Resource allocation method and device, equipment, storage medium and program product

Abstract

The invention relates to a resource allocation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a resource state of target equipment and a network mode to be subjected to resource allocation; simulating to allocate resources for the network mode according to a plurality of allocation strategies based on the resource state, and obtaining an evaluation result of each allocation strategy on the target index; based on the evaluation result of each distribution strategy on the target index, updating the Pareto solution set to obtain an updated Pareto solution set; on the basis of the evaluation result of the target distribution strategy newly added into the Pareto solution set on the target index, updating the target distribution strategy to obtain an updated distribution strategy until a convergence condition is reached; and based on the resource state, allocating resources to the network mode according to an allocation strategy in the Pareto solution set during convergence to obtain a resource allocation result. By adopting the method, reasonable allocation of resources can be realized.

Description

Technical Field

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

[0002] With the continuous development of cloud computing technology and Internet of Things technology, in modern network environments, the same device needs to support different network modes for multiple applications. Each mode has different resource requirements for network devices, which leads to problems of resource sharing and competition. For example, on a server, it may be necessary to support real-time video communication mode, Internet of Things mode, and cloud computing mode at the same time. When these network modes use server resources, they will compete for key resources such as storage, forwarding, and computing power. Therefore, a reasonable resource allocation strategy is needed to reasonably allocate device resources.

[0003] Traditional resource allocation schemes usually allocate resources according to predefined allocation rules, such as allocating resources according to the priority of the network mode. These predefined allocation rules are static, while the resource status of the device and the resource requirements of the network mode are dynamically changing. This resource allocation scheme cannot adapt to changes in resource status and resource requirements, resulting in unreasonable resource allocation. Summary of the invention

[0004] Based on this, it is necessary to provide a resource allocation method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the resource allocation effect in response to the above technical problems.

[0005] In a first aspect, the present application provides a resource allocation method, the method comprising:

[0006] Obtain the resource status of the target device and the network mode to be allocated resources;

[0007] Based on the resource status, simulating resource allocation for the network mode according to multiple allocation strategies, obtaining a simulated allocation result corresponding to each allocation strategy, and determining the evaluation results of each allocation strategy on the target indicator based on the simulated allocation result of each allocation strategy;

[0008] Based on the evaluation results of each allocation strategy on the target indicator, the Pareto solution set is updated to obtain an updated Pareto solution set;

[0009] Based on the evaluation result of the target allocation strategy on the target indicator, the target allocation strategy is updated to obtain an updated allocation strategy, and the step of simulating allocating resources for the network mode according to multiple allocation strategies based on the resource state is returned to execute to obtain the simulation allocation result step corresponding to each allocation strategy until the convergence condition is reached, and the allocation strategy in the Pareto solution set at the time of convergence is determined as the optimal allocation strategy; the target allocation strategy is the allocation strategy among the multiple allocation strategies that belongs to the updated Pareto solution set;

[0010] Based on the resource status, resources are allocated to the network mode according to the optimal allocation strategy to obtain a resource allocation result.

[0011] In one embodiment, simulating allocating resources to the network mode according to multiple allocation strategies based on the resource state, obtaining a simulated allocation result corresponding to each allocation strategy, and determining the evaluation results of each on the target indicator based on the simulated allocation result of each allocation strategy, includes:

[0012] Taking the resource state as the initial environment state of the environment where the target device is located, the multiple allocation strategies are respectively subjected to N simulation interactions with the environment in a parallel manner to obtain N sub-simulation allocation results corresponding to each allocation strategy;

[0013] Based on the N sub-simulation allocation results corresponding to each of the allocation strategies, determine N sub-evaluation results of each of the allocation strategies on the target indicator;

[0014] The N sub-evaluation results of each allocation strategy on the target indicator are respectively fused to obtain the evaluation result of each allocation strategy on the target indicator.

[0015] In one embodiment, the target indicator includes a benefit indicator and a satisfaction indicator, the evaluation result includes resource benefit and resource satisfaction, and the N sub-simulation allocation results corresponding to each allocation strategy are determined based on the N sub-evaluation results of each allocation strategy on the target indicator, including:

[0016] Based on the N sub-simulation allocation results corresponding to each of the allocation strategies, determine the N sub-resource benefits of each of the allocation strategies on the benefit index and the N sub-resource satisfaction of each of the allocation strategies on the satisfaction index;

[0017] The N sub-evaluation results of each allocation strategy on the target indicator are respectively integrated to obtain the evaluation result of each allocation strategy on the target indicator, including:

[0018] Respectively integrating the N sub-resource benefits of each allocation strategy on the benefit indicator to obtain the resource benefits of each allocation strategy on the benefit indicator;

[0019] The N sub-resource satisfactions of each of the allocation strategies on the satisfaction index are merged respectively to obtain the resource satisfaction of each of the allocation strategies on the satisfaction index.

[0020] In one embodiment, the determining of the N sub-resource benefits of each allocation strategy on the benefit index and the N sub-resource satisfaction of each allocation strategy on the satisfaction index based on the N sub-simulation allocation results corresponding to each allocation strategy includes:

[0021] Obtaining resource unit cost, resource demand status of the network modality, and resource unit benefit of the network modality;

[0022] Determine the N sub-resource benefits of each allocation strategy on the benefit indicator based on the N sub-simulation allocation results, the resource unit cost and the resource unit benefit corresponding to each allocation strategy;

[0023] Based on the N sub-simulation allocation results corresponding to each of the allocation strategies and the resource demand state of the network mode, the N sub-resource satisfaction of each of the allocation strategies on the satisfaction index is determined.

[0024] In one of the embodiments, the resource status includes the quantized status of storage resources, the quantized status of forwarding resources, and the quantized status of computing power resources; the resource demand status of the network modality includes the demand status for the storage resources, the demand status for the forwarding resources, and the demand status for the computing power resources; the sub-simulation allocation result includes the simulated allocation status of the storage resources, the simulated allocation status of the forwarding resources, and the simulated allocation status of the computing power resources of the network modality.

[0025] In one embodiment, the Pareto solution set is updated based on the evaluation result of each allocation strategy on the target indicator to obtain an updated Pareto solution set, including:

[0026] Determine a non-dominated allocation strategy that is a non-dominated solution among the multiple allocation strategies based on an evaluation result of each allocation strategy on a target indicator;

[0027] Determine a target allocation strategy among the non-dominated strategies that is superior to the allocation strategy in the Pareto solution set;

[0028] The Pareto solution set is updated based on the target allocation strategy to obtain an updated Pareto solution set.

[0029] In one embodiment, the allocation strategy is a strategy model defined based on multiple network parameters, and the target allocation strategy is updated based on the evaluation result of the target allocation strategy on the target indicator to obtain an updated allocation strategy, including

[0030] Based on the evaluation results of the target allocation strategy on the target indicator, determine the update gradient;

[0031] The network parameters of the target allocation strategy are updated based on the update gradient to obtain an updated allocation strategy.

[0032] In one embodiment, allocating resources to the network mode according to the optimal allocation strategy based on the resource state to obtain a resource allocation result includes:

[0033] When the number of the optimal allocation strategies is at least two, selecting a target optimal allocation strategy from the at least two optimal allocation strategies;

[0034] Based on the resource status, resources are allocated to the network mode according to the target optimal allocation strategy to obtain a resource allocation result.

[0035] In a second aspect, the present application further provides a resource allocation device, the device comprising:

[0036] A resource status acquisition module is used to obtain the resource status of the target device and the network mode to be used for resource allocation;

[0037] An allocation strategy evaluation module is used to simulate the allocation of resources to the network mode according to multiple allocation strategies based on the resource status, obtain the simulated allocation result corresponding to each allocation strategy, and determine the evaluation result of each allocation strategy on the target indicator based on the simulated allocation result of each allocation strategy;

[0038] A Pareto solution set updating module, used to update the Pareto solution set based on the evaluation results of each allocation strategy on the target indicator to obtain an updated Pareto solution set;

[0039] An allocation strategy updating module, used to update the target allocation strategy based on the evaluation result of the target allocation strategy on the target indicator to obtain an updated allocation strategy; the target allocation strategy is an allocation strategy among the multiple allocation strategies that belongs to the updated Pareto solution set;

[0040] The allocation strategy evaluation module is further used to return to execute the step of simulating the allocation of resources to the network mode according to multiple allocation strategies based on the resource state, and obtaining the simulation allocation result corresponding to each allocation strategy until the convergence condition is reached;

[0041] The Pareto solution set updating module is further used to determine the allocation strategy in the Pareto solution set at the time of convergence as the optimal allocation strategy;

[0042] The resource allocation module is used to allocate resources to the network mode based on the resource status and according to the optimal allocation strategy to obtain a resource allocation result.

[0043] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0044] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0045] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0046] The above-mentioned resource allocation method, device, computer equipment, computer-readable storage medium and computer program product obtain the resource status of the nearest target device and the network mode to be allocated resources in real time. Under the current resource status, multiple allocation strategies are simulated to allocate resources to each network mode to obtain the simulated allocation results of each allocation strategy, and then each allocation strategy is evaluated based on the simulated allocation results, and those allocation strategies with better performance are selected to be added to the Pareto solution set. At the same time, more allocation strategies can be obtained by further updating the allocation strategies with better performance. By re-simulating, allocating, evaluating and screening more allocation strategies, multiple possible allocation strategies can be explored. Finally, the optimal allocation strategy suitable for the current resource status and network mode is selected from many possible allocation strategies, and then the optimal allocation strategy can be used for resource allocation, thereby realizing reasonable allocation of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 An application environment diagram of a resource allocation method in an embodiment;

[0049] Figure 2 A schematic diagram of a flow chart of a resource allocation method in an embodiment;

[0050] Figure 3 is a schematic diagram of resource status in one embodiment;

[0051] Figure 4 A schematic diagram of a resource boundary model building platform in one embodiment;

[0052] Figure 5 A schematic diagram of a flow chart of a resource allocation method in another embodiment;

[0053] Figure 6 A flowchart of steps for solving a multi-dimensional resource elastic organization optimization problem in one embodiment;

[0054] Figure 7 is a structural block diagram of a resource allocation device in an embodiment;

[0055] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The resource allocation method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the target device 102 can communicate with the terminal 104 or the server 106 through the network respectively. The data storage system can store the data that the target device 102 needs to process. The data storage system can be integrated on the target device 102, or it can be placed on the cloud or other network servers; the resource allocation method can be executed by the target device 102, the terminal 104 or the server 106 separately, or it can be executed interactively by at least two of the target device 102, the terminal 104 or the server 106. Taking the execution on the terminal 104 as an example, the terminal 104 is the management terminal of the target device 102, and the terminal 104 obtains the resource status of the target device and the network mode to be allocated resources; based on the resource status, the resources are allocated to the network mode according to multiple allocation strategies to obtain the simulated allocation results corresponding to each allocation strategy, and the evaluation results of each allocation strategy on the target indicators are determined based on the simulated allocation results of each allocation strategy. result; based on the evaluation result of each allocation strategy on the target indicator, the Pareto solution set is updated to obtain an updated Pareto solution set; based on the evaluation result of the target allocation strategy on the target indicator, the target allocation strategy is updated to obtain an updated allocation strategy, and the execution is returned to simulate the allocation of resources to the network mode according to multiple allocation strategies based on the resource status, and the simulation allocation result step corresponding to each allocation strategy is obtained until the convergence condition is reached, and the allocation strategy in the Pareto solution set at the time of convergence is determined as the optimal allocation strategy; the target allocation strategy is the allocation strategy among the multiple allocation strategies that belongs to the updated Pareto solution set; based on the resource status, resources are allocated to the network mode according to the optimal allocation strategy to obtain the resource allocation result.

[0058] Among them, the target device 102 refers to the actual hardware resources and equipment that support the cloud network / computing network integration and multimodal intelligent computing network, which can be servers, storage devices, network devices, data center facilities, sensors and IoT devices, wireless access network devices, computing units, etc. The terminal 104 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 106 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0059] In an exemplary embodiment, Figure 2 As shown, a resource allocation method is provided, which is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps S202 to S210 are included. Among them:

[0060] S202, obtaining the resource status of the target device and the network mode to be allocated resources.

[0061] Among them, the target devices are the actual hardware resources and equipment that support the integration of cloud network / computing network and multimodal intelligent computing networks. Specifically, they can be servers, storage devices, network equipment, data center facilities, sensors and Internet of Things devices, wireless access network equipment, computing units, etc.

[0062] The resource status may specifically be a quantitative status of the resources of the target device. The resources of the target device include resources of different dimensions, such as Figure 3 As shown, the dimensions may specifically include storage dimension, forwarding dimension and computing power dimension. The resources corresponding to the storage dimension may be called storage resources, the resources corresponding to the forwarding dimension may be called forwarding resources, and the resources corresponding to the computing power dimension may be called computing power resources. The quantified states of storage resources include the quantified values ​​of mechanical hard disk space and the quantified values ​​of solid-state hard disk space. The quantified states corresponding to forwarding resources include the quantified values ​​of bandwidth, latency and packet loss rate. The quantified states corresponding to computing power resources include the quantified values ​​of central processing unit clock frequency and the quantified values ​​of required computing power.

[0063] The network mode to be resource allocated refers to the application or service type to which the task that the target device needs to process belongs in the current network environment. The target device needs to allocate resources according to the characteristics and requirements of each network mode. Each network mode corresponds to different tasks and has different resource requirements. For example, network modes include real-time video communication mode, Internet of Things mode and cloud computing mode. The real-time video communication mode requires high bandwidth and low latency to ensure smooth video transmission and real-time performance. The Internet of Things mode has requirements for low power consumption, concurrent connections and large-scale data collection of devices. The bandwidth requirements may not be as strict as video communication, but there are higher requirements for data traffic and number of connections. The cloud computing mode requires powerful computing resources and storage resources, focusing on computing power and dynamic scheduling of resources.

[0064] In one embodiment, the terminal detects the resource state of the target device and the network mode to which the task to be processed belongs in real time, determines the network mode to which the task to be processed belongs as the network mode to which resources are to be allocated, and vectorizes the resource state of the target device to obtain the resource state of the target device represented by the vectorization. For example, the resource state of the target device can be represented as follows:

[0065] R= R 1 , R 2 , R 3 =[ R 1 1 , R 1 2 ,…, R 1 n 1 , R 2 1 , R 2 2 ,…, R 2 n 2 ,( R 3 1 , R 3 2 ,…, R 3 n 3 )]

[0066] in, Indicates the quantitative status of the first resource dimension, Indicates the quantitative status of the second resource dimension, Indicates the quantitative status of the third resource dimension, Indicates that the quantitative status of the first resource dimension includes Quantitative resources, Indicates the quantitative status of the second resource dimension includes Quantitative resources, Indicates the quantitative status of the third resource dimension includes Quantitative resources, Indicates the resource value of the second quantized resource in the quantized state of the first resource dimension, Indicates the resource value of the second quantized resource in the quantized state of the second resource dimension. Indicates the resource value of the second quantized resource in the quantized state of the third resource dimension.

[0067] S204, based on the resource status, simulate allocating resources to the network mode according to multiple allocation strategies, obtain the simulated allocation result corresponding to each allocation strategy, and determine the evaluation results of each allocation strategy on the target indicator based on the simulated allocation result of each allocation strategy.

[0068] The multiple allocation strategies may be the initial allocation strategy or the allocation strategy obtained after adjusting the parameters of the initial allocation strategy, which is used to describe how to allocate resources according to the resource status. The allocation strategy may be a strategy model defined by multiple strategy parameters. For example, the initial n allocation strategies are , , … .

[0069] Simulating resource allocation for a network mode according to multiple allocation strategies refers to simulating resource allocation of a target device using multiple different allocation strategies under the current environment of the target device and the resource status of the target device, so as to evaluate the allocation effect of each allocation strategy.

[0070] The target indicator refers to an indicator for evaluating the allocation effect of the allocation strategy, which can be a resource benefit indicator, a resource satisfaction indicator, etc. The resource benefit indicator is an indicator used to measure the resource benefit effect of the allocation strategy, and the resource satisfaction indicator is an indicator used to evaluate whether the allocation strategy meets the resource requirements of each network mode.

[0071] Specifically, the terminal can also determine the resource demand status of each network mode to which resources are to be allocated, and based on the current resource status and the resource demand status of each network mode, simulate the allocation of resources to the network mode in accordance with multiple allocation strategies in a parallel manner. Assuming that there are n allocation strategies, for the i-th allocation strategy among the n allocation strategies, based on the current resource status and the resource demand status of each network mode, allocate resources to each network mode according to the i-th allocation strategy, obtain the simulated allocation result corresponding to the i-th allocation strategy, and determine the evaluation result of the i-th allocation strategy on the target indicator based on the simulated allocation result corresponding to the i-th allocation strategy.

[0072] The resource demand state of the network mode includes the demand state for storage resources, the demand state for forwarding resources, and the demand state for computing resources. The resource demand state of the network mode can also be specifically vectorized. For example, the resource demand state of the mth network mode among M network modes is It can be expressed as follows:

[0073] D m =[ D 1,1 m , D 1,2 m ,…, D 1, n 1 m , D 2,1 m , D 2,2 m ,…, D 2,, n 2 m , D 3,1 m , D 3,2 m ,…, D 3,, n 3 m ]

[0074] in, represents the demand value of the first quantized resource in the quantized state of the first resource dimension of the mth network mode, represents the demand value of the n1th quantized resource in the quantized state of the first resource dimension by the mth network mode, Represents the demand value of the first quantitative resource in the quantitative state of the second resource dimension of the mth network mode.

[0075] The simulation allocation result includes the simulated allocation resource status corresponding to each network mode. The simulated allocation resource status includes the simulated allocation status of storage resources, the simulated allocation status of forwarding resources, and the simulated allocation status of computing resources. For example, the simulated allocation resource status of the mth network mode among M network modes It can be expressed as follows:

[0076] x m =[ x 1,1 m , x 1,2 m ,…, x 1, n 1 m , x 2,1 m , x 2,2 m ,…, x 2,, n 2 m , x 3,1 m , x 3,2 m ,…, x 3,, n 3 m ]

[0077] in, represents the simulated allocation value of the first quantized resource in the quantized state of the first resource dimension of the mth network mode, represents the simulated allocation value of the n1th quantized resource in the quantized state of the first resource dimension for the mth network mode, Represents the simulated allocation value of the first quantized resource in the quantized state of the second resource dimension of the mth network mode.

[0078] It should be noted that each allocation strategy must meet the following constraints when simulating resource allocation for network modes:

[0079]

[0080]

[0081]

[0082] Among them, C1 is the total resource constraint, C2 is the minimum requirement of each network mode for each quantitative resource, and C3 means that each quantitative resource allocated to each network mode does not exceed its required value to avoid resource waste.

[0083] S206, based on the evaluation results of each allocation strategy on the target indicator, the Pareto solution set is updated to obtain an updated Pareto solution set.

[0084] Among them, the Pareto solution set refers to the solution set in which it is impossible to improve another objective by changing one objective in a multi-objective optimization problem. Specifically, if one allocation strategy performs better than another allocation strategy in some indicators, but performs equally well in other indicators, then the allocation strategy is considered to "dominate" the other strategy. The dominated strategy should be removed from the solution set, and those solutions that are not dominated by any other strategy should be retained as the Pareto solution set. The Pareto solution set that needs to be updated in the embodiment of the present application can be the Pareto solution set obtained in the previous round of simulation and evaluation.

[0085] S208, based on the evaluation result of the target allocation strategy on the target indicator, the target allocation strategy is updated to obtain the updated allocation strategy, and the execution is returned to simulate the allocation of resources for the network mode according to multiple allocation strategies based on the resource status, and the simulation allocation result step corresponding to each allocation strategy is obtained until the convergence condition is reached, and the allocation strategy in the Pareto solution set at the time of convergence is determined as the optimal allocation strategy.

[0086] Among them, the convergence condition refers to the standard for determining when to terminate further operations or calculations during the optimization or iteration process. In the embodiment of the present application, if the optimal strategy in the Pareto solution set no longer changes or changes very slightly in multiple rounds of iterations, it means that a relatively stable set of optimal strategies has been found and the algorithm can stop.

[0087] The target allocation strategy is the allocation strategy that belongs to the updated Pareto solution set among the multiple allocation strategies evaluated in the current round. For example, the multiple allocation strategies include strategy 1, strategy 2, and strategy 3, where strategy 1 is the allocation strategy updated to the Pareto solution set. Then, the parameters of strategy 1 are updated to obtain strategy 4.

[0088] Specifically, after obtaining the updated Pareto solution set, the terminal can determine the target allocation strategy added to the updated Pareto solution set from the multiple allocation strategies of this round, and determine the parameter update value based on the evaluation result of the target allocation strategy, and update the target allocation strategy according to the parameter update value to obtain the updated allocation strategy, and return to execute the steps of simulating the allocation of resources for the network mode according to the multiple allocation strategies based on the resource status, and obtaining the simulation allocation result corresponding to each allocation strategy, so as to simulate and evaluate each updated allocation strategy obtained, and evaluate the updated allocation strategy obtained in the previous round based on the evaluation result of each updated allocation strategy on the target indicator. The Pareto solution set is updated to obtain an updated Pareto solution set, and the updated Pareto solution set is compared with the Pareto solution set of the previous round to obtain a comparison result. If the comparison result indicates that the convergence condition is met, the iteration is stopped, and the allocation strategy in the Pareto solution set at the time of convergence is determined as the optimal allocation strategy. If the comparison result indicates that the convergence condition is not met, the execution continues. Based on the evaluation result of the target allocation strategy on the target indicator, the target allocation strategy is updated to obtain the steps of the updated allocation strategy, until the convergence condition is met, the iteration is stopped, and the allocation strategy in the Pareto solution set at the time of convergence is determined as the optimal allocation strategy.

[0089] S210, allocating resources to the network mode based on the resource status and in accordance with the optimal allocation strategy to obtain a resource allocation result.

[0090] Specifically, after the terminal device determines the optimal allocation strategy, the terminal can allocate resources to each network mode according to the optimal allocation strategy based on the resource status of the target device and the resource demand status of each network mode to be allocated resources, and obtain the resource allocation results of each network mode.

[0091] In the above resource allocation method, the resource status of the nearest target device and the network mode to be allocated resources are obtained in real time. Under the current resource status, resources are allocated to each network mode by simulating multiple allocation strategies to obtain the simulated allocation results of each allocation strategy. Then, each allocation strategy is evaluated based on the simulated allocation results, and those allocation strategies with better performance are selected to be added to the Pareto solution set. At the same time, more allocation strategies can be obtained by further updating the allocation strategies with better performance. By re-simulating, allocating, evaluating and screening more allocation strategies, a variety of possible allocation strategies can be explored. Finally, the optimal allocation strategy suitable for the current resource status and network mode is selected from many possible allocation strategies, and then the optimal allocation strategy can be used for resource allocation, so as to achieve reasonable allocation of resources.

[0092] In one embodiment, the terminal simulates resource allocation for the network mode according to multiple allocation strategies based on the resource status, obtains the simulated allocation result corresponding to each allocation strategy, and determines the evaluation result of each allocation strategy on the target indicator based on the simulated allocation result of each allocation strategy, including the following steps: taking the resource status as the initial environmental state of the environment in which the target device is located, simulating the interaction of multiple allocation strategies with the environment N times in parallel, and obtaining N sub-simulated allocation results corresponding to each allocation strategy; determining N sub-evaluation results of each allocation strategy on the target indicator based on the N sub-simulated allocation results corresponding to each allocation strategy; and fusing the N sub-evaluation results of each allocation strategy on the target indicator to obtain the evaluation result of each allocation strategy on the target indicator.

[0093] Specifically, for H allocation strategies, these H allocation strategies are simulated and interacted with the environment N times in parallel. Each simulation interaction will produce a corresponding sub-simulation allocation result. For any allocation strategy, N simulation interactions will produce N sub-simulation allocation results.

[0094] In one embodiment, the process of simulating the interaction between the i-th allocation strategy among the H allocation strategies and the environment comprises the following steps: With T j The environment at each moment interacts to obtain the allocation strategy The j-th sub-simulation allocation result corresponding to the j-th interaction with the environment, and the allocation strategy determined based on the j-th sub-simulation allocation result The jth sub-evaluation result r on the target indicator i,j and T j+1 The environmental state S at the moment i,Tj+1 , where T j The environmental state at the moment is S i,Tj ; Let j = j + 1, and return to execute the i-th allocation strategy With T j The environment at the moment j is interacted until the maximum number of interactions N is reached. The sub-evaluation result r obtained by N interactions is i,j Sum and get the allocation strategy evaluation results.

[0095] Among them, T j The time refers to the time of the jth simulated interaction, which can also be understood as the timestamp or stage of each round of interaction in the simulation process. Each simulated interaction corresponds to a specific time.

[0096] It is understandable that the i-th allocation strategy With T j The interaction with the environment at the moment means that the current environment state S is allocated according to the i-th allocation strategy. i,Tj Perform resource allocation and obtain sub-simulation allocation results, including the simulation allocation values ​​of various quantitative resources allocated to each network mode. The environment where the target device is located performs corresponding actions according to the sub-simulation allocation results. i,Tj , action a i,Tj It refers to the environment in which the target device is located to simulate the execution allocation strategy The sub-simulation allocation results are obtained, and the processing process of the tasks corresponding to each network mode is simulated. Action a i,Tj The execution time length is T j+1 Moment and T j The time interval between moments can be pre-set. It represents the transition time from the current state to the next state, that is, the duration required to perform an action (resource allocation and task processing). When the action execution reaches the time interval, the environment state S at the next moment is obtained. i,Tj+1 In the embodiment of the present application, after each simulated interaction, the current state of the environment, the executed action, the obtained sub-evaluation result and the next state of the environment at each simulated interaction can be expressed as quaternions. i,Tj , a i,Tj , r i,j , S i,Tj+1 > is stored in the experience replay pool. After completing N simulated interactions, the sub-evaluation result r on the target indicator of each simulated interaction can be directly obtained from the experience replay pool. i,j , and sum up these sub-evaluation results to get the i-th allocation strategy​ Evaluation results on target indicators.

[0097] In the above embodiment, the terminal uses the resource state as the initial environmental state of the environment in which the target device is located to simulate the interaction of multiple allocation strategies with the environment multiple times, so that each allocation strategy can be accurately evaluated. The parallel simulation of the interaction between multiple allocation strategies and the environment can evaluate more allocation strategies in a shorter time, thereby improving the accuracy and efficiency of the allocation strategy evaluation.

[0098] In one embodiment, the target indicator includes a benefit indicator and a satisfaction indicator, and the evaluation result includes a resource benefit and a resource satisfaction. The process in which the terminal determines the N sub-evaluation results of each allocation strategy on the target indicator based on the N sub-simulation allocation results corresponding to each allocation strategy includes the following steps: determining the N sub-resource benefits on the benefit indicator and the N sub-resource satisfaction on the satisfaction indicator of each allocation strategy based on the N sub-simulation allocation results corresponding to each allocation strategy; the terminal fuses the N sub-evaluation results of each allocation strategy on the target indicator respectively to obtain the evaluation result of each allocation strategy on the target indicator, and the process includes the following steps: fuses the N sub-resource benefits on the benefit indicator of each allocation strategy respectively to obtain the resource benefit on the benefit indicator of each allocation strategy; fuses the N sub-resource satisfaction on the satisfaction indicator of each allocation strategy respectively to obtain the resource satisfaction on the satisfaction indicator of each allocation strategy.

[0099] Specifically, for the j-th sub-simulation allocation result, the terminal determines the resource benefits of each quantized resource corresponding to each network mode according to the simulated allocation value of each quantized resource corresponding to each network mode in the j-th sub-simulation allocation result, and sums the resource benefits of each quantized resource corresponding to the same network mode to obtain the resource benefit corresponding to each network mode, and sums the resource benefits corresponding to each network mode to obtain the sub-resource benefit corresponding to the j-th sub-simulation allocation result; at the same time, the simulated allocation value of each quantized resource corresponding to each network mode in the j-th sub-simulation allocation result determines the resource satisfaction of each quantized resource corresponding to each network mode, and sums the resource benefits of each quantized resource corresponding to the same network mode to obtain the sub-resource benefit corresponding to the j-th sub-simulation allocation result. The resource satisfaction of each quantized resource corresponding to each network mode is summed to obtain the resource satisfaction corresponding to each network mode, and the resource satisfaction corresponding to each network mode is summed to obtain the sub-resource satisfaction corresponding to the j-th sub-simulation allocation result; the above process is performed on the N sub-simulation allocation nodes of each allocation strategy, so that the N sub-resource benefits of each allocation strategy on the benefit index and the N sub-resource satisfaction on the satisfaction index can be obtained. For any allocation strategy, the corresponding N sub-resource benefits are summed to obtain the resource benefit of the allocation strategy, and the corresponding N sub-resource satisfactions are summed to obtain the resource satisfaction of the allocation strategy.

[0100] In the above embodiment, the terminal can reduce the influence of deviation and accidental factors in a single simulation by fusing multiple sub-results of each allocation strategy on the benefit and satisfaction index, thereby improving the evaluation accuracy of each allocation strategy.

[0101] In one embodiment, the process of the terminal determining the N sub-resource benefits of each allocation strategy on the benefit index and the N sub-resource satisfaction on the satisfaction index based on the N sub-simulation allocation results corresponding to each allocation strategy includes the following steps: obtaining the resource unit cost, the resource demand status of the network modality and the resource unit benefit of the network modality; determining the N sub-resource benefits of each allocation strategy on the benefit index based on the N sub-simulation allocation results corresponding to each allocation strategy, the resource unit cost and the resource unit benefit; determining the N sub-resource satisfaction of each allocation strategy on the satisfaction index based on the N sub-simulation allocation results corresponding to each allocation strategy and the resource demand status of the network modality.

[0102] The resource unit cost specifically includes the unit cost of each quantitative resource, the resource demand state of the network modality includes the demand value of the network modality for each quantitative resource, and the resource unit benefit of the network modality includes the resource unit benefit of the network modality for each quantitative resource.

[0103] In one embodiment, for any classification strategy, the corresponding resource benefit on the benefit indicator is , and its corresponding resource satisfaction on the satisfaction index It can be expressed as follows:

[0104]

[0105]

[0106] in, Indicates the nth dimension corresponding to the kth dimension of the mth network mode k The simulated allocation value corresponding to the quantized resource, represents the nth dimension of the kth dimension k The resource unit benefit that can be obtained by allocating quantified resources to the mth network mode is represents the nth dimension of the kth dimension k The unit cost of resources allocated to the mth network mode.

[0107] In the above embodiment, the terminal can more accurately evaluate the economic benefits of the allocation strategy by considering the resource unit cost and resource unit benefit when evaluating the benefit; and can more accurately evaluate the satisfaction of the allocation strategy by considering the resource demand state of the network mode when evaluating the satisfaction. By considering both the benefit and satisfaction dimensions at the same time, it ensures that both economic benefits and service quality are considered when allocating resources. Balance.

[0108] In one embodiment, the terminal updates the Pareto solution set based on the evaluation results of each allocation strategy on the target indicator, and the process of obtaining the updated Pareto solution set includes the following steps: based on the evaluation results of each allocation strategy on the target indicator, determining a non-dominated allocation strategy that is a non-dominated solution among multiple allocation strategies; determining a target allocation strategy among the non-dominated strategies that is better than the allocation strategy in the Pareto solution set; and updating the Pareto solution set based on the target allocation strategy to obtain an updated Pareto solution set.

[0109] Specifically, for the first round of simulation evaluation, the non-dominated allocation strategies that belong to the non-dominated solutions can be determined directly based on the evaluation results of each allocation strategy on the target indicator, and the set formed by these non-dominated strategies can be determined as the Pareto solution set; for the second round of simulation evaluation, the Pareto solution set obtained in the first round can be updated directly based on the evaluation results of each allocation strategy on the target indicator to obtain an updated Pareto solution set; for other rounds of simulation evaluation after the second round, the Pareto solution set obtained in the previous round can be updated directly based on the evaluation results of each allocation strategy on the target indicator to obtain an updated Pareto solution set.

[0110] A non-dominated solution is one in which a strategy is considered to dominate another strategy if it performs better on one objective and no worse than another strategy on other objectives. Conversely, a non-dominated solution is one that is not dominated by other strategies on all objectives.

[0111] In one embodiment, the target indicators include a benefit indicator and a satisfaction indicator. The process of solving the Pareto solution set is to solve the resource benefit. and resource satisfaction The optimization problem can be expressed as follows:

[0112]

[0113]

[0114]

[0115]

[0116] Among them, C1 is the total resource constraint, C2 is the minimum requirement of each network mode for each quantitative resource, and C3 means that each quantitative resource allocated to each network mode does not exceed its required value to avoid resource waste.

[0117] In the above embodiment, the terminal can find new, high-quality allocation strategies that have not yet been included outside the existing Pareto solution set by determining the allocation strategies that belong to the non-dominated solutions. This helps to explore more diverse allocation strategies, avoid staying within the limitations of the current Pareto solution set, and further broaden the selection range of resource allocation strategies; by incorporating strategies that are better than the Pareto solution set among the non-dominated solutions, the quality of the Pareto solution set can be improved, ensuring that the solution set is closer to the global optimal solution.

[0118] In one embodiment, the allocation strategy is a policy model defined based on multiple network parameters. The terminal updates the target allocation strategy based on the evaluation result of the target allocation strategy on the target indicator. The process of obtaining the updated allocation strategy includes the following steps: determining an update gradient based on the evaluation result of the target allocation strategy on the target indicator; and updating the network parameters of the target allocation strategy based on the update gradient to obtain the updated allocation strategy.

[0119] It should be noted that in the context of machine learning and optimization, "gradient" refers to the derivative or partial derivative of the objective function, which indicates the direction of the steepest ascent or descent of the objective function. In this case, the updated gradient of the target allocation strategy reflects how to adjust the network parameters to improve the performance of the target indicator.

[0120] In one embodiment, the target indicator includes a benefit indicator and a satisfaction indicator. The benefit gradient is determined based on the resource benefit of the target allocation strategy on the benefit indicator, the satisfaction gradient is determined based on the resource satisfaction of the target allocation strategy on the satisfaction indicator, and the benefit weight corresponding to the benefit indicator is obtained, and the satisfaction weight corresponding to the satisfaction indicator is obtained. The benefit gradient and the satisfaction gradient are weighted and summed based on the benefit weight and the satisfaction weight to obtain an updated gradient. The network parameters of the target allocation strategy are updated based on the updated gradient to obtain an updated allocation strategy.

[0121] In the above embodiment, the terminal guides parameter updates according to the evaluation results of the target indicators to ensure that the target allocation strategy is always adjusted towards the optimization goal (such as maximizing revenue, improving user satisfaction, etc.). This goal-based optimization method can directly improve the performance of the resource allocation strategy in various goals.

[0122] In one embodiment, the terminal allocates resources to the network mode according to the optimal allocation strategy based on the resource status, and the process of obtaining the resource allocation result includes the following steps: when the number of optimal allocation strategies is at least two, selecting a target optimal allocation strategy from at least two optimal allocation strategies; based on the resource status, allocating resources to the network mode according to the target optimal allocation strategy to obtain the resource allocation result.

[0123] Among them, the method of selecting the target optimal allocation strategy from at least two optimal allocation strategies can be randomly selected or selected from at least two optimal allocation strategies according to a preset selection rule. The preset selection rule can specifically be a priority rule, for example, giving priority to selecting the allocation strategy with the highest satisfaction, or giving priority to selecting the allocation strategy with the highest resource benefit, or for each optimal allocation strategy, determining a comprehensive score based on its corresponding resource benefit and resource satisfaction, and selecting the allocation strategy with the highest comprehensive score from each optimal allocation strategy.

[0124] In the above embodiment, when there are multiple optimal allocation strategies, the terminal can select the strategy that best suits the current resource status and needs. This flexibility enables the system to select the best solution based on real-time network conditions, resource changes and application requirements, avoiding the limitations brought about by the fixed use of a single strategy.

[0125] The present application also provides an application scenario, which applies the above resource allocation method. Figure 4 The resource boundary model construction platform shown in the figure includes (1) a resource perception and modeling module, (2) a multi-dimensional resource elastic organization solution generation module, and (3) a multi-dimensional resource elastic organization solution screening module. Figure 5As shown in the flowchart, the process of executing the above method by the resource boundary model construction platform includes the following steps: the resource perception and modeling module is used to perceive the current multi-dimensional quantitative resource status of the system according to the real-time feedback of the network, and construct a resource space model. The constructed resource space model can be specifically characterized by the resource status of the vectorized target device; the multi-dimensional resource elastic organization scheme generation module is used to construct a utility model of the network modality for multi-dimensional resource allocation based on the resource status and modal resource requirements in the current network, and then establish a multi-dimensional resource elastic organization optimization problem, and obtain an optimal solution set by solving the multi-dimensional resource elastic organization optimization problem. The optimal solution set includes at least one optimal solution, and the optimal solution is the multi-modal co-existence bearing resource boundary, which can also be called the optimal allocation strategy; the multi-dimensional resource elastic organization scheme screening module is used to select the target optimal solution that is most suitable for the actual needs and preferences of the current network from at least one optimal solution included in the optimal solution set, that is, select the most suitable optimal allocation strategy for distribution, and complete the optimal mapping of the network modality to the multi-dimensional resources in the resource base, that is, resource allocation.

[0126] In the above application scenario, the multi-dimensional resource elastic organization solution generation module solves the multi-dimensional resource elastic organization optimization problem to obtain the optimal solution set, which can be specifically implemented by using the Pareto algorithm. Figure 6 The process specifically includes the following steps:

[0127] (1) Initialize multiple policy networks, using policy parameters express.

[0128] Among them, for the same policy network, when its policy parameters are updated, the allocation strategy it represents also changes.

[0129] (2) Each allocation strategy Interact with the environment N times. For the jth interaction, in the current state S i,Tj Next, perform action a i,Tj Get rewards i,j , and transfer to the next state S i,Tj+1 , and each time you get i,Tj , a i,Tj , r i,j ,S i,Tj+1 >Deposit into experience replay pool.

[0130] (3) After N interactions, each allocation strategy Calculate its rewards on the resource benefit index and resource satisfaction index, and evaluate the performance of each allocation strategy in terms of total resource benefit and resource satisfaction.

[0131] ​(4) Compare the allocation strategies one by one to determine whether they have a dominant relationship. Select the Pareto optimal solution based on the performance of each allocation strategy. and , compare their total resource benefits and resource satisfaction cumulative rewards. If the strategy No worse than in all objectives , and outperforms , then it is believed that Dominate According to the above method, we retain those strategies that are not dominated by any other strategy, namely the Pareto optimal solutions. These Pareto optimal solutions constitute the current Pareto frontier, which represents the optimal compromise between maximizing the total benefit of resources and maximizing the satisfaction of resources.

[0132] (5) For the allocation strategies in the Pareto frontier, their total resource benefits and resource satisfaction advantage functions are calculated respectively, and their policy update gradients are calculated respectively based on the policy gradient theorem. Then, the gradients of these Pareto optimal strategies are used to update the parameters of the policy network. Specifically, the policy gradients of the two objectives of total resource benefits and resource satisfaction can be combined together through linear combination to form a weighted policy gradient, which can simultaneously optimize multiple objectives during policy update.

[0133] (6) Repeat steps (2) to (5). With more interactions and policy updates, the Pareto front gradually approaches the optimal solution set in the multi-objective space. In each iteration, new policy solutions will appear. The Pareto front is dynamically updated based on these new policy solutions, eliminating old solutions dominated by new solutions and retaining the latest optimal solution.

[0134] (7) When the new strategy solution is no longer significantly better than the existing solution set, or the Pareto front no longer changes significantly, the algorithm can be considered to have converged. At this time, the solution in the Pareto front is the final multi-objective optimal solution set. Output all the optimal allocation strategies in the Pareto front for selection and use according to actual needs.

[0135] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0136] Based on the same inventive concept, the embodiment of the present application also provides a resource allocation device for implementing the resource allocation method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more resource allocation device embodiments provided below can refer to the limitations on the resource allocation method above, and will not be repeated here.

[0137] In an exemplary embodiment, Figure 7 As shown, a resource allocation device is provided, including: a resource status acquisition module 702, an allocation strategy evaluation module 704, a Pareto solution set update module 706, an allocation strategy update module 708 and a resource allocation module 710, wherein:

[0138] The resource status acquisition module 702 is used to acquire the resource status of the target device and the network mode to be allocated resources;

[0139] An allocation strategy evaluation module 704 is used to simulate resource allocation for the network mode according to multiple allocation strategies based on the resource status, obtain a simulated allocation result corresponding to each allocation strategy, and determine the evaluation result of each allocation strategy on the target indicator based on the simulated allocation result of each allocation strategy;

[0140] A Pareto solution set updating module 706 is used to update the Pareto solution set based on the evaluation result of each allocation strategy on the target indicator to obtain an updated Pareto solution set;

[0141] The allocation strategy updating module 708 is used to update the target allocation strategy based on the evaluation result of the target allocation strategy on the target indicator to obtain an updated allocation strategy; the target allocation strategy is the allocation strategy that belongs to the updated Pareto solution set among the multiple allocation strategies;

[0142] The allocation strategy evaluation module 704 is further used to return to execute the steps of simulating resource allocation for the network mode according to multiple allocation strategies based on the resource status, and obtaining the simulation allocation result step corresponding to each allocation strategy until the convergence condition is reached;

[0143] The Pareto solution set updating module 706 is further used to determine the allocation strategy in the Pareto solution set at the time of convergence as the optimal allocation strategy;

[0144] The resource allocation module 710 is used to allocate resources to the network mode according to the optimal allocation strategy based on the resource status to obtain the resource allocation result.

[0145] In the above embodiment, the resource status of the nearest target device and the network mode to be allocated resources are obtained in real time. Under the current resource status, resources are allocated to each network mode by simulating multiple allocation strategies to obtain the simulated allocation results of each allocation strategy. Then, each allocation strategy is evaluated based on the simulated allocation results, and those allocation strategies with better performance are selected to be added to the Pareto solution set. At the same time, more allocation strategies can be obtained by further updating the allocation strategies with better performance. By re-simulating, allocating, evaluating and screening more allocation strategies, a variety of possible allocation strategies can be explored. Finally, the optimal allocation strategy suitable for the current resource status and network mode is selected from many possible allocation strategies, and then the optimal allocation strategy can be used for resource allocation, thereby achieving reasonable allocation of resources.

[0146] In one of the embodiments, the allocation strategy evaluation module 704 is further used to: take the resource state as the initial environmental state of the environment in which the target device is located, and simulate the interaction of multiple allocation strategies with the environment N times in parallel to obtain N sub-simulation allocation results corresponding to each allocation strategy; determine the N sub-evaluation results of each allocation strategy on the target indicator based on the N sub-simulation allocation results corresponding to each allocation strategy; and fuse the N sub-evaluation results of each allocation strategy on the target indicator to obtain the evaluation result of each allocation strategy on the target indicator.

[0147] In one embodiment, the target indicator includes a benefit indicator and a satisfaction indicator, and the allocation strategy evaluation module 704 is further used to: determine the N sub-resource benefits of each allocation strategy on the benefit indicator and the N sub-resource satisfactions on the satisfaction indicator based on the N sub-simulation allocation results corresponding to each allocation strategy; fuse the N sub-resource benefits of each allocation strategy on the benefit indicator to obtain the resource benefit of each allocation strategy on the benefit indicator; fuse the N sub-resource satisfactions of each allocation strategy on the satisfaction indicator to obtain the resource satisfaction of each allocation strategy on the satisfaction indicator.

[0148] In one embodiment, the allocation strategy evaluation module 704 is further used to: obtain the resource unit cost, the resource demand status of the network mode and the resource unit benefit of the network mode; determine the N sub-resource benefits of each allocation strategy on the benefit index based on the N sub-simulation allocation results, resource unit cost and resource unit benefit corresponding to each allocation strategy; determine the N sub-resource satisfaction of each allocation strategy on the satisfaction index based on the N sub-simulation allocation results and the resource demand status of the network mode corresponding to each allocation strategy.

[0149] In one of the embodiments, the resource status includes the quantized status of storage resources, the quantized status of forwarding resources, and the quantized status of computing power resources; the resource demand status of the network modality includes the demand status for storage resources, the demand status for forwarding resources, and the demand status for computing power resources; the sub-simulation allocation results include the simulated allocation status of storage resources, the simulated allocation status of forwarding resources, and the simulated allocation status of computing power resources of the network modality.

[0150] In one embodiment, the Pareto solution set updating module 706 is used to: determine a non-dominated allocation strategy that is a non-dominated solution among multiple allocation strategies based on the evaluation result of each allocation strategy on the target indicator; determine a target allocation strategy that is better than the allocation strategy in the Pareto solution set among the non-dominated strategies; and update the Pareto solution set based on the target allocation strategy to obtain an updated Pareto solution set.

[0151] In one embodiment, the allocation strategy is a strategy model defined based on multiple network parameters, and the allocation strategy update module 708 is used to: determine the update gradient based on the evaluation result of the target allocation strategy on the target indicator; update the network parameters of the target allocation strategy based on the update gradient to obtain an updated allocation strategy.

[0152] In one of the embodiments, the resource allocation module 710 is further used to: when the number of optimal allocation strategies is at least two, select a target optimal allocation strategy from at least two optimal allocation strategies; based on the resource status, allocate resources to the network mode according to the target optimal allocation strategy to obtain a resource allocation result.

[0153] Each module in the resource allocation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0154] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a resource allocation method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0155] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0156] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0157] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0158] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0159] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0160] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0161] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0162] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A resource allocation method, characterized in that: The method comprises: Obtain the resource status of the target device and the network mode to be allocated resources; Based on the resource status, simulating resource allocation for the network mode according to multiple allocation strategies, obtaining a simulated allocation result corresponding to each allocation strategy, and determining the evaluation results of each allocation strategy on the target indicator based on the simulated allocation result of each allocation strategy; Based on the evaluation results of each allocation strategy on the target indicator, the Pareto solution set is updated to obtain an updated Pareto solution set; Based on the evaluation result of the target allocation strategy on the target indicator, the target allocation strategy is updated to obtain an updated allocation strategy, and the step of simulating allocating resources for the network mode according to multiple allocation strategies based on the resource state is returned to execute to obtain the simulation allocation result step corresponding to each allocation strategy until the convergence condition is reached, and the allocation strategy in the Pareto solution set at the time of convergence is determined as the optimal allocation strategy; the target allocation strategy is the allocation strategy among the multiple allocation strategies that belongs to the updated Pareto solution set; Based on the resource status, resources are allocated to the network mode according to the optimal allocation strategy to obtain a resource allocation result.

2. The method according to claim 1, characterized in that The method of simulating allocating resources to the network mode according to a plurality of allocation strategies based on the resource state to obtain a simulation allocation result corresponding to each allocation strategy, and determining the evaluation results of each allocation strategy on the target indicator based on the simulation allocation result of each allocation strategy includes: Taking the resource state as the initial environment state of the environment where the target device is located, the multiple allocation strategies are respectively subjected to N simulation interactions with the environment in a parallel manner to obtain N sub-simulation allocation results corresponding to each allocation strategy; Based on the N sub-simulation allocation results corresponding to each of the allocation strategies, determine N sub-evaluation results of each of the allocation strategies on the target indicator; The N sub-evaluation results of each allocation strategy on the target indicator are respectively fused to obtain the evaluation result of each allocation strategy on the target indicator.

3. The method according to claim 2, characterized in that The target indicator includes a benefit indicator and a satisfaction indicator, the evaluation result includes resource benefit and resource satisfaction, and the N sub-simulation allocation results corresponding to each allocation strategy are determined based on the N sub-evaluation results of each allocation strategy on the target indicator, including: Based on the N sub-simulation allocation results corresponding to each of the allocation strategies, determine the N sub-resource benefits of each of the allocation strategies on the benefit index and the N sub-resource satisfaction of each of the allocation strategies on the satisfaction index; The N sub-evaluation results of each allocation strategy on the target indicator are respectively integrated to obtain the evaluation result of each allocation strategy on the target indicator, including: Respectively integrating the N sub-resource benefits of each allocation strategy on the benefit indicator to obtain the resource benefits of each allocation strategy on the benefit indicator; The N sub-resource satisfactions of each of the allocation strategies on the satisfaction index are merged respectively to obtain the resource satisfaction of each of the allocation strategies on the satisfaction index.

4. The method according to claim 3, characterized in that The determining, based on the N sub-simulation allocation results corresponding to each allocation strategy, the N sub-resource benefits of each allocation strategy on the benefit index and the N sub-resource satisfaction of each allocation strategy on the satisfaction index, comprises: Obtaining resource unit cost, resource demand status of the network modality, and resource unit benefit of the network modality; Determine the N sub-resource benefits of each allocation strategy on the benefit indicator based on the N sub-simulation allocation results, the resource unit cost and the resource unit benefit corresponding to each allocation strategy; Based on the N sub-simulation allocation results corresponding to each of the allocation strategies and the resource demand state of the network mode, the N sub-resource satisfaction of each of the allocation strategies on the satisfaction index is determined.

5. The method according to claim 4, characterized in that The resource status includes the quantized status of storage resources, the quantized status of forwarding resources and the quantized status of computing power resources; the resource demand status of the network modality includes the demand status for the storage resources, the demand status for the forwarding resources and the demand status for the computing power resources; the sub-simulation allocation result includes the simulated allocation status of the storage resources of the network modality, the simulated allocation status of the forwarding resources and the simulated allocation status of the computing power resources.

6. The method according to claim 1, characterized in that The Pareto solution set is updated based on the evaluation result of each allocation strategy on the target indicator to obtain an updated Pareto solution set, including: Determine a non-dominated allocation strategy that is a non-dominated solution among the multiple allocation strategies based on an evaluation result of each allocation strategy on a target indicator; Determine a target allocation strategy among the non-dominated strategies that is superior to the allocation strategy in the Pareto solution set; The Pareto solution set is updated based on the target allocation strategy to obtain an updated Pareto solution set.

7. The method according to claim 1, characterized in that The allocation strategy is a strategy model defined based on multiple network parameters. The target allocation strategy is updated based on the evaluation result of the target allocation strategy on the target indicator to obtain an updated allocation strategy, including: Based on the evaluation results of the target allocation strategy on the target indicator, determine the update gradient; The network parameters of the target allocation strategy are updated based on the update gradient to obtain an updated allocation strategy.

8. The method according to any one of claims 1 to 7, characterized in that The allocating resources to the network mode according to the optimal allocation strategy based on the resource state to obtain a resource allocation result includes: When the number of the optimal allocation strategies is at least two, selecting a target optimal allocation strategy from the at least two optimal allocation strategies; Based on the resource status, resources are allocated to the network mode according to the target optimal allocation strategy to obtain a resource allocation result.

9. A resource allocation device, characterized in that: The device comprises: A resource status acquisition module is used to obtain the resource status of the target device and the network mode to be used for resource allocation; An allocation strategy evaluation module is used to simulate the allocation of resources to the network mode according to multiple allocation strategies based on the resource status, obtain the simulated allocation result corresponding to each allocation strategy, and determine the evaluation result of each allocation strategy on the target indicator based on the simulated allocation result of each allocation strategy; A Pareto solution set updating module, used to update the Pareto solution set based on the evaluation results of each allocation strategy on the target indicator to obtain an updated Pareto solution set; An allocation strategy updating module, used to update the target allocation strategy based on the evaluation result of the target allocation strategy on the target indicator to obtain an updated allocation strategy; the target allocation strategy is an allocation strategy among the multiple allocation strategies that belongs to the updated Pareto solution set; The allocation strategy evaluation module is further used to return to execute the step of simulating the allocation of resources to the network mode according to multiple allocation strategies based on the resource state, and obtaining the simulation allocation result corresponding to each allocation strategy until the convergence condition is reached; The Pareto solution set updating module is further used to determine the allocation strategy in the Pareto solution set at the time of convergence as the optimal allocation strategy; A resource allocation module is used to allocate resources to the network mode based on the resource status and according to the optimal allocation strategy to obtain a resource allocation result.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images