Scheduling method and device for edge service, electronic equipment and storage medium

Abstract

The invention provides a scheduling method, device and equipment for edge service and a computer program product. The method comprises the steps of obtaining a to-be-processed target user request set of a server cluster of edge service, and constructing a first density matrix model for expressing the target user request set by taking a user request as a state vector and taking a service quality requirement corresponding to the user request as a probability; and constructing a second model for expressing the server cluster by taking a server state as a state vector, and simulating the server cluster to process the server state change of the target user request set by using a quantum interference theory based on the first model and the second model, and determining a scheduling strategy for maximizing the resource utilization rate of the server cluster under the condition that each user request in the target user request set meets the corresponding service quality requirement.

Description

Technical Field

[0001] The present invention relates to the field of unmanned driving, and in particular to a scheduling method, device, equipment and computer program product for edge services. Background Art

[0002] With the rapid growth of mobile Internet and IoT devices, traditional cloud computing models face high latency and bandwidth pressure, which affects user experience and service efficiency. To solve these problems, edge computing has emerged as an emerging computing paradigm. It processes data and provides services at the edge of the network close to users, reduces data transmission distance, reduces latency, and optimizes network bandwidth, thereby providing users with reliable computing or storage services.

[0003] Edge computing is between cloud computing and end users, providing users with storage and computing resources on the side close to users. In addition, various applications are deployed on edge cloud platforms. Some of these applications have high real-time requirements, which requires sufficient bandwidth resources, while others have high storage resource requirements, which requires edge service providers to allocate more disks to users. And as time changes, the number of user requests at different times is also different.

[0004] In the process of implementing edge computing, how to dynamically schedule resources according to the actual needs of users and optimize service benefits is an important technical challenge. Current technologies mainly focus on fixed algorithms and static resource allocation, which makes it difficult to flexibly respond to changes and diversity in user needs. In addition, how to achieve the scheduling of user requests while ensuring service quality is also a key issue that edge computing needs to solve. Summary of the invention

[0005] The purpose is to provide a scheduling method, device, equipment and computer program product for edge services, which can...

[0006] In order to achieve the above purpose, the embodiment is implemented as follows:

[0007] In a first aspect, a vehicle driving control method is provided, comprising:

[0008] Obtain a target user request set to be processed by the server cluster of the edge service;

[0009] Taking user requests as state vectors and service quality requirements corresponding to user requests as probabilities, a first density matrix model expressing the target user request set is constructed; and taking server states as state vectors, a second model expressing the server cluster is constructed;

[0010] Based on the first model and the second model, quantum interference theory is used to simulate the server state changes of the server cluster in processing the target user request set, and a scheduling strategy for maximizing the resource utilization of the server cluster while meeting the corresponding service quality requirements for each user request in the target user request set is determined.

[0011] In a second aspect, a vehicle driving control device is provided, comprising:

[0012] An acquisition module, used to acquire a target user request set to be processed by a server cluster of an edge service;

[0013] A modeling module, for constructing a first density matrix model expressing the target user request set with user request as state vector and service quality requirement corresponding to the user request as probability; and constructing a second model expressing the server cluster with server state as state vector;

[0014] A simulation module is used to simulate the server state changes of the server cluster processing the target user request set based on the first model and the second model using quantum interference theory, and determine a scheduling strategy for maximizing the resource utilization of the server cluster while satisfying the corresponding service quality requirements for each user request in the target user request set.

[0015] In a third aspect, an embodiment provides an electronic device, comprising: a processor; and a memory configured to store computer-executable instructions, wherein the computer-executable instructions, when executed, cause the processor to execute the method described in the first aspect.

[0016] According to a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store computer-executable instructions, and the computer-executable instructions implement the method described in the first aspect when executed by a processor.

[0017] The embodiments of the present application use concepts such as quantum states and density matrices in quantum theory to model and represent user requests and server states, thereby effectively describing and characterizing user requests and server states. Since when user requests are dispatched to a specific server, the server must allocate necessary computing resources, memory, storage space, and network bandwidth to process these requests, this resource allocation will cause changes in the server state. For this reason, based on quantum state modeling, the principle of quantum interference is used to simulate changes in server states after resource allocation and scheduling. Ultimately, the principle of quantum measurement is used to determine the scheduling strategy for maximizing resource utilization of the server cluster while meeting the corresponding service quality requirements for each user request in the target user request set. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments recorded in the embodiments. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 This is a flow chart of a scheduling method for edge services according to an embodiment of the present application.

[0020] Figure 2 A schematic diagram of modeling user requests and server status in a scheduling method for edge services according to an embodiment of the present application.

[0021] Figure 3 Schematic diagram of a quantum interference module according to an embodiment of the present application.

[0022] Figure 4 A schematic diagram of determining the probability of allocating user requests to each server in a scheduling method for edge services according to an embodiment of the present application.

[0023] Figure 5 This is a schematic diagram of the structure of a scheduling device for edge services according to an embodiment of the present application.

[0024] Figure 6 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments will be described clearly and completely below in conjunction with the drawings in the embodiments. Obviously, the described embodiments are only part of the embodiments in this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0026] The problem solved by the present invention mainly focuses on the edge cloud scenario, in which there are a large number of heterogeneous edge cloud servers (server clusters) with significant differences in resource characteristics (such as geographical location, memory size). At the same time, these servers need to handle various user requests from multiple different users, which vary in type, urgency, and resource requirements.

[0027] In order to better describe the scenario set by the present invention, the server cluster in the scenario is represented by To represent, in the whole scenario, there are M servers in total, and each server has different resource attributes, such as different memory size, disk size, CPU utilization, bandwidth capacity, and geographical location. The set of all edge servers at time t can be described in the following form:

[0028]

[0029] in d s It is the characteristic dimension of the server resource attribute, indicating that the server contains d s resource attributes. Used to indicate the status of the Mth server at time t.

[0030] In addition, user requests at different times are grouped together To indicate that The set of all user requests at time t can be expressed as:

[0031]

[0032] in d u It is the characteristic dimension of the user request. Represents the rth user request at time t, used to describe user requests Right u The minimum requirements for different resources.

[0033] This application aims to ensure maximum benefits while scheduling and allocating resources for different user requests. The maximum benefits mentioned here are the maximization of the resource interest rate of the server cluster. With high resource utilization, tasks can be completed on less physical hardware, reducing the need to migrate tasks between physical resources, reducing latency, and improving response speed. This improved efficiency can translate into a better user experience and higher customer satisfaction, which may increase the user's frequency of use and the attractiveness of the service.

[0034] Therefore, this scenario mainly uses resource utilization as an important indicator to measure the system's benefit. The higher the resource utilization, the greater the benefit. The benefit function can be formalized as follows:

[0035]

[0036] Revenue is the benefit function, which is calculated by comprehensive utilization rate. Different weights are assigned to different resource characteristics according to the importance of each resource in system performance. The sum of the satisfaction weights is 1, that is,

[0037] Specifically, based on the above, an embodiment of the present application provides a scheduling method for edge services.

[0038] Figure 1 It is a flowchart of the scheduling method, which includes the following steps:

[0039] S102: Obtain a target user request set to be processed by a server cluster of the edge service.

[0040] In this embodiment, the target user request set is the unprocessed user requests received by the server cluster at time t.

[0041] S104, using user requests as state vectors and service quality requirements corresponding to user requests as probabilities, construct a first density matrix model expressing a target user request set; and using server states as state vectors, construct a second model expressing a server cluster.

[0042] This embodiment uses concepts such as quantum state and density matrix in the quantum theory framework to model user requests and server states. In quantum mechanics, quantum state is used to describe the state of a quantum system. Quantum state can be in a pure state or in a mixed state. A pure state means that the system is in a certain quantum state, which can be represented by the state vector |ψ> in the Hilbert space. A mixed state is a quantum state composed of several pure states according to quantum probability, which can usually be represented by a density matrix.

[0043] like Figure 2 As shown, specifically, for all user requests at time t Convert each user request into a state vector that conforms to the quantum theory modeling method The state vector usually needs to be mapped from the real space to the Hilbert space. The specific steps are as follows:

[0044] First, the user request input to the model is passed through a fully connected neural network layer. Upgrade to in d q It represents the characteristic dimension of the state space modeled by quantum theory, called Request for user The quantum embedding vector of .

[0045] Since the representation of the state vector requires that it must be a unit vector with a norm of 1. Therefore, in order to obtain a unit vector, the quantum embedding vector requested by each user needs to be standardized:

[0046]

[0047] All user requests at time t can be represented by a description of a quantum system in a mixed state, which is usually represented by a density matrix.

[0048]

[0049] in, Represents the first density matrix model r ; t represents the time of the target user request set; represents the target user request set; r represents the number of user requests in the target user request set; The state vector representing the user request; Represents the probability of the user request corresponding to the density matrix. It can be calculated based on the service quality requirements corresponding to the user request. The higher the service quality requirements, the The larger the value of

[0050] Similarly, the server state of each server in the server cluster (severs) can also be modeled according to the modeling method of quantum theory and represented by a state vector. The server status can be passed through a fully connected neural network layer Upgrade to in d q represents the characteristic dimension in the state space of quantum theory modeling, Server status The quantum embedding vector of is normalized as follows:

[0051]

[0052] The state vector set of the server state at time t is obtained as:

[0053]

[0054] For a single server state, it can be represented as a quantum system in a pure state, also using a density matrix to describe it:

[0055]

[0056] in, Indicates the status of the Mth server at time t; A state vector representing the state of the server.

[0057] S106, based on the first model and the second model, the server state changes of the server cluster processing the target user request set are simulated using quantum interference theory, and a scheduling strategy for maximizing the resource utilization of the server cluster while satisfying the corresponding service quality requirements for each user request in the target user request set is determined.

[0058] When user requests are dispatched to a specific server, the server must allocate necessary computing resources, memory, storage space, and network bandwidth to process these requests. This resource allocation will cause the server state to change, so that for user request scheduling at time t, user requests cannot be simply dispatched and allocated resources one by one in a sequential manner.

[0059] Quantum theory provides an innovative solution, especially the phenomenon of quantum interference, which describes how quantum states produce new quantum states through interactions. Using the principle of quantum interference, we can simulate the changes in server status after processing requests, which not only enables more accurate predictions of server loads, but also optimizes resource allocation strategies. By simulating quantum interference, various possible server status changes can be taken into account during resource scheduling, thereby achieving more efficient and dynamic scheduling solutions, ensuring that servers can respond to user requests in the best state, while improving the overall performance and efficiency of the system.

[0060] This embodiment is based on the first model and the second model, and in the direction of maximizing the resource utilization of the server cluster (the optimization function is set to the resource utilization of the system as a whole), uses quantum interference theory to simulate the server state changes of the server cluster in processing the target user request set, and determines the probability of each user request in the target user request set being allocated to each server in the server cluster while meeting the corresponding service quality requirements; then, for each user request in the target user request set, the server with the largest probability is selected as the corresponding scheduling strategy.

[0061] The following is an introduction to determining the scheduling strategy by simulating quantum interference.

[0062] In quantum interference theory, the wave function is usually used The probability amplitude complex function to describe the position x of the microscopic particle represents the fluctuation of the probability of the position of the microscopic particle, which will be used to explain the double-slit interference experiment. Before the emission, the state of the microscopic particle is in the superposition state of slit 1 and slit 2, which can be formalized as:

[0063]

[0064] in, is the wave function of slit 1, is the wave function of slit 2, and α, β satisfy |α| 2+|β| 2 =1.

[0065] Determines the status The probability (density) of a microscopic particle appearing at position x, so according to this formula, the position curve of the microscopic particle after the quantum interference phenomenon can be deduced as follows:

[0066]

[0067] Among them, θ is The phase angle, is represented as an interference term.

[0068] like Figure 2 , Figure 3 As shown, the Quantum Interference Module phenomenon can be used to simulate the impact of user request scheduling on the server status, and this process can be modeled according to the theoretical formula of quantum interference.

[0069] The mixed state density matrix requested by the user Flatten directly into a vector through the flatten operation And the density matrix of each server at time t is represented as It is also flattened into M vectors through the flatten operation to obtain the set

[0070] The server state of the Mth server after quantum interference at time t can be expressed as:

[0071]

[0072] After network dimension reduction and standardization, we get

[0073] Finally, for each server at time t, quantum interference processing is performed to simulate the impact of allocating resources to user requests on the server state, and the server state set after interference is obtained:

[0074]

[0075] In this step, the user request at time t is determined by quantum measurement. The specific steps can be found in the following table. Figure 5 .

[0076] Quantum measurement is a core concept in quantum mechanics, which describes the interaction between a quantum system and a measuring device. The probability of observing |ψ> in the density operator space ρ can be calculated by calculating the projection operator |ψ><ψ| through quantum measurement, which is usually calculated as follows:

[0077] p ψ (ρ)=<ψ|ρ|ψ>=tr(ρ|ψ><ψ|)

[0078] Observation probability p ψ (ρ) is a nonnegative real-valued scalar, since both ρ and |ψ><ψ| are Hermitian.

[0079] Therefore, each user request at time t And all servers after quantum interference processing Perform quantum measurements to determine the probability of each user request being scheduled to different servers.

[0080] For this purpose, refer to Figure 4 As shown, for the user request at time t It is deployed on the server The probability of can be calculated by the following formula:

[0081]

[0082] Represents the rth user request at time t The probability of being deployed on the Mth server, where Is a density matrix used to describe user requests The state vector requested by the rth user at time t is obtained by taking the outer product of itself:

[0083]

[0084] Finally, we will get a probability matrix represents the probability that the user request at time t is deployed on M servers, satisfying Among them, r is the number of user requests at time t, and M is the number of edge servers in this scenario.

[0085] Probability Matrix Structure reference Figure 4 shown.

[0086] The rows of the matrix represent the probability of a user request being deployed on M servers. The maximum value of each row is taken as the scheduling strategy for the user request, and the final decision result is obtained. represents the decision result of the user's request at time t, It represents the scheduling position requested by the rth user at time t, and satisfies

[0087] In summary, the method of this embodiment uses concepts such as quantum states and density matrices in quantum theory to model and represent user requests and server states, thereby effectively describing and characterizing user requests and server states. Since when user requests are scheduled to a specific server, the server must allocate necessary computing resources, memory, storage space, and network bandwidth to process these requests, this resource allocation will cause changes in the server state. For this reason, based on quantum state modeling, the principle of quantum interference is used to simulate changes in server states after resource allocation and scheduling. Finally, the principle of quantum measurement is used to determine the scheduling strategy for maximizing resource utilization of the server cluster while meeting the corresponding service quality requirements for each user request in the target user request set.

[0088] In addition, corresponding to Figure 1 The method shown, another embodiment of this embodiment further provides a scheduling device for edge services. Figure 5 is a schematic diagram of the structure of the scheduling device 500, including:

[0089] An acquisition module 510 is used to acquire a target user request set to be processed by a server cluster of an edge service;

[0090] Modeling module 520, used to construct a first density matrix model expressing the target user request set with user request as state vector and service quality requirement corresponding to the user request as probability; and to construct a second model expressing the server cluster with server state as state vector;

[0091] The simulation module 530 is used to simulate the server state changes of the server cluster processing the target user request set based on the first model and the second model using quantum interference theory, and determine the scheduling strategy for maximizing the resource utilization of the server cluster while satisfying the corresponding service quality requirements for each user request in the target user request set.

[0092] Optionally, the simulation module 530 is based on the first model and the second model, and uses quantum interference theory to simulate the server state changes of the server cluster processing the target user request set, and determines the scheduling strategy for maximizing the resource utilization of the server cluster while meeting the corresponding service quality requirements for each user request in the target user request set, including: based on the first model and the second model, in the direction of maximizing the resource utilization of the server cluster, using quantum interference theory to simulate the server state changes of the server cluster processing the target user request set, and determines the probability of each user request in the target user request set being allocated to each server in the server cluster while meeting the corresponding service quality requirements; for each user request in the target user request set, selecting the server with the highest probability as the corresponding scheduling strategy.

[0093] Optionally, the first density matrix model is:

[0094] in, represents the first density matrix model; t represents the time of the target user request set; represents the target user request set; r represents the number of user requests in the target user request set; The state vector representing the user request; Represents the probability of the user request corresponding to the density matrix.

[0095] Optionally, the second density matrix model is:

[0096] in, Indicates the status of the Mth server at time t; A state vector representing the state of the server.

[0097] Optionally, the probability of each user request in the target user request set being allocated to each server in the server cluster is:

[0098] in, Represents the rth user request at time t The probability of being deployed on the Mth server;

[0099]

[0100] Optionally, the server status is associated with idle computing resources of the server.

[0101] Optionally, the computing resources include at least one of CPU resources, memory resources, storage space resources and network bandwidth resources.

[0102] It should be noted that the scheduling device of this embodiment can be used as Figure 1 The execution subject of the method shown can thus realize Figure 1 The steps and functions in the method shown will not be repeated here.

[0103] Figure 6 is a schematic diagram of the structure of an electronic device provided in an embodiment. Figure 6 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0104] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0105] The memory is used to store the computer program. Specifically, the computer program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides the computer program to the processor. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming the above-mentioned logic layer. Figure 5 The scheduling device for edge services shown in the figure. Correspondingly, the processor executes the program stored in the memory and is specifically used to perform the following operations:

[0106] Get the target user request set to be processed by the server cluster of the edge service.

[0107] A first density matrix model expressing the target user request set is constructed with user request as state vector and service quality requirement corresponding to the user request as probability; and a second model expressing the server cluster is constructed with server status as state vector.

[0108] Based on the first model and the second model, quantum interference theory is used to simulate the server state changes of the server cluster in processing the target user request set, and a scheduling strategy for maximizing the resource utilization of the server cluster while meeting the corresponding service quality requirements for each user request in the target user request set is determined.

[0109] The above is as in this manual Figure 1 The scheduling method for edge services shown can be applied to a processor and implemented by the processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiment can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0110] Of course, in addition to software implementation, the electronic device of this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0111] In addition, the embodiment further provides a computer-readable storage medium, which stores one or more computer programs, wherein the one or more computer programs include instructions. When the instructions are executed by a portable electronic device including a plurality of application programs, the portable electronic device can execute Figure 1The steps in the method shown include:

[0112] Get the target user request set to be processed by the server cluster of the edge service.

[0113] A first density matrix model expressing the target user request set is constructed with user request as state vector and service quality requirement corresponding to the user request as probability; and a second model expressing the server cluster is constructed with server status as state vector.

[0114] Based on the first model and the second model, quantum interference theory is used to simulate the server state changes of the server cluster in processing the target user request set, and a scheduling strategy for maximizing the resource utilization of the server cluster while meeting the corresponding service quality requirements for each user request in the target user request set is determined.

[0115] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] The above are only embodiments of this specification and are not intended to limit this specification. For those skilled in the art, this specification may be subject to various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this specification shall be included in the scope of the claims of this specification. In addition, all other embodiments obtained by ordinary technicians in this field without creative work shall fall within the scope of protection of this document.

Claims

1. A scheduling method for edge services, characterized in that: include: Obtain a target user request set to be processed by the server cluster of the edge service; Taking user requests as state vectors and service quality requirements corresponding to user requests as probabilities, a first density matrix model expressing the target user request set is constructed; and taking server states as state vectors, a second model expressing the server cluster is constructed; Based on the first model and the second model, quantum interference theory is used to simulate the server state changes of the server cluster in processing the target user request set, and a scheduling strategy for maximizing the resource utilization of the server cluster while meeting the corresponding service quality requirements for each user request in the target user request set is determined.

2. The method according to claim 1, characterized in that Based on the first model and the second model, using quantum interference theory, the server state change of the server cluster processing the target user request set is simulated, and a scheduling strategy for maximizing the resource utilization of the server cluster is determined for each user request in the target user request set while satisfying the corresponding service quality requirements, including: Based on the first model and the second model, in the direction of maximizing the resource utilization of the server cluster, the server state change of the server cluster processing the target user request set is simulated by quantum interference theory, and the probability of each user request in the target user request set being allocated to each server in the server cluster while meeting the corresponding service quality requirements is determined; For each user request in the target user request set, a server with the highest probability is selected as the corresponding scheduling strategy.

3. The method according to claim 1, characterized in that The first density matrix model is: in, represents the first density matrix model; t represents the time of the target user request set; represents the target user request set; r represents the number of user requests in the target user request set; The state vector representing the user request; Represents the probability of the user request corresponding to the density matrix.

4. The method according to claim 3, characterized in that The second density matrix model is: in, Indicates the status of the Mth server at time t; A state vector representing the state of the server.

5. The method according to claim 3, characterized in that: The probability of each user request in the target user request set being assigned to each server in the server cluster is: in, Represents the rth user request at time t The probability of being deployed on the Mth server; 6. The method according to claim 1, characterized in that The server status is associated with idle computing resources of the server.

7. The method according to claim 6, characterized in that The computing resources include at least one of CPU resources, memory resources, storage space resources and network bandwidth resources.

8. A scheduling device for edge services, characterized in that: include: An acquisition module, used to acquire a target user request set to be processed by a server cluster of an edge service; A modeling module, used to construct a first density matrix model expressing the target user request set, taking the user request as a state vector and the service quality requirement corresponding to the user request as a probability; And, constructing a second model expressing the server cluster using the server state as a state vector; A simulation module is used to simulate the server state changes of the server cluster processing the target user request set based on the first model and the second model using quantum interference theory, and determine a scheduling strategy for maximizing the resource utilization of the server cluster while satisfying the corresponding service quality requirements for each user request in the target user request set.

9. An electronic device, comprising: processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer-readable storage medium storing a computer program, characterized in that: The computer program is operable to cause a computer to perform the method according to any one of claims 1 to 7.

Images