CN116932185A - Calculation force processing method and device and calculation force node - Google Patents
Calculation force processing method and device and calculation force node Download PDFInfo
- Publication number
- CN116932185A CN116932185A CN202210337151.0A CN202210337151A CN116932185A CN 116932185 A CN116932185 A CN 116932185A CN 202210337151 A CN202210337151 A CN 202210337151A CN 116932185 A CN116932185 A CN 116932185A
- Authority
- CN
- China
- Prior art keywords
- computing
- node
- force
- information
- computing power
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 160
- 238000003672 processing method Methods 0.000 title claims description 17
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000003993 interaction Effects 0.000 claims abstract description 14
- 230000004044 response Effects 0.000 claims description 45
- 238000003860 storage Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000013461 design Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 9
- 238000005304 joining Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 230000000694 effects 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
- 241000282412 Homo Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
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]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- 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]
-
- 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
- G06F9/505—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 considering the load
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Power Sources (AREA)
Abstract
The invention provides a method and a device for processing calculation force and a calculation force node, wherein the method comprises the following steps: the first computing node receives a computing force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address; determining at least one computing node capable of providing computing power to the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes; sending calculation force feedback information to the terminal, wherein the calculation force feedback information comprises: determining an IP address of the at least one computing node; on one hand, the target computing power network is a decentralised architecture, so that the related problems of centralized decision making can be avoided; on the other hand, interaction is performed between all the computing nodes based on the application layer, so that the problem of cross-layer design is avoided.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for computing power processing, and a computing power node.
Background
The core mechanism of the computing power network is to combine the network condition and the computing power condition to carry out the flow dispatching, thereby achieving the purpose of balancing the network load and the computing power load, better utilizing the computing and the network resource and supporting the strategy of 'east-west calculation' and 'double-carbon standard reaching'.
For example, computer Vision (CV) is a typical scenario of a computing network. The method is widely applied to scenes such as smart cities and industrial production, and the social management and industrial level are effectively improved. Real-time video analysis of CVs requires a significant amount of deep neural network computational processing resources.
Current networks are also systems designed towards human cognition, e.g. the frame rate selection of video content takes into account the human visual perception of moving objects, defined as 30 frames/sec, and the collected audio also exploits the masking effect mechanisms of the human cognitive system. For human cognition, such encoding quality can be considered fine quality, but far from adequate for use cases requiring beyond humans, e.g., a robotic monitoring system can detect anomalies from sounds exceeding human audible frequencies. The response speed when a person sees an event is about 100ms, so many applications are designed based on this time delay, but applications outside the person, such as an emergency stop system, require further shortening of the response time.
In the prior art, the centralized architecture of the computing network and the distributed architecture based on the network layer are included.
For a centralized architecture, the decision point is at the upper level node, which has the following drawbacks:
The node on the upper layer can be used for communicating problems and/or centralizing some inherent problems of decision-making (such as centralized storage of calculation network information, single point fault hidden danger exists, centralized processing of calculation service access decision-making, performance bottleneck exists, and more network time delay can be brought by central decision-making according to a near scheduling principle.
For a distributed architecture based on network layer scheduling, the decision point may be closer to the client at the Ingress node (Ingress Router), which has the following drawbacks:
belongs to a cross-layer design, network protocol needs to be enhanced, and the pushing difficulty is high. In the current network architecture, the network layer should not sense too much service information, which is worry to increase the cost and affect the forwarding efficiency.
Disclosure of Invention
The embodiment of the invention aims to provide a computing power processing method, a computing power processing device and a computing power node, so as to solve the centralization problem in a centralized architecture and the cross-layer design problem in a distributed architecture of a computing power network in the prior art.
In order to solve the above-mentioned problems, the present invention provides a computing force processing method, applied to a first computing force node, comprising:
receiving a calculation force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address;
Determining at least one computing node capable of providing computing power to the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
sending calculation force feedback information to the terminal, wherein the calculation force feedback information comprises: and determining the IP address of the at least one computing node.
Before receiving the calculation force request sent by the terminal, the method further comprises the following steps:
and constructing the calculation force record information through information interaction of an application layer with a second calculation force node in the target calculation force network.
The method for constructing the computing power record information through information interaction of an application layer with a second computing power node in a target computing power network comprises the following steps:
sending a first request for requesting to join the target power computing network to the second power computing node in an anycast mode;
receiving calculation force record information stored by the second calculation force node after the second calculation force node verifies the first request;
and constructing the computing power record information stored locally by the first computing power node according to the computing power record information stored by the second computing power node, wherein the computing power record information stored locally by the first computing power node comprises information of at least one computing power node selectively stored.
Wherein the method further comprises:
sending an information inquiry request to at least one computing node corresponding to the selective storage;
receiving an information inquiry response sent by the computing power node, wherein the information inquiry response comprises the following steps: the calculation force node stores calculation force record information;
and selectively storing the information of at least one computing node included in the computing force record information into the computing force record information stored locally in the first computing force node according to the information query response.
Wherein the manner of selectively storing information of at least one computing node comprises:
selectively storing information of the computing force nodes, of which the distance with the first computing force node is smaller than a threshold value, according to the position information of the computing force nodes;
or alternatively, the process may be performed,
and selectively storing information of the computing force nodes of a preset type according to the computing force types of the computing force nodes.
Wherein determining at least one computing node capable of providing computing power to the terminal according to the computing power request and locally stored computing power record information comprises:
judging whether the first computing node can provide service for the terminal according to the computing request;
determining at least one computing node capable of providing computing power to the terminal as the first computing node in the case that the first computing node is capable of providing service to the terminal;
Or in case that the first computing node cannot provide service for the terminal, determining at least one computing node capable of providing computing power for the terminal according to the locally stored computing power record information.
Wherein, in case the first computing power node is unable to provide services for the terminal, determining at least one computing power node capable of providing computing power for the terminal according to the locally stored computing power record information, comprises:
sending the computing force request to one or more computing force nodes in locally stored computing force record information;
and receiving a computational force response sent by at least one computational force node, wherein the computational force response is used for indicating that the computational force node can provide service for the terminal, or the computational force response is used for indicating the IP address of the computational force node capable of providing service for the terminal.
Wherein, the calculation force feedback information further includes:
calculating force information of the force calculation node; and/or the number of the groups of groups,
and calculating the position information of the force node.
Wherein the method further comprises:
and deleting the information of the third computing power node from the locally stored computing power record information under the condition that the third computing power node leaves the target computing power network.
The embodiment of the invention also provides a computing force processing device which is applied to the first computing force node and comprises:
the first receiving module is used for receiving the calculation force request sent by the terminal; the terminal accesses the first computing node according to the anycast IP address;
the first determining module is used for determining at least one computing node capable of providing computing power for the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
the first sending module is configured to send calculation force feedback information to the terminal, where the calculation force feedback information includes: and determining the IP address of the at least one computing node.
The embodiment of the invention also provides a computing force node, which is a first computing force node, and comprises a processor and a transceiver, wherein the transceiver receives and transmits data under the control of the processor, and the processor is used for executing the following operations:
receiving a calculation force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address;
determining at least one computing node capable of providing computing power to the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
Sending calculation force feedback information to the terminal, wherein the calculation force feedback information comprises: and determining the IP address of the at least one computing node.
Wherein the processor is further configured to perform the following operations:
and constructing the calculation force record information through information interaction of an application layer with a second calculation force node in the target calculation force network.
Wherein the processor is further configured to perform the following operations:
sending a first request for requesting to join the target power computing network to the second power computing node in an anycast mode;
receiving calculation force record information stored by the second calculation force node after the second calculation force node verifies the first request;
and constructing the computing power record information stored locally by the first computing power node according to the computing power record information stored by the second computing power node, wherein the computing power record information stored locally by the first computing power node comprises information of at least one computing power node selectively stored.
Wherein the processor is further configured to perform the following operations:
sending an information inquiry request to at least one computing node corresponding to the selective storage;
receiving an information inquiry response sent by the computing power node, wherein the information inquiry response comprises the following steps: the calculation force node stores calculation force record information;
And selectively storing the information of at least one computing node included in the computing force record information into the computing force record information stored locally in the first computing force node according to the information query response.
Wherein the manner of selectively storing information of at least one computing node comprises:
selectively storing information of the computing force nodes, of which the distance with the first computing force node is smaller than a threshold value, according to the position information of the computing force nodes;
or alternatively, the process may be performed,
and selectively storing information of the computing force nodes of a preset type according to the computing force types of the computing force nodes.
Wherein the processor is further configured to perform the following operations:
judging whether the first computing node can provide service for the terminal according to the computing request;
determining at least one computing node capable of providing computing power to the terminal as the first computing node in the case that the first computing node is capable of providing service to the terminal;
or in case that the first computing node cannot provide service for the terminal, determining at least one computing node capable of providing computing power for the terminal according to the locally stored computing power record information.
Wherein the processor is further configured to perform the following operations:
sending the computing force request to one or more computing force nodes in locally stored computing force record information;
and receiving a computational force response sent by at least one computational force node, wherein the computational force response is used for indicating that the computational force node can provide service for the terminal, or the computational force response is used for indicating the IP address of the computational force node capable of providing service for the terminal.
Wherein, the calculation force feedback information further includes:
calculating force information of the force calculation node; and/or the number of the groups of groups,
and calculating the position information of the force node.
Wherein the processor is further configured to perform the following operations:
and deleting the information of the third computing power node from the locally stored computing power record information under the condition that the third computing power node leaves the target computing power network.
The embodiment of the invention also provides a computing power node which comprises a memory, a processor and a program stored in the memory and capable of running on the processor, wherein the computing power processing method is realized when the processor executes the program.
The embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the computing power processing method as described above.
The technical scheme of the invention has at least the following beneficial effects:
in the computing power processing method, the computing power processing device and the computing power nodes, computing power record information stored locally is interactively determined between computing power nodes in a target computing power network through intercommunication of an application layer, and a terminal is helped to find out a proper computing power node according to the computing power record information so as to complete related computing power tasks; on one hand, the target computing power network is a decentralised architecture, so that the related problems of centralized decision making can be avoided; on the other hand, interaction is performed between all the computing nodes based on the application layer, and the problem that the cross-layer design of the distributed computing network based on the network layer is complex is avoided.
Drawings
FIG. 1 is a flow chart showing the steps of a method for computing power processing according to an embodiment of the present invention;
FIG. 2 is a diagram of an example of a target computing power network in a computing power processing method according to an embodiment of the present invention;
FIG. 3 is a diagram showing another example of a target computing power network in a computing power processing method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a computing power processing apparatus according to an embodiment of the present invention;
fig. 5 shows a schematic structural diagram of a computing node according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, an embodiment of the present invention provides a computing power processing method, which is applied to a first computing power node, and includes:
step 101, receiving a calculation force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address;
step 102, determining at least one computing node capable of providing computing power for the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
optionally, the information of the computing node includes: the method comprises the steps of identifying the computing force node, IP address of the computing force node, load of the computing force node, position of the computing force node, distance information of the computing force node and the first computing force node, computing force type supported by the computing force node, total computing force of the computing force node, available computing force of the computing force node, information of computing force service provided by the computing force node at present and the like.
Step 103, sending calculation force feedback information to the terminal, wherein the calculation force feedback information comprises: and determining the IP address of the at least one computing node.
The computing power processing method provided by the embodiment of the invention hopes to provide service for the terminal nearby, and meanwhile, the node providing the service needs to have sufficient computing power so as to more fully realize load balancing LB.
For example, as shown in fig. 2, the terminal accesses a computing node 1 nearby, the computing node 1 stores computing record information (including information of surrounding computing nodes) according to the need or by type, and the computing node 1 performs scheduling according to the computing requirement of the terminal and the computing record information stored by itself. For example, the information of the computing node 2 includes: the distance from the force calculation node 1 is closer, and the load is smaller; the information of the computing node 3 includes: the distance from the force calculation node 1 is relatively short; the information of the computing node 4 includes: the distance from the force calculation node 1 is relatively close, and the service 1 or 2 or 3 is supported; the information of the computing node 5 includes: the distance from the calculation force node 1 is large and the available calculation force or the total calculation force is large.
Optionally, the computing force feedback information further includes:
calculation force information of the calculation force node (such as total calculation force of the calculation force node, available calculation force of the calculation force node, etc.); and/or the number of the groups of groups,
and calculating the position information of the force node.
Optionally, the service currently supported by the first computing node that should acknowledge the feedback can be matched with the service requested by the terminal.
In at least one optional embodiment of the application, before receiving the calculation force request sent by the terminal, the method further comprises:
and constructing the calculation force record information through information interaction of an application layer with a second calculation force node in the target calculation force network.
In the embodiment of the application, the target computing power network can also be called as a computing power alliance, and all computing power nodes joining the computing power alliance can issue an ID or an IP of the same anycast (anycast) to support the access of the terminal.
In at least one embodiment of the present application, the information interaction with a second computing node in a target computing network through an application layer constructs the computing record information, including:
sending a first request for requesting to join the target power computing network to the second power computing node in an anycast mode;
receiving calculation force record information stored by the second calculation force node after the second calculation force node verifies the first request;
and constructing the computing power record information stored locally by the first computing power node according to the computing power record information stored by the second computing power node, wherein the computing power record information stored locally by the first computing power node comprises information of at least one computing power node selectively stored.
As shown in fig. 2, the process of joining the computing node to the target computing network includes:
a new computing node (e.g., computing node 2, computing node 3, or computing node 4) needs to be added, a nearest computing node (e.g., computing node 1) needs to be found according to an anacast, and a coalition adding request is sent, including computing information (including total computing power, available computing power), then longitude and latitude information, or other types of address information, which is not particularly limited herein;
the power computing node 1 receiving the joining request verifies the joining request, and after passing the joining request, the power computing node sends information of nearby power computing nodes collected by the power computing node to the power computing node 2, the power computing node 3 or the power computing node 4, namely power computing record information stored by the power computing node;
the power calculation node 2, the power calculation node 3 or the power calculation node 4 which receives the power calculation record information sorts the power calculation record information, and selectively records the information of the power calculation node, for example, the information of the power calculation node close to the power calculation node is recorded preferentially.
In the embodiment of the present invention, the method further includes:
sending an information inquiry request to at least one computing node corresponding to the selective storage;
receiving an information inquiry response sent by the computing power node, wherein the information inquiry response comprises the following steps: the calculation force node stores calculation force record information;
And selectively storing the information of at least one computing node included in the computing force record information into the computing force record information stored locally in the first computing force node according to the information query response.
For example, as shown in fig. 3, after receiving the information of the power node 2 of the power record information, if the information of the power node 3 is recorded, the power node 2 further sends an information query request to the power node 3, and selectively records part or all of the information of the power node based on the response of the power node 3, and the above steps are circulated until the number of the power nodes in the locally stored power record information reaches a preset value, and then the locally stored power record information is built.
It should be noted that, according to the above operation (such as sending the first request for joining the target computing network and/or sending the information query request), each computing node selectively stores some information of surrounding computing nodes, so as to obtain a distributed computing force record information (alternatively, the computing force record information may be implemented by a computing force record table), so as to support distributed computing force scheduling. The distributed power calculation scheduling specifically comprises the following steps: according to the local optimal principle decision, each service interacts with an algorithm node; the method is high in expandability.
In at least one embodiment of the present invention, the manner in which information for at least one computing node is selectively stored includes:
selectively storing information of the computing force nodes, of which the distance with the first computing force node is smaller than a threshold value, according to the position information of the computing force nodes; the computing power nodes in the computing power alliance do not need to store the information of all other nodes in the computing power alliance; only the information of the part needs to be stored, and the addressing of the computational forces supports recursive finding.
Alternatively, the means for selectively storing information of at least one computing node includes:
according to the calculation force type of the calculation force node, selectively storing information of the calculation force node of a preset type; the computing power nodes in the computing power alliance can store according to the computing power capability information of other nodes and types so as to better perform service matching; for example, the relevant types include far-end extra-high computing power, near-end computing power nodes, and AI reasoning-supporting nodes. The calculation force type of the calculation force node is matched with the calculation force requirement and the calculation force supply better, and the calculation force type does not exclude more type identification.
For another example, according to the ID of the power computing service supported by the power computing node, selectively storing information of the power computing node of a preset type; for example, the related service is a face recognition service, or a vehicle recognition service.
In the embodiment of the invention, each computing node stores the capability information of other computing nodes according to a certain screening mode, such as the information of a plurality of alternative nodes nearby or the information of a plurality of alternative nodes according to the computing type. For example, each node stores information of surrounding 3 or 4 nodes.
Optionally, the computing power nodes are sorted by a certain algorithm, and then stored in computing power record information. The top ranking is recommended with priority, and the ranking may depend on distance, degree of computational idleness, etc., and is not particularly limited herein.
As an alternative embodiment, the method further comprises:
and deleting the information of the third computing power node from the locally stored computing power record information under the condition that the third computing power node leaves the target computing power network. For example, a third power node leaves the network, and other power nodes may find that the third power node does not update its own state for a long time, thereby deleting the information of the third power node from the information of surrounding nodes stored by itself.
In at least one embodiment of the present invention, step 102 comprises:
judging whether the first computing node can provide service for the terminal according to the computing request;
Determining at least one computing node capable of providing computing power to the terminal as the first computing node in the case that the first computing node is capable of providing service to the terminal;
or in case that the first computing node cannot provide service for the terminal, determining at least one computing node capable of providing computing power for the terminal according to the locally stored computing power record information.
Wherein, in case the first computing power node is unable to provide services for the terminal, determining at least one computing power node capable of providing computing power for the terminal according to the locally stored computing power record information, comprises:
sending the computing force request to one or more computing force nodes in locally stored computing force record information;
and receiving a computational force response sent by at least one computational force node, wherein the computational force response is used for indicating that the computational force node can provide service for the terminal, or the computational force response is used for indicating the IP address of the computational force node capable of providing service for the terminal.
The purpose of the computational scheduling process of the terminal is to find a node which is close in distance (meets the time delay of service requirements) and has enough computational power. For example, the power-calculation scheduling procedure of the terminal includes:
Step (1): a new calculation request needs to find a nearest calculation node 1 according to an angust, and initiates a request, wherein the request comprises information of required calculation force and optionally carries position information;
step (2): the computing node 1 which receives the request verifies the computing request, and then judges whether the computing node can provide service or not after the computing node passes the verification, or judges whether a better node is available for providing service according to the load condition and the position condition of the computing node which are known by the computing node;
step (3): if it is determined that another node is desired to provide service, sending one or more requests to surrounding nodes;
step (4): executing a flow similar to the steps (2) - (3) by the computing node which receives the request, and continuously searching for a proper node until the node receives the task, and feeding back to the computing node 1;
step (5): the IP of the node for providing the computing power for the terminal fed back by the computing power node 1 can be the IP of the node or other nodes, and can be one or more than one IP; if the number of the nodes is multiple, optionally, carrying calculation information, position information and the like of each node for evaluating the terminal;
step (6): the terminal accesses the service according to the fed back IP.
In summary, the embodiment of the invention constructs an decentralized distributed decision computing alliance (target computing network), and the joining and leaving of nodes are free; related mechanisms of computational power transaction, incentive, security and the like can be overlapped later. Among the benefits of decentralization are: support computing power sharing across operators, across vendors, across management entities. And propagating the calculation force information in the mode of notification at the application layer, wherein each node records the information of nearby calculation force nodes or the information of a plurality of calculation force nodes of specific types and is used for supporting distributed calculation force addressing; the node need not maintain information for all other nodes, only for computing nodes in the vicinity of the user, as needed.
As shown in fig. 4, an embodiment of the present invention further provides a computing force processing apparatus, applied to a first computing force node, including:
a first receiving module 401, configured to receive a computing force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address;
a first determining module 402, configured to determine at least one computing node capable of providing computing power to the terminal according to the computing power request and locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
a first sending module 403, configured to send calculation force feedback information to the terminal, where the calculation force feedback information includes: and determining the IP address of the at least one computing node.
As an alternative embodiment, the apparatus further comprises:
the construction module is used for constructing the calculation force record information through information interaction of an application layer with a second calculation force node in the target calculation force network.
As an alternative embodiment, the building block comprises:
a first sub-module, configured to send, by means of anycast, a first request to the second computing node requesting to join the target computing network;
the second sub-module is used for receiving calculation force record information stored by the second calculation force node after the first request is verified and transmitted by the second calculation force node;
And the third sub-module is used for constructing the calculation force record information locally stored in the first calculation force node according to the calculation force record information stored in the second calculation force node, wherein the calculation force record information locally stored in the first calculation force node comprises information of at least one calculation force node selectively stored.
As an alternative embodiment, the apparatus further comprises:
the second sending module is used for sending an information query request to at least one computing node which is selectively stored;
the second receiving module is configured to receive an information query response sent by the computing node, where the information query response includes: the calculation force node stores calculation force record information;
and the storage module is used for selectively storing the information of at least one computing power node included in the computing power record information into the computing power record information locally stored in the first computing power node according to the information query response.
As an alternative embodiment, the manner of selectively storing information of at least one computing node includes:
selectively storing information of the computing force nodes, of which the distance with the first computing force node is smaller than a threshold value, according to the position information of the computing force nodes;
Or alternatively, the process may be performed,
and selectively storing information of the computing force nodes of a preset type according to the computing force types of the computing force nodes.
As an alternative embodiment, the determining module includes:
a fourth sub-module, configured to determine, according to the computing power request, whether the first computing power node is capable of providing a service for the terminal;
a fifth sub-module, configured to determine, in a case where the first computing node is capable of providing a service for the terminal, that at least one computing node capable of providing computing power for the terminal is the first computing node;
or a sixth sub-module, configured to determine, according to the locally stored computing power record information, at least one computing power node capable of providing computing power to the terminal, in a case that the first computing power node is not capable of providing service to the terminal.
As an alternative embodiment, the sixth submodule is further configured to:
sending the computing force request to one or more computing force nodes in locally stored computing force record information;
and receiving a computational force response sent by at least one computational force node, wherein the computational force response is used for indicating that the computational force node can provide service for the terminal, or the computational force response is used for indicating the IP address of the computational force node capable of providing service for the terminal.
As an alternative embodiment, the computing force feedback information further includes:
calculating force information of the force calculation node; and/or the number of the groups of groups,
and calculating the position information of the force node.
As an alternative embodiment, the apparatus further comprises:
and the deleting module is used for deleting the information of the third computing power node from the locally stored computing power record information under the condition that the third computing power node leaves the target computing power network.
In the embodiment of the invention, the computing nodes in the target computing network interactively determine the locally stored computing record information through the intercommunication of the application layers, and help the terminal to find the proper computing node according to the computing record information so as to complete the related computing task; on one hand, the target computing power network is a decentralised architecture, so that the related problems of centralized decision making can be avoided; on the other hand, interaction is performed between all the computing nodes based on the application layer, so that the problem of cross-layer design is avoided.
It should be noted that, the computing force processing device provided in the embodiment of the present invention is a device capable of executing the computing force processing method, so all embodiments of the computing force processing method are applicable to the device, and the same or similar beneficial effects can be achieved.
As shown in fig. 5, the embodiment of the present invention further provides a computing node, which is a first computing node, and the first computing node includes a processor 500 and a transceiver 510, where the transceiver 510 receives and transmits data under the control of the processor 500, and the processor 500 is configured to perform the following operations:
receiving a calculation force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address;
determining at least one computing node capable of providing computing power to the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
sending calculation force feedback information to the terminal, wherein the calculation force feedback information comprises: and determining the IP address of the at least one computing node.
As an alternative embodiment, the processor is further configured to:
and constructing the calculation force record information through information interaction of an application layer with a second calculation force node in the target calculation force network.
As an alternative embodiment, the processor is further configured to:
sending a first request for requesting to join the target power computing network to the second power computing node in an anycast mode;
Receiving calculation force record information stored by the second calculation force node after the second calculation force node verifies the first request;
and constructing the computing power record information stored locally by the first computing power node according to the computing power record information stored by the second computing power node, wherein the computing power record information stored locally by the first computing power node comprises information of at least one computing power node selectively stored.
As an alternative embodiment, the processor is further configured to:
sending an information inquiry request to at least one computing node corresponding to the selective storage;
receiving an information inquiry response sent by the computing power node, wherein the information inquiry response comprises the following steps: the calculation force node stores calculation force record information;
and selectively storing the information of at least one computing node included in the computing force record information into the computing force record information stored locally in the first computing force node according to the information query response.
As an alternative embodiment, the manner of selectively storing information of at least one computing node includes:
selectively storing information of the computing force nodes, of which the distance with the first computing force node is smaller than a threshold value, according to the position information of the computing force nodes;
Or alternatively, the process may be performed,
and selectively storing information of the computing force nodes of a preset type according to the computing force types of the computing force nodes.
As an alternative embodiment, the processor is further configured to:
judging whether the first computing node can provide service for the terminal according to the computing request;
determining at least one computing node capable of providing computing power to the terminal as the first computing node in the case that the first computing node is capable of providing service to the terminal;
or in case that the first computing node cannot provide service for the terminal, determining at least one computing node capable of providing computing power for the terminal according to the locally stored computing power record information.
As an alternative embodiment, the processor is further configured to:
sending the computing force request to one or more computing force nodes in locally stored computing force record information;
and receiving a computational force response sent by at least one computational force node, wherein the computational force response is used for indicating that the computational force node can provide service for the terminal, or the computational force response is used for indicating the IP address of the computational force node capable of providing service for the terminal.
As an alternative embodiment, the computing force feedback information further includes:
calculating force information of the force calculation node; and/or the number of the groups of groups,
and calculating the position information of the force node.
As an alternative embodiment, the processor is further configured to:
and deleting the information of the third computing power node from the locally stored computing power record information under the condition that the third computing power node leaves the target computing power network.
In the embodiment of the invention, the computing nodes in the target computing network interactively determine the locally stored computing record information through the intercommunication of the application layers, and help the terminal to find the proper computing node according to the computing record information so as to complete the related computing task; on one hand, the target computing power network is a decentralised architecture, so that the related problems of centralized decision making can be avoided; on the other hand, interaction is performed between all the computing nodes based on the application layer, so that the problem of cross-layer design is avoided.
It should be noted that, the computing node provided in the embodiment of the present invention is a node capable of executing the computing method, so all embodiments of the computing method are applicable to the computing node, and the same or similar beneficial effects can be achieved.
The embodiment of the application also provides a computing node, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes each process in the computing processing method embodiment when executing the program and can achieve the same technical effect, and the repetition is avoided, so that the description is omitted.
The embodiment of the present application further provides a computer readable storage medium, on which a computer program is stored, where the program when executed by a processor implements each process in the embodiment of the computing power processing method described above, and the same technical effects can be achieved, and for avoiding repetition, a detailed description is omitted herein. Wherein the computer readable storage medium is selected from Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, magnetic disk storage and optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block or blocks.
These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the foregoing is directed to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the present invention.
Claims (21)
1. A computing power processing method applied to a first computing power node, comprising:
receiving a calculation force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address;
determining at least one computing node capable of providing computing power to the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
Sending calculation force feedback information to the terminal, wherein the calculation force feedback information comprises: and determining the IP address of the at least one computing node.
2. The method of claim 1, wherein prior to receiving the computing power request sent by the terminal, the method further comprises:
and constructing the calculation force record information through information interaction of an application layer with a second calculation force node in the target calculation force network.
3. The method of claim 2, wherein the constructing the computing power record information through information interaction of an application layer with a second computing power node in a target computing power network comprises:
sending a first request for requesting to join the target power computing network to the second power computing node in an anycast mode;
receiving calculation force record information stored by the second calculation force node after the second calculation force node verifies the first request;
and constructing the computing power record information stored locally by the first computing power node according to the computing power record information stored by the second computing power node, wherein the computing power record information stored locally by the first computing power node comprises information of at least one computing power node selectively stored.
4. A method according to claim 3, characterized in that the method further comprises:
Sending an information inquiry request to at least one computing node corresponding to the selective storage;
receiving an information inquiry response sent by the computing power node, wherein the information inquiry response comprises the following steps: the calculation force node stores calculation force record information;
and selectively storing the information of at least one computing node included in the computing force record information into the computing force record information stored locally in the first computing force node according to the information query response.
5. The method of claim 3 or 4, wherein the manner in which information of at least one computing node is selectively stored comprises:
selectively storing information of the computing force nodes, of which the distance with the first computing force node is smaller than a threshold value, according to the position information of the computing force nodes;
or alternatively, the process may be performed,
and selectively storing information of the computing force nodes of a preset type according to the computing force types of the computing force nodes.
6. The method of claim 1, wherein determining at least one computing node capable of providing computing power to the terminal based on the computing power request and locally stored computing power record information comprises:
judging whether the first computing node can provide service for the terminal according to the computing request;
Determining at least one computing node capable of providing computing power to the terminal as the first computing node in the case that the first computing node is capable of providing service to the terminal;
or in case that the first computing node cannot provide service for the terminal, determining at least one computing node capable of providing computing power for the terminal according to the locally stored computing power record information.
7. The method of claim 6, wherein determining at least one computing node capable of providing computing power to the terminal based on locally stored computing power record information in the event that the first computing power node is not capable of providing services to the terminal comprises:
sending the computing force request to one or more computing force nodes in locally stored computing force record information;
and receiving a computational force response sent by at least one computational force node, wherein the computational force response is used for indicating that the computational force node can provide service for the terminal, or the computational force response is used for indicating the IP address of the computational force node capable of providing service for the terminal.
8. The method of claim 1, wherein the computing force feedback information further comprises:
Calculating force information of the force calculation node; and/or the number of the groups of groups,
and calculating the position information of the force node.
9. The method according to claim 2, wherein the method further comprises:
and deleting the information of the third computing power node from the locally stored computing power record information under the condition that the third computing power node leaves the target computing power network.
10. A computing force processing device applied to a first computing force node, comprising:
the first receiving module is used for receiving the calculation force request sent by the terminal; the terminal accesses the first computing node according to the anycast IP address;
the first determining module is used for determining at least one computing node capable of providing computing power for the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
the first sending module is configured to send calculation force feedback information to the terminal, where the calculation force feedback information includes: and determining the IP address of the at least one computing node.
11. A computing node, the computing node being a first computing node comprising a processor and a transceiver, the transceiver receiving and transmitting data under control of the processor, the processor being configured to:
Receiving a calculation force request sent by a terminal; the terminal accesses the first computing node according to the anycast IP address;
determining at least one computing node capable of providing computing power to the terminal according to the computing power request and the locally stored computing power record information; wherein the calculation force record information includes: information of a plurality of computing nodes;
sending calculation force feedback information to the terminal, wherein the calculation force feedback information comprises: and determining the IP address of the at least one computing node.
12. The computing power node of claim 11, wherein the processor is further configured to:
and constructing the calculation force record information through information interaction of an application layer with a second calculation force node in the target calculation force network.
13. The computing power node of claim 12, wherein the processor is further configured to:
sending a first request for requesting to join the target power computing network to the second power computing node in an anycast mode;
receiving calculation force record information stored by the second calculation force node after the second calculation force node verifies the first request;
and constructing the computing power record information stored locally by the first computing power node according to the computing power record information stored by the second computing power node, wherein the computing power record information stored locally by the first computing power node comprises information of at least one computing power node selectively stored.
14. The computing power node of claim 13, wherein the processor is further configured to:
sending an information inquiry request to at least one computing node corresponding to the selective storage;
receiving an information inquiry response sent by the computing power node, wherein the information inquiry response comprises the following steps: the calculation force node stores calculation force record information;
and selectively storing the information of at least one computing node included in the computing force record information into the computing force record information stored locally in the first computing force node according to the information query response.
15. The computing power node of claim 13 or 14, wherein the means for selectively storing information of at least one computing power node comprises:
selectively storing information of the computing force nodes, of which the distance with the first computing force node is smaller than a threshold value, according to the position information of the computing force nodes;
or alternatively, the process may be performed,
and selectively storing information of the computing force nodes of a preset type according to the computing force types of the computing force nodes.
16. The computing power node of claim 11, wherein the processor is further configured to:
judging whether the first computing node can provide service for the terminal according to the computing request;
Determining at least one computing node capable of providing computing power to the terminal as the first computing node in the case that the first computing node is capable of providing service to the terminal;
or in case that the first computing node cannot provide service for the terminal, determining at least one computing node capable of providing computing power for the terminal according to the locally stored computing power record information.
17. The computing power node of claim 16, wherein the processor is further configured to:
sending the computing force request to one or more computing force nodes in locally stored computing force record information;
and receiving a computational force response sent by at least one computational force node, wherein the computational force response is used for indicating that the computational force node can provide service for the terminal, or the computational force response is used for indicating the IP address of the computational force node capable of providing service for the terminal.
18. The computing force node of claim 11, wherein the computing force feedback information further comprises:
calculating force information of the force calculation node; and/or the number of the groups of groups,
and calculating the position information of the force node.
19. The computing power node of claim 12, wherein the processor is further configured to:
And deleting the information of the third computing power node from the locally stored computing power record information under the condition that the third computing power node leaves the target computing power network.
20. A computing node comprising a memory, a processor, and a program stored on the memory and executable on the processor; the method according to any one of claims 1 to 9, characterized in that the processor implements the method for computing power when executing the program.
21. A computer readable storage medium having stored thereon a computer program, which when executed by a processor performs the steps in the computing power processing method according to any of claims 1-9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210337151.0A CN116932185A (en) | 2022-03-31 | 2022-03-31 | Calculation force processing method and device and calculation force node |
| PCT/CN2023/084951 WO2023185976A1 (en) | 2022-03-31 | 2023-03-30 | Computing power processing method and apparatus, and computing power node |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210337151.0A CN116932185A (en) | 2022-03-31 | 2022-03-31 | Calculation force processing method and device and calculation force node |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116932185A true CN116932185A (en) | 2023-10-24 |
Family
ID=88199364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210337151.0A Pending CN116932185A (en) | 2022-03-31 | 2022-03-31 | Calculation force processing method and device and calculation force node |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116932185A (en) |
| WO (1) | WO2023185976A1 (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113810977A (en) * | 2020-06-11 | 2021-12-17 | 中国移动通信有限公司研究院 | Method, system, node and medium for generating computational power topology |
| CN114095577A (en) * | 2020-07-31 | 2022-02-25 | 中国移动通信有限公司研究院 | Resource request method and device, calculation network element node and calculation application equipment |
| CN112188547B (en) * | 2020-09-09 | 2022-03-15 | 中国联合网络通信集团有限公司 | Service processing method and device |
| CN114048857B (en) * | 2021-10-22 | 2024-04-09 | 天工量信(苏州)科技发展有限公司 | Calculation force distribution method and device and calculation force server |
-
2022
- 2022-03-31 CN CN202210337151.0A patent/CN116932185A/en active Pending
-
2023
- 2023-03-30 WO PCT/CN2023/084951 patent/WO2023185976A1/en unknown
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023185976A1 (en) | 2023-10-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ning et al. | Deep reinforcement learning for vehicular edge computing: An intelligent offloading system | |
| CN102739411B (en) | The service of proof is provided | |
| Al Ridhawi et al. | Comparing fog solutions for energy efficiency in wireless networks: Challenges and opportunities | |
| CN107950038A (en) | Subscribe to and notify to carry efficient method and apparatus with clustering service layer for analyzing | |
| WO2020258967A1 (en) | Industrial application service processing method and system | |
| CN113905044A (en) | Business cascade expansion method of talkback service cluster and execution unit thereof | |
| CN105722089A (en) | Equipment authentication method | |
| Ma et al. | Key technologies of MEC towards 5G-enabled vehicular networks | |
| KR102300124B1 (en) | video surveillance system by use of core VMS and edge VMS in mobile edge computing | |
| CN112330519A (en) | Data processing method and device | |
| Dai et al. | A software-defined-networking-enabled approach for edge-cloud computing in the internet of things | |
| Chen et al. | Vehicle as a service (VaaS): Leverage vehicles to build service networks and capabilities for smart cities | |
| CN106656653B (en) | Registration and keep-alive processing method and processing device | |
| Wang et al. | Service delay and optimization of the energy efficiency of a system in fog-enabled smart cities | |
| CN107950005A (en) | Service element Selection of chiller | |
| CN111422078B (en) | Electric vehicle charging data allocation monitoring method based on block chain | |
| US20140254548A1 (en) | Method and system for forming a common network using shared private wireless networks | |
| CN116932185A (en) | Calculation force processing method and device and calculation force node | |
| CN110233791B (en) | Data deduplication method and device | |
| CN109040075B (en) | Management method, server and system for nodes in wireless mobile sensor network | |
| KR102435830B1 (en) | Method and architecture of Network Infrastructure for Optimal Application Service Processing and Data Sharing among Application domains | |
| CN107181929A (en) | Method and apparatus for video monitoring | |
| US20230300198A1 (en) | Method and device for resource guiding, apparatus and storage medium | |
| Manogaran et al. | Optimizing resource and service allocations for iot-assisted intelligent transportation systems | |
| CN115460617A (en) | Network load prediction method and device based on federal learning, electronic equipment and 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 |