Network resource allocation method and device, equipment, storage medium and program product

Abstract

The invention discloses a network resource allocation method and device, equipment, a storage medium and a program product, and relates to the technical field of wireless, and the method comprises the steps: determining an initial game strategy of a game theory model according to a real-time network state data set of a communication network, and allocating initial network resources for each game participant of the game theory model, the game participants perform dynamic adjustment based on the initial network resources to generate an optimized resource allocation strategy; and based on the network state change data, performing network scheduling on the optimized resource allocation strategy through an intelligent scheduling algorithm to generate a resource allocation scheme. Since the initial network resources are allocated to each game participant through the game theory model and each game participant can dynamically adjust the initial network resources, the resource allocation scheme can be generated by flexibly adapting to the network state change data finally. The situation that existing 5G resource allocation and scheduling ignore multi-dimensional resource requirements is avoided, so that the overall network resource utilization efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of wireless technology, and in particular to a network resource allocation method, device, equipment, storage medium and program product. Background Art

[0002] With the continuous development of mobile communication technology, 5G network, as the fifth generation of mobile communication technology, has become an important force in promoting the process of social informatization. 5G network has the characteristics of high bandwidth, low latency and large connection, and can support more device access and higher data transmission rate. Therefore, with the widespread application of 5G network, the allocation and scheduling of 5G resources is the key.

[0003] However, for example, traditional spectrum allocation methods are usually based on fixed spectrum allocation strategies, which are difficult to respond to changes in network load and user demand in real time, resulting in low spectrum resource utilization and poor network performance. Similarly, bandwidth allocation methods generally rely on static bandwidth allocation strategies, which are also difficult to flexibly respond to dynamic changes in user device locations, resulting in uneven bandwidth resource allocation and poor user experience.

[0004] Therefore, the existing 5G resource allocation and scheduling generally rely on static predefined rules, usually only considering the network status at a specific moment, lacking dynamic adjustment capabilities, and ignoring the comprehensive optimization of multi-dimensional resource requirements in 5G networks, resulting in inefficient overall network resource utilization. Summary of the invention

[0005] The main purpose of this application is to provide a network resource allocation method, device, equipment, storage medium and program product, aiming to solve the technical problem that the existing 5G resource allocation and scheduling generally rely on static predefined rules, ignore the multi-dimensional resource requirements in the 5G network, and lead to low overall network resource utilization efficiency.

[0006] To achieve the above objectives, the present application proposes a network resource allocation method, the method comprising:

[0007] Determining an initial game strategy corresponding to a preset game theory model according to a real-time network status data set of the communication network, wherein the game theory model includes various game participants;

[0008] Allocating initial network resources to each of the game participants through the initial game strategy, and the game participants dynamically adjusting and generating an optimized resource allocation strategy based on the initial network resources;

[0009] Based on the network status change data of the real-time network status data set, the optimized resource allocation strategy is network scheduled through a preset intelligent scheduling algorithm to generate a resource allocation plan.

[0010] In one embodiment, the step of determining an initial game strategy corresponding to a preset game theory model according to a real-time network status data set of the communication network includes:

[0011] Collect real-time network status data sets of the communication network through the network monitoring module;

[0012] Determine the benefit value of each network resource strategy combination under the current network conditions according to the corresponding benefit function in the game theory model and the real-time network status data set;

[0013] Determining, from the various network resource strategy combinations, an initial spectrum allocation strategy and an initial bandwidth allocation strategy corresponding to a highest benefit value among the benefit values;

[0014] The initial spectrum allocation strategy and the initial bandwidth allocation strategy are used as initial game strategies of the game theory model.

[0015] In one embodiment, the step of allocating initial network resources to each of the game participants through the initial game strategy includes:

[0016] Extracting network load and spectrum utilization of the real-time network status data set;

[0017] Determining the current load of each base station in the game theory model according to the network load, wherein the game participants include each base station and user equipment;

[0018] Determining spectrum utilization of each base station according to the spectrum utilization rate;

[0019] Based on the initial spectrum allocation strategy, the initial bandwidth allocation strategy, the current load condition and the spectrum utilization condition, initial network resources are allocated to each base station and the user equipment.

[0020] In one embodiment, the step of performing network scheduling on the optimized resource allocation strategy based on the network status change data of the real-time network status data set through a preset intelligent scheduling algorithm to generate a resource allocation solution includes:

[0021] Determining user needs corresponding to each of the game participants according to the optimized resource allocation strategy and the initial game strategy;

[0022] Determining network status change data based on historical network status data and the real-time network status data set;

[0023] According to the network status change data and the user demand, the optimized resource allocation strategy is predicted by a preset intelligent scheduling algorithm to obtain an adjusted resource allocation strategy;

[0024] The network resources are scheduled according to the adjusted resource allocation strategy to generate a resource allocation plan.

[0025] In one embodiment, after the step of performing network scheduling on the optimized resource allocation strategy based on the network status change data of the real-time network status data set by using a preset intelligent scheduling algorithm to generate a resource allocation solution, the step further includes:

[0026] Through the feedback mechanism, the resource allocation effect and network performance corresponding to the resource allocation scheme are used as feedback results;

[0027] Iteratively adjusting the game model parameters of the game theory model and the intelligent scheduling algorithm according to the feedback result to obtain an indicator deviation;

[0028] When the indicator deviation does not reach the preset threshold, returning to execute the step of iteratively adjusting the game model parameters of the game theory model and the intelligent scheduling algorithm according to the feedback result until the indicator deviation converges to the preset threshold, and obtaining the adjusted game model parameters and intelligent scheduling algorithm;

[0029] According to the adjusted game model parameters and intelligent scheduling algorithm, return to the step of determining an initial game strategy corresponding to a preset game theory model according to the real-time network status data set of the communication network.

[0030] In one embodiment, before the step of determining the initial game strategy corresponding to the preset game theory model according to the real-time network status data set of the communication network, the step further includes:

[0031] Defining each base station and user equipment in the communication network as a game participant, wherein the game participant is set with a strategy space, and the strategy space includes selectable resource allocation strategies;

[0032] The selectable resource allocation strategy is trained and optimized by an adaptive learning algorithm to obtain a weight coefficient;

[0033] A game theory model is constructed based on the strategy space, the game participants, the weight coefficients and the preset benefit function.

[0034] In addition, to achieve the above purpose, the present application also proposes a network resource allocation device, the device comprising:

[0035] A real-time data module, used to determine an initial game strategy corresponding to a preset game theory model according to a real-time network status data set of the communication network, wherein the game theory model includes various game participants;

[0036] An initial allocation module, used to allocate initial network resources to each of the game participants through the initial game strategy, and the game participants dynamically adjust and generate an optimized resource allocation strategy based on the initial network resources;

[0037] The resource allocation module is used to perform network scheduling on the optimized resource allocation strategy based on the network status change data of the real-time network status data set through a preset intelligent scheduling algorithm to generate a resource allocation plan.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a network resource allocation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the network resource allocation method described above.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the network resource allocation method described above are implemented.

[0040] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the network resource allocation method described above are implemented.

[0041] One or more technical solutions proposed in the present application have at least the following technical effects: A network resource allocation method proposed in the present application includes: determining an initial game strategy corresponding to a preset game theory model based on a real-time network status data set of a communication network, wherein the game theory model includes various game participants; allocating initial network resources to each game participant through the initial game strategy, and the game participants dynamically adjust and generate an optimized resource allocation strategy based on the initial network resources; based on the network status change data of the real-time network status data set, performing network scheduling on the optimized resource allocation strategy through a preset intelligent scheduling algorithm to generate a resource allocation plan.

[0042] Since this application uses a game theory model, in the initial stage, based on the real-time network status data set, the initial game strategy is used to allocate initial network resources to each game participant, and then each game participant can dynamically adjust the initial network resources, and finally can flexibly adapt to the network status change data to perform network scheduling and generate a resource allocation plan. This avoids the situation where the existing 5G resource allocation and scheduling ignores multi-dimensional resource requirements, thereby improving the overall network resource utilization efficiency and reducing resource waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 This is a schematic diagram of the overall process of network resource allocation and scheduling based on game theory in this application;

[0046] Figure 2 A flowchart of the first embodiment of the network resource allocation method of the present application is provided;

[0047] Figure 3 A schematic diagram of the resource structure provided in Example 1 of the present application;

[0048] Figure 4 A flowchart of the third embodiment of the network resource allocation method of the present application is provided;

[0049] Figure 5 This is a schematic diagram of the module structure of the network resource allocation device according to an embodiment of the present application;

[0050] Figure 6 A schematic diagram of the device structure of the hardware operating environment involved in the network resource allocation method in the embodiment of the present application.

[0051] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] It should be noted that the existing network resource allocation generally ignores the multi-dimensional resource requirements in 5G networks and usually only focuses on single-dimensional resource optimization. The specific problems are as follows:

[0055] 1. For example, the mutual influence between various resources such as spectrum, bandwidth, computing resources and storage resources has not been fully considered, resulting in low overall resource utilization efficiency. At the same time, the existing network resource allocation lacks accurate prediction of resource demand, making it difficult to adjust resource allocation strategies in advance, resulting in difficulty in achieving the expected resource utilization efficiency in actual applications.

[0056] 2. In the existing technology, there is a lack of a resource scheduling method that can comprehensively consider multi-dimensional resource demands, dynamically adjust resource allocation strategies, and achieve real-time optimization. For example, game theory, as a mathematical model, can effectively solve the optimization problems in resource allocation and scheduling by simulating the strategic interactions between participants. However, in 5G networks, the use of game theory for resource allocation and scheduling has not yet been fully applied.

[0057] 3. Existing game theory models have certain limitations in practical applications. For example, traditional game theory models usually assume that the strategy space and payoff function of participants are fixed, which makes it difficult to dynamically adjust to adapt to real-time changes in network status. In addition, existing game theory models lack effective feedback mechanisms and optimization algorithms, making it difficult to achieve efficient resource allocation in a complex network environment.

[0058] Therefore, if Figure 1 As shown, Figure 1 This is a schematic diagram of the overall process of network resource allocation and scheduling based on game theory in this application. This application proposes a network resource allocation method. Before starting, it is necessary to build an improved game theory model. Through this game theory model and actual application in the 5G network, the solution can be output and deployed to solve the above problems.

[0059] It should be noted that the execution subject of this embodiment can be a computing service device with data collection, resource allocation and network scheduling functions, such as a personal computer, a server, a switch, etc., or an electronic device capable of realizing the above functions, a network resource allocation device (referred to as allocation device) that executes the network resource allocation method of this application, etc., and this embodiment does not limit this. The following takes the allocation device as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the embodiment of the present application provides a network resource allocation method, referring to Figure 2 , Figure 2 A flowchart of the first embodiment of the network resource allocation method of the present application is provided.

[0061] In this embodiment, the network resource allocation method includes steps S10 to S30:

[0062] Step S10: determining an initial game strategy corresponding to a preset game theory model according to a real-time network status data set of the communication network, wherein the game theory model includes various game participants.

[0063] It should be noted that the communication network may be a mobile communication network in wireless communication technology. Exemplarily, the communication network may include a 5G network, a 6G network, etc. For ease of understanding, the following description will take the 5G network as an example, and this embodiment is not limited to this.

[0064] It is understandable that the game theory model can be a model used to study the decision and equilibrium of network resource allocation by various participants (such as base stations and users) in a communication network. In the game theory model, participants make decisions based on their own interests and expectations of the behavior of other participants.

[0065] Furthermore, if Figure 1 As shown, before collecting data on the 5G network, it is necessary to pre-build the required game theory model. Therefore, before the step S10, it also includes the following steps: defining each base station and user equipment in the communication network as a game participant, the game participant is set with a strategy space, and the strategy space includes selectable resource allocation strategies; training and optimizing the selectable resource allocation strategy through an adaptive learning algorithm to obtain a weight coefficient; constructing a game theory model based on the strategy space, the game participant, the weight coefficient and the preset benefit function.

[0066] It should be noted that game participants can be the main participants in building game theory models in the 5G resource allocation scenario, and can include base stations and user equipment. Among them, each base station and user equipment is an independent subject of the game, and can obtain resources and benefits by choosing different strategy combinations.

[0067] It is understandable that the policy space can be a space including various resource allocation strategies set for each game participant, including selectable resource allocation strategies, such as spectrum and bandwidth allocation strategies. It should be noted that the scope of the policy space is dynamically adjusted to adapt to the changing network status.

[0068] It should be understood that the payoff function can be the core of a game theory model, used to quantify the payoffs of each game participant under different strategy combinations.

[0069] For ease of understanding, refer to Figure 3 , Figure 3Schematic diagram of resource structure provided for the first embodiment of the present application. The benefit function of this embodiment not only takes into account the efficiency of resource use (for example, spectrum and bandwidth utilization), but also proposes multiple indicators to adapt to the complex 5G network requirements. The 5G network resource structure specifically includes: spectrum resources (for example, frequency band allocation, spectrum efficiency, bandwidth, etc.), which can be used to measure the utilization of spectrum allocation; bandwidth resources (for example, bandwidth capacity, allocation strategy, QoS guarantee, etc.), which can be used to reflect the efficiency of bandwidth use; computing resources (for example, edge computing, base station computing, user computing, etc.), which are used to calculate the fluctuations in the demand for computing resources of 5G devices; storage resources (for example, base station storage, user cache, distributed storage, etc.), which are used to determine the storage resource consumption of 5G devices; user experience (for example, QoS, delay control, transmission rate, etc.), which can be reflected by the quality of service of user equipment; network performance, to measure the overall performance of the network under a specific strategy.

[0070] Exemplarily, in order to facilitate the understanding of the constructed game theory model, based on the above data, this example constructs an improved game theory model, the input is the network environment and user demand data, and the output is the game participants, strategy space and benefit function. In the construction process, base stations and user equipment are defined as game participants, and a strategy space is set for each participant. The strategy space includes optional resource allocation strategies; then the benefit function is defined to measure the benefits of each participant under different strategy combinations. The specific construction process is as follows:

[0071] S101. Construct an improved game theory model, define the base station and the user equipment as game participants (hereinafter referred to as participants), and the set of each game participant is recorded as:

[0072] P={p1,p2,...,p n};

[0073] Among them, p i represents the i-th game participant.

[0074] S102. Set a strategy space S for each game participant i , strategy space S i Includes optional resource allocation strategies ij ,Right now:

[0075] S i ={s i1 ,s i2 ,...,s im};

[0076] Among them, s ij Denotes the game participant p i The jth optional strategy of i , represents the game participant pi The strategy space contains multiple selectable resource allocation strategies, each of which is represented by s ij It represents the game participant p i The jth optional strategy.

[0077] Exemplarily, the dimensions of the resource allocation strategy may specifically include: high frequency band priority allocation, which is used to improve the data transmission rate and is suitable for high-demand areas. Low frequency band priority allocation, which is suitable for scenarios with large coverage and strong signal penetration. Dynamic frequency band switching, which adjusts the frequency band according to the real-time network load and interference. Target, which is used to improve the spectrum utilization efficiency and meet the concurrent needs of multiple users.

[0078] For example, the bandwidth resources, computing resources, storage resources, and user experience related resources are described as follows:

[0079] 1. For bandwidth resources, the policy options may include: Bandwidth on-demand allocation: Dynamically allocate bandwidth according to user needs to adapt to network load. Bandwidth fair allocation: Allocate equal bandwidth to all user devices to ensure fairness. Priority allocation: High-priority users or tasks can get more bandwidth. Goal: Improve network response speed and ensure quality of service (QoS).

[0080] 2. For computing resources, the policy options may include: Edge computing priority strategy: give priority to edge node computing resources to reduce latency. Base station computing strategy: use the computing resources of the base station to process tasks, suitable for scenarios with intensive computing requirements. Distributed computing strategy: assign tasks to multiple nodes to improve computing resource utilization. Goal: meet the low latency and high response requirements of computing-intensive applications.

[0081] 3. For storage resources, the policy options may include: Data caching strategy: caching frequently used data to user devices or edge nodes. On-demand storage allocation: allocating storage resources based on real-time data needs. Distributed storage strategy: distributing data to multiple nodes to improve access speed and fault tolerance. Goal: improving data storage and access efficiency and ensuring high availability of key data.

[0082] 4. For user experience related resources (QoS), the policy options may include: Service quality priority policy: Provide better service quality for high-demand users. Low latency priority policy: Provide low latency transmission for applications with high real-time requirements. Data transmission rate priority policy: Provide higher transmission rate for applications with high bandwidth requirements. Goal: Improve user experience and ensure service quality for real-time applications.

[0083] S103. In the improved game theory model, a dynamic weight adjustment mechanism can be introduced to define the payoff function Ui To measure the participants’ i The benefits under different strategy combinations s∈S can dynamically adjust the weight coefficient in the benefit function to adapt to the real-time changes in the network status. The benefit function is expressed as U i (s,t), where t represents time.

[0084] S104. In the improved game theory model, the payoff function U i The calculation of (s, t) can comprehensively consider the following dynamic factors: spectrum resource utilization Denotes the game participant p i In strategies ij Spectrum resource utilization at time t; bandwidth allocation efficiency Denotes the game participant p i In strategies ij and bandwidth resource allocation efficiency at time t; computing resource requirements Denotes the game participant p i In strategies ij and computing resource requirements at time t; storage resource requirements Denotes the game participant p i In strategies ij and storage resource requirements at time t; user experience Q i (s,t), indicates that the user device is in policy s ij and service quality at time t; network performance P i (s,t), which means the network is in strategy s ij and the overall performance at time t.

[0085] S105. Profit function U i (s,t) is expressed as follows:

[0086]

[0087] Among them, w1(t), w2(t), w3(t), w4(t), w5(t), and w6(t) are dynamic weight coefficients of spectrum resource utilization, bandwidth allocation efficiency, computing resource requirements, storage resource requirements, user experience, and network performance, respectively, satisfying w1(t)+w2(t)+w3(t)+w4(t)+w5(t)+w6(t)=1.

[0088] S106, such as Figure 1As shown, at this time, the constructed game theory model is trained and optimized, and an adaptive learning algorithm (a learning algorithm that can automatically adjust its own parameters or strategies according to changes in data and environment) can be introduced. Its input is the strategy space and profit function, and the output is the optimized weight coefficient. The machine learning model is used to optimize the strategies of each game participant and adjust the weight coefficient w in real time. i (t), as follows:

[0089] S1061. Establish a machine learning model for weight adjustment, and input real-time network status data and profit function into the model for training.

[0090] S1062. Define the training objective to minimize the deviation of the profit function:

[0091]

[0092] in, For expected revenue.

[0093] S1063, using the gradient descent algorithm, adjust the weight coefficient w i (t):

[0094]

[0095] Among them, η is the learning rate.

[0096] S1064, continue to iterate until ∈ i Converge to the preset threshold.

[0097] S107. Based on the strategy space and profit function defined above, select an initial strategy s for each participant. i0 , the initial strategy is the optimal strategy under the current network status;

[0098] S108. Input the strategy space, profit function and adaptive learning algorithm of each participant into the improved game theory model. The improved game theory model starts to run. The participants select and adjust strategies according to the feedback of the profit function to realize dynamic resource allocation and scheduling.

[0099] In this implementation, by constructing an improved game theory model, defining base stations and user equipment as game participants, and setting strategy space and profit function for each participant, user needs can be comprehensively considered, which significantly improves resource utilization efficiency compared to traditional static allocation methods.

[0100] like Figure 1As shown, after constructing the improved game theory model, real-time network monitoring of the 5G network is performed. The input of this process is real-time network status data, and the output is a cleaned real-time network status data set (i.e., a data set including various information related to the 5G network status).

[0101] Exemplarily, the network status data set may include data in the following multiple dimensions: network load L(t), which represents the overall load of the 5G network at time t, and the data comes from real-time monitoring of base stations and core networks; spectrum utilization U s (t), represents the spectrum resource utilization of each base station at time t, and the data comes from the spectrum monitoring of the base station; bandwidth demand D b (t) represents the bandwidth demand of the user equipment at time t, and the data comes from the user equipment monitoring unit; the calculation resource demand D c (t), represents the computing resource requirements of the user equipment and the base station at time t, and the data comes from the monitoring of the base station and the user equipment; the storage resource requirement D st (t), represents the storage resource requirements of the user equipment and the base station at time t, and the data comes from the monitoring of the user equipment and the base station; the user equipment position P u (t) represents the location data of the user device at time t, and the data comes from the positioning system of the user device.

[0102] After obtaining the real-time network status data set, the real-time network status data set can be input into the initial game theory model. After calculation by the game theory model, the initial game strategy adopted by the participants at the beginning under the current real-time network status data set can be obtained.

[0103] In this embodiment, after the improved game theory model is constructed, the distribution device can collect the network status data of the communication network in real time, and then pre-process the network status data (such as data cleaning, data completion, etc., which are not limited in this embodiment) to obtain a real-time network status data set. Then, the real-time network status data set is input into the initial game theory model, and after calculation by the game theory model, the initial game strategy adopted by the participants at the beginning under the current real-time network status data set can be obtained.

[0104] In a feasible implementation, step S10 of this embodiment may include the steps of: collecting a real-time network status data set of the communication network through a network monitoring module; determining the benefit value of each network resource strategy combination under current network conditions based on the corresponding benefit function in the game theory model and the real-time network status data set; determining the initial spectrum allocation strategy and the initial bandwidth allocation strategy corresponding to the highest benefit value among the benefit values ​​from the various network resource strategy combinations; and using the initial spectrum allocation strategy and the initial bandwidth allocation strategy as the initial game strategy of the game theory model.

[0105] It should be noted that the network monitoring module may be a component for monitoring network traffic, bandwidth usage, etc. of the 5G network. Exemplarily, the network monitoring module may include a base station monitoring unit, a user equipment monitoring unit, and a core network monitoring unit to monitor each device in the 5G network respectively.

[0106] Specifically, the process of obtaining the real-time network status data set may include:

[0107] First, the network monitoring module can collect real-time network status data of the 5G network. The network status data may include network load, spectrum utilization, bandwidth requirements, computing resource requirements, storage resource requirements and the location of user equipment.

[0108] The network monitoring module can then collect the data from the above dimensions in an integrated manner through the data collection interface to form a real-time network status data set:

[0109] S(t)={L(t),U s (t),D b (t),D c (t),D st (t),P u (t)};

[0110] Where, L(t) is the network load; U s (t) is the spectrum utilization rate; D b (t) is the bandwidth requirement; D c (t) is the computing resource requirement; D st (t) is the storage resource requirement; P u (t) is the user equipment location.

[0111] Then the network monitoring module preprocesses the collected data, including data cleaning, data completion and abnormal data detection, to ensure the integrity and accuracy of the data set.

[0112] Finally, the preprocessed real-time network status data set S(t) is transmitted to the input interface of the game theory model for subsequent resource allocation and scheduling. Through the above data collection, the accurate collection and preprocessing of the real-time network status data set of the 5G network can be ensured, providing a reliable data basis for the resource allocation and scheduling of the subsequent game theory model.

[0113] Furthermore, after collecting and processing the above-mentioned real-time network status data set, initial resources can be allocated to each participant based on the real-time network status data set using an initial game strategy, and each base station can select an initial spectrum allocation strategy and an initial bandwidth allocation strategy according to the current load and user needs.

[0114] It should be noted that the real-time network status data set of the above real-time network monitoring can provide basic input for determining the initial game strategy.

[0115] The process of determining the initial game strategy can be calculated using the profit function: based on the profit function defined above, the real-time network status data set can be input to calculate the profit of each participant's possible strategy combination. The profit function is used to evaluate the profit value of each strategy combination under the current network conditions. The profit function usually takes into account factors such as spectrum resource utilization, bandwidth allocation efficiency, and user experience quality. Then the strategy combination with the highest profit is selected as the initial game strategy to ensure that a reasonable resource allocation is provided to each participant in the initial state. Furthermore, the dynamics of the current network load and user demand can be considered, and the strategy can be appropriately adjusted according to real-time demand to match the current demand to ensure the rationality and adaptability of the initial strategy.

[0116] It should be noted that the initial game strategy may include the following resource allocation strategies: Spectrum allocation strategy: Select appropriate spectrum bands according to the load and interference of the base station. Bandwidth allocation strategy: Allocate appropriate bandwidth to user devices and base stations according to user needs and service quality requirements. Computing and storage resource strategy: Reasonably allocate computing resources and storage space on edge nodes and base stations to meet real-time computing and storage needs. The strategy combination calculated by using real-time network data and profit function is used to provide an initial resource allocation basis for game participants. Subsequently, the strategy is further optimized in subsequent steps through subsequent feedback mechanisms and adaptive learning algorithms.

[0117] Further, such as Figure 1As shown in the figure, after obtaining the real-time network status data set, it is the resource allocation and strategy adjustment process. The input of this process is the above-mentioned cleaned real-time network status data set and the optimized weight coefficient, and the output is the initial resource allocation plan and adjustment strategy. This process can allocate initial resources to participants in the game model (base station and user equipment) through the initial game strategy, including spectrum resources, bandwidth resources, computing resources and storage resources. These resources serve as the starting point for initial allocation and provide a basis for strategy adjustment in the subsequent game process.

[0118] The allocated initial resources and the methods of obtaining them may include:

[0119] Regarding spectrum resources: Spectrum resources refer to the frequency bands allocated to base stations and user devices, which affect the frequency range of communication. The acquisition method can obtain the current network spectrum utilization, interference and user demand data through the real-time network monitoring module, and calculate the most suitable spectrum allocation strategy in combination with the benefit function.

[0120] Regarding bandwidth resources: Bandwidth resources refer to the available capacity of data transmission rate, which is an important factor affecting network transmission speed. The acquisition method can also obtain user demand data through the network monitoring module, and determine the bandwidth allocation strategy based on the demand of user equipment and service quality (QoS) requirements.

[0121] Computing resources: Computing resources refer to the computing power of base stations and edge nodes, which provide computing power guarantee to support high-demand applications. The way to obtain them is to analyze the computing task requirements of each participant based on real-time data and allocate corresponding edge computing or base station computing resources.

[0122] For storage resources: Storage resources include the cache capacity of base stations and user equipment, which is used to store data in transmission and processing. The acquisition method is to allocate corresponding storage space according to the amount of user data and access frequency in the network monitoring data.

[0123] It should be noted that the initial game strategy may include the initial spectrum allocation strategy and the initial bandwidth allocation strategy. The initial spectrum allocation strategy and the initial bandwidth allocation strategy are key parts of the initial resource allocation and can be calculated based on the real-time network status and the benefit function. The purpose is to ensure the basic operation of the network and the effective use of resources in the initial stage.

[0124] Among them, for the initial spectrum allocation strategy, the appropriate frequency band can be selected for allocation based on the load and interference of the base station. The strategy can consider the choice between high frequency band (small coverage, suitable for high-density areas) and low frequency band (large coverage, suitable for low-density areas). For example, the high frequency band is allocated in the high-load area of ​​the network to increase the communication rate, and the low frequency band is allocated in the low-load area to extend the coverage.

[0125] As for the initial bandwidth allocation strategy, it can be allocated according to the QoS requirements and bandwidth requirements of the user equipment. For example, more bandwidth is allocated to high-priority users or tasks to ensure their service quality; less bandwidth is allocated to low-priority users. More bandwidth is allocated to video streaming applications, and less bandwidth is allocated to ordinary data transmission to ensure overall network performance.

[0126] It is understandable that there is a correlation between initial resources (such as spectrum and bandwidth resources) and initial game strategies. Initial resources are the basis, and initial game strategies determine the allocation method and priority of these resources. For example, spectrum resources and bandwidth resources are the basic units of allocation, while spectrum allocation strategies and bandwidth allocation strategies are allocation methods calculated based on the benefit function and real-time network status to achieve optimal use of resources. The formulation of the initial allocation strategy directly affects the allocation efficiency of the initial resources. Through strategy optimization, it is ensured that the allocated spectrum and bandwidth resources can meet the current user needs, while achieving fair and efficient use of resources within a certain range.

[0127] In this implementation, by constructing an improved game theory model, in the initial stage, based on the real-time network status data set, an initial spectrum allocation strategy and an initial bandwidth allocation strategy are determined as the initial game strategy of the game theory model, which not only considers the requirements of spectrum and bandwidth, but also comprehensively considers the requirements of multiple dimensions such as computing resources and storage resources.

[0128] Step S20: allocating initial network resources to each of the game participants through the initial game strategy, and the game participants dynamically adjust and generate an optimized resource allocation strategy based on the initial network resources.

[0129] It should be noted that the optimized resource allocation strategy is a strategy generated by each game participant in the game theory model after dynamically adjusting the initial network resources.

[0130] In this embodiment, the allocation device can allocate initial network resources to each game participant through the initial game strategy. Then the initial network resources are displayed to each game participant. Then each game participant dynamically adjusts resource allocation through strategy selection and interaction to generate an optimized resource allocation strategy.

[0131] In a feasible implementation manner, step S20 of this embodiment may include the steps of: extracting the network load and spectrum utilization of the real-time network status data set; determining the current load status of each base station in the game theory model based on the network load, and the game participants include each base station and user equipment; determining the spectrum utilization status of each base station based on the spectrum utilization; and allocating initial network resources to each base station and the user equipment based on the initial spectrum allocation strategy, the initial bandwidth allocation strategy, the current load status and the spectrum utilization status.

[0132] Exemplarily, in order to facilitate understanding of this embodiment, the initial network resources are allocated to each game participant, and the specific process is as follows:

[0133] S21. First, based on the above real-time network status data set S(t), initial resources are allocated to each game participant, and each base station selects an initial spectrum and bandwidth allocation strategy according to the current load and user demand.

[0134] S22. Define the initial game strategy s i0 The initial resource allocation strategy for each participant is denoted by S0 = {s 10 ,s 20 ,...,s n0}.

[0135] S23. Calculate the current load of each base station based on the network load L(t) in the real-time network status data set

[0136]

[0137] Among them, U i Indicates that the base station b i The collection of connected user devices, represents the bandwidth requirement of user equipment j at time t, d ij (t) represents the distance between user equipment j and base station b i The distance between max is the maximum transmission distance, α is the distance attenuation factor, Indicates base station b i bandwidth capacity.

[0138] S24, based on the spectrum utilization U in the real-time network status data set s (t), calculate the current spectrum utilization of each base station

[0139]

[0140] in, Indicates base station bi The spectrum bandwidth usage at time t, Indicates base station b i The total spectrum bandwidth, N i Indicates base station b i The set of neighboring base stations, d ik (t) represents base station b i With neighboring base station b k The distance between them, β is the attenuation factor.

[0141] S25, based on the user equipment position P in the real-time network status data set u (t), calculate the distance d between the user equipment and the base station ij (t), and adjust resource allocation priority according to distance:

[0142]

[0143] Among them, (x i (t),y i (t)) and (x j (t),y j (t)) respectively represent base station b i and user device u j The position coordinates at time t.

[0144] For example, to understand the allocation priority, the following is illustrated: Assume that in a network, there are two user equipments u1 and u2, and the distances between them and the base station b1 are d 1,1 (t) = 50 m and d 1,2 (t) = 200 meters, and the threshold distance D is set to 100 meters. For user equipment u1, because d 1,1 (t) = 50 < 100, which meets the high priority condition. Therefore, base station b1 will allocate more bandwidth and spectrum resources to u1 to ensure its network service quality. For user equipment u2, because d 1,2 (t)=200≥100, which meets the low priority condition. Therefore, base station b1 will allocate relatively few resources to u2, which may limit the use of bandwidth or spectrum. Distance-based resource allocation adjustment can improve the service quality of close-range users, while making rational use of resources and avoiding allocating a large amount of resources to distant user devices with weak signals, thereby optimizing the overall performance and resource utilization of the network.

[0145] S26. Allocate initial resources to each base station and user equipment using the initial game strategy set S0 and the above calculation results. The initial resource allocation strategy includes a spectrum allocation strategy. and bandwidth allocation strategy

[0146] S27, each base station according to the current load and user needs Selecting the optimal spectrum allocation strategy and bandwidth allocation strategy Allocation strategy, the initial resource allocation formula is:

[0147]

[0148] in, and They represent the benefit functions of spectrum and bandwidth allocation respectively, and λ and γ are adjustment parameters used to balance the stability of benefit and allocation.

[0149] Among them, the role of the initial resource allocation formula is:

[0150] The goal of the formula is to maximize the profit function U si (s,t) and U bi (s, t), obtain the optimal resource allocation strategy in spectrum and bandwidth allocation.

[0151] Used to determine spectrum allocation strategies to maximize revenue.

[0152] Used to determine bandwidth allocation strategy, it is also based on the principle of maximizing the profit function.

[0153] Among them, for the selection of the optimal spectrum and bandwidth allocation strategy: the initial resource allocation formula not only calculates the maximization of the benefit function, but also considers the balance and stability of the allocation. By adjusting the parameters λ and γ, a balance is ensured between the benefit and the stability of the allocation. In the formula, by weighting the partial derivative of the benefit function, the fluctuation caused by over-allocation is reduced, ensuring that the resource allocation is optimal on a stable basis.

[0154] The above initial resource allocation formula is the calculation basis for selecting the optimal spectrum allocation strategy and bandwidth allocation strategy. The result calculated by this formula is the optimal spectrum and bandwidth allocation plan under the current network status and user needs. Therefore, the optimal spectrum and bandwidth allocation strategy is made based on the calculation result of the initial resource allocation formula, that is, the corresponding strategy is selected according to the result of the formula.

[0155] For example, it is assumed that base station b i Spectrum and bandwidth resources need to be allocated to a user device. Based on the current network status: Use s i The formula maximizes the benefits of spectrum allocation while balancing stability (by adjusting λ) and calculating the optimal spectrum resource allocation strategy. biThe formula maximizes the benefits of bandwidth allocation while balancing the stability of allocation (by adjusting γ), resulting in the optimal bandwidth resource allocation strategy.

[0156] Furthermore, after the initial network resources are allocated, each game participant can dynamically adjust resource allocation through strategy selection and interaction. Each base station and user equipment selects the optimal strategy for resource request and adjustment based on its own benefit function and current network status. The specific process is as follows:

[0157] S201, each game participant uses the real-time network status data set S(t) and the initial game strategy s i0 , calculate the profit function U under the current strategy i (s, t), and determine the profit of the current strategy combination s∈S.

[0158] S202: Based on the current strategy combination s, each game participant makes strategy selection and interaction. The game participants make strategy selection and interaction according to their own benefit function U i (s, t) and other participants’ strategy choices, dynamically adjusting their strategies s ij .

[0159] S203, define the strategy update rules for each game participant, the strategy update formula is:

[0160]

[0161] Where η is the learning rate, Denotes the payoff function for strategy s ij The partial derivative of .

[0162] S204, each base station calculates the network status S(t) and the revenue function according to the current network status S(t). Dynamically adjust spectrum and bandwidth resource allocation strategies:

[0163]

[0164] Among them, η s and η b are the learning rates of spectrum and bandwidth strategies respectively, and denote the partial derivatives of the profit function with respect to the spectrum and bandwidth strategies, respectively.

[0165] S205, the user equipment calculates the network status S(t) according to the current network status and the benefit function Dynamically adjust resource request strategies:

[0166]

[0167] Among them, η u is the learning rate of the user device policy, represents the partial derivative of the payoff function with respect to the user device policy.

[0168] S206. Through the above strategy selection and interaction process, each game participant adjusts the strategy according to the feedback of the profit function, gradually approaches the optimal strategy combination, and ensures the dynamic optimization and efficient utilization of resource allocation.

[0169] S207, repeat the above strategy selection and adjustment process until the profit function U i (s, t) converges or reaches the preset optimization goal, and finally determines the optimal resource allocation strategy of each game participant.

[0170] Through the dynamic strategy adjustments of the above-mentioned game participants in the game model, real-time interaction and profit feedback can be achieved, realizing the efficient allocation and optimal utilization of 5G network resources.

[0171] In this implementation, an improved game theory model is constructed, base stations and user equipment are defined as game participants, and a strategy space and a benefit function are set for each participant. In the initial stage, based on the real-time network status data set, initial resources are allocated to each participant using the initial game strategy, and each base station selects the optimal spectrum and bandwidth allocation strategy based on the current load and user demand. Compared with the traditional static allocation method, this dynamic resource allocation method significantly improves resource utilization efficiency and reduces resource waste.

[0172] Step S30: Based on the network status change data of the real-time network status data set, the optimized resource allocation strategy is network scheduled through a preset intelligent scheduling algorithm to generate a resource allocation plan.

[0173] It should be noted that network status change data may refer to data describing changes in various status characteristics of the 5G network at different times. The intelligent scheduling algorithm may be an algorithm for rationally allocating resources again for the optimized resource allocation strategy. For example, the dynamic strategy adjustment mechanism may be used to adjust the strategies of participants in real time according to changes in network load and user demand. It may also include a resource demand prediction model to predict future resource demand and adjust the allocation strategy in advance. It may also be other intelligent scheduling algorithms, which are not limited in this embodiment.

[0174] like Figure 1 As shown, after the game participants make dynamic adjustments based on the initial network resources, there is an intelligent scheduling process, the input of which is the initial resource allocation plan and the network status change data corresponding to the real-time network data, and the output is the dynamic adjustment strategy.

[0175] In this embodiment, the allocation device can dynamically adjust the optimized resource allocation strategy of the participants based on the network status change data of the real-time network status data set through a preset intelligent scheduling algorithm to perform network scheduling and generate the final resource allocation plan. This can adaptively improve resource utilization efficiency and achieve efficient allocation and scheduling of 5G network resources.

[0176] In the technical solution provided by this embodiment, after the improved game theory model is constructed, the allocation device can collect the network status data of the communication network in real time, and then pre-process the network status data (such as data cleaning, data completion, etc., which are not limited in this embodiment) to obtain a real-time network status data set. Then the real-time network status data set is input into the initial game theory model. After the calculation of the game theory model, the initial game strategy adopted by the participants at the beginning under the current real-time network status data set can be obtained. After that, the initial network resources can be allocated to each game participant through the initial game strategy. Then the initial network resources are displayed to each game participant. Each game participant dynamically adjusts resource allocation through strategy selection and interaction to generate an optimized resource allocation strategy. Finally, based on the network status change data of the real-time network status data set, the optimized resource allocation strategy of the participants can be dynamically adjusted through a preset intelligent scheduling algorithm to perform network scheduling and generate a final resource allocation plan. Thereby, the resource utilization efficiency can be adaptively improved to achieve efficient allocation and scheduling of 5G network resources. Since this embodiment uses a game theory model, in the initial stage, based on the real-time network status data set, the initial game strategy is used to allocate initial network resources to each game participant, and then each game participant can dynamically adjust the initial network resources, and finally can flexibly adapt to the network status change data to perform network scheduling and generate a resource allocation plan. This avoids the situation where the existing 5G resource allocation and scheduling ignores multi-dimensional resource requirements, thereby improving the overall network resource utilization efficiency and reducing resource waste.

[0177] Based on the above-mentioned first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those of the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated later.

[0178] Step S30 of this example includes the steps of: determining the user needs corresponding to each game participant based on the optimized resource allocation strategy and the initial game strategy; determining the network status change data based on the historical network status data and the real-time network status data set; predicting the optimized resource allocation strategy through a preset intelligent scheduling algorithm based on the network status change data and the user needs to obtain an adjusted resource allocation strategy; scheduling network resources according to the adjusted resource allocation strategy to generate a resource allocation plan.

[0179] It should be noted that historical network status data can be various information data about the operation status of the network recorded in the past period of time. Adjusting the resource allocation strategy can be an allocation strategy obtained by optimizing and changing the optimized resource allocation strategy of the participant.

[0180] For example, after the game participants dynamically adjust and generate an optimized resource allocation strategy, the allocation device can monitor the network status change data in real time and perform network scheduling based on the improved game theory model and the pre-designed intelligent scheduling algorithm. The specific process is as follows:

[0181] S31. Based on the improved game theory model, we first need to design an intelligent scheduling algorithm, which includes: a dynamic strategy adjustment mechanism that can adjust the strategies of participants in real time according to changes in network load and user demand; a resource demand prediction model that can predict future resource demand and adjust the allocation strategy in advance; an adaptive optimization mechanism that can optimize the game model parameters and improve resource utilization efficiency through machine learning algorithms. The intelligent scheduling algorithm includes the following steps:

[0182] S311, dynamic strategy adjustment mechanism: according to the changes in network load L(t) and user demand D(t), the strategies of each game participant are adjusted in real time:

[0183] Monitor the current network load L(t) and user demand D(t).

[0184] Calculate the strategy adjustment Δs ij (t):

[0185]

[0186] Where η is the learning rate, and f(L(t), D(t)) is the adjustment function of load and demand, which reflects the impact of load and demand on strategy adjustment.

[0187] S312, Resource Demand Prediction Model: Use historical network status data and real-time data to predict future resource demand and adjust allocation strategies in advance: First, collect historical network status data H(t) = {S(t-1), S(t-2), ..., S(tn)}. Then build a prediction model Predict resource requirements at future time t+Δt:

[0188]

[0189] Among them, g(H(t)) is the prediction function, which is trained based on the machine learning algorithm.

[0190] Then, based on the predicted resource requirements Adjust resource allocation strategies in advance ij (t+Δt).

[0191] S313, Adaptive optimization mechanism: Through machine learning algorithms, optimize the game model parameters and improve resource utilization efficiency: First, define the optimization objective function J(θ), where θ is the parameter of the game model:

[0192]

[0193] Then use the gradient descent algorithm to optimize the parameter θ:

[0194]

[0195] Among them, η θ is the parameter learning rate. Dynamically adjusting the game model parameter θ can improve the overall efficiency of resource allocation.

[0196] S32. Then, the network status changes are monitored in real time, the network status change data is determined, and the intelligent scheduling algorithm is dynamically adjusted according to the monitoring data to ensure efficient use and optimal allocation of network resources.

[0197] The intelligent scheduling algorithm designed through an improved game theory model can monitor changes in network status in real time, dynamically adjust the strategies of participants, predict future resource requirements, and improve resource utilization efficiency through an adaptive optimization mechanism to achieve efficient allocation and scheduling of 5G network resources.

[0198] In the technical solution provided in this embodiment, the designed intelligent scheduling algorithm includes a dynamic strategy adjustment mechanism, a resource demand prediction model and an adaptive optimization mechanism. Each game participant dynamically adjusts the resource allocation strategy according to the current network status and benefit function through strategy selection and interaction. This mechanism ensures that resource allocation can respond to changes in network load and user demand in real time, and realizes dynamic optimization and efficient utilization of resources. By introducing an adaptive optimization mechanism, the game model parameters can be dynamically adjusted using a machine learning algorithm to adapt to the ever-changing network environment. The intelligent scheduling algorithm can automatically adjust the resource allocation strategy based on real-time monitoring data and feedback results to ensure the stability and efficiency of the system in a complex network environment. At the same time, by using historical data and machine learning algorithms to predict future resource needs, resources can be configured in advance to avoid network congestion and waste of resources, and further improve the stability and reliability of the network.

[0199] Based on the above embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the above embodiments can be referred to the above introduction, and will not be described in detail later. Figure 4 , Figure 4 A flowchart of the third embodiment of the network resource allocation method of the present application is provided.

[0200] After step S30, this example further includes steps S41 to S44:

[0201] Step S41: Through a feedback mechanism, the resource allocation effect and network performance corresponding to the resource allocation scheme are used as feedback results.

[0202] like Figure 1 As shown, the feedback mechanism can be used to continuously evaluate the resource allocation effect and network performance as feedback results, and output optimization feedback to optimize the above-mentioned game theory model and intelligent scheduling algorithm.

[0203] Specifically, resource allocation effect evaluation indicators can be defined, including spectrum utilization U s (t), bandwidth utilization U b (t), computing resource utilization U c (t), storage resource utilization U st (t), user experience quality Q(t) and network performance index P(t); then collect the data of the above evaluation indicators E(t) = {U s (t),U b (t),U c (t),U st (t),Q(t),P(t)} and use it as feedback to input into the game theory model and intelligent scheduling algorithm.

[0204] Step S42: iteratively adjusting the game model parameters of the game theory model and the intelligent scheduling algorithm according to the feedback result to obtain an indicator deviation.

[0205] Step S43: When the indicator deviation does not reach the preset threshold, return to execute the step of iteratively adjusting the game model parameters of the game theory model and the intelligent scheduling algorithm according to the feedback result until the indicator deviation converges to the preset threshold, and obtain the adjusted game model parameters and intelligent scheduling algorithm.

[0206] It should be noted that the indicator deviation may be the deviation between the indicator generated according to the feedback result and the above evaluation indicator. The preset threshold is a pre-set data used to determine whether the indicator deviation converges.

[0207] Exemplarily, the allocation device may dynamically adjust the game model parameters and the intelligent scheduling algorithm according to the feedback results. The specific steps may include:

[0208] S421. Calculate the deviation δE(t) of the evaluation index using the formula:

[0209] δE(t)=E(t)-E ref (t);

[0210] Among them, E ref(t) is a preset reference value or target value.

[0211] S422. Use the feedback results to adjust the game model parameter θ and the strategy of the intelligent scheduling algorithm. The specific adjustment formula is:

[0212]

[0213] Among them, η θ is the parameter learning rate, and J(θ) is the optimization objective function.

[0214] S423. Adjust the policy parameters of the intelligent scheduling algorithm

[0215]

[0216] in, is the strategy parameter learning rate, To optimize the objective function.

[0217] Through iterative optimization, the game model parameters and intelligent scheduling algorithms can be continuously adjusted and optimized. The specific steps include:

[0218] S431. Define the iterative optimization goal to minimize the deviation of the evaluation index ∈(t):

[0219]

[0220] Among them, λ is the regularization coefficient to prevent overfitting.

[0221] S432, iteratively update the game model parameters and scheduling algorithm strategy until the deviation ∈(t) converges to the preset threshold ∈ tj .

[0222] According to the feedback results, the game model parameters and intelligent scheduling algorithm are adjusted and optimized. Through iterative optimization, the efficiency and fairness of resource allocation can be improved.

[0223] Step S44: according to the adjusted game model parameters and intelligent scheduling algorithm, return to the step of determining the initial game strategy corresponding to the preset game theory model according to the real-time network status data set of the communication network.

[0224] Finally, the effect of iterative optimization is evaluated in real time, and the optimization process can be reinitialized or adjusted as needed, returning to execute the step of determining the initial game strategy corresponding to the preset game theory model based on the real-time network status data set of the communication network to ensure that the efficiency and fairness of resource allocation are continuously improved.

[0225] Through continuous monitoring and evaluation of the feedback mechanism in the above steps, the game model parameters and intelligent scheduling algorithms can be dynamically adjusted and optimized. Through iterative optimization, the efficiency and fairness of resource allocation can be improved, and efficient utilization and optimized management of 5G network resources can be achieved.

[0226] Further, such as Figure 1 As shown in the figure, the scheme can be output and deployed under the feedback mechanism. The input of this process is the final optimized resource allocation strategy, and the output is the scheme deployed to the 5G network, which finally completes the allocation of network resources. The final resource allocation scheme can ensure the efficient allocation and fair use of spectrum, bandwidth, computing resources and storage resources. The optimized resource allocation scheme is deployed to the 5G network, adjusted and applied in real time, and continuously monitored and adjusted to ensure the continuous improvement of network performance and user experience.

[0227] The final resource allocation scheme after the above continuous optimization is officially deployed in the 5G network, which can ensure efficient and fair resource allocation. During the scheme deployment process, the real-time monitoring module provides support to ensure that the resource allocation in actual applications adapts to the dynamically changing network environment. That is, this step performs fine-tuning and adaptive maintenance to ensure the stability and applicability of the scheme in actual operation.

[0228] In the technical solution provided in this embodiment, by real-time monitoring of network status changes, the feedback mechanism is used to continuously evaluate resource allocation effects and network performance, and the game model parameters and intelligent scheduling algorithms are adjusted and optimized according to the feedback results. The iterative optimization mechanism ensures that the efficiency and fairness of resource allocation are continuously improved, effectively reduces network latency, increases data transmission rates, and significantly improves the overall user experience. Through this continuous optimization process, the overall efficiency and fairness of resource allocation can be continuously improved, ensuring that the benefits of each game participant are maximized, promoting healthy competition and cooperation, and promoting the healthy development of the entire 5G network ecosystem.

[0229] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the network resource allocation method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0230] This application also provides a network resource allocation device, please refer to Figure 5 , Figure 5 This is a schematic diagram of the module structure of the network resource allocation device according to an embodiment of the present application; the network resource allocation device includes:

[0231] A real-time data module 501 is used to determine an initial game strategy corresponding to a preset game theory model according to a real-time network status data set of a communication network, wherein the game theory model includes various game participants;

[0232] An initial allocation module 502 is used to allocate initial network resources to each of the game participants through the initial game strategy, and the game participants dynamically adjust and generate an optimized resource allocation strategy based on the initial network resources;

[0233] The resource allocation module 503 is used to perform network scheduling on the optimized resource allocation strategy based on the network status change data of the real-time network status data set through a preset intelligent scheduling algorithm to generate a resource allocation plan.

[0234] Other embodiments or specific implementations of the network resource allocation device of the present application can refer to the above-mentioned method embodiments and will not be described in detail here.

[0235] The network resource allocation device provided by the present application adopts the network resource allocation method in the above embodiment, which can solve the technical problem that the existing 5G resource allocation and scheduling generally rely on static predefined rules, ignore the multi-dimensional resource requirements in the 5G network, and lead to low overall network resource utilization efficiency. Compared with the prior art, the beneficial effects of the network resource allocation device provided by the present application are the same as the beneficial effects of the network resource allocation method provided by the above embodiment, and the other technical features in the network resource allocation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0236] The present application provides a network resource allocation device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the network resource allocation method in the above-mentioned embodiment one.

[0237] Reference below Figure 6 , Figure 6 The schematic diagram of the device structure of the hardware operating environment involved in the network resource allocation method in the embodiment of the present application shows a schematic diagram of the structure of the network resource allocation device suitable for implementing the embodiment of the present application. The network resource allocation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The network resource allocation device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0238] like Figure 6 As shown, the network resource allocation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the network resource allocation device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the network resource allocation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a network resource allocation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.

[0239] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0240] The network resource allocation device provided by the present application adopts the network resource allocation method in the above embodiment, which can solve the technical problem that the existing 5G resource allocation and scheduling generally rely on static predefined rules, ignore the multi-dimensional resource requirements in the 5G network, and lead to low overall network resource utilization efficiency. Compared with the prior art, the beneficial effects of the network resource allocation device provided by the present application are the same as the beneficial effects of the network resource allocation method provided by the above embodiment, and the other technical features in the network resource allocation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0241] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0242] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0243] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the network resource allocation method in the above-mentioned embodiment.

[0244] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0245] The computer-readable storage medium may be included in the network resource allocation device; or may exist independently without being assembled into the network resource allocation device.

[0246] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0247] The modules involved in the embodiments described in the present application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0248] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned network resource allocation method, and can solve the technical problem that the existing 5G resource allocation and scheduling generally rely on static predefined rules, ignore the multi-dimensional resource requirements in the 5G network, and lead to low overall network resource utilization efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the network resource allocation method provided by the above-mentioned embodiment, which will not be repeated here.

[0249] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned network resource allocation method when executed by a processor.

[0250] The computer program product provided by the present application can solve the technical problem that the existing 5G resource allocation and scheduling generally rely on static predefined rules, ignore the multi-dimensional resource requirements in the 5G network, and lead to low overall network resource utilization efficiency. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the network resource allocation method provided by the above embodiment, which will not be repeated here.

[0251] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A network resource allocation method, characterized in that: The method comprises: Determining an initial game strategy corresponding to a preset game theory model according to a real-time network status data set of the communication network, wherein the game theory model includes various game participants; Allocating initial network resources to each of the game participants through the initial game strategy, and the game participants dynamically adjusting and generating an optimized resource allocation strategy based on the initial network resources; Based on the network status change data of the real-time network status data set, the optimized resource allocation strategy is network scheduled through a preset intelligent scheduling algorithm to generate a resource allocation plan.

2. The method according to claim 1, characterized in that The step of determining the initial game strategy corresponding to the preset game theory model according to the real-time network status data set of the communication network includes: Collect real-time network status data sets of the communication network through the network monitoring module; Determine the benefit value of each network resource strategy combination under the current network conditions according to the corresponding benefit function in the game theory model and the real-time network status data set; Determining, from the various network resource strategy combinations, an initial spectrum allocation strategy and an initial bandwidth allocation strategy corresponding to a highest benefit value among the benefit values; The initial spectrum allocation strategy and the initial bandwidth allocation strategy are used as initial game strategies of the game theory model.

3. The method according to claim 2, characterized in that The step of allocating initial network resources to each of the game participants through the initial game strategy includes: Extracting network load and spectrum utilization of the real-time network status data set; Determining the current load of each base station in the game theory model according to the network load, wherein the game participants include each base station and user equipment; Determining spectrum utilization of each base station according to the spectrum utilization rate; Based on the initial spectrum allocation strategy, the initial bandwidth allocation strategy, the current load condition and the spectrum utilization condition, initial network resources are allocated to each base station and the user equipment.

4. The method according to claim 1, characterized in that The step of performing network scheduling on the optimized resource allocation strategy based on the network status change data of the real-time network status data set through a preset intelligent scheduling algorithm to generate a resource allocation solution includes: Determining user needs corresponding to each of the game participants according to the optimized resource allocation strategy and the initial game strategy; Determining network status change data based on historical network status data and the real-time network status data set; According to the network status change data and the user demand, the optimized resource allocation strategy is predicted by a preset intelligent scheduling algorithm to obtain an adjusted resource allocation strategy; The network resources are scheduled according to the adjusted resource allocation strategy to generate a resource allocation plan.

5. The method according to any one of claims 1 to 4, characterized in that After the step of performing network scheduling on the optimized resource allocation strategy based on the network status change data of the real-time network status data set through a preset intelligent scheduling algorithm to generate a resource allocation solution, the method further includes: Through the feedback mechanism, the resource allocation effect and network performance corresponding to the resource allocation scheme are used as feedback results; Iteratively adjusting the game model parameters of the game theory model and the intelligent scheduling algorithm according to the feedback result to obtain an indicator deviation; When the indicator deviation does not reach the preset threshold, returning to execute the step of iteratively adjusting the game model parameters of the game theory model and the intelligent scheduling algorithm according to the feedback result until the indicator deviation converges to the preset threshold, and obtaining the adjusted game model parameters and intelligent scheduling algorithm; According to the adjusted game model parameters and intelligent scheduling algorithm, return to the step of determining an initial game strategy corresponding to a preset game theory model according to the real-time network status data set of the communication network.

6. The method according to any one of claims 1 to 4, characterized in that Before the step of determining the initial game strategy corresponding to the preset game theory model according to the real-time network status data set of the communication network, the method further includes: Defining each base station and user equipment in the communication network as a game participant, wherein the game participant is set with a strategy space, and the strategy space includes selectable resource allocation strategies; The selectable resource allocation strategy is trained and optimized by an adaptive learning algorithm to obtain a weight coefficient; A game theory model is constructed based on the strategy space, the game participants, the weight coefficients and the preset benefit function.

7. A network resource allocation device, characterized in that: The device comprises: A real-time data module, used to determine an initial game strategy corresponding to a preset game theory model according to a real-time network status data set of the communication network, wherein the game theory model includes various game participants; An initial allocation module, used to allocate initial network resources to each of the game participants through the initial game strategy, and the game participants dynamically adjust and generate an optimized resource allocation strategy based on the initial network resources; The resource allocation module is used to perform network scheduling on the optimized resource allocation strategy based on the network status change data of the real-time network status data set through a preset intelligent scheduling algorithm to generate a resource allocation plan.

8. A network resource allocation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the network resource allocation method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the network resource allocation method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the network resource allocation method according to any one of claims 1 to 6 are implemented.

Images