CN112486674A - Artificial intelligence service-oriented resource allocation method and device and electronic equipment - Google Patents
Artificial intelligence service-oriented resource allocation method and device and electronic equipment Download PDFInfo
- Publication number
- CN112486674A CN112486674A CN202011295444.4A CN202011295444A CN112486674A CN 112486674 A CN112486674 A CN 112486674A CN 202011295444 A CN202011295444 A CN 202011295444A CN 112486674 A CN112486674 A CN 112486674A
- Authority
- CN
- China
- Prior art keywords
- edge server
- resources
- edge
- computing resources
- resource allocation
- 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
- 238000013468 resource allocation Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 41
- 238000012163 sequencing technique Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computer And Data Communications (AREA)
Abstract
One or more embodiments of the present disclosure provide a resource allocation method, an apparatus, and an electronic device for artificial intelligence service, which determine, according to a network model to be computed, the number N of edge servers that need to participate in training, obtain edge servers from an edge server queue one by one, determine, for each obtained edge server, whether the computing resources and link resources of the edge server are sufficient until the N edge servers with sufficient computing resources and link resources are obtained, and then perform resource allocation according to the computing resources and link resources of each edge server, optimize resources, and effectively save model training time.
Description
Technical Field
One or more embodiments of the present disclosure relate to the technical field of resource allocation, and in particular, to a resource allocation method and apparatus for artificial intelligence service, and an electronic device.
Background
The existing technology for training the distributed artificial intelligence model based on the cloud nodes mainly comprises the following steps: the method comprises the steps that a training network formed by a cloud server and a plurality of edge servers is built, the cloud server divides an artificial intelligence original data set to be trained, each module obtained by division is distributed to each edge server to be trained, a training result is fed back to the cloud server, and therefore the training process of an artificial intelligence model is achieved.
However, the inventor finds that in the model training mode of performing synchronous update based on the cloud server, the computing and bandwidth resources of the edge server are not fully utilized, so that the resource waste is caused, and the model training time is increased. For example, on an edge server with sufficient resources, the training process time is short, and in the process of one training iteration, a lot of time is spent waiting for the edge server participating in the training to complete the iteration process, while an edge server with limited resources spends more time on calculation and data transmission, and becomes a "bottleneck" node in the training process.
Disclosure of Invention
In view of this, one or more embodiments of the present disclosure provide a resource allocation method and apparatus for artificial intelligence service, and an electronic device, which are capable of allocating resources to an edge server in an elastic optical network, optimizing the resources, and saving model training time.
In view of the above, one or more embodiments of the present specification provide a resource allocation method for artificial intelligence service, including:
obtaining a network model to be calculated;
determining the number N of edge servers participating in training based on the network model;
acquiring an edge server from an edge server queue;
judging whether the edge server has enough computing resources and link resources, if the computing resources and/or the link resources of the edge server are insufficient, giving up the edge server, and returning to execute the step of obtaining the edge server; if the computing resources and the link resources of the edge servers are enough, judging whether the number N of the obtained edge servers is equal to N or not, if N is less than N, returning to the step of obtaining the edge servers, and if N is equal to N, performing resource allocation according to the computing resources and the link resources of each edge server.
As an optional implementation, the obtaining an edge server from the edge server queue includes:
acquiring computing resources and link resources of each edge server in an edge server queue;
based on the computing resources and the link resources, sequencing the edge servers to obtain a sequenced edge server queue;
and acquiring an edge server from the sorted edge server queue.
As an optional implementation, the ranking the edge servers based on the computing resources and link resources includes:
and weighting the computing resources and the link resources of each edge server, and sequencing the edge servers according to the weighted value from large to small.
As an optional implementation manner, if N is equal to N, performing resource allocation according to the computing resource and the link resource of each edge server includes:
if N is equal to N, judging whether the computing resources and the link resources of the N edge servers meet the QoS training;
if the computing resources and the link resources of the n edge servers meet the QoS (quality of service) training, performing resource allocation according to the computing resources and the link resources of each edge server; and if the computing resources and the link resources of the n edge servers do not meet the QoS training, stopping resource allocation.
As an optional implementation, the abandoning the edge server and returning to perform the step of acquiring the edge server includes:
discarding the edge server;
judging whether an unused edge server exists in the edge server queue, and if the unused edge server exists in the edge server queue, returning to execute the step of acquiring the edge server; and if the edge server queue does not have an unused edge server, stopping resource allocation.
As an optional implementation manner, if N < N, returning to perform the step of acquiring the edge server, includes:
if N is less than N, judging whether an unused edge server exists in the edge server queue, and if the unused edge server exists in the edge server queue, returning to execute the step of obtaining the edge server; and if the edge server queue does not have an unused edge server, stopping resource allocation.
Corresponding to the artificial intelligence service-oriented resource allocation method, the embodiment of the invention also provides an artificial intelligence service-oriented resource allocation device, which comprises:
the first acquisition unit is used for acquiring a network model to be calculated;
the distribution unit is used for determining the number N of the edge servers participating in training based on the network model;
a second obtaining unit, configured to obtain an edge server from the edge server queue;
the allocation unit is used for judging whether the edge server has enough computing resources and link resources or not, if the computing resources and/or the link resources of the edge server are insufficient, the edge server is abandoned, and the step of obtaining the edge server is executed in a return mode; if the computing resources and the link resources of the edge servers are enough, judging whether the number N of the obtained edge servers is equal to N or not, if N is less than N, returning to the step of obtaining the edge servers, and if N is equal to N, performing resource allocation according to the computing resources and the link resources of each edge server.
As an optional implementation, the second obtaining unit includes:
an obtaining module, configured to obtain a computing resource and a link resource of each edge server in an edge server queue;
and the sequencing module is used for sequencing the edge servers based on the computing resources and the link resources to obtain a sequenced edge server queue.
As an optional implementation, the sorting module is configured to:
and weighting the computing resources and the link resources of each edge server, and sequencing the edge servers according to the weighted value from large to small.
Corresponding to the artificial intelligence service-oriented resource allocation method, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the method when executing the program.
As can be seen from the foregoing, in the resource allocation method, device and electronic device for artificial intelligence service provided in one or more embodiments of the present disclosure, the number N of edge servers that need to participate in training is determined according to a network model to be calculated, the edge servers are obtained from an edge server queue one by one, and whether the computing resources and link resources of the edge servers obtained each time are sufficient is determined until the N edge servers with sufficient computing resources and link resources are obtained, and then resource allocation is performed according to the computing resources and link resources of each edge server, so as to optimize resources and effectively save model training time.
Drawings
In order to more clearly illustrate one or more embodiments or prior art solutions of the present specification, the drawings that are needed in the description of the embodiments or prior art will be briefly described below, and it is obvious that the drawings in the following description are only one or more embodiments of the present specification, and that other drawings may be obtained by those skilled in the art without inventive effort from these drawings.
FIG. 1 is a schematic illustration of a dispensing method according to one or more embodiments of the present disclosure;
FIG. 2 is a schematic view of an electronic device of one or more embodiments of the present disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the present disclosure more apparent, the present disclosure is further described in detail below with reference to specific embodiments.
In order to achieve the above object, embodiments of the present invention provide a resource allocation method, a resource allocation device and an electronic device for artificial intelligence services, where the method and the device are applied to a cloud server or a server cluster, and are not limited specifically. First, a detailed description is given to the resource allocation method for artificial intelligence service according to the embodiment of the present invention.
The embodiment of the invention provides a resource allocation method for artificial intelligence service, which comprises the following steps:
obtaining a network model to be calculated;
determining the number N of edge servers participating in training based on the network model;
acquiring an edge server from an edge server queue;
judging whether the edge server has enough computing resources and link resources, if the computing resources and/or the link resources of the edge server are insufficient, giving up the edge server, and returning to execute the step of obtaining the edge server; if the computing resources and the link resources of the edge servers are enough, judging whether the number N of the obtained edge servers is equal to N or not, if N is less than N, returning to the step of obtaining the edge servers, and if N is equal to N, performing resource allocation according to the computing resources and the link resources of each edge server.
In the embodiment of the invention, the number N of edge servers needing to participate in training is determined according to a network model to be calculated, the edge servers are acquired from an edge server queue one by one, whether the computing resources and link resources of the edge servers are sufficient or not is judged aiming at the edge servers acquired each time until the edge servers with the N computing resources and the link resources are sufficient are acquired, and then the resources are distributed according to the computing resources and the link resources of each edge server, so that the resources are optimized, and the model training time is effectively saved.
FIG. 1 shows that an embodiment of the present invention provides a resource allocation method for artificial intelligence service, including:
s100, obtaining a network model to be calculated;
s200, determining the number N of edge servers participating in training based on the network model;
s300, obtaining an edge server from an edge server queue;
as an alternative embodiment, S300 includes:
acquiring computing resources and link resources of each edge server in an edge server queue;
based on the computing resources and the link resources, sequencing the edge servers to obtain a sequenced edge server queue;
and acquiring an edge server from the sorted edge server queue.
Optionally, the sorting the edge servers based on the computing resources and the link resources includes:
and weighting the computing resources and the link resources of each edge server, and sequencing the edge servers according to the weighted value from large to small.
S400, judging whether the edge server has enough computing resources and link resources;
if the computing resources and/or link resources of the edge server are not enough, executing S500: abandoning the edge server and returning to execute S300;
if the computing resources and link resources of the edge server are sufficient, executing S600: judging whether the number N of the acquired edge servers is equal to N or not;
if N is less than N, returning to execute S300;
if N is equal to N, S700 is executed: and performing resource allocation according to the computing resource and the link resource of each edge server.
Optionally, the resource allocation according to the computing resource and the link resource of each edge server includes:
and distributing training data with corresponding size to each edge server, and performing routing and spectrum resource distribution.
Optionally, three alternative paths from the edge server to the cloud server are calculated according to the K shortest path algorithm, so as to determine link resources of the edge server.
As an optional implementation manner, if N is equal to N, performing resource allocation according to the computing resource and the link resource of each edge server includes:
if N is equal to N, S800 is executed: judging whether the computing resources and the link resources of the n edge servers meet the QoS training;
if the computational resources and link resources of the n edge servers satisfy the QoS requirement, S700 is executed: according to the computing resource and the link resource of each edge server, resource allocation is carried out;
if the computational resources and link resources of the n edge servers do not satisfy the QoS training, S900 is executed: the resource allocation is stopped.
As an optional implementation, the abandoning the edge server and returning to perform S300 includes:
s500, abandoning the edge server;
s1000, judging whether an unused edge server exists in an edge server queue;
if the edge server queue has an unused edge server, returning to execute S300;
if there is no unused edge server in the edge server queue, S900 is executed.
As an optional implementation manner, if N < N, returning to execute S300 includes:
if N is less than N, executing S1000: judging whether an unused edge server exists in an edge server queue;
if the edge server queue has an unused edge server, returning to execute S300;
if there is no unused edge server in the edge server queue, S900 is executed.
The following describes a resource allocation method for artificial intelligence services by taking an interest recommendation algorithm as an example.
Examples
The cloud server obtains an interest recommendation algorithm to be calculated, and sets the number of edge servers participating in training based on the operation scale of the interest recommendation algorithm, for example, the number is set to be 2;
sequencing the edge servers connected with the cloud server according to scores obtained after weighting of computing resources and link resources from large to small;
sequentially selecting computing resources and link resources sufficient for the edge servers A and B to participate in the calculation of the interest recommendation algorithm;
the deployment mode of training data and the routing path of transmission data are determined according to an artificial intelligence model training data segmentation algorithm, a model training service providing algorithm determines that 40% of training data are deployed in an edge server A and the rest of the training data are deployed in an edge server B with sufficient resources, and meanwhile the routing path in the elastic optical network is determined and transmission resources are distributed, so that the waiting time of the edge server caused by synchronous aggregation of the model in a cloud server is effectively reduced.
It is to be appreciated that the method can be performed by any apparatus, device, platform, cluster of devices having computing and processing capabilities.
It should be noted that the method of one or more embodiments of the present disclosure may be performed by a single device, such as a computer or server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the devices may perform only one or more steps of the method of one or more embodiments of the present disclosure, and the devices may interact with each other to complete the method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Corresponding to the artificial intelligence service-oriented resource allocation method, the embodiment of the invention also provides an artificial intelligence service-oriented resource allocation device, which comprises:
the first acquisition unit is used for acquiring a network model to be calculated;
the distribution unit is used for determining the number N of the edge servers participating in training based on the network model;
a second obtaining unit, configured to obtain an edge server from the edge server queue;
the allocation unit is used for judging whether the edge server has enough computing resources and link resources or not, if the computing resources and/or the link resources of the edge server are insufficient, the edge server is abandoned, and the step of obtaining the edge server is executed in a return mode; if the computing resources and the link resources of the edge servers are enough, judging whether the number N of the obtained edge servers is equal to N or not, if N is less than N, returning to the step of obtaining the edge servers, and if N is equal to N, performing resource allocation according to the computing resources and the link resources of each edge server.
In the embodiment of the invention, the number N of edge servers needing to participate in training is determined according to a network model to be calculated, the edge servers are acquired from an edge server queue one by one, whether the computing resources and link resources of the edge servers are sufficient or not is judged aiming at the edge servers acquired each time until the edge servers with the N computing resources and the link resources are sufficient are acquired, and then the resources are distributed according to the computing resources and the link resources of each edge server, so that the resources are optimized, and the model training time is effectively saved.
As an optional implementation, the second obtaining unit includes:
an obtaining module, configured to obtain a computing resource and a link resource of each edge server in an edge server queue;
and the sequencing module is used for sequencing the edge servers based on the computing resources and the link resources to obtain a sequenced edge server queue.
As an optional implementation, the sorting module is configured to:
and weighting the computing resources and the link resources of each edge server, and sequencing the edge servers according to the weighted value from large to small.
It is to be noted that unless otherwise defined, technical or scientific terms used in one or more embodiments of the present specification should have the ordinary meaning as understood by those of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in one or more embodiments of the specification is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the modules may be implemented in the same one or more software and/or hardware implementations in implementing one or more embodiments of the present description.
Corresponding to the artificial intelligence service-oriented resource allocation method, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method described above.
Fig. 2 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
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, is limited to these examples; within the spirit of the present disclosure, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present description as described above, which are not provided in detail for the sake of brevity.
It is intended that the one or more embodiments of the present specification embrace all such alternatives, modifications and variations as fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of one or more embodiments of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (10)
1. A resource allocation method for artificial intelligence service is characterized by comprising the following steps:
obtaining a network model to be calculated;
determining the number N of edge servers participating in training based on the network model;
acquiring an edge server from an edge server queue;
judging whether the edge server has enough computing resources and link resources, if the computing resources and/or the link resources of the edge server are insufficient, giving up the edge server, and returning to execute the step of obtaining the edge server; if the computing resources and the link resources of the edge servers are enough, judging whether the number N of the obtained edge servers is equal to N or not, if N is less than N, returning to the step of obtaining the edge servers, and if N is equal to N, performing resource allocation according to the computing resources and the link resources of each edge server.
2. The method for allocating resources for artificial intelligence services according to claim 1, wherein the obtaining an edge server from an edge server queue comprises:
acquiring computing resources and link resources of each edge server in an edge server queue;
based on the computing resources and the link resources, sequencing the edge servers to obtain a sequenced edge server queue;
and acquiring an edge server from the sorted edge server queue.
3. The method for allocating resources for artificial intelligence services according to claim 2, wherein said ranking the edge servers based on the computing resources and link resources comprises:
and weighting the computing resources and the link resources of each edge server, and sequencing the edge servers according to the weighted value from large to small.
4. The method for allocating resources for artificial intelligence services according to claim 1, wherein if N is equal to N, then performing resource allocation according to the computing resources and link resources of each edge server includes:
if N is equal to N, judging whether the computing resources and the link resources of the N edge servers meet the QoS training;
if the computing resources and the link resources of the n edge servers meet the QoS (quality of service) training, performing resource allocation according to the computing resources and the link resources of each edge server; and if the computing resources and the link resources of the n edge servers do not meet the QoS training, stopping resource allocation.
5. The method for allocating resources for artificial intelligence services according to claim 1, wherein said step of abandoning the edge server and returning to execute the step of acquiring the edge server comprises:
discarding the edge server;
judging whether an unused edge server exists in the edge server queue, and if the unused edge server exists in the edge server queue, returning to execute the step of acquiring the edge server; and if the edge server queue does not have an unused edge server, stopping resource allocation.
6. The method for allocating resources for artificial intelligence services according to claim 1, wherein if N < N, returning to perform the step of acquiring the edge server includes:
if N is less than N, judging whether an unused edge server exists in the edge server queue, and if the unused edge server exists in the edge server queue, returning to execute the step of obtaining the edge server; and if the edge server queue does not have an unused edge server, stopping resource allocation.
7. An artificial intelligence service-oriented resource allocation device, comprising:
the first acquisition unit is used for acquiring a network model to be calculated;
the distribution unit is used for determining the number N of the edge servers participating in training based on the network model;
a second obtaining unit, configured to obtain an edge server from the edge server queue;
the allocation unit is used for judging whether the edge server has enough computing resources and link resources or not, if the computing resources and/or the link resources of the edge server are insufficient, the edge server is abandoned, and the step of obtaining the edge server is executed in a return mode; if the computing resources and the link resources of the edge servers are enough, judging whether the number N of the obtained edge servers is equal to N or not, if N is less than N, returning to the step of obtaining the edge servers, and if N is equal to N, performing resource allocation according to the computing resources and the link resources of each edge server.
8. The artificial intelligence service-oriented resource allocation apparatus according to claim 7, wherein the second obtaining unit includes:
an obtaining module, configured to obtain a computing resource and a link resource of each edge server in an edge server queue;
and the sequencing module is used for sequencing the edge servers based on the computing resources and the link resources to obtain a sequenced edge server queue.
9. The artificial intelligence service-oriented resource allocation apparatus according to claim 8, wherein the sorting module is configured to:
and weighting the computing resources and the link resources of each edge server, and sequencing the edge servers according to the weighted value from large to small.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011295444.4A CN112486674A (en) | 2020-11-18 | 2020-11-18 | Artificial intelligence service-oriented resource allocation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011295444.4A CN112486674A (en) | 2020-11-18 | 2020-11-18 | Artificial intelligence service-oriented resource allocation method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112486674A true CN112486674A (en) | 2021-03-12 |
Family
ID=74931346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011295444.4A Pending CN112486674A (en) | 2020-11-18 | 2020-11-18 | Artificial intelligence service-oriented resource allocation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112486674A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108810170A (en) * | 2018-07-19 | 2018-11-13 | 中国联合网络通信集团有限公司 | resource allocation method and system |
| CN109413676A (en) * | 2018-12-11 | 2019-03-01 | 西北大学 | Combine the edge calculations moving method of lower uplink in a kind of ultra dense heterogeneous network |
| CN110489176A (en) * | 2019-08-27 | 2019-11-22 | 湘潭大学 | A kind of multiple access edge calculations task discharging method based on bin packing |
| CN111641891A (en) * | 2020-04-16 | 2020-09-08 | 北京邮电大学 | Task peer-to-peer unloading method and device in multi-access edge computing system |
-
2020
- 2020-11-18 CN CN202011295444.4A patent/CN112486674A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108810170A (en) * | 2018-07-19 | 2018-11-13 | 中国联合网络通信集团有限公司 | resource allocation method and system |
| CN109413676A (en) * | 2018-12-11 | 2019-03-01 | 西北大学 | Combine the edge calculations moving method of lower uplink in a kind of ultra dense heterogeneous network |
| CN110489176A (en) * | 2019-08-27 | 2019-11-22 | 湘潭大学 | A kind of multiple access edge calculations task discharging method based on bin packing |
| CN111641891A (en) * | 2020-04-16 | 2020-09-08 | 北京邮电大学 | Task peer-to-peer unloading method and device in multi-access edge computing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11121949B2 (en) | Distributed assignment of video analytics tasks in cloud computing environments to reduce bandwidth utilization | |
| CN109032801B (en) | Request scheduling method, system, electronic equipment and storage medium | |
| CN109254842B (en) | Resource management method and device for distributed stream system and readable storage medium | |
| CN112363813A (en) | Resource scheduling method and device, electronic equipment and computer readable medium | |
| CN111694646B (en) | Resource scheduling method, device, electronic equipment and computer readable storage medium | |
| CN112380020A (en) | Computing power resource allocation method, device, equipment and storage medium | |
| CN112784989A (en) | Inference system, inference method, electronic device, and computer storage medium | |
| CN110413510B (en) | Data processing method, device and equipment | |
| CN112667400A (en) | Edge cloud resource scheduling method, device and system managed and controlled by edge autonomous center | |
| CN113553160A (en) | Task scheduling method and system for edge computing node of artificial intelligence Internet of things | |
| CN110851987B (en) | Method, apparatus and storage medium for predicting calculated duration based on acceleration ratio | |
| CN109783236B (en) | Method and apparatus for outputting information | |
| EP3731089B1 (en) | Scheduling method and related apparatus | |
| CN110113269B (en) | Flow control method based on middleware and related device | |
| CN116915869A (en) | Cloud edge cooperation-based time delay sensitive intelligent service quick response method | |
| CN112486674A (en) | Artificial intelligence service-oriented resource allocation method and device and electronic equipment | |
| CN114301907B (en) | Service processing method, system and device in cloud computing network and electronic equipment | |
| CN115525394A (en) | Method and device for adjusting number of containers | |
| CN115797267A (en) | Image quality evaluation method, system, electronic device, and storage medium | |
| CN113590141B (en) | Method, device, medium and program product for distributing cloud mobile phone | |
| CN114626531A (en) | Model reasoning parameter determination method and device, electronic equipment and storage medium | |
| CN111694670B (en) | Resource allocation method, apparatus, device and computer readable medium | |
| CN114091807A (en) | Method, device and system for distributing and scheduling tasks of multiple unmanned aerial vehicles and storage medium | |
| CN111143033B (en) | Operation execution method and device based on scalable operation system | |
| CN113935472A (en) | Model scheduling processing method, device, equipment and storage medium |
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 |
Application publication date: 20210312 |
|
| RJ01 | Rejection of invention patent application after publication |