CN115907022A - Multi-quantum service conversion and simulation scheduling method, device, equipment and medium - Google Patents
Multi-quantum service conversion and simulation scheduling method, device, equipment and medium Download PDFInfo
- Publication number
- CN115907022A CN115907022A CN202310005100.2A CN202310005100A CN115907022A CN 115907022 A CN115907022 A CN 115907022A CN 202310005100 A CN202310005100 A CN 202310005100A CN 115907022 A CN115907022 A CN 115907022A
- Authority
- CN
- China
- Prior art keywords
- quantum
- business system
- dispatcher
- data
- decision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000006243 chemical reaction Methods 0.000 title claims description 9
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims description 56
- 238000013528 artificial neural network Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013461 design Methods 0.000 claims description 9
- 230000003287 optical effect Effects 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 6
- 230000006978 adaptation Effects 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 abstract description 6
- 230000002787 reinforcement Effects 0.000 description 23
- 238000007726 management method Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 239000000835 fiber Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device, equipment and a readable medium for converting and simulating multi-quantum services, wherein the method comprises the following steps: collecting data of each quantum system unit through a cloud data center, and constructing a quantum business system simulation environment based on the collected data; designing a quantum business system dispatcher decision model; obtaining data of a quantum business system dispatcher executing a decision, and training a quantum business system dispatcher decision model in a simulation environment based on the obtained data of the executing decision; and using the trained quantum business system dispatcher decision model to assist a quantum business system dispatcher in executing a decision. By using the scheme of the invention, the influence caused by artificial misoperation can be reduced, the scheduling efficiency and accuracy are improved, the difficulty of micro-service application deployment and management can be reduced, and the adaptive management of different types of quantum services can be realized. The present invention relates to the field of computers.
Description
Technical Field
The present invention relates to the field of computers, and more particularly, to a method, an apparatus, a device, and a readable medium for multi-quantum service conversion and simulation scheduling.
Background
In recent years, the reinforcement learning technology has attracted extensive attention, and particularly, the reinforcement learning technology is combined with deep learning to bring great progress to the field of artificial intelligence. Reinforcement learning differs from traditional supervised learning mainly in that reinforcement signals provided by the environment in reinforcement learning are an evaluation (usually scalar signals) of how good or bad actions are generated, rather than telling the reinforcement learning system RLS how to generate correct actions. The reinforcement learning continuously learns to make optimal actions under different environments through the interactive tasks between the intelligent agent and the environments, and the perception generation strategies are utilized, so that higher machine intelligence can be created. Reinforcement learning is applied in the fields of robot control, automatic driving, recommendation systems and the like, and surpasses human performance in many fields.
The large quantum business system cluster scheduling is a combination of the calculation power provided by a plurality of quantum calculation participating nodes and the classical calculation, and is a complex large cluster system. With the development of quantum computing, higher requirements are placed on a quantum system cluster, data from each computing node are collected through various sensors, states of participants participating in a large-scale quantum system are better known through data analysis, problems can be found in advance, abnormal faults occurring in the quantum system can be responded and processed in time, manual operation errors of dispatchers can be reduced, the real environment can be simulated through simulation of the large-scale quantum service system cluster by effectively utilizing a reinforcement learning technology, an accurate and efficient dispatching strategy of the dispatchers of the large-scale quantum service system cluster is formed, and the problem that adverse consequences are to be solved due to the dispatching errors is avoided.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, a device, and a readable medium for multi-quantum service conversion and simulation scheduling, which can reduce the impact caused by human misoperation, improve scheduling efficiency and accuracy, reduce difficulty in micro-service application deployment and management, and implement adaptive management of different types of quantum services.
Based on the above object, an aspect of the embodiments of the present invention provides a method for multi-quantum service transformation and simulation scheduling, which includes the following steps:
collecting data of each quantum system unit through a cloud data center, and constructing a quantum service system simulation environment based on the collected data;
designing a quantum business system dispatcher decision model;
obtaining data of a quantum service system dispatcher executing a decision, and training a quantum service system dispatcher decision model in a simulation environment based on the obtained data of the executing decision;
and using the trained quantum business system dispatcher decision model to assist a quantum business system dispatcher in executing a decision.
According to one embodiment of the invention, the steps of collecting data of each quantum system unit through a cloud data center and constructing the quantum business system simulation environment based on the collected data comprise:
collecting running data of each quantum system unit, wherein the running data comprises real-time state data, running logs, scheduling plans, fault data and data executed by a scheduler in a scheduling way of each quantum system unit;
and constructing a quantum business system analog simulation environment based on the acquired data and by utilizing a digital twinning technology.
According to one embodiment of the present invention, obtaining data for a quantum service system dispatcher to execute a decision, and training a quantum service system dispatcher decision model in a simulation environment based on the obtained data for executing the decision comprises:
acquiring data for a quantum business system dispatcher to execute a decision;
constructing a scheduling operation instruction execution sequence of the quantum service system scheduler according to the actual operation of the quantum service system scheduler and by combining the state environment of the quantum service system;
determining the next step of executing scheduling operation in the simulation environment according to the current quantum business system plan, the running state of each quantum system unit and the accident abnormal practical condition;
setting a reward function of the quantum business system simulation environment according to the scheduling operation and the actual execution effect of a quantum business system dispatcher by combining the scheduling operation determined in the simulation environment;
and training a quantum business system dispatcher decision model based on a reward function and by adopting an A3C algorithm.
According to one embodiment of the invention, training a scheduler decision model of a quantum business system based on a reward function and adopting an A3C algorithm comprises the following steps:
setting the number of worker threads, the global shared iteration number, the global maximum iteration number, the state feature dimension and the global parameters of an operation instruction set, setting a global model public neural network, and setting an initialization state of a simulation environment;
initializing a quantum business system dispatcher decision model;
enabling each worker thread to independently interact with the simulation environment by adopting a global model public neural network, executing scheduling operation to obtain feedback, updating the gradient of the local global model public neural network, and updating the model parameters of the global model public neural network;
and circularly executing the previous step until the decision model of the quantum business system dispatcher converges.
According to one embodiment of the invention, the global model public neural network comprises an Actor network and a Critic network.
According to one embodiment of the invention, assisting a quantum business system dispatcher in executing a decision by using a trained quantum business system dispatcher decision model comprises:
acquiring actual operation data of the current quantum business system in real time, and updating the actual operation data into a simulation environment in real time;
outputting the next scheduling operation according to the current actual condition by using the trained quantum service system dispatcher decision model;
recording the current simulation environment state and the next scheduling operation output by the quantum service system dispatcher decision model, and feeding back and updating the simulation environment;
and setting a time period, repeatedly executing the steps to form a recommended operation sequence of the quantum service system dispatcher, and using the recommended operation sequence to assist the quantum service system dispatcher in executing a decision.
According to one embodiment of the invention, using the recommended operation sequence to assist the quantum business system dispatcher in making a decision comprises:
a quantum business system dispatcher refers to the recommended operation sequence and carries out dispatching operation by combining with actual conditions;
and after the scheduling operation, acquiring an actual operation result, updating actual operation data of the current quantum service system, and updating the actual operation data into the simulation environment in real time.
According to an embodiment of the present invention, further comprising:
and optimizing a quantum business system dispatcher decision model according to the actual operation of each quantum business system dispatcher.
According to an embodiment of the present invention, optimizing a quantum business system dispatcher decision model according to the actual operation of each quantum business system dispatcher comprises:
acquiring actual operation data of each quantum business system dispatcher;
training a quantum business system dispatcher decision model by using actually operated data in a simulation environment;
simulating the operation and scheduling of the quantum business system in a simulation environment by using a quantum business system dispatcher decision model;
comparing the scheduling result of the quantum business system dispatcher decision model with the optimal scheduling instruction;
and optimizing a scheduling strategy of a quantum service system scheduler decision model according to the comparison result.
According to an embodiment of the present invention, further comprising:
comparing the scheduling operation of the quantum business system dispatcher decision model with the optimal scheduling instruction;
and optimizing the scheduling strategy of the quantum business system dispatcher decision model according to the comparison result.
According to one embodiment of the invention, the collecting data of each quantum system unit through the cloud data center comprises the following steps:
and data of the superconducting quantum system, the nuclear spin quantum system, the optical cavity quantum system and the ion well quantum system are acquired through the cloud data center.
According to one embodiment of the invention, the cloud data center is a service which can be processed by the cloud center and is converted by the actual quantum business system of each quantum system unit through a quantum business adapter.
According to an embodiment of the present invention, further comprising:
micro-services are created in the cloud data center to encapsulate different quantum business processing classes in the cloud data center adaptation interface.
According to one embodiment of the invention, creating a microservice in a cloud data center comprises:
acquiring a micro-service creation request, wherein the micro-service creation request comprises creation information and a target quantum service;
searching a target processing class corresponding to the target quantum business according to the corresponding relation between the processing class and the quantum business;
the creation information is deployed with the target processing class to create instances of the microservice on the target quantum traffic.
According to an embodiment of the present invention, further comprising:
responding to a received micro-service creation request input by a user in a cloud data center, and acquiring creation information of the creation request and a target quantum service;
and calling a corresponding processing class in the cloud data center based on the target quantum business to establish an instance of the micro service.
According to one embodiment of the invention, creating a microservice in a cloud data center comprises:
acquiring metadata and service type examples corresponding to various quantum computers;
orchestrating the service type instances to construct a software environment for the service type instances;
and configuring parameters of the corresponding service type instances according to the metadata to obtain the processing classes of the quantum services.
According to an embodiment of the present invention, finding a target processing class corresponding to a target quantum service according to a correspondence between the processing class and the quantum service includes:
judging whether a target quantum business is recorded in the corresponding relation between the processing class and the quantum business;
responding to the target quantum business recorded, and taking a processing class corresponding to the target quantum business as a target processing class;
and in response to the target quantum business is not recorded, calling a preset general processing class as a target processing class.
In another aspect of the embodiments of the present invention, there is also provided a device for multi-quantum service conversion and simulation scheduling, where the device includes:
the building module is configured to collect data of each quantum system unit through the cloud data center and build a quantum business system simulation environment based on the collected data;
the design module is configured to design a quantum business system dispatcher decision model;
the training module is configured to acquire data of a quantum business system dispatcher executing decision and train a quantum business system dispatcher decision model in a simulation environment based on the acquired data of the executing decision;
and the execution module is configured to assist a quantum business system dispatcher in executing a decision by using the trained quantum business system dispatcher decision model.
In another aspect of an embodiment of the present invention, there is also provided a computer apparatus including:
at least one processor; and
a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of any of the methods described above.
In another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium storing a computer program, which when executed by a processor implements the steps of any one of the above-mentioned methods.
The invention has the following beneficial technical effects: the quantum business system simulation scheduling method provided by the embodiment of the invention collects data of each quantum system unit through the cloud data center, and constructs a quantum business system simulation environment based on the collected data; designing a quantum business system dispatcher decision model; obtaining data of a quantum business system dispatcher executing a decision, and training a quantum business system dispatcher decision model in a simulation environment based on the obtained data of the executing decision; the technical scheme of using the trained quantum service system dispatcher decision model to assist the quantum service system dispatcher in executing the decision can reduce the influence caused by artificial misoperation, improve the dispatching efficiency and accuracy, reduce the difficulty of micro-service application deployment and management, and realize the adaptive management of different types of quantum services.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method of multi-quantum service conversion and simulation scheduling according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an apparatus for multi-quantum service conversion and simulation scheduling according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a computer device according to one embodiment of the present invention;
fig. 4 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention are described in further detail with reference to the accompanying drawings.
In view of the above-mentioned objects, a first aspect of the embodiments of the present invention provides an embodiment of a method for multi-quantum service transformation and simulation scheduling. Fig. 1 shows a schematic flow diagram of the method.
As shown in fig. 1, the method may comprise the steps of:
s1, data of each quantum system unit are collected through a cloud data center, and a quantum business system simulation environment is constructed based on the collected data. The data from each participating quantum system unit is collected through a large quantum service cluster cloud data center, a quantum service system analog simulation environment is formed by utilizing a digital twin technology, the collected data mainly refers to data operated by each quantum system unit, and the operated data comprises real-time state data, operation logs, scheduling plans, fault data and data executed by a scheduler in a scheduling mode. Each quantum system unit comprises a superconducting quantum system, a nuclear spin quantum system, an optical cavity quantum system and an ion well quantum system. The quantum business system simulation environment runs in a quantum business system cloud data center, a data twin operation body participating in quantum business system units is realized through data acquisition and instruction control of all participating quantum business system units, the quantum business system cloud data center is used for providing computing, storage and network cloud technical facility services, a business management system of a running quantum system collects sensing data of all participating quantum business system units and provides computing power and storage required by reinforcement learning training, data from all quantum participating nodes are unit data of the quantum business system, and the data are converted into quantum business classical data.
And S2, designing a quantum business system dispatcher decision model. The decision model of the dispatcher of the reinforcement learning quantum business system is a strategy model formed by simulating the actual operation of the dispatcher, is obtained through reinforcement training and is a serialized neural network model, and the dispatching operation to be executed by the dispatcher of the system is determined according to the business plan, the business process and the actual business operation condition of the current quantum business system.
S3, data of the quantum business system dispatcher executing decision are obtained, and a quantum business system dispatcher decision model is trained in a simulation environment based on the obtained data of the executing decision. The method comprises the steps of firstly obtaining data of a quantum business system dispatcher executing a decision, constructing a quantum business system dispatcher dispatching operation instruction execution sequence according to actual operation of the quantum business system dispatcher and combining with a state environment of a quantum business system, determining the next step of executing the dispatching operation in a simulation environment according to a current quantum business system plan, the operation state of each quantum system unit and an accident abnormal practice condition, setting a reward function of the simulation environment of the quantum business system according to the dispatching operation and the actual execution effect of the quantum business system dispatcher and combining with the dispatching operation determined in the simulation environment, and training a decision model of the quantum business system dispatcher by adopting an A3C algorithm based on the reward function. The training process comprises the steps of setting the number of worker threads, the number of global shared iterations, the number of global maximum iterations, state feature dimensions and global parameters of an operation instruction set, setting a global model public neural network, setting an initialization state of a simulation environment, initializing a quantum business system dispatcher decision model, enabling each worker thread to independently interact with the simulation environment by adopting the global model public neural network, executing scheduling operation to obtain feedback, updating the gradient of the local global model public neural network, updating the model parameters of the global model public neural network, and circularly executing the previous step until the quantum business system dispatcher decision model is converged.
And S4, using the trained quantum business system dispatcher decision model to assist a quantum business system dispatcher in executing a decision.
By the technical scheme, the influence caused by manual operation errors can be reduced, the scheduling efficiency and accuracy are improved, the difficulty of micro-service application deployment and management can be reduced, and the adaptive management of different types of quantum services can be realized.
In a preferred embodiment of the present invention, the collecting data of each quantum system unit by the cloud data center, and constructing the quantum business system simulation environment based on the collected data includes:
collecting the running data of each quantum system unit, wherein the running data comprises real-time state data, running logs, scheduling plans, fault data and data scheduled and executed by a dispatcher of each quantum system unit;
and constructing a quantum business system analog simulation environment based on the acquired data and by utilizing a digital twinning technology.
In a preferred embodiment of the present invention, the obtaining data of the quantum business system dispatcher decision execution, and training the quantum business system dispatcher decision model in the simulation environment based on the obtained data of the decision execution comprises:
acquiring data for a quantum business system dispatcher to execute a decision;
constructing a scheduling operation instruction execution sequence of the quantum service system scheduler according to the actual operation of the quantum service system scheduler and by combining the state environment of the quantum service system;
determining the next step of executing scheduling operation in the simulation environment according to the current quantum business system plan, the running state of each quantum system unit and the accident abnormal practical condition;
setting a reward function of the quantum business system simulation environment according to the scheduling operation and the actual execution effect of a quantum business system dispatcher by combining the scheduling operation determined in the simulation environment;
and training a quantum business system dispatcher decision model based on a reward function and by adopting an A3C algorithm.
In a preferred embodiment of the present invention, training a quantum business system dispatcher decision model based on a reward function and using an A3C algorithm comprises:
setting the number of worker threads, the global shared iteration number, the global maximum iteration number, the state feature dimension and the global parameters of an operation instruction set, setting a global model public neural network, and setting an initialization state of a simulation environment;
initializing a quantum business system dispatcher decision model;
enabling each worker thread to independently interact with the simulation environment by adopting a global model public neural network, executing scheduling operation to obtain feedback, updating the gradient of the local global model public neural network, and updating the model parameters of the global model public neural network;
and circularly executing the previous step until the decision model of the quantum business system dispatcher converges.
In a preferred embodiment of the present invention, the global model public neural network includes an Actor network and a Critic network. Applying for resources in a cloud data center of a quantum business system, training a reinforcement learning quantum business system dispatcher decision model by adopting an A3C algorithm, firstly setting the number of worker threads, the global shared iteration number, the global maximum iteration number, state feature dimensions and global parameters of an operation instruction set, initializing the reinforcement learning quantum business system dispatcher decision model, setting a global model public neural network, and setting a simulation environment initialization state of the quantum business system, wherein the global model public neural network comprises an Actor network and a criticic network, each worker thread adopts an Actor network and criticic network structure by utilizing the A3C algorithm, independently interacts with the simulation environment of the quantum business system, executes dispatching operation to obtain feedback, updates the gradients of the Actor network and the criticic network, collects the updated results to the global model public neural network, updates the model parameters of the global model public neural network, and circularly executes the steps until the reinforcement learning quantum business system dispatcher decision model converges to obtain an optimal reinforcement learning quantum business system dispatcher model.
In a preferred embodiment of the present invention, assisting a quantum service system dispatcher in making a decision by using a trained quantum service system dispatcher decision model comprises:
acquiring actual operation data of the current quantum business system in real time, and updating the actual operation data into a simulation environment in real time;
outputting the next scheduling operation according to the current actual condition by using the trained quantum service system dispatcher decision model;
recording the current simulation environment state and the next scheduling operation output by the quantum service system dispatcher decision model, and feeding back and updating the simulation environment;
and setting a time period, repeatedly executing the steps to form a recommended operation sequence of the quantum service system dispatcher, and using the recommended operation sequence to assist the quantum service system dispatcher in executing a decision. The actual operation data of the current quantum business system is updated to the simulation environment in real time, so that the simulation environment is consistent with the real quantum business system, a series of scheduling operations required by a dispatcher are simulated in the simulation environment according to the trained decision model, and the real dispatcher can be used as a reference when the dispatching operations are carried out, so that the dispatcher is prevented from operating incorrectly due to personal reasons.
In a preferred embodiment of the present invention, using the recommended sequence of operations to assist the quantum business system dispatcher in making decisions comprises:
a quantum business system dispatcher refers to the recommended operation sequence and carries out dispatching operation by combining with actual conditions;
and after scheduling operation, acquiring an actual operation result, updating actual operation data of the current quantum business system, and updating the actual operation data into a simulation environment in real time. And updating the actual operation result fact of the dispatcher into the simulation environment so that the decision model can make the most correct decision under the latest data.
In a preferred embodiment of the present invention, the method further comprises:
and optimizing the decision model of the quantum business system dispatcher according to the actual operation of each quantum business system dispatcher. The method comprises the steps of utilizing a quantum business system simulation environment, aiming at the actual operation of each quantum business system dispatcher, training a personalized reinforcement learning quantum business system dispatcher decision model by adopting a reinforcement learning method, taking the personalized reinforcement learning quantum business system dispatcher decision model of the quantum business system dispatcher as a simulation dispatcher, continuously interacting with the quantum business system simulation environment, simulating the operation and dispatching of a quantum business system, evaluating the dispatching result of the quantum business system dispatcher personalized reinforcement learning quantum business system dispatcher decision model of the quantum business system dispatcher, comparing the dispatching result with an optimal dispatching instruction execution strategy, finding a dispatching problem in the model, further improving a dispatching strategy, simulating the dispatching operation of all dispatchers in the quantum business system simulation environment according to the actual situation, comparing the dispatching result with the optimal dispatching instruction execution strategy, finding an abnormal link, optimizing a dispatching mode, simulating the operation and dispatching of the quantum business system at a future moment by combining actual data of the quantum business system in the quantum business system simulation environment according to the future actual situation, finding a problem in advance, avoiding the occurrence of quantum accidents, continuously collecting data from the operation and dispatching of the actual quantum business system, and optimizing the reinforcement learning quantum business system dispatcher for optimizing the reinforcement learning business system dispatcher decision model.
In a preferred embodiment of the present invention, optimizing the quantum business system dispatcher decision model according to the actual operation of each quantum business system dispatcher comprises:
acquiring actual operation data of each quantum business system dispatcher;
training a quantum business system dispatcher decision model by using actually operated data in a simulation environment;
simulating the operation and scheduling of the quantum business system in a simulation environment by using a quantum business system dispatcher decision model;
comparing the scheduling result of the quantum business system dispatcher decision model with the optimal scheduling instruction;
and optimizing the scheduling strategy of the quantum business system dispatcher decision model according to the comparison result.
In a preferred embodiment of the present invention, further comprising:
comparing the scheduling operation of the quantum business system dispatcher decision model with the optimal scheduling instruction;
and optimizing the scheduling strategy of the quantum business system dispatcher decision model according to the comparison result.
In a preferred embodiment of the present invention, the collecting data of each quantum system unit by the cloud data center includes:
and data of the superconducting quantum system, the nuclear spin quantum system, the optical cavity quantum system and the ion well quantum system are acquired through the cloud data center.
In a preferred embodiment of the present invention, the cloud data center is a service that is converted by the actual quantum business system of each quantum system unit through a quantum business adapter to be processed by the cloud center. The quantum business cloud data center is a classic business which can be processed by the cloud center and is converted by an actual quantum business system of each quantum node through a quantum business adapter, the flow of the classic business is established in the cloud center and is realized through a flow arrangement mode, and a micro-service management method for adapting the quantum business and the classic business is provided.
In a preferred embodiment of the present invention, further comprising:
micro-services are created in the cloud data center to encapsulate different quantum business processing classes in the cloud data center adaptation interface.
In a preferred embodiment of the present invention, creating a microservice in a cloud data center comprises:
acquiring a micro-service creation request, wherein the micro-service creation request comprises creation information and a target quantum service;
searching a target processing class corresponding to the target quantum business according to the corresponding relation between the processing class and the quantum business;
the creation information is deployed with the target processing class to create instances of the microservice on the target quantum traffic.
In a preferred embodiment of the present invention, the method further comprises:
in response to receiving a micro-service creation request input by a user in a cloud data center, obtaining creation information of the creation request and a target quantum service;
and calling a corresponding processing class in the cloud data center based on the target quantum business to establish an instance of the micro service. The difficulty of micro-service application deployment and management can be reduced, and the adaptive management of different types of quantum services is realized.
In a preferred embodiment of the present invention, creating a microservice in a cloud data center comprises:
acquiring metadata and service type examples corresponding to various quantum computers;
arranging the service type instances to construct a software environment of the service type instances;
and configuring parameters of the corresponding service type instances according to the metadata to obtain the processing classes of the quantum services.
In a preferred embodiment of the present invention, finding the target processing class corresponding to the target quantum service according to the correspondence between the processing class and the quantum service includes:
judging whether a target quantum business is recorded in the corresponding relation between the processing class and the quantum business;
responding to the record of the target quantum business, and taking a processing class corresponding to the target quantum business as a target processing class;
and in response to the target quantum business is not recorded, calling a preset general processing class as a target processing class.
The method collects quantum business system data through a large number of sensing devices, utilizes a digital twin technology to form a simulation environment based on mass data, designs a decision model for a reinforcement learning quantum business system dispatcher, and adopts an A3C training method to interact with the simulation environment according to the condition of the actual quantum business system dispatcher so as to finally form an optimal execution strategy for assisting the quantum business system dispatcher to make decision and execute, eliminates the influence caused by artificial misoperation as much as possible, and improves the dispatching efficiency and accuracy.
The invention encapsulates different quantum business processing classes in the data platform adaptation interface, and shields different deployment and management modes of the platform bottom layer. When a user needs to provide services by using a certain type of quantum services, the user only needs to directly input a micro-service creation request on a platform management interface, and the management platform can establish a micro-service instance on a target quantum service by searching and calling a corresponding processing type, so that the difficulty of micro-service application deployment and management is reduced, and the adaptive management of different types of quantum services is realized.
It should be noted that, as will be understood by those skilled in the art, all or part of the processes in the methods of the above embodiments may be implemented by instructing relevant hardware through a computer program, and the above programs may be stored in a computer-readable storage medium, and when executed, the programs may include the processes of the embodiments of the methods as described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like. The embodiments of the computer program may achieve the same or similar effects as any of the above-described method embodiments.
Furthermore, the method disclosed according to an embodiment of the present invention may also be implemented as a computer program executed by a CPU, which may be stored in a computer-readable storage medium. The computer program, when executed by the CPU, performs the functions defined above in the methods disclosed in the embodiments of the present invention.
In view of the above object, according to a second aspect of the embodiments of the present invention, there is provided an apparatus for multi-quantum service conversion and simulation scheduling, as shown in fig. 2, the apparatus 200 includes:
the building module is configured to collect data of each quantum system unit through a cloud data center and build a quantum service system simulation environment based on the collected data;
a design module configured to design a quantum business system dispatcher decision model;
the training module is configured to acquire data of a quantum business system dispatcher executing a decision, and train a quantum business system dispatcher decision model in a simulation environment based on the acquired data of the executing decision;
an execution module configured to assist a quantum service system dispatcher in executing a decision using the trained quantum service system dispatcher decision model.
In view of the above object, a third aspect of the embodiments of the present invention provides a computer device. Fig. 3 is a schematic diagram of an embodiment of a computer device provided by the present invention. As shown in fig. 3, the embodiment of the present invention includes the following means: at least one processor 21; and a memory 22, the memory 22 storing computer instructions 23 executable on the processor, the instructions when executed by the processor implementing the method of:
collecting data of each quantum system unit through a cloud data center, and constructing a quantum business system simulation environment based on the collected data;
designing a quantum business system dispatcher decision model;
obtaining data of a quantum service system dispatcher executing a decision, and training a quantum service system dispatcher decision model in a simulation environment based on the obtained data of the executing decision;
and using the trained quantum business system dispatcher decision model to assist a quantum business system dispatcher in executing a decision.
In a preferred embodiment of the present invention, the collecting data of each quantum system unit by the cloud data center, and constructing the quantum business system simulation environment based on the collected data includes:
collecting the running data of each quantum system unit, wherein the running data comprises real-time state data, running logs, scheduling plans, fault data and data scheduled and executed by a dispatcher of each quantum system unit;
and constructing a quantum business system analog simulation environment based on the acquired data and by utilizing a digital twin technology.
In a preferred embodiment of the present invention, the obtaining data of the quantum business system dispatcher decision execution, and training the quantum business system dispatcher decision model in the simulation environment based on the obtained data of the decision execution comprises:
acquiring data for a quantum business system dispatcher to execute a decision;
constructing a scheduling operation instruction execution sequence of the quantum service system scheduler according to the actual operation of the quantum service system scheduler and by combining the state environment of the quantum service system;
determining the next step of executing scheduling operation in the simulation environment according to the current quantum business system plan, the running state of each quantum system unit and the accident abnormal practical condition;
setting a reward function of the quantum business system simulation environment according to the scheduling operation and the actual execution effect of a quantum business system dispatcher by combining the scheduling operation determined in the simulation environment;
and training a decision model of a dispatcher of the quantum service system by adopting an A3C algorithm based on a reward function.
In a preferred embodiment of the present invention, training a quantum business system dispatcher decision model based on a reward function and using an A3C algorithm comprises:
setting the number of worker threads, the global shared iteration number, the global maximum iteration number, the state feature dimension and the global parameters of an operation instruction set, setting a global model public neural network, and setting an initialization state of a simulation environment;
initializing a quantum business system dispatcher decision model;
enabling each worker thread to independently interact with the simulation environment by adopting a global model public neural network, executing scheduling operation to obtain feedback, updating the gradient of the local global model public neural network, and updating the model parameters of the global model public neural network;
and circularly executing the previous step until the decision model of the quantum business system dispatcher converges.
In a preferred embodiment of the present invention, the global model public neural network comprises an Actor network and a Critic network.
In a preferred embodiment of the present invention, assisting a quantum service system dispatcher in making a decision by using a trained quantum service system dispatcher decision model comprises:
acquiring actual operation data of the current quantum business system in real time, and updating the actual operation data into a simulation environment in real time;
outputting the next scheduling operation according to the current actual condition by using the trained quantum service system dispatcher decision model;
recording the current simulation environment state and the next scheduling operation output by the quantum service system dispatcher decision model, and feeding back and updating the simulation environment;
and setting a time period, repeatedly executing the steps to form a recommended operation sequence of the quantum service system dispatcher, and using the recommended operation sequence to assist the quantum service system dispatcher in executing a decision.
In a preferred embodiment of the present invention, using the recommended sequence of operations to assist the quantum business system dispatcher in making decisions comprises:
a quantum business system dispatcher refers to the recommended operation sequence and carries out dispatching operation by combining with actual conditions;
and after scheduling operation, acquiring an actual operation result, updating actual operation data of the current quantum business system, and updating the actual operation data into a simulation environment in real time.
In a preferred embodiment of the present invention, the method further comprises:
and optimizing the decision model of the quantum business system dispatcher according to the actual operation of each quantum business system dispatcher.
In a preferred embodiment of the present invention, optimizing the quantum business system dispatcher decision model according to the actual operation of each quantum business system dispatcher comprises:
acquiring actual operation data of each quantum business system dispatcher;
training a quantum business system dispatcher decision model by using actually operated data in a simulation environment;
simulating the operation and scheduling of the quantum business system in a simulation environment by using a quantum business system dispatcher decision model;
comparing the scheduling result of the quantum business system dispatcher decision model with the optimal scheduling instruction;
and optimizing the scheduling strategy of the quantum business system dispatcher decision model according to the comparison result.
In a preferred embodiment of the present invention, the method further comprises:
comparing the scheduling operation of the quantum business system dispatcher decision model with the optimal scheduling instruction;
and optimizing the scheduling strategy of the quantum business system dispatcher decision model according to the comparison result.
In a preferred embodiment of the present invention, the collecting data of each quantum system unit by the cloud data center includes:
and data of the superconducting quantum system, the nuclear spin quantum system, the optical cavity quantum system and the ion well quantum system are acquired through the cloud data center.
In a preferred embodiment of the present invention, the cloud data center is a service that is converted by the actual quantum business system of each quantum system unit through a quantum business adapter into a cloud center capable of processing.
In a preferred embodiment of the present invention, the method further comprises:
micro-services are created in the cloud data center to encapsulate different quantum business processing classes in the cloud data center adaptation interface.
In a preferred embodiment of the present invention, creating a microservice in a cloud data center comprises:
acquiring a micro-service creation request, wherein the micro-service creation request comprises creation information and a target quantum service;
searching a target processing class corresponding to the target quantum business according to the corresponding relation between the processing class and the quantum business;
the creation information is deployed with the target processing class to establish instances of microservices on the target quantum traffic.
In a preferred embodiment of the present invention, the method further comprises:
in response to receiving a micro-service creation request input by a user in a cloud data center, obtaining creation information of the creation request and a target quantum service;
and calling a corresponding processing class in the cloud data center based on the target quantum business to establish an instance of the micro service.
In a preferred embodiment of the present invention, creating a microservice in a cloud data center comprises:
acquiring metadata and service type examples corresponding to various quantum computers;
orchestrating the service type instances to construct a software environment for the service type instances;
and configuring parameters of the corresponding service type instances according to the metadata to obtain the processing classes of the quantum services.
In a preferred embodiment of the present invention, finding the target processing class corresponding to the target quantum service according to the correspondence between the processing class and the quantum service includes:
judging whether a target quantum business is recorded in the corresponding relation between the processing class and the quantum business;
responding to the record of the target quantum business, and taking a processing class corresponding to the target quantum business as a target processing class;
and in response to the target quantum business is not recorded, calling a preset general processing class as a target processing class.
In view of the above object, a fourth aspect of the embodiments of the present invention proposes a computer-readable storage medium. FIG. 4 is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by the present invention. As shown in fig. 4, the computer readable storage medium 31 stores a computer program 32 which, when executed by a processor, performs the method as described above.
Furthermore, the methods disclosed according to embodiments of the present invention may also be implemented as a computer program executed by a processor, which may be stored in a computer-readable storage medium. Which when executed by a processor performs the above-described functions defined in the methods disclosed in embodiments of the invention.
Further, the above method steps and system elements may also be implemented using a controller and a computer readable storage medium for storing a computer program for causing the controller to implement the functions of the above steps or elements.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as software or hardware depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed embodiments of the present invention.
In one or more exemplary designs, the functions may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. Disk and disc, as used herein, includes Compact Disc (CD), laser disc, optical disc, digital Versatile Disc (DVD), floppy disk, blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.
The foregoing are exemplary embodiments of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the present disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the embodiments of the invention may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items.
The numbers of the embodiments disclosed in the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, where the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, of embodiments of the invention is limited to these examples; within the idea of an embodiment of the invention, also technical features in the above embodiment or in different embodiments may be combined and there are many other variations of the different aspects of the embodiments of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the embodiments of the present invention.
Claims (20)
1. A method for converting and simulating scheduling of multi-quantum services is characterized by comprising the following steps:
collecting data of each quantum system unit through a cloud data center, and constructing a quantum business system simulation environment based on the collected data;
designing a quantum business system dispatcher decision model;
obtaining data of a quantum business system dispatcher executing a decision, and training a quantum business system dispatcher decision model in a simulation environment based on the obtained data of the executing decision;
and using the trained quantum business system dispatcher decision model to assist a quantum business system dispatcher in executing a decision.
2. The method of claim 1, wherein collecting data of each quantum system unit through a cloud data center, and constructing a quantum business system simulation environment based on the collected data comprises:
collecting running data of each quantum system unit, wherein the running data comprises real-time state data, running logs, scheduling plans, fault data and data executed by a scheduler in a scheduling way of each quantum system unit;
and constructing a quantum business system analog simulation environment based on the acquired data and by utilizing a digital twin technology.
3. The method of claim 1, wherein obtaining data for a quantum business system dispatcher to execute decisions and training a quantum business system dispatcher decision model in a simulation environment based on the obtained data for executing decisions comprises:
acquiring data for a quantum business system dispatcher to execute a decision;
constructing a scheduling operation instruction execution sequence of the quantum service system scheduler according to the actual operation of the quantum service system scheduler and by combining the state environment of the quantum service system;
determining the next step of executing scheduling operation in the simulation environment according to the current quantum business system plan, the running state of each quantum system unit and the accident abnormal practical condition;
setting a reward function of the quantum business system simulation environment according to the scheduling operation and the actual execution effect of a quantum business system dispatcher by combining the scheduling operation determined in the simulation environment;
and training a decision model of a dispatcher of the quantum service system by adopting an A3C algorithm based on a reward function.
4. The method of claim 3, wherein training the quantum business system dispatcher decision model based on the reward function and using an A3C algorithm comprises:
setting the number of worker threads, the global shared iteration number, the global maximum iteration number, the state feature dimension and the global parameters of an operation instruction set, setting a global model public neural network, and setting an initialization state of a simulation environment;
initializing a quantum business system dispatcher decision model;
enabling each worker thread to independently interact with the simulation environment by adopting a global model public neural network, executing scheduling operation to obtain feedback, updating the gradient of the local global model public neural network, and updating the model parameters of the global model public neural network;
and circularly executing the previous step until the decision model of the quantum business system dispatcher converges.
5. The method of claim 4, wherein the global model public neural network comprises an Actor network and a Critic network.
6. The method of claim 1, wherein using the trained quantum business system dispatcher decision model to assist a quantum business system dispatcher in making a decision comprises:
acquiring actual operation data of a current quantum business system in real time, and updating the actual operation data into an analog simulation environment in real time;
outputting the next scheduling operation according to the current actual condition by using the trained quantum service system dispatcher decision model;
recording the current simulation environment state and the next scheduling operation output by the quantum service system dispatcher decision model, and feeding back and updating the simulation environment;
and setting a time period, repeatedly executing the steps to form a recommended operation sequence of the quantum service system dispatcher, and using the recommended operation sequence to assist the quantum service system dispatcher in executing a decision.
7. The method of claim 6, wherein using the recommended sequence of operations to assist a quantum business system dispatcher in making decisions comprises:
a quantum service system dispatcher refers to the recommended operation sequence and carries out dispatching operation by combining with actual conditions;
and after scheduling operation, acquiring an actual operation result, updating actual operation data of the current quantum business system, and updating the actual operation data into a simulation environment in real time.
8. The method of claim 1, further comprising:
and optimizing a quantum business system dispatcher decision model according to the actual operation of each quantum business system dispatcher.
9. The method of claim 8, wherein optimizing the quantum business system dispatcher decision model based on the actual operation of each quantum business system dispatcher comprises:
acquiring actual operation data of each quantum business system dispatcher;
training a quantum business system dispatcher decision model by using actually operated data in a simulation environment;
simulating the operation and scheduling of the quantum business system in a simulation environment by using a quantum business system dispatcher decision model;
comparing the scheduling result of the quantum service system scheduler decision model with the optimal scheduling instruction;
and optimizing the scheduling strategy of the quantum business system dispatcher decision model according to the comparison result.
10. The method of claim 9, further comprising:
comparing the scheduling operation of the quantum business system dispatcher decision model with the optimal scheduling instruction;
and optimizing the scheduling strategy of the quantum business system dispatcher decision model according to the comparison result.
11. The method of claim 1, wherein collecting data for each quantum system unit through a cloud data center comprises:
and data of the superconducting quantum system, the nuclear spin quantum system, the optical cavity quantum system and the ion well quantum system are acquired through the cloud data center.
12. The method of claim 1, wherein the cloud data center is a service that is converted by the actual quantum business system of each quantum system unit into a cloud center capable of processing through a quantum business adapter.
13. The method of claim 1, further comprising:
micro-services are created in the cloud data center to encapsulate different quantum business processing classes in the cloud data center adaptation interface.
14. The method of claim 13, wherein creating a microservice in a cloud data center comprises:
acquiring a micro-service creation request, wherein the micro-service creation request comprises creation information and a target quantum service;
searching a target processing class corresponding to the target quantum business according to the corresponding relation between the processing class and the quantum business;
the creation information is deployed with the target processing class to create instances of the microservice on the target quantum traffic.
15. The method of claim 14, further comprising:
responding to a received micro-service creation request input by a user in a cloud data center, and acquiring creation information of the creation request and a target quantum service;
and calling a corresponding processing class in the cloud data center based on the target quantum business to establish an instance of the micro service.
16. The method of claim 14, wherein creating a microservice in a cloud data center comprises:
acquiring metadata and service type examples corresponding to various quantum computers;
arranging the service type instances to construct a software environment of the service type instances;
and configuring parameters of the corresponding service type instances according to the metadata to obtain the processing classes of the quantum services.
17. The method of claim 16, wherein searching for the target processing class corresponding to the target quantum service according to the correspondence between the processing class and the quantum service comprises:
judging whether a target quantum business is recorded in the corresponding relation between the processing class and the quantum business;
responding to the record of the target quantum business, and taking a processing class corresponding to the target quantum business as a target processing class;
and in response to the target quantum business is not recorded, calling a preset general processing class as a target processing class.
18. An apparatus for multi-quantum service conversion and simulation scheduling, the apparatus comprising:
the building module is configured to collect data of each quantum system unit through a cloud data center and build a quantum service system simulation environment based on the collected data;
a design module configured to design a quantum business system dispatcher decision model;
the training module is configured to acquire data for executing a decision by a quantum service system dispatcher, and train a decision model of the quantum service system dispatcher in a simulation environment based on the acquired data for executing the decision;
an execution module configured to assist a quantum business system dispatcher in executing a decision using the trained quantum business system dispatcher decision model.
19. A computer device, comprising:
at least one processor; and
a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of the method of any one of claims 1 to 17.
20. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 17.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310005100.2A CN115907022A (en) | 2023-01-04 | 2023-01-04 | Multi-quantum service conversion and simulation scheduling method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310005100.2A CN115907022A (en) | 2023-01-04 | 2023-01-04 | Multi-quantum service conversion and simulation scheduling method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115907022A true CN115907022A (en) | 2023-04-04 |
Family
ID=86476379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310005100.2A Pending CN115907022A (en) | 2023-01-04 | 2023-01-04 | Multi-quantum service conversion and simulation scheduling method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115907022A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151137A (en) * | 2023-04-24 | 2023-05-23 | 之江实验室 | Simulation system, method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157422A (en) * | 2021-04-29 | 2021-07-23 | 清华大学 | Cloud data center cluster resource scheduling method and device based on deep reinforcement learning |
| CN113886080A (en) * | 2021-09-29 | 2022-01-04 | 苏州浪潮智能科技有限公司 | High-performance cluster task scheduling method and device, electronic equipment and storage medium |
| CN114139354A (en) * | 2021-11-12 | 2022-03-04 | 山东浪潮科学研究院有限公司 | Power system simulation scheduling method and system based on reinforcement learning |
-
2023
- 2023-01-04 CN CN202310005100.2A patent/CN115907022A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113157422A (en) * | 2021-04-29 | 2021-07-23 | 清华大学 | Cloud data center cluster resource scheduling method and device based on deep reinforcement learning |
| CN113886080A (en) * | 2021-09-29 | 2022-01-04 | 苏州浪潮智能科技有限公司 | High-performance cluster task scheduling method and device, electronic equipment and storage medium |
| CN114139354A (en) * | 2021-11-12 | 2022-03-04 | 山东浪潮科学研究院有限公司 | Power system simulation scheduling method and system based on reinforcement learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116151137A (en) * | 2023-04-24 | 2023-05-23 | 之江实验室 | Simulation system, method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110322010B (en) | Pulse neural network operation system and method for brain-like intelligence and cognitive computation | |
| CN112862281A (en) | Method, device, medium and electronic equipment for constructing scheduling model of comprehensive energy system | |
| CN113031983B (en) | Intelligent software upgrading method and device based on deep reinforcement learning | |
| CN115907022A (en) | Multi-quantum service conversion and simulation scheduling method, device, equipment and medium | |
| CN114422322B (en) | Alarm compression method, device, equipment and storage medium | |
| CN109344969B (en) | Neural network system, training method thereof, and computer-readable medium | |
| CN118365099B (en) | Multi-AGV scheduling method, device, equipment and storage medium | |
| CN114020413A (en) | Distributed reinforcement learning system design method based on Kubernetes container cluster | |
| CN116047934B (en) | Real-time simulation method and system for unmanned aerial vehicle cluster and electronic equipment | |
| CN115934344A (en) | Heterogeneous distributed reinforcement learning calculation method, system and storage medium | |
| Harbin et al. | Model-driven simulation-based analysis for multi-robot systems | |
| CN117076077A (en) | Planning and scheduling optimization method based on big data analysis | |
| CN117669874A (en) | QPSO-based intelligent recognition method and system for power grid planning data distortion | |
| CN110083350B (en) | Micro-service self-adaptive evolution method based on RMAE (remote Markov experience) in cloud computing environment | |
| CN111612152A (en) | Simulation control method and system of quantum computer and related components | |
| Kinneer et al. | Building reusable repertoires for stochastic self-* planners | |
| Nguyen et al. | Review, analysis and design of a comprehensive deep reinforcement learning framework | |
| CN114239406A (en) | Financial process mining method based on reinforcement learning and related device | |
| CN113206712A (en) | Software radio conformance testing method and system | |
| CN113962384A (en) | Automatic integrated architecture search system and method for click rate prediction model | |
| Nielsen | Application of artificial intelligence techniques to simulation | |
| CN113535510B (en) | Self-adaptive sampling model optimization method for data acquisition of large-scale data center | |
| Avé et al. | Policy Compression for Low-Power Intelligent Scaling in Software-Based Network Architectures | |
| CN117389569B (en) | Program interpretation execution method | |
| CN109472363B (en) | Interpretable competitor modeling method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230404 |