Quantum computing resource allocation method and apparatus, storage medium, and electronic device

Abstract

This application discloses a quantum computing resource allocation method, apparatus, storage medium, and electronic device. The quantum computing resource allocation method includes: acquiring multiple quantum computing resource requests; parsing and prioritizing these requests to generate a standardized request queue; evaluating the real-time resource status of the quantum computing system and generating resource allocation constraints based on the real-time resource status; performing multi-objective optimization on the requests in the standardized request queue based on the resource allocation constraints to generate an initial resource allocation scheme; enforcing fairness on the initial resource allocation scheme, quantifying a preset fairness strategy into mathematical constraints, and adjusting the initial resource allocation scheme to satisfy the mathematical constraints to generate a target resource allocation scheme; and performing performance certification on the target resource allocation scheme, calculating the performance limits of the target resource allocation scheme, and outputting a certified resource allocation plan including the performance limits.

Description

Technical Field

[0001] This application relates to the field of quantum computing technology, specifically to a quantum computing resource allocation method, apparatus, storage medium, and electronic device. Background Technology

[0002] With the rapid development of quantum computing technology, quantum computing resources (such as quantum processors, qubits, and quantum computing time) are gradually becoming scarce and expensive high-value computing resources. In practical applications, quantum computing systems typically need to serve multiple users, applications, or tasks simultaneously, posing a significant challenge to their resource management capabilities. How to efficiently and fairly allocate limited quantum computing resources while meeting the service quality requirements of different users has become a critical issue that urgently needs to be addressed in the field of quantum computing.

[0003] Currently, the allocation and management of quantum computing resources mainly adopt the following methods: The first method is a simple first-come, first-served scheduling strategy, which allocates resources sequentially according to the order in which resource requests arrive. This strategy is simple to implement but cannot distinguish task priorities or cope with dynamically changing resource demands and system loads. The second method is a priority-based scheduling strategy, which assigns static priorities to different users or tasks and allocates resources according to priority. This strategy can guarantee the resource needs of high-priority tasks but lacks flexibility, and low-priority tasks may experience a "starvation" phenomenon where they cannot be executed for a long time. The third method is a resource allocation strategy based on single-objective optimization. This type of method usually aims to maximize system throughput or minimize task completion time, and uses techniques such as integer programming and heuristic algorithms to generate resource allocation schemes.

[0004] However, existing methods lack formal support for multi-objective optimization and can only allocate resources for a single optimization objective. They cannot simultaneously consider multiple conflicting objectives such as fairness, service quality, and energy efficiency in complex scenarios involving multiple users and applications, making it difficult for resource allocation schemes to achieve a reasonable balance between system efficiency and user satisfaction. Summary of the Invention

[0005] This application provides a quantum computing resource allocation method, apparatus, storage medium, and electronic device, which can realize multi-objective optimized allocation of quantum computing resources in multi-user and multi-application scenarios. While taking into account fairness and resource utilization efficiency, it provides an authenticated resource allocation scheme with formal performance guarantees.

[0006] In a first aspect, embodiments of this application provide a method for allocating quantum computing resources, including: Multiple quantum computing resource requests are obtained, and the multiple quantum computing resource requests are parsed and prioritized to generate a standardized request queue; Evaluate the real-time resource status of the quantum computing system and generate resource allocation constraints based on the real-time resource status; Based on the resource allocation constraints, multi-objective optimization is performed on the requests in the standardized request queue to generate an initial resource allocation scheme; Fairness enforcement is performed on the initial resource allocation scheme. The preset fairness strategy is quantified into mathematical constraints and the initial resource allocation scheme is adjusted to satisfy the mathematical constraints, thereby generating the target resource allocation scheme. The target resource allocation scheme is evaluated for performance, the performance limits of the target resource allocation scheme are calculated, and an evaluated resource allocation plan containing the performance limits is output.

[0007] In the quantum computing resource allocation method provided in this application embodiment, the step of parsing and prioritizing the plurality of quantum computing resource requests to generate a standardized request queue includes: Each quantum computing resource request is parsed to obtain the corresponding request metadata and governance strategy; Based on the request metadata and the governance strategy, an initial priority value is calculated for each quantum computing resource request; Based on the initial priority value, multiple quantum computing resource requests are inserted into a multi-level priority queue to generate an initial sorting queue; The waiting time of each quantum computing resource request in the initial sorting queue is dynamically monitored, and the priority value is dynamically adjusted according to the waiting time to generate a standardized request queue.

[0008] In the quantum computing resource allocation method provided in this application embodiment, the step of dynamically adjusting the priority value according to the waiting time and generating a standardized request queue includes: The initial sorted queue is traversed at preset time intervals; For each quantum computing resource request in the initial sorting queue, its dynamic priority adjustment amount is calculated based on the waiting time; The dynamic priority adjustment amount is added to the initial priority value to generate an updated priority value; The initial sorting queue is reordered according to the updated priority value to generate the standardized request queue.

[0009] In the quantum computing resource allocation method provided in this application embodiment, the step of evaluating the real-time resource state of the quantum computing system and generating resource allocation constraints based on the real-time resource state includes: Real-time status data of multiple resource types in the quantum computing system are collected through a monitoring interface; The real-time status data is parsed and aggregated to generate a resource status snapshot; Based on the resource status snapshot, a set of resource allocation constraints is generated.

[0010] In the quantum computing resource allocation method provided in this application embodiment, the step of performing multi-objective optimization on the requests in the standardized request queue based on the resource allocation constraints to generate an initial resource allocation scheme includes: Obtain the set of tasks to be assigned in the standardized request queue and the resource allocation constraints; Construct a multi-objective optimization model, which includes decision variables, a set of objective functions, and a set of constraints. A multi-objective evolutionary algorithm is used to solve the multi-objective optimization model to generate a Pareto optimal solution set containing multiple non-dominated solutions; Select one solution from the Pareto optimal solution set as the initial resource allocation scheme.

[0011] In the quantum computing resource allocation method provided in this application embodiment, the step of enforcing fairness in the initial resource allocation scheme, quantifying the preset fairness strategy into mathematical constraints and adjusting the initial resource allocation scheme to satisfy the mathematical constraints, and generating a target resource allocation scheme, includes: Obtain the initial resource allocation scheme and the preset fairness strategy; Based on the fairness strategy, select the corresponding fairness model and quantify the fairness model into mathematical constraints; Calculate the fairness index value of the initial resource allocation scheme under the mathematical constraints, and compare the fairness index value with a preset fairness threshold; Based on the comparison results, a target resource allocation scheme that satisfies the mathematical constraints is generated.

[0012] In the quantum computing resource allocation method provided in this application embodiment, the step of generating a target resource allocation scheme that satisfies the mathematical constraints based on the comparison results includes: When the fairness index value is lower than the fairness threshold, a fairness adjustment process is initiated. By adjusting the resource allocation weights or executing task preemption, an adjusted resource allocation scheme that satisfies the mathematical constraints is generated. The adjusted resource allocation scheme is taken as the target resource allocation scheme.

[0013] Secondly, embodiments of this application provide a quantum computing resource allocation device, comprising: The acquisition unit is used to acquire multiple quantum computing resource requests, parse and prioritize the multiple quantum computing resource requests, and generate a standardized request queue. An evaluation unit is used to evaluate the real-time resource status of the quantum computing system and generate resource allocation constraints based on the real-time resource status. An optimization unit is configured to perform multi-objective optimization on requests in the standardized request queue based on the resource allocation constraints, so as to generate an initial resource allocation scheme; An execution unit is used to enforce fairness in the initial resource allocation scheme, quantify the preset fairness strategy into mathematical constraints, adjust the initial resource allocation scheme to satisfy the mathematical constraints, and generate a target resource allocation scheme. The authentication unit is used to perform performance authentication on the target resource allocation scheme, calculate the performance limits of the target resource allocation scheme, and output an authenticated resource allocation plan that includes the performance limits.

[0014] Thirdly, this application provides a storage medium storing a plurality of instructions adapted for loading by a processor to execute any of the quantum computing resource allocation methods described above.

[0015] Fourthly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the quantum computing resource allocation method described in any of the preceding claims.

[0016] In summary, the quantum computing resource allocation method provided in this application first generates a standardized request queue by parsing and prioritizing resource requests from multiple users or applications, thus solving the problems of request heterogeneity and priority differentiation in multi-user scenarios. Secondly, it generates quantified resource allocation constraints by evaluating the real-time resource status of the quantum computing system, ensuring that the optimization process is based on accurate system information. Then, based on the resource allocation constraints, it performs multi-objective optimization on the standardized request queue, constructs an optimization model containing at least two conflicting optimization objectives, solves for the Pareto optimal solution set, and generates an initial resource allocation scheme, achieving synergistic optimization of system efficiency and user satisfaction. By enforcing fairness in the initial resource allocation scheme, the preset fairness strategy is quantified into mathematical constraints, and the allocation scheme is adjusted to satisfy these constraints, generating a target resource allocation scheme and providing a verifiable fairness guarantee. Finally, the target resource allocation scheme is performance certified, its performance limits are calculated, and a certified resource allocation plan containing these limits is output, realizing a formal performance guarantee for the resource allocation scheme. Through the synergistic effect of the above steps, multi-objective optimized allocation of quantum computing resources in multi-user, multi-application scenarios is achieved, providing a certified resource allocation scheme with formal performance guarantees while taking into account both fairness and resource utilization efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram illustrating an application scenario of the quantum computing resource allocation method provided in this application embodiment.

[0019] Figure 2 This is a flowchart illustrating the quantum computing resource allocation method provided in an embodiment of this application.

[0020] Figure 3 This is a schematic diagram of the structure of the quantum computing resource allocation device provided in the embodiments of this application.

[0021] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0023] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0024] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0025] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0026] In the description of this application, it should be noted that the terms "upper," "lower," "left," "right," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. In addition, terms such as "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0027] Current quantum computing allocation methods lack formal support for multi-objective optimization and can only allocate resources for a single optimization objective. They cannot simultaneously consider multiple conflicting objectives such as fairness, service quality, and energy efficiency in complex scenarios with multiple users and applications, making it difficult for resource allocation schemes to achieve a reasonable balance between system efficiency and user satisfaction.

[0028] Based on this, embodiments of this application provide a quantum computing resource allocation method, apparatus, storage medium, and electronic device. Specifically, the quantum computing resource allocation apparatus can be integrated into an electronic device, which can be a server or a terminal, etc. The terminal can include mobile phones, wearable smart devices, tablet computers, laptops, and personal computers (PCs), etc., as well as other computer and auxiliary devices. The server can be a single server or a server cluster composed of multiple servers, and can be a physical server or a virtual server.

[0029] For example, such as Figure 1 As shown, the electronic device can acquire multiple quantum computing resource requests, parse and prioritize these requests to generate a standardized request queue; evaluate the real-time resource status of the quantum computing system and generate resource allocation constraints based on this status; perform multi-objective optimization on the requests in the standardized request queue based on these constraints to generate an initial resource allocation scheme; enforce fairness on the initial resource allocation scheme by quantifying the preset fairness strategy into mathematical constraints and adjusting the initial scheme to satisfy these constraints, thereby generating a target resource allocation scheme; perform performance certification on the target resource allocation scheme by calculating its performance limits and outputting a certified resource allocation plan that includes these limits.

[0030] The technical solutions shown in this application will be described in detail below through specific embodiments. It should be noted that the order of description of the following embodiments is not intended to limit the priority of the embodiments.

[0031] Please see Figure 2 , Figure 2 This is a flowchart illustrating the quantum computing resource allocation method provided in an embodiment of this application. The specific flow of this quantum computing resource allocation method can be as follows: 101. Obtain multiple quantum computing resource requests, parse and prioritize these requests, and generate a standardized request queue.

[0032] In this embodiment, the electronic device can first obtain multiple quantum computing resource requests from multiple users or multiple applications. These quantum computing resource requests can come from different tenants, different research projects, or different business applications, and each quantum computing resource request carries different resource configuration requirements and service quality requirements.

[0033] For example, in a typical multi-tenant quantum computing cloud platform scenario, an electronic device may simultaneously receive requests from three users: User A submits a quantum chemical simulation task requiring 32 qubits and a runtime of 100 microseconds, specifying a "high priority" level; User B submits a quantum machine learning training task requiring 8 qubits and a runtime of 500 microseconds, requesting "standard service quality"; and User C submits a quantum random number generation task requiring 16 qubits and a runtime of 200 microseconds, belonging to a "low priority" background job.

[0034] Then, the electronic device parses each quantum computing resource request to obtain the corresponding request metadata and governance strategy.

[0035] The request metadata includes user identifier, application identifier, resource requirement vector (such as number of qubits, quantum processor time, classical memory capacity, and network bandwidth), and service quality requirements (such as job deadline and minimum fidelity). Governance policies include user priority levels, tenant weights, service quality assurance levels, or resource usage quotas.

[0036] Next, based on the request metadata and governance policy, an initial priority value is calculated for each quantum computing resource request.

[0037] For example, a weighted priority function can be used for calculation, taking user weight, service quality level coefficient, and total resource requirement as input parameters, and calculating the initial priority value through preset weight coefficients. In the example above, user A's task, due to its high priority level and short running time, received the highest initial priority value; user C's task, due to its lower priority and moderate resource requirement, received the lowest initial priority value.

[0038] Then, based on the initial priority value, multiple quantum computing resource requests are inserted into a multi-level priority queue to generate an initial sorting queue.

[0039] It should be noted that this multi-level priority queue includes at least two priority levels. The high priority level is used to handle quantum computing resource requests with real-time requirements exceeding a preset threshold, while the low priority level is used to handle non-real-time quantum computing resource requests.

[0040] Finally, to further prevent resource "starvation" in low-priority tasks, the electronic device dynamically monitors the waiting time of each quantum computing resource request in the initial sorting queue and dynamically adjusts the priority value according to the waiting time to generate a standardized request queue.

[0041] Specifically, the electronic device can traverse the initial sorting queue at preset time intervals (e.g., every 100 milliseconds). For each quantum computing resource request in the initial sorting queue, a dynamic priority adjustment is calculated based on the waiting time, which is positively correlated with the waiting time. The dynamic priority adjustment is then added to the initial priority value to generate an updated priority value. The initial sorting queue is reordered based on the updated priority value to generate a standardized request queue. Through this dynamic adjustment mechanism, requests with longer waiting times receive a greater priority increase, thus ensuring that all requests have a chance to be allocated resources within a reasonable timeframe.

[0042] 102. Evaluate the real-time resource status of the quantum computing system and generate resource allocation constraints based on the real-time resource status.

[0043] In this embodiment of the application, the electronic device can first collect real-time status data of multiple resource types in the quantum computing system through a monitoring interface.

[0044] In some embodiments, a quantum computing system typically includes multiple types of resources, such as quantum processor resources, qubit resources, classical computing resources, and network resources. Taking a superconducting quantum computing platform as an example, quantum processor resources include the current list of tasks being executed by each quantum processing unit (QPU), the processor time occupied by each task, the processor cooling cycle status, and the calibration status; qubit resources include the occupancy status of physical qubits, the coherence time of physical qubits, the connectivity topology graph between physical qubits, and the qubit error rate; classical computing resources include CPU utilization, GPU utilization, and memory usage; and network resources include network bandwidth usage and network latency.

[0045] Next, the real-time status data is parsed and aggregated to generate a resource status snapshot.

[0046] This resource status snapshot reflects the capacity, occupancy, availability, and topology information of each resource at the current moment. For example, the resource status snapshot might show: QPU1 currently has two tasks executing, with an occupancy time of 150 microseconds and a remaining available time of 350 microseconds; among physical qubits q1 to q20, q1 to q10 are occupied, while q11 to q20 are idle; the qubit topology connectivity graph shows that q11 is coupled to q12 and q13, and q14 is coupled to q15, etc.

[0047] Finally, a set of resource allocation constraints is generated based on the resource state snapshot.

[0048] In this embodiment, the resource allocation constraint set includes hard constraints and soft constraints. Hard constraints are mandatory conditions that the resource allocation scheme must meet, including: resource capacity constraints (e.g., the total amount of a certain type of resource allocated to all tasks must not exceed the total capacity of that type of resource), resource exclusivity constraints (any physical qubit can be allocated to at most one task at a time), and qubit topology constraints (all physical qubits allocated to the same task must form a connected subgraph in the connectivity topology). Soft constraints are non-mandatory conditions that are preferentially satisfied when optimizing the resource allocation scheme, including: energy consumption ceiling constraints (e.g., the total energy consumption of all tasks does not exceed the system's set energy consumption ceiling), and load balancing constraints (e.g., the difference in resource utilization among quantum processors or computing nodes does not exceed a preset threshold to avoid local hotspots).

[0049] In one embodiment, it is assumed that the quantum computing system managed by the electronic device currently has only one QPU available, with a linear chain-like qubit topology, where q11 is only connected to q12 and q20. If a task requires three qubits and requires that these qubits be able to perform two-qubit gate operations, then the qubit topology constraint in the resource allocation constraint will prohibit the electronic device from allocating q11, q14, and q15 for this task, because q14 and q15 are not connected to q11 and cannot form a connected subgraph. The electronic device will only consider allocating combinations of qubits such as q11, q12, q13, or q18, q19, q20, which can form connected paths.

[0050] 103. Based on resource allocation constraints, perform multi-objective optimization on requests in the standardized request queue to generate an initial resource allocation scheme.

[0051] In some embodiments, step 103 may specifically be as follows: First, obtain the set of tasks to be assigned and the resource allocation constraints from the standardized request queue. Then, construct a multi-objective optimization model, which includes a set of decision variables, a set of objective functions, and a set of constraints.

[0052] Among them, the decision variables represent the allocation relationship and timing arrangement between each task and quantum computing resources. For example, the decision variable can be represented as the start time t of whether task i is allocated to QPU j; the objective function set includes at least two conflicting optimization objectives, such as maximizing throughput, maximizing fairness, optimizing energy efficiency, and guaranteeing quality of service; the constraint set includes at least the resource allocation constraints generated in step 102.

[0053] In some embodiments, the set of objective functions may include at least two of the following objective functions: a throughput maximization objective function, which is to maximize the number of tasks completed within a preset time window; a fairness maximization objective function, which is to maximize the Jain fairness index, which is used to measure the degree of balance of resource shares obtained by each user; an energy efficiency objective function, which is to maximize the number of tasks completed per unit of energy consumption; and a service quality objective function, which is to maximize the proportion of tasks that meet the deadline requirements.

[0054] Next, a multi-objective evolutionary algorithm is used to solve the multi-objective optimization model, generating a Pareto optimal solution set containing multiple non-dominated solutions.

[0055] For example, a non-dominated sorting genetic algorithm (NSGA-II) or a decomposition-based multi-objective evolutionary algorithm (MOEA / D) can be used. Taking NSGA-II as an example, the electronic device first generates an initial population, where each individual represents a resource allocation scheme (i.e., a specific mapping and timing arrangement of tasks to resources); a progeny population is generated through genetic operations (crossover and mutation); after merging the parent and progeny populations, non-dominated sorting is performed to divide the individuals into different Pareto fronts; within each front, the density of individuals is calculated using crowding distance, and individuals with more even distribution are preferentially retained; after multiple generations of iterative evolution, a set of non-dominated solutions is finally obtained. These solutions are not mutually dominant among multiple objectives and together constitute the Pareto optimal solution set.

[0056] Finally, a solution is selected from the Pareto optimal solution set as the initial resource allocation scheme.

[0057] It should be noted that the selection strategy can be determined based on the system's preset preferences. For example, during high-load periods, the solution with higher throughput can be selected first, while during low-load periods, the solution with better fairness can be selected first, or a compromise solution that performs best in terms of multiple objectives can be selected.

[0058] Taking the three user requests in step 101 as an example, after multi-objective optimization, the electronic device may generate multiple Pareto optimal solutions: Solution A prioritizes user A's high-priority task, ensuring its immediate execution, but user B and user C's tasks may be delayed; Solution B uses a round-robin scheduling method, with the three tasks executed alternately, achieving high fairness but with a longer overall completion time; Solution C allocates user A and user B's tasks in parallel to different qubit groups for execution, while scheduling user C's task for execution during inter-qubit periods, achieving a good balance between throughput and fairness. The electronic device selects Solution C as the initial resource allocation scheme based on the current system load strategy.

[0059] 104. Enforce fairness in the initial resource allocation scheme, quantify the preset fairness strategy into mathematical constraints, adjust the initial resource allocation scheme to satisfy the mathematical constraints, and generate the target resource allocation scheme.

[0060] In some embodiments, step 104 may include the following steps: 1041. Obtain the initial resource allocation plan and the preset fairness strategy.

[0061] The fairness policy can be pre-configured by the administrator or dynamically adjusted according to the service level agreement. The fairness policy includes the fairness model type (such as proportional fairness, max-min fairness, priority-based fairness) and fairness parameters (such as the weight coefficient of each user and the minimum resource guarantee share).

[0062] 1042. Based on the fairness strategy, select the corresponding fairness model and quantify the fairness model into mathematical constraints.

[0063] For example, for a proportional fairness strategy, the mathematical constraint can be defined as follows: the ratio of the resource amount r_u to the weight w_u of each user u remains consistent across all users, i.e., r_u / w_u = r_v / w_v holds true for all users u and v. For a max-min fairness strategy, the mathematical constraint can be defined as: maximizing the resource share of the user with the smallest resource share while satisfying the basic needs of all users.

[0064] 1043. Calculate the fairness index value of the initial resource allocation scheme under mathematical constraints, and compare the fairness index value with the preset fairness threshold.

[0065] In this embodiment, the fairness index can be quantified using the Jain fairness index, which ranges from 0 to 1, with a value closer to 1 indicating better fairness. For example, if the resource shares obtained by the three users in the initial resource allocation scheme are 60%, 30%, and 10% respectively, the Jain fairness index is approximately 0.56; if the preset fairness threshold is 0.8, then the scheme does not meet the fairness requirements.

[0066] 1044. Generate a target resource allocation scheme that satisfies mathematical constraints based on the comparison results.

[0067] Specifically, when the fairness index value is lower than the fairness threshold, a fairness adjustment process is initiated. This process generates an adjusted resource allocation scheme that satisfies mathematical constraints by adjusting resource allocation weights or executing task preemption. The adjusted resource allocation scheme is then used as the target resource allocation scheme.

[0068] Continuing with the example above, since the initial resource allocation scheme's Jain fairness index of 0.56 is lower than the threshold of 0.8, the electronic device initiates a fairness adjustment process. If a proportional fairness strategy is adopted and the weights of the three users are equal (all 1), the electronic device will adjust the resource allocation so that the three users receive similar resource shares. Adjustment methods may include: reducing the resource consumption of user A's task (e.g., reallocating some qubits to user C), or preempting part of user A's task execution time slice and allocating it to user C. After the adjustment, in the new resource allocation scheme, the resource shares obtained by the three users are 40%, 35%, and 25%, respectively, and the Jain fairness index increases to approximately 0.92, meeting the fairness threshold requirement. This scheme is then determined as the target resource allocation scheme.

[0069] In a practical application of a multi-tenant quantum computing platform, a fairness enforcement mechanism is crucial for protecting tenants' rights. For example, a quantum computing service provider may sign a service level agreement with a tenant, stipulating that the tenant will receive at least 1000 qubit-hours of computing resources per month. When the electronic device detects that a tenant's resource usage is lower than agreed upon in the agreement, the fairness enforcement mechanism will automatically adjust the resource allocation weights for subsequent tasks to ensure that the tenant reaches the minimum guaranteed share before the end of the settlement cycle.

[0070] 105. Perform performance certification on the target resource allocation scheme, calculate the performance limits of the target resource allocation scheme, and output a certified resource allocation plan that includes the performance limits.

[0071] In this embodiment, the electronic device can first perform performance certification on the target resource allocation scheme and calculate the performance limits of the target resource allocation scheme. These performance limits include key performance indicators such as the upper bound of job completion time, the predicted range of resource utilization, and the fairness audit value.

[0072] For calculating the upper bound of task completion time, electronic devices can use queuing theory models or resource conflict graphs for analysis. For example, for tasks with a determined allocation scheme, the electronic device can estimate the expected completion time of each task based on the amount of resources allocated, task complexity, and current resource load, and then calculate the worst-case upper bound of completion time by combining this with the task queuing order. For quantum computing tasks, the coherence time limit of qubits also needs to be considered—if the actual execution time of the task exceeds the coherence time of the qubits, the calculation results may become invalid due to decoherence. Therefore, the electronic device needs to ensure that the upper bound of completion time is within the coherence time range.

[0073] For calculating the resource utilization prediction interval, electronic devices can predict the expected utilization of each quantum processor, quantum bit, and classical computing resource during task execution based on the allocation of each resource in the target resource allocation scheme, and give a reasonable confidence interval (such as [75%, 85%]).

[0074] For fairness audit values, electronic devices can recalculate fairness index values ​​(such as the Jain Fairness Index) based on the actual resource share allocated under the target resource allocation scheme and record them as audit values.

[0075] The electronic device can then generate a structured certified resource allocation plan. This plan includes performance limits (such as upper bounds on job completion times, predicted resource utilization ranges, and fairness audit values) and detailed resource allocation mappings (which user receives which qubits and computing resources at what time). This certified resource allocation plan can be output to the user terminal or the system management terminal for user confirmation or system archiving.

[0076] In a practical application scenario, a research team submitted a complex quantum chemistry simulation task to a quantum computing cloud platform. After processing steps 101 to 104, the electronic device generated a target resource allocation plan and, through performance certification, calculated the upper bound of the estimated completion time for the task to be 2 hours and 15 minutes, the predicted resource utilization range to be [82%, 90%], and the Jain fairness index to be 0.95. The electronic device returned the certified resource allocation plan, which included these performance limits, to the user. Based on this, the user could reasonably plan subsequent experiments, and the operator of the electronic device could also use these performance indicators and service level agreements for settlement and auditing.

[0077] Furthermore, during the execution of the target resource allocation scheme, the electronic device can monitor changes in the resource status of the quantum computing system in real time. When a change in resource status (such as quantum processor failure, new task preemption, or user priority adjustment) is detected that causes the certified resource allocation plan to fail to meet performance limits, the electronic device triggers real-time allocation adjustment or task preemption, generates an updated resource allocation scheme, re-certifies the performance of the updated resource allocation scheme, and outputs a new certified resource allocation plan. This mechanism ensures that the quantum computing system always operates in a certified state, providing users with a continuous and stable quality of service guarantee.

[0078] In summary, the quantum computing resource allocation method provided in this application first generates a standardized request queue by parsing and prioritizing resource requests from multiple users or applications, thus solving the problems of request heterogeneity and priority differentiation in multi-user scenarios. Secondly, it generates quantified resource allocation constraints by evaluating the real-time resource status of the quantum computing system, ensuring that the optimization process is based on accurate system information. Then, based on the resource allocation constraints, it performs multi-objective optimization on the standardized request queue, constructs an optimization model containing at least two conflicting optimization objectives, solves for the Pareto optimal solution set, and generates an initial resource allocation scheme, achieving synergistic optimization of system efficiency and user satisfaction. By enforcing fairness in the initial resource allocation scheme, the preset fairness strategy is quantified into mathematical constraints, and the allocation scheme is adjusted to satisfy these constraints, generating a target resource allocation scheme and providing a verifiable fairness guarantee. Finally, the target resource allocation scheme is performance certified, its performance limits are calculated, and a certified resource allocation plan containing these limits is output, realizing a formal performance guarantee for the resource allocation scheme. Through the synergistic effect of the above steps, multi-objective optimized allocation of quantum computing resources in multi-user, multi-application scenarios is achieved, providing a certified resource allocation scheme with formal performance guarantees while taking into account both fairness and resource utilization efficiency.

[0079] To facilitate better implementation of the quantum computing resource allocation method provided in this application, this application also provides a quantum computing resource allocation device. The meanings of the terms used are the same as in the quantum computing resource allocation method described above, and specific implementation details can be found in the descriptions within the method embodiments.

[0080] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a quantum computing resource allocation device provided in an embodiment of this application. The quantum computing resource allocation device may include an acquisition unit 201, an evaluation unit 202, an optimization unit 203, an execution unit 204, and an authentication unit 205. The acquisition unit 201 is used to acquire multiple quantum computing resource requests, parse and prioritize the multiple quantum computing resource requests, and generate a standardized request queue. Evaluation unit 202 is used to evaluate the real-time resource status of the quantum computing system and generate resource allocation constraints based on the real-time resource status; The optimization unit 203 is used to perform multi-objective optimization on requests in the standardized request queue based on resource allocation constraints to generate an initial resource allocation scheme; The execution unit 204 is used to enforce fairness in the initial resource allocation scheme, quantify the preset fairness strategy into mathematical constraints and adjust the initial resource allocation scheme to meet the mathematical constraints, and generate the target resource allocation scheme. The authentication unit 205 is used to perform performance authentication on the target resource allocation scheme, calculate the performance limits of the target resource allocation scheme, and output an authenticated resource allocation plan that includes the performance limits.

[0081] For specific implementation methods of each of the above units, please refer to the embodiments of the quantum computing resource allocation method described above, which will not be repeated here.

[0082] In summary, the quantum computing resource allocation device provided in this application embodiment can acquire multiple quantum computing resource requests through the acquisition unit 201, parse and prioritize these requests to generate a standardized request queue; the evaluation unit 202 evaluates the real-time resource status of the quantum computing system and generates resource allocation constraints based on the real-time resource status; the optimization unit 203 performs multi-objective optimization on the requests in the standardized request queue based on the resource allocation constraints to generate an initial resource allocation scheme; the execution unit 204 enforces fairness on the initial resource allocation scheme, quantifies the preset fairness strategy into mathematical constraints, and adjusts the initial resource allocation scheme to satisfy the mathematical constraints, generating a target resource allocation scheme; and the authentication unit 205 performs performance authentication on the target resource allocation scheme, calculates the performance limits of the target resource allocation scheme, and outputs an authenticated resource allocation plan containing the performance limits. This application embodiment can achieve multi-objective optimized allocation of quantum computing resources in multi-user, multi-application scenarios, providing an authenticated resource allocation scheme with formal performance guarantees while balancing fairness and resource utilization efficiency.

[0083] This application also provides an electronic device that may integrate the quantum computing resource allocation device of this application, such as... Figure 4 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically: The electronic device may include components such as a processor 301 with one or more processing cores and a memory 302 with one or more computer-readable storage media. Those skilled in the art will understand that... Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs stored in the memory 302 and / or this application, and by calling data stored in the memory 302, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operation of the storage medium, user interface, and application programs, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 301.

[0084] The memory 302 can be used to store software programs and this application. The processor 301 executes various functional applications and data processing by running the software programs and this application stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store applications required for operating the storage medium and at least one function; the data storage area may store data created based on the use of the electronic device. In addition, the memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0085] Although not shown, the electronic device may also include a display unit, an input unit, and a power supply, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device loads the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 runs the application programs stored in the memory 302 to realize various functions, as follows: The system acquires multiple quantum computing resource requests, parses and prioritizes these requests, and generates a standardized request queue. Evaluate the real-time resource status of a quantum computing system and generate resource allocation constraints based on the real-time resource status; Based on resource allocation constraints, multi-objective optimization is performed on requests in a standardized request queue to generate an initial resource allocation scheme; Enforce fairness in the initial resource allocation scheme, quantify the preset fairness strategy into mathematical constraints, adjust the initial resource allocation scheme to satisfy the mathematical constraints, and generate the target resource allocation scheme. The target resource allocation scheme is evaluated for performance, the performance limits of the target resource allocation scheme are calculated, and the evaluated resource allocation scheme containing the performance limits is output.

[0086] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0087] Therefore, embodiments of this application provide a storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the methods provided in embodiments of this application. For example, the instructions can execute the following steps: The system acquires multiple quantum computing resource requests, parses and prioritizes these requests, and generates a standardized request queue. Evaluate the real-time resource status of a quantum computing system and generate resource allocation constraints based on the real-time resource status; Based on resource allocation constraints, multi-objective optimization is performed on requests in a standardized request queue to generate an initial resource allocation scheme; Enforce fairness in the initial resource allocation scheme, quantify the preset fairness strategy into mathematical constraints, adjust the initial resource allocation scheme to satisfy the mathematical constraints, and generate the target resource allocation scheme. The target resource allocation scheme is evaluated for performance, the performance limits of the target resource allocation scheme are calculated, and the evaluated resource allocation scheme containing the performance limits is output.

[0088] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0089] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0090] Since the instructions stored in the storage medium can execute the steps of any method provided in the embodiments of this application, the beneficial effects that any method provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0091] The quantum computing resource allocation method, apparatus, storage medium, and electronic device provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for allocating quantum computing resources, characterized in that, include: Multiple quantum computing resource requests are obtained, and the multiple quantum computing resource requests are parsed and prioritized to generate a standardized request queue; Evaluate the real-time resource status of the quantum computing system and generate resource allocation constraints based on the real-time resource status; Based on the resource allocation constraints, multi-objective optimization is performed on the requests in the standardized request queue to generate an initial resource allocation scheme; Fairness enforcement is performed on the initial resource allocation scheme. The preset fairness strategy is quantified into mathematical constraints and the initial resource allocation scheme is adjusted to satisfy the mathematical constraints, thereby generating the target resource allocation scheme. The target resource allocation scheme is evaluated for performance, the performance limits of the target resource allocation scheme are calculated, and an evaluated resource allocation plan containing the performance limits is output.

2. The quantum computing resource allocation method as described in claim 1, characterized in that, The step of parsing and prioritizing the multiple quantum computing resource requests to generate a standardized request queue includes: Each quantum computing resource request is parsed to obtain the corresponding request metadata and governance strategy; Based on the request metadata and the governance strategy, an initial priority value is calculated for each quantum computing resource request; Based on the initial priority value, multiple quantum computing resource requests are inserted into a multi-level priority queue to generate an initial sorting queue; The waiting time of each quantum computing resource request in the initial sorting queue is dynamically monitored, and the priority value is dynamically adjusted according to the waiting time to generate a standardized request queue.

3. The quantum computing resource allocation method as described in claim 2, characterized in that, The step of dynamically adjusting the priority value based on the waiting time to generate a standardized request queue includes: The initial sorted queue is traversed at preset time intervals; For each quantum computing resource request in the initial sorting queue, its dynamic priority adjustment amount is calculated based on the waiting time; The dynamic priority adjustment amount is added to the initial priority value to generate an updated priority value; The initial sorting queue is reordered according to the updated priority value to generate the standardized request queue.

4. The quantum computing resource allocation method as described in claim 1, characterized in that, The evaluation of the real-time resource status of the quantum computing system and the generation of resource allocation constraints based on the real-time resource status include: Real-time status data of multiple resource types in the quantum computing system are collected through a monitoring interface; The real-time status data is parsed and aggregated to generate a resource status snapshot; Based on the resource status snapshot, a set of resource allocation constraints is generated.

5. The quantum computing resource allocation method as described in claim 1, characterized in that, The step of performing multi-objective optimization on requests in the standardized request queue based on the resource allocation constraints to generate an initial resource allocation scheme includes: Obtain the set of tasks to be assigned in the standardized request queue and the resource allocation constraints; Construct a multi-objective optimization model, which includes decision variables, a set of objective functions, and a set of constraints. A multi-objective evolutionary algorithm is used to solve the multi-objective optimization model to generate a Pareto optimal solution set containing multiple non-dominated solutions; Select one solution from the Pareto optimal solution set as the initial resource allocation scheme.

6. The quantum computing resource allocation method as described in claim 1, characterized in that, The step of enforcing fairness in the initial resource allocation scheme, quantifying the preset fairness strategy into mathematical constraints and adjusting the initial resource allocation scheme to satisfy the mathematical constraints, and generating the target resource allocation scheme includes: Obtain the initial resource allocation scheme and the preset fairness strategy; Based on the fairness strategy, select the corresponding fairness model and quantify the fairness model into mathematical constraints; Calculate the fairness index value of the initial resource allocation scheme under the mathematical constraints, and compare the fairness index value with a preset fairness threshold; Based on the comparison results, a target resource allocation scheme that satisfies the mathematical constraints is generated.

7. The quantum computing resource allocation method as described in claim 6, characterized in that, The step of generating a target resource allocation scheme that satisfies the mathematical constraints based on the comparison results includes: When the fairness index value is lower than the fairness threshold, a fairness adjustment process is initiated. By adjusting the resource allocation weights or executing task preemption, an adjusted resource allocation scheme that satisfies the mathematical constraints is generated. The adjusted resource allocation scheme is taken as the target resource allocation scheme.

8. A quantum computing resource allocation device, characterized in that, include: The acquisition unit is used to acquire multiple quantum computing resource requests, parse and prioritize the multiple quantum computing resource requests, and generate a standardized request queue. An evaluation unit is used to evaluate the real-time resource status of the quantum computing system and generate resource allocation constraints based on the real-time resource status. An optimization unit is configured to perform multi-objective optimization on requests in the standardized request queue based on the resource allocation constraints, so as to generate an initial resource allocation scheme; An execution unit is used to enforce fairness in the initial resource allocation scheme, quantify the preset fairness strategy into mathematical constraints, adjust the initial resource allocation scheme to satisfy the mathematical constraints, and generate a target resource allocation scheme. The authentication unit is used to perform performance authentication on the target resource allocation scheme, calculate the performance limits of the target resource allocation scheme, and output an authenticated resource allocation plan that includes the performance limits.

9. A storage medium, characterized in that, The storage medium stores multiple instructions, which are adapted for loading by a processor to execute the quantum computing resource allocation method according to any one of claims 1-7.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the quantum computing resource allocation method as described in any one of claims 1-7.

Images