: The priority score S(Ci) is calculated according to the following formula: Among them, p ij Indicates the priority of the target service, w ij For C i The weight coefficient corresponding to the jth target service in the category to be selected area is, i is the index of the category to be selected area, and j is the index of a target service in the category to be selected area.

9. The adjustment method for 5G network slicing according to claim 8, characterized in that: The specific steps of determining the weight coefficients corresponding to the target services in each category of the selected area include: Determine the service importance basic weight coefficient corresponding to the target service in each category of the candidate area based on the number of service users, business revenue contribution and business continuity requirements of each target service in each category of the candidate area; Determine the resource occupancy basic weight coefficient corresponding to the target service in each category of the to-be-selected area based on the bandwidth information, CPU utilization information and storage space information of each target service in each category of the to-be-selected area; The weight coefficients corresponding to the target services in each category of the selected area are determined based on the service importance basic weight coefficient, the resource occupancy basic weight coefficient, the first weight coefficient and the second weight coefficient, wherein the first weight coefficient is the weight coefficient corresponding to the service importance basic weight coefficient, and the second weight coefficient is the weight coefficient corresponding to the resource occupancy basic weight coefficient.

10. A 5G network slice adjustment system, characterized in that: include: A first acquisition unit, used to acquire historical demand information of a target service; A first determining unit, configured to determine an initial network slicing strategy based on the historical demand information; A second determining unit, configured to determine an initial network slice based on the initial network slicing strategy; A monitoring unit, configured to monitor performance data of each of the initial network slices; A second acquisition unit is used to obtain priority information of a target service corresponding to each network slice; An adjustment unit is used to adjust the initial network slice based on the performance data and the priority information to determine an optimized network slice.

Images