WO2021212982A1 - 路由信息扩散方法、装置和存储介质 - Google Patents
路由信息扩散方法、装置和存储介质 Download PDFInfo
- Publication number
- WO2021212982A1 WO2021212982A1 PCT/CN2021/076406 CN2021076406W WO2021212982A1 WO 2021212982 A1 WO2021212982 A1 WO 2021212982A1 CN 2021076406 W CN2021076406 W CN 2021076406W WO 2021212982 A1 WO2021212982 A1 WO 2021212982A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- diffusion
- routing
- target
- function
- network
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/122—Shortest path evaluation by minimising distances, e.g. by selecting a route with minimum of number of hops
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/20—Hop count for routing purposes, e.g. TTL
Definitions
- This application relates to the field of network communication technology, and more specifically, to a routing information diffusion method, device, and storage medium.
- edge computing there are a huge number of smart terminals and edge network devices on the Internet, which will provide a wide range of computing capabilities, thereby promoting the emergence and development of edge computing.
- computing nodes that can provide computing services in the network need to publish their computing capabilities, such as CPU and storage capabilities, as part of routing information through flooding and other network information diffusion technologies, so that Other nodes in the network that may need computing services learn the existence and addresses of computing nodes, and then request the computing services.
- the purpose of this application is to provide a routing information diffusion method, device and storage medium.
- the information is diffused to the routing nodes within the optimal routing diffusion range, which can solve the problems of slow network convergence and waste of bandwidth resources, and improve routing diffusion Efficiency, reduce network delay.
- this application discloses a routing information diffusion method, including:
- the routing information of the network computing node determines the first target diffusion range of the routing information in the routing network, where the routing network includes the target routing node; send routing information to the routing network according to the first target diffusion range, so that the target routing node Obtain routing information.
- the routing information will no longer be distributed to all possible routing nodes during the diffusion process. Diffusing information, but diffusing information to routing nodes within the optimal range, so as to solve the problem of bandwidth resource waste and slow network convergence, improve the efficiency of routing information diffusion, and reduce network delay.
- determining the first target diffusion range of routing information in the routing network includes: obtaining a first diffusion benefit function; the first diffusion benefit function is used to characterize the mapping relationship between the diffusion range and the diffusion benefit; The first diffusion benefit function determines the diffusion range corresponding to the maximum value of the diffusion benefit as the first target diffusion range.
- the first diffusion benefit function can accurately characterize the relationship between the diffusion range and the diffusion benefit. As the diffusion range of routing information increases, the probability of routing information being received by the target route will gradually increase, but at the same time, the network delay will gradually increase. Therefore, by confirming the diffusion range corresponding to the maximum diffusion benefit in the first diffusion benefit function as the first target diffusion range, the optimal routing information diffusion range can be determined accurately and reasonably, and the diffusion efficiency of routing information can be further improved And effectiveness.
- obtaining the first diffusion benefit function includes: obtaining a first diffusion benefit function, which is used to characterize the probability of a target routing node in different diffusion ranges; obtaining the first diffusion cost function, The first diffusion cost function is used to characterize the cumulative delay of the routing network in different diffusion ranges; the first diffusion benefit function is determined according to the cumulative difference between the first diffusion benefit function and the first diffusion cost function.
- the first diffusion benefit function By decomposing the first diffusion benefit function into two specific functions, the first diffusion benefit function and the first diffusion cost function, the observability of the function change is improved. With the increase of the diffusion range, the first diffusion benefit function and The first diffusion benefit function has an independent change law, which can better characterize the relationship between the diffusion range, the diffusion benefit and the diffusion cost, and further improve the calculation accuracy and effectiveness of the first diffusion benefit function.
- the routing network includes a plurality of routing nodes
- obtaining the first diffusion benefit function includes: obtaining a preset first target probability, and the first target probability is used to characterize the probability that the routing node is the target routing node ; According to the first target probability, determine the first diffusion return function.
- obtaining the first diffusion cost function includes: obtaining a preset first delay parameter, where the first delay parameter includes: a one-way network delay between the first nodes and a first maximum one-way network delay; The first delay parameter determines the first diffusion cost function.
- the embodiment of the present application provides a specific implementation method of the first diffusion benefit function, which can effectively evaluate the routing as the diffusion range increases.
- the changes in the benefits brought about by the diffusion of information can then determine the optimal diffusion range corresponding to the maximum benefit, and further improve the efficiency and effectiveness of the diffusion of routing information.
- obtaining the first diffusion cost function includes: obtaining a preset first delay parameter, where the first delay parameter includes: a first maximum diffusion hop count; according to different diffusion ranges and the first maximum diffusion hop count The ratio of, determines the first diffusion cost function.
- the first maximum number of diffusion hops is a preset value, through the ratio of the diffusion range to the first maximum number of diffusion hops, the realization of the first diffusion cost function is more simple and effective, and will not be affected by the specific network connection conditions.
- the first diffusion cost function has better robustness.
- determining the diffusion range corresponding to the maximum value of the diffusion benefit as the first target diffusion range includes: obtaining one or more preset diffusion ranges; The diffusion range where the difference between the function value of the diffusion gain function and the function value of the first diffusion cost function is less than or equal to the preset threshold is determined as the first target diffusion range.
- the routing information includes survival time information
- sending the routing information to the routing network according to the first target diffusion range includes: setting the survival time information according to the first target diffusion range; and sending the information containing the survival time to the routing network Time information routing information.
- the time to live information is a time to live value (Time to Live, TTL).
- sending routing information to the routing network, so that the target routing node obtains the routing information further includes: updating the first target diffusion range to obtain the second target diffusion range; The second target spreads the range and sends routing information to the routing network.
- the second target diffusion range is obtained by updating the first target diffusion range, and the second target diffusion range is sent to the routing network according to the second target diffusion range. Routing information, thereby further improving the real-time performance of routing information diffusion control, and further improving the effect of routing information diffusion.
- updating the first target diffusion range to obtain the second target diffusion range includes: updating the first diffusion benefit function according to the response probability of the target routing node to the routing information to obtain the second diffusion benefit Function; Determine the second diffusion benefit function according to the cumulative difference between the second diffusion benefit function and the first diffusion cost function; According to the second diffusion benefit function, determine the diffusion range corresponding to the maximum value of the diffusion benefit as the second target diffusion Scope.
- updating the first diffusion benefit function according to the response probability of the target routing node to the routing information to obtain the second diffusion benefit function includes: obtaining the number of target routing nodes that respond to the routing information within a preset time Number; the ratio of the number of target routing nodes to the first target diffusion range is determined as the second target probability; the second diffusion benefit function is determined according to the second target probability.
- updating the first target diffusion range to obtain the second target diffusion range includes: updating the first diffusion cost function according to the changes of routing nodes in the routing network to obtain the second diffusion cost function ; According to the cumulative difference between the first diffusion benefit function and the second diffusion cost function, determine the second diffusion benefit function; according to the second diffusion benefit function, determine the diffusion range corresponding to the maximum value of the diffusion benefit as the second target diffusion range .
- updating the first diffusion cost function to obtain the second diffusion cost function according to the changes of routing nodes in the routing network includes: obtaining the topology structure of the routing node in the current routing network; according to the topology structure, The first delay parameter is updated to obtain the second delay parameter; according to the second delay parameter, the second diffusion cost function is determined.
- this application discloses a routing information diffusion device, including:
- the obtaining module is used to obtain the routing information of the network computing node; the determining module is used to determine the first target diffusion range of the routing information in the routing network, where the routing network includes the target routing node; and the sending module is used to Target diffusion range, sending routing information to the routing network, so that the target routing node can obtain routing information.
- the routing information will no longer be diffused to all possible routing nodes during the diffusion process Information, but to diffuse information to routing nodes within the optimal range, so as to solve the problem of bandwidth resource waste and slow network convergence, improve the efficiency of routing information diffusion, and reduce network delay.
- the determining module is specifically used to: obtain the first diffusion benefit function; the first diffusion benefit function is used to characterize the mapping relationship between the diffusion range and the diffusion benefit; according to the first diffusion benefit function, The diffusion range corresponding to the maximum diffusion benefit is determined as the first target diffusion range.
- the first diffusion benefit function can accurately characterize the relationship between the diffusion range and the diffusion benefit. As the diffusion range of routing information increases, the probability that the routing information is received by the target route will gradually increase, but at the same time, the network delay will gradually increase. Therefore, by confirming the diffusion range corresponding to the maximum diffusion benefit in the first diffusion benefit function as the first target diffusion range, the optimal routing information diffusion range can be determined accurately and reasonably, and the diffusion efficiency of routing information can be further improved And effectiveness.
- the determining module includes: a diffusion revenue sub-module, which is used to obtain a first diffusion revenue function, and the first diffusion revenue function is used to characterize the probability of a target routing node in different diffusion ranges; and a diffusion cost sub-module , Used to obtain the first diffusion cost function, the first diffusion cost function is used to characterize the cumulative delay of the routing network in different diffusion ranges; the calculation sub-module is used to calculate the cumulative difference between the first diffusion benefit function and the first diffusion cost function , Determine the first diffusion benefit function.
- the determining sub-module is used to determine the first target diffusion range according to the diffusion range corresponding to the maximum value of the diffusion benefit.
- the first diffusion benefit function By decomposing the first diffusion benefit function into two specific functions, the first diffusion benefit function and the first diffusion cost function, the observability of the function change is improved. With the increase of the diffusion range, the first diffusion benefit function and The first diffusion benefit function has an independent change law, which can better characterize the relationship between the diffusion range, the diffusion benefit and the diffusion cost, and further improve the calculation accuracy and effectiveness of the first diffusion benefit function.
- the routing network includes a plurality of routing nodes, and the diffusion benefit sub-module is specifically used to: obtain a preset first target probability, and the first target probability is used to characterize the probability that the routing node is the target routing node ; According to the first target probability, determine the first diffusion return function.
- the diffusion cost submodule is specifically used to: obtain a preset first delay parameter, the first delay parameter including: a one-way network delay between the first nodes and a first maximum one-way network delay; The first delay parameter determines the first diffusion cost function.
- the embodiment of the present application provides a specific implementation method of the first diffusion benefit function, which can effectively evaluate the routing as the diffusion range increases.
- the changes in the benefits brought about by the diffusion of information can then determine the optimal diffusion range corresponding to the maximum benefit, and further improve the efficiency and effectiveness of the diffusion of routing information.
- the diffusion cost sub-module is specifically used to: obtain a preset first delay parameter, the first delay parameter includes: a first maximum diffusion hop count; according to different diffusion ranges and the first maximum diffusion hop count The ratio of, determines the first diffusion cost function.
- the first maximum number of diffusion hops is a preset value, through the ratio of the diffusion range to the first maximum number of diffusion hops, the realization of the first diffusion cost function is more simple and effective, and will not be affected by the specific network connection conditions.
- the first diffusion cost function has better robustness, and further improves the diffusion efficiency and effectiveness of routing information.
- the determining sub-module is specifically used to: obtain one or more preset diffusion ranges; make the difference between the function value of the first diffusion gain function and the function value of the first diffusion cost function less than or The diffusion range equal to the preset threshold is determined as the first target diffusion range.
- the routing information includes time-to-live information
- the sending module is specifically configured to: set the time-to-live information according to the first target diffusion range; and send routing information containing the time-to-live information to the routing network.
- the device further includes: an update module configured to update the first target diffusion range to obtain the second target diffusion range; the sending module is further configured to route to the route according to the second target diffusion range The network sends routing information.
- the second target diffusion range is obtained by updating the first target diffusion range, and the second target diffusion range is sent to the routing network according to the second target diffusion range. Routing information, thereby improving the real-time performance of routing information diffusion control, and further improving the effect of routing information diffusion.
- the update module is specifically used to: update the first diffusion income function according to the response probability of the target routing node to the routing information to obtain the second diffusion income function; according to the second diffusion income function and the first diffusion income function The cumulative difference of the diffusion cost function determines the second diffusion benefit function; according to the second diffusion benefit function, the diffusion range corresponding to the maximum value of the diffusion benefit is determined as the second target diffusion range.
- the update module updates the first diffusion revenue function according to the response probability of the target routing node to the routing information, and when obtaining the second diffusion revenue function, it is specifically used to: obtain the response route within the preset time
- the number of target routing nodes of the information; the ratio of the number of target routing nodes to the first target diffusion range is determined as the second target probability; the second diffusion benefit function is determined according to the second target probability.
- the update module is specifically used to: update the first diffusion cost function according to the changes of routing nodes in the routing network to obtain the second diffusion cost function; according to the first diffusion benefit function and the second diffusion cost function The cumulative difference of the cost function determines the second diffusion benefit function; according to the second diffusion benefit function, the diffusion range corresponding to the maximum value of the diffusion benefit is determined as the second target diffusion range.
- the update module updates the first diffusion cost function according to the changes of the routing nodes in the routing network, and obtains the second diffusion cost function, is specifically used to: obtain the topology of the routing nodes in the current routing network Structure; According to the topology, the first delay parameter is updated to obtain the second delay parameter; according to the second delay parameter, the second diffusion cost function is determined.
- an embodiment of the present application provides a network device, and the network device includes: a transmitter, a receiver, a memory, and a processor;
- the memory is used to store computer instructions; the processor is used to run the computer instructions stored in the memory to execute the method provided by any one of the implementations of the first aspect above.
- the routing information will no longer be diffused to all possible routing nodes during the diffusion process Information, but to diffuse information to routing nodes within the optimal range, so as to solve the problem of bandwidth resource waste and slow network convergence, improve the efficiency of routing information diffusion, and reduce network delay.
- an embodiment of the present application provides a network device, including: a processor, a memory, and a transceiver;
- the processor is used to control the transceiver to send and receive signals; the memory is used to store a computer program; the processor is also used to call and run the computer program stored in the memory, so that the network device executes the method provided by any implementation manner of the first aspect above.
- an embodiment of the present application provides a network device, including a processor, which is configured to execute a computer program to execute the method provided in any implementation manner of the first aspect above; the network device also includes a communication interface; the processor and Communication interface connection.
- an embodiment of the present application provides a computer-readable storage medium, including computer code, which, when run on a computer, causes the computer to execute the method provided in any implementation manner of the first aspect above.
- an embodiment of the present application provides a computer program product, including program code.
- the program code executes the method provided by any one of the implementations of the first aspect above.
- this application also provides a chip including a processor.
- the processor is used to call and run a computer program stored in the memory to execute the corresponding operation and/or process performed by the network device in the routing information diffusion method of the embodiment of the present application.
- the chip further includes a memory, the memory and the processor are connected to the memory through a circuit or a wire, and the processor is used to read and execute the computer program in the memory.
- the chip further includes a communication interface, and the processor is connected to the communication interface.
- the communication interface is used to receive data and/or information that needs to be processed, and the processor obtains the data and/or information from the communication interface, and processes the data and/or information.
- the communication interface can be an input and output interface.
- this application determines the first target diffusion range of the routing information in the routing network by obtaining the routing information of the network computing node, where the routing network includes the target routing node, and sends to the routing network according to the first target diffusion range Routing information enables the target routing node to obtain routing information. Since the optimal routing diffusion range for routing information diffusion is determined, that is, the first target diffusion range, the routing information is no longer diffused to all possible routing nodes during the diffusion process, but to the routing nodes within the optimal range. Diffusion information, so as to solve the problem of bandwidth resource waste and slow network convergence, improve the efficiency of routing information diffusion, and reduce network delay.
- FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the application
- FIG. 2 is a schematic diagram of routing information diffusion provided by an embodiment of this application.
- FIG. 3 is a flowchart of a routing information diffusion method provided by an embodiment of this application.
- FIG. 4 is a schematic diagram of sending routing information to a routing network according to a first target diffusion range according to an embodiment of the application
- FIG. 5 is a flowchart of another routing information diffusion method provided by an embodiment of this application.
- FIG. 6 is a flowchart of an implementation manner of step S202 in the embodiment shown in FIG. 5;
- FIG. 7 is a schematic diagram of a routing network structure provided by an embodiment of the application.
- FIG. 8 is a schematic diagram of another routing network structure provided by an embodiment of this application.
- FIG. 9 is a flowchart of an implementation manner of step S203 in the embodiment shown in FIG. 5;
- FIG. 10 is a flowchart of another implementation manner of step S203 in the embodiment shown in FIG. 5;
- FIG. 11 is a schematic diagram of a curve of a difference function between diffusion benefits and diffusion costs according to an embodiment of the application.
- FIG. 12 is a flowchart of an implementation manner of step S205 in the embodiment shown in FIG. 5;
- FIG. 13 is a schematic diagram of a change curve of a first diffusion benefit function and a first diffusion cost function according to an embodiment of the application;
- FIG. 15 is a flowchart of another implementation manner of step S307 in the embodiment shown in FIG. 14;
- FIG. 16 is a schematic block diagram of a routing information diffusion device provided by an embodiment of this application.
- FIG. 17 is a schematic block diagram of another routing information diffusion device provided by an embodiment of this application.
- FIG. 18 is a schematic block diagram of the structure of a network device according to an embodiment of this application.
- FIG. 19 is a schematic block diagram of the structure of another network device provided by an embodiment of this application.
- wireless communication systems can be applied to wireless communication systems.
- the wireless communication systems mentioned in the embodiments of this application include, but are not limited to: wireless local area network (WLAN) systems, general packet radio services (general packet radio service, GPRS, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), universal mobile telecommunication system (UMTS), global interconnection microwave access Into (worldwide interoperability for microwave access, WiMAX) communication system, Narrow Band-Internet of Things (NB-IoT), Global System for Mobile Communications (GSM), enhanced data rate GSM evolution System (Enhanced Data rate for GSM Evolution, EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA2000), Time Division Synchronous Code Division Multiple Access (Time Division-Synchronization Code Division Multiple Access, TD-SCDMA), Long Term Evolution (LTE) and the next generation 5G mobile communication system NR.
- WLAN wireless local area network
- GPRS general packet radio services
- FDD frequency division duplex
- Edge computing refers to the use of an open platform that integrates network, computing, storage, and application core capabilities on the side close to the source of things or data, and provides nearest-end services nearby. Its applications are initiated on the edge side to generate faster network service responses and meet the industry's basic needs in real-time business, application intelligence, security and privacy protection. Edge computing is between physical entities and industrial connections, or at the top of physical entities. And cloud computing, you can still access the historical data of edge computing. Among them, devices that provide edge computing capabilities are network computing nodes, and edge computing devices, smart terminals, or other network devices with computing capabilities in the network can all serve as network computing nodes.
- Terminal equipment also known as terminal, user equipment, is a device that provides users with voice and/or data connectivity, for example, handheld devices with wireless connection functions, vehicle-mounted devices, etc.; terminal devices can also be detection devices Data devices, such as sensors, etc.; terminal devices can also be smart devices, such as smart home devices and wearable devices deployed indoors.
- Common terminal devices include, for example, air quality monitoring sensors, temperature sensors, smoke sensors, mobile phones, tablet computers, notebook computers, handheld computers, mobile internet devices (MID), and wearable devices.
- wearable devices include, for example, : Smart watches, smart bracelets, pedometers, etc.
- the terminal device is the terminal device of wireless communication or the terminal device of limited communication that is possible now and in the future.
- Network equipment also known as radio access network (RAN) equipment, is a device that connects terminal equipment to a wireless network. It includes equipment in various communication standards.
- network equipment includes but not Limited to: transmission point (transmission reception point, TRP), base station (eg, gNB), radio network controller (RNC), node B (NodeB, NB), base station controller (BSC) , BTS (base transmitter station), HeNB (home evolved NodeB), or HNB (home Node B), baseband unit (baseband uit, BBU), etc.
- Multiple means two or more than two, and other quantifiers are similar.
- And/or describes the association relationship of the associated objects, indicating that there can be three types of relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone.
- the character “/” generally indicates that the associated objects before and after are in an "or” relationship.
- Correspondence can refer to an association or binding relationship, and the correspondence between A and B means that there is an association or binding relationship between A and B.
- FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of this application.
- the schematic diagram is an application scenario of smart city video monitoring.
- the network computing node is an edge computing device.
- the network device is connected to one or more video capture terminals 12 and receives the video image data transmitted by the video capture terminal 12.
- the edge computing device is, for example, an edge computing server, which is in communication connection with the network device N, and is accessed via the network device N To the routing network, and provide computing power to process video image data.
- the cloud server is in communication connection with the routing network, and can obtain the video image data or the processing result of the video processing image data.
- network computing nodes At present, there are a huge number of smart terminals and edge computing devices on the Internet. As network computing nodes, they will provide a wide range of computing capabilities, thus promoting the emergence and development of edge computing. In the context of edge computing, network computing nodes that can provide computing services in the network need to use their own computing capabilities, such as CPU and storage capabilities, as part of routing information, and publish them through network information diffusion technologies such as flooding, so that the network Other nodes that may need computing services learn the existence and addresses of computing nodes, and then request the computing services.
- network information diffusion technologies such as flooding
- Figure 2 is a schematic diagram of routing information diffusion provided by an embodiment of this application.
- Figure 2 in related technologies, when routing information is diffused through flooding in a routing network, as the diffusion range increases, network calculations will be improved. The probability that the routing information of the node is received by the routing node that needs to use the computing resource, but at the same time, it will also increase the number of routing nodes that communicate with each other, and the scale of the routing network will gradually increase, which will cause a waste of bandwidth resources. And the problem of slow network convergence and high network delay.
- FIG. 3 is a schematic flowchart of a routing information diffusion method provided by an embodiment of the application. As shown in FIG. 3, the method includes:
- the execution subject of the embodiments of the present application may be an edge computing device, such as a server; or a smart terminal device, such as a smart phone, a personal computer, etc.; or a network device, such as a router; or other devices that can execute the embodiments of the present application Or equipment.
- an edge computing device such as a server
- a smart terminal device such as a smart phone, a personal computer, etc.
- a network device such as a router
- the routing information may be a routing information message to be sent by the network computing node to the routing network, and the routing information message contains the computing capabilities of the network computing node, such as CPU computing capabilities, storage space size, link bandwidth, and so on.
- the routing node in the routing network can request the computing power of the network computing node as needed through routing information.
- the target routing node refers to a routing node that needs to request the computing power of the network computing node.
- a video capture device that needs to request the computing power of the network computing node to process video images is connected to the network, and the video capture device corresponds to The routing node is the target routing node.
- the target routing node is within the coverage of the first target diffusion range, that is, routing information is diffused through the first target diffusion range, so that the target routing node can receive the routing information, so as to realize the request and calculation ability corresponding to the routing information. use.
- the method for determining the first target diffusion range includes obtaining a first diffusion benefit function; the first diffusion benefit function is used to characterize the mapping relationship between the diffusion range and the diffusion benefit. According to the first diffusion benefit function, the diffusion range corresponding to the maximum value of the diffusion benefit is determined as the first target diffusion range.
- the first diffusion benefit function represents the mapping relationship between the diffusion range and the diffusion benefit.
- the diffusion benefit is the comprehensive benefit obtained with the increase in the scope of the diffusion.
- the diffusion benefits in the first diffusion benefit function have different specific expressions in different application scenarios. Exemplarily, in some delay-sensitive application scenarios, such as online games, autonomous driving, etc., as the diffusion range increases, the diffusion benefits will rapidly decrease, while in some non-delay-sensitive application scenarios, such as Non-real-time data processing, model training, etc., as the diffusion range increases, the diffusion benefits will slowly decrease.
- the corresponding first diffusion benefit function can be determined according to specific usage requirements.
- the first diffusion benefit function func_A is used to determine the first target diffusion range; when used in smart city video monitoring
- the specific form of the first diffusion benefit function is not limited here.
- the diffusion range corresponding to the maximum value of the diffusion benefit in the first diffusion benefit function is confirmed as the first target diffusion range.
- the first diffusion benefit function is a quadratic function, there is a global maximum in the variable interval of the diffusion range, and the diffusion range corresponding to the global maximum is determined as the first target diffusion range.
- the first diffusion benefit function can also be a higher-order function with multiple global maxima in the variable interval of the diffusion range. In this case, one of the local maxima can be selected according to specific requirements.
- the diffusion range is determined as the first target diffusion range.
- S103 Send routing information to the routing network according to the first target diffusion range, so that the target routing node can obtain the routing information.
- FIG. 4 is a schematic diagram of sending routing information to the routing network according to the first target diffusion range according to an embodiment of the application.
- the routing information is sent to the routing
- the network sends routing information, and all routing nodes within the first target diffusion range can receive the routing information of the network computing node.
- sending routing information to the routing network includes: the first target diffusion range is the number of routing nodes diffused by the routing information, and the number of routing nodes diffused by the routing information is set to be sent
- the TTL of the header of the routing information message is used to implement the diffusion of the routing information of the network computing node within the first target diffusion range through TTL.
- the method of diffusing routing information through TTL is an existing technical means in the art, and will not be repeated here.
- the first target diffusion range of the routing information in the routing network is determined by obtaining the routing information of the network computing node, where the routing network includes the target routing node, and the routing information is sent to the routing network according to the first target diffusion range, Make the target routing node obtain routing information. Since the optimal routing diffusion range for routing information diffusion is determined, that is, the first target diffusion range, the routing information is no longer diffused to all possible routing nodes during the diffusion process, but to the routing nodes within the optimal range. Diffusion information, so as to solve the problem of bandwidth resource waste and slow network convergence, improve the efficiency of routing information diffusion, and reduce network delay.
- FIG. 5 is a schematic flowchart of another routing information diffusion method provided by an embodiment of this application. As shown in FIG. 5, the routing information diffusion method provided in this embodiment is based on the routing information diffusion method provided in the embodiment shown in FIG. 3 Above, step S102 is further refined, and the method includes:
- the first diffusion benefit function is a function that characterizes the relationship between different diffusion ranges and the probability that the target routing node exists in the diffusion range.
- the diffusion range gradually increases, the greater the probability that the routing information of the network computing node will be accepted by other routing nodes, that is, the greater the diffusion benefit.
- the first diffusion income function can be determined.
- the routing network includes multiple routing nodes, and S202 includes two specific implementation steps of S2021 and S2022:
- S2021 Acquire a preset first target probability, where the first target probability is used to characterize the probability that the routing node is the target routing node.
- the first target probability is used to characterize the probability that the routing node is the target routing node.
- the probability that the routing node is the target routing node can be determined by calculating the historical data of each routing information access terminal device, or it can be It is preset according to the number of routing nodes in the routing network in a specific application scenario, and the specific method for obtaining the first target probability is not limited here.
- the first target probability can be a value, that is, 0.2.
- the probability that routing node a accesses equipment that needs the computing power of the network computing node is 50%, and routing node b access needs to use the computing power of the network computing node
- the probability of other routing nodes is 30%, and the probability of other routing nodes accessing devices that need to use the computing power of the network computing node is 20%.
- the first target probability can be an array of length 10, in which routing node a corresponds to The value is 0.5, the value corresponding to routing node b in the array is 0.3, and the other 8 values in the array are 0.2.
- the first diffusion benefit function is used to characterize the probability that at least one routing node is the target routing node within the diffusion range.
- the diffusion range may be implemented by the number of diffusion nodes. After determining the first target probability, that is, the probability that the routing node is the target routing node, correspondingly, the probability that the routing node is not the target routing node can be determined, and then it can be determined that there is at least one routing node after the routing information passes through N diffusion nodes. The probability of the destination routing node.
- the first diffusion return function is as shown in formula (1):
- gain(n) is the diffusion gain when the diffusion range is n
- p is the first target probability
- n is the diffusion range.
- the first diffusion return function is as shown in formula (2):
- gain(n) is the diffusion gain when the diffusion range is n
- pi is the i-th value in the first target probability p
- n is the diffusion range.
- the overall probability of the node for example:
- the first diffusion gain function is 0.25.
- the first diffusion gain function is 0.625.
- the first diffusion gain function is 0.813.
- a specific implementation method of the first diffusion return function is provided, which can effectively evaluate the income change brought by the diffusion of routing information as the diffusion range increases, that is, at least within the diffusion range
- the probability that a routing node is the target routing node realizes an accurate assessment of the routing information diffusion revenue, and by pre-setting the first target probability in numerical form, for different diffusion ranges, corresponding to different first target probability values, further improving routing
- the accuracy of information diffusion benefit evaluation improves the effect of routing information diffusion control.
- the first diffusion cost function is a function that characterizes the relationship between different diffusion ranges and the overall diffusion cost of the routing network.
- the diffusion range gradually increases, as the number of routing nodes through which routing information increases, the overall diffusion cost of the routing network will increase accordingly. For example, the network transmission delay increases and the network convergence time increases, that is, the greater the diffusion cost. According to the relationship between the diffusion range and the diffusion cost, the first diffusion cost function can be determined.
- S203 includes two specific implementation steps of S2031 and S2032:
- the first delay parameter includes: a one-way network delay between the first nodes and a first maximum one-way network delay.
- the one-way network delay between the first nodes refers to the delay amount when routing information is transmitted between different routing nodes, and the delay amount is determined by the specific routing node performance and the network state between the routing nodes; the first largest order The delay to the network refers to the delay required to traverse all the routing nodes in the routing network after routing information is sent from the initial network computing node, that is, the maximum amount of delay.
- the first largest one-way network delay is related to the scale and structure of the specific routing network.
- the one-way network delay between routing node a and routing node b is 30 delay units, and routing node b is between other routing nodes and other routing nodes.
- the one-way network delay between the time is 10 delay units, then the first one-way network delay can be an array of length 10, the value corresponding to routing node a in the array is 30, and the other 9 values in the array are 10.
- the normalized delay amount between each routing node on the routing information transmission path can be determined, and further, the The product of the normalized delay and the diffusion range, the total delay of the routing network within the diffusion range, that is, the overall diffusion cost of the routing network.
- the first diffusion cost function is as shown in equation (3):
- cost(n) is the diffusion cost when the diffusion range is n
- ci is the one-way network delay between the first nodes corresponding to the i-th routing node
- dmax is the first maximum one-way network delay
- n is the diffusion range.
- S203 includes two specific implementation steps of S2033 and S2034:
- the first maximum number of diffusion hops is the number of routing nodes corresponding to the maximum diffusion range in the routing network.
- the maximum diffusion range of the routing network is 4 routing nodes, the first maximum number of diffusion hops is 4.
- the one-way network delays between the routing nodes are the same, for example, the one-way network delay is determined to be the average one-way network delay. Then the first diffusion cost function can be determined according to the ratio of the diffusion range to the first maximum diffusion hops.
- the first diffusion cost function is as shown in equation (4):
- cost(n) is the diffusion cost when the diffusion range is n
- tmax is the first maximum diffusion hop number
- n is the diffusion range.
- S204 Determine the first diffusion benefit function according to the cumulative difference between the first diffusion benefit function and the first diffusion cost function.
- the function values of the first diffusion income function and the first diffusion cost function also change accordingly, and the first diffusion income function and the first diffusion income function change accordingly.
- the accumulation of the difference of a diffusion cost function can reflect the benefit change of the routing network, that is, the first diffusion benefit function.
- the first diffusion benefit function is shown in formula (5):
- utility(n) is the diffusion benefit when the diffusion range is n; gain(n) is the diffusion benefit when the diffusion range is n; cost(n) is the diffusion cost when the diffusion range is n, w1 is the first weight coefficient ; W2 is the second weight coefficient; w1 and w2 are used to adjust the weights of the first diffusion benefit function and the first diffusion cost function.
- FIG. 11 is a schematic diagram of a curve of the difference function between diffusion benefits and diffusion costs provided by an embodiment of the application.
- the horizontal axis in the figure is the diffusion range
- the vertical axis is the diffusion income and the diffusion cost.
- the diffusion range As the diffusion range increases, the cumulative amount of the difference between the diffusion benefit and the diffusion cost gradually decreases. Furthermore, the first diffusion benefit function The value of the function gradually becomes smaller. Therefore, the independent variable corresponding to the maximum function value of the first diffusion benefit function, that is, the diffusion range nop, can be determined as the first target diffusion range.
- S205 includes two specific implementation steps of S2051 and S2052:
- n_list [1,2,3,4]
- the preset threshold may be a preset error threshold
- the diffusion range values in the diffusion range sequence n_list are sequentially input into the judgment function shown in formula (6):
- ⁇ is the preset error threshold, which is determined by specific routing network parameters.
- the corresponding diffusion range value is determined as the first target diffusion range.
- Figure 13 is a schematic diagram of the change curve of the first diffusion income function and the first diffusion cost function.
- ⁇ is 0.1, which is an error range of 10%.
- the number of nops meeting the condition is greater than one, the largest of all nops is selected as the first target diffusion range.
- the embodiment of the present application provides a specific implementation method of the first diffusion benefit function, which can effectively evaluate the routing as the diffusion range increases. The change of benefits brought about by the diffusion of information, and then realize the determination of the optimal diffusion range corresponding to the maximum benefit.
- the first diffusion benefit function can be applied to delay-sensitive or non-delay-sensitive application scenarios.
- pass Relatively increasing the weight coefficient of the first diffusion cost function can determine a smaller optimal diffusion range to meet the low latency requirements in this application scenario; in non-delay sensitive application scenarios, the first diffusion benefit can be relatively increased
- the weight coefficient of the function determines a larger optimal diffusion range, so that the computing power of the network computing node can be used by more devices, improves the economics of the network system, and at the same time improves the calculation accuracy and effectiveness of the first diffusion benefit function sex.
- implementation manners of S201 and S206 are the same as the implementation manners of S101 and S103 in the embodiment shown in FIG. 3 of the present invention, and will not be repeated here.
- FIG. 14 is a schematic flowchart of another routing information diffusion method provided by an embodiment of this application. As shown in FIG. 14, the routing information diffusion method provided in this embodiment is based on the routing information diffusion method provided in the embodiment shown in FIG. 5 Above, after S206, a step of updating the first target diffusion range is added, and the method includes:
- S304 Determine the first diffusion benefit function according to the cumulative difference between the first diffusion benefit function and the first diffusion cost function.
- the diffusion range of the routing information can be determined according to the specific conditions of the routing network.
- the timing of the update can be a preset update interval, for example, 2 hours; it can also be updated when a change in routing network transmission is detected.
- S207 includes three specific steps of S2071, S2072, and S2073:
- the first diffusion income function is updated, and the method for obtaining the second diffusion income function includes:
- the average response probability to routing information is 0.5, which is the second target probability.
- the second diffusion benefit function is determined.
- a new diffusion income function that is, the second diffusion income function
- the first diffusion cost function is updated, and the method for obtaining the second diffusion cost function includes:
- the second diffusion cost function is determined.
- the topology of the routing network will also change accordingly.
- the delay parameters such as network delay, maximum one-way network delay, and maximum diffusion hops
- the second delay including the one-way network delay between the second nodes, the second largest one-way network delay, or the second largest diffusion hops is formed parameter.
- a new diffusion cost function that is, the second diffusion cost function
- the first diffusion benefit function shown in formula (5) is updated to form a new function for characterizing the diffusion benefit and diffusion range, that is, the second Diffusion benefit function.
- S3073 are the same as those of S205 in the embodiment shown in FIG. 5, and will not be repeated here.
- S308 Send routing information to the routing network according to the second target diffusion range.
- the first target diffusion range can be updated to obtain the second target diffusion range, and send to the routing network according to the second target diffusion range Routing information, thereby improving the real-time performance of routing information diffusion control and improving the effect of routing information diffusion.
- S301-S306 is the same as the implementation of S201-S206 in the embodiment shown in FIG. 5 of the present invention
- the implementation of S308 is the same as the implementation of S206 in the embodiment shown in FIG. 5 of the present invention , I will not repeat them here.
- routing information diffusion method of the embodiment of the present application is described in detail above, and the routing information diffusion apparatus of the embodiment of the present application will be described below.
- FIG. 16 is a schematic block diagram of a routing information diffusion apparatus according to an embodiment of the application.
- the routing information diffusion apparatus 4 in the embodiment of the present application may be a network computing node or a network device in the foregoing method embodiment, or may be one or more chips in a network computing node or a network device.
- the routing information diffusion device 4 may be used to perform part or all of the functions of the network computing node or network equipment in the foregoing method embodiment.
- the routing information diffusion device 4 may include the following modules.
- the obtaining module 41 is used to obtain the routing information of the network computing node; at this time, the obtaining module 41 may perform step S101 of the method shown in FIG. 2; or may perform step S201 of the method shown in FIG. 5; or may perform the step S201 shown in FIG. Step S301 of the method.
- the determining module 42 is configured to determine the first target diffusion range of the routing information in the routing network, where the routing network includes the target routing node. At this time, the determining module 42 may execute step S102 of the method shown in FIG. 2.
- the sending module 43 is configured to send routing information to the routing network according to the first target diffusion range, so that the target routing node can obtain the routing information. At this time, the sending module 43 may perform step S103 of the method shown in FIG. 2 or may perform step S206 of the method shown in FIG. 5.
- the routing information diffusion device of the embodiment shown in FIG. 16 can be used to implement the technical solution of the embodiment shown in FIG. 2 in the foregoing method, and its implementation principles and technical effects are similar, and will not be repeated here.
- FIG. 17 is a schematic block diagram of another routing information diffusion apparatus provided by an embodiment of the application.
- the determining module 42 includes:
- the diffusion revenue sub-module 421 is configured to obtain a first diffusion revenue function, and the first diffusion revenue function is used to characterize the probability of a target routing node in different diffusion ranges.
- the diffusion revenue sub-module 421 may perform step S202 of the method shown in FIG. 5; or may perform step S302 of the method shown in FIG. 14.
- the diffusion cost sub-module 422 is used to obtain a first diffusion cost function, which is used to characterize the cumulative delay of the routing network in different diffusion ranges; the diffusion cost sub-module 422 can perform step S203 of the method shown in FIG. 5; or Step S303 of the method shown in FIG. 14 may be executed.
- the calculation sub-module 423 is configured to determine the first diffusion benefit function according to the cumulative difference between the first diffusion benefit function and the first diffusion cost function.
- the calculation sub-module 423 may perform step S204 of the method shown in FIG. 5; or may perform step S304 of the method shown in FIG. 14.
- the determining sub-module 424 is configured to determine the first target diffusion range according to the diffusion range corresponding to the maximum value of the diffusion benefit.
- the determining submodule 424 may perform step S205 of the method shown in FIG. 5; or may perform step S305 of the method shown in FIG. 14.
- the determining module 42 is specifically used for:
- the first diffusion benefit function is used to characterize the mapping relationship between the diffusion range and the diffusion benefit. According to the first diffusion benefit function, the diffusion range corresponding to the maximum value of the diffusion benefit is determined as the first target diffusion range.
- the determining module 42 may execute step S102 of the method shown in FIG. 2.
- the first diffusion benefit function can accurately characterize the relationship between the diffusion range and the diffusion benefit. As the diffusion range of routing information increases, the probability that the routing information is received by the target route will gradually increase, but at the same time, the network delay will gradually increase. Therefore, by confirming the diffusion range corresponding to the maximum diffusion benefit function in the first diffusion benefit function as the first target diffusion range, the optimal routing information diffusion range can be determined accurately and reasonably, and the diffusion efficiency of routing information can be improved. Effectiveness.
- the routing network includes multiple routing nodes, and the diffusion revenue sub-module 421 is specifically used for:
- the preset first target probability is obtained, and the first target probability is used to characterize the probability that the routing node is the target routing node.
- the diffusion revenue sub-module 421 may execute step S2021 of the method shown in FIG. 5.
- the diffusion revenue sub-module 421 may execute step S2022 of the method shown in FIG. 5.
- the diffusion cost sub-module 422 is specifically used for:
- the diffusion cost sub-module 422 may execute step S2031 of the method shown in FIG. 5.
- the diffusion cost sub-module 422 may execute step S2032 of the method shown in FIG. 5.
- the diffusion cost sub-module 422 is specifically used for:
- the diffusion cost sub-module 422 may execute step S2033 of the method shown in FIG. 5.
- the first diffusion cost function is determined.
- the diffusion cost sub-module 422 may execute step S2034 of the method shown in FIG. 5.
- the determining submodule 424 is specifically used for:
- the determining sub-module 424 can execute step S2051 of the method shown in FIG. 5.
- the routing information includes time-to-live information
- the sending module 43 is specifically used for:
- the sending module 43 may execute step S206 of the method shown in FIG. 5, or may execute step S306 of the method shown in FIG. 14.
- the sending module 43 may execute step S206 of the method shown in FIG. 5, or may execute step S306 of the method shown in FIG. 14.
- the device further includes: an update module 44 configured to update the first target diffusion range to obtain the second target diffusion range.
- the update module 44 can execute step S307 of the method shown in FIG. 14.
- the sending module 43 is further configured to send routing information to the routing network according to the second target diffusion range. At this time, the sending module 43 can execute step S308 of the method shown in FIG. 14.
- the first target diffusion range can be updated to obtain the second target diffusion range, and send to the routing network according to the second target diffusion range Routing information, thereby improving the real-time performance of routing information diffusion control and improving the effect of routing information diffusion.
- the update module 44 is specifically used for:
- the update module 44 can execute step S3071 of the method shown in FIG. 14.
- the second diffusion benefit function is determined.
- the update module 44 can execute step S3071 of the method shown in FIG. 14.
- the second diffusion benefit function is determined.
- the update module 44 can execute step S3072 of the method shown in FIG. 14.
- the diffusion range corresponding to the maximum value of the diffusion benefit is determined as the second target diffusion range.
- the update module 44 may execute step S3073 of the method shown in FIG. 14.
- update module 44 updates the first diffusion benefit function according to the response probability of the target routing node to the routing information to obtain the second diffusion benefit function, it is specifically used to:
- the update module 44 can execute step S3071 of the method shown in FIG. 14.
- the update module 44 is specifically used for:
- the first diffusion cost function is updated to obtain the second diffusion cost function
- the second diffusion benefit function is determined according to the cumulative difference between the first diffusion benefit function and the second diffusion cost function.
- the second diffusion benefit function determines the diffusion range corresponding to the maximum value of the diffusion benefit as the second target diffusion range.
- the update module 44 can execute step S3072 of the method shown in FIG. 14.
- the update module 44 updates the first diffusion cost function according to the changes of routing nodes in the routing network to obtain the second diffusion cost function, specifically for:
- the update module 44 can execute step S3071 of the method shown in FIG. 14.
- the routing information diffusion device of the embodiment shown in FIG. 17 can be used to implement the technical solution of any one of the embodiments shown in FIG. 5 or FIG.
- this embodiment does not depend on whether the embodiment shown in FIG. 16 is implemented or not, and this embodiment can be implemented independently.
- FIG. 18 is a schematic block diagram of the structure of a network device provided by an embodiment of this application. As shown in FIG. 18, the network device includes a transmitter 51, a receiver 52, and a processor 53.
- the processor 53 is used to execute each step in FIG. 2, or the processor 53 is used to execute each step in FIG. 5, or the processor 53 is used to execute each step in FIG. 14.
- the processor 53 is used to implement the modules shown in FIG. 16 and FIG. 17.
- the network device of the embodiment shown in FIG. 18 can be used to execute the technical solution of the above method embodiment, or the program of each module of the embodiment shown in FIG. 16 and FIG. 17, the processor 53 calls the program to perform the operation of the above method embodiment, In order to realize the various modules shown in Figure 16 and Figure 17.
- the processor 53 may also be a controller, which is represented as "controller/processor 53" in FIG. 18.
- the transmitter 51 and the receiver 52 are used to support sending and receiving information between the network device and each device in the network environment in the foregoing embodiment, and to support communication between the network device and each device in the network environment in the foregoing embodiment.
- the network device may also include a memory 54 for storing program codes and data of the network device. Further, the network device may also include a communication interface 55.
- the processor 53 such as a central processing unit (CPU), may also be one or more integrated circuits configured to implement the above methods, for example: one or more specific integrated circuits (ASIC), Or, one or more microprocessors (digital singnal processors, DSP), or, one or more field programmable gate arrays (Field Programmable Gate Array, FPGA), etc.
- the memory 54 may be one memory or a collective name for multiple storage elements.
- the transmitter 51 included in the network device of FIG. 18 provided by the embodiment of the present application can perform a sending action corresponding to the foregoing method embodiment, the processor 53 performs a processing action, and the receiver can perform a receiving action.
- the transmitter 51 included in the network device of FIG. 18 provided by the embodiment of the present application can perform a sending action corresponding to the foregoing method embodiment, the processor 53 performs a processing action, and the receiver can perform a receiving action.
- the transmitter 51 included in the network device of FIG. 18 provided by the embodiment of the present application can perform a sending action corresponding to the foregoing method embodiment
- the processor 53 performs a processing action
- the receiver can perform a receiving action.
- FIG. 19 is a schematic block diagram of the structure of another network device provided in an embodiment of the application.
- the network device provided in this embodiment includes: a transceiver 61, a memory 62, a processor 63, and Computer program.
- the processor 63 is used to control the transceiver 61 to send and receive signals, and a computer program is stored in the memory 62 and is configured to be executed by the processor 63 to implement the method provided by any implementation manner corresponding to FIGS. 2-14 of the present invention.
- the transceiver 61, the memory 62, and the processor 63 are connected through a bus 64.
- the embodiment of the present application also provides a network device, including a processor, which is used to execute a computer program to execute the method provided in any of the above implementations corresponding to Figures 2-14; the network device also includes a communication interface; the processor Connect with the communication interface.
- the embodiment of the present application also provides a computer-readable storage medium, including computer code, which, when it runs on a computer, causes the computer to execute the method provided in any implementation manner corresponding to Figure 2-14.
- the embodiment of the present application also provides a computer program product, including program code.
- program code executes the method provided in any implementation manner corresponding to Figure 2-14.
- the embodiment of the present application also provides a chip including a processor.
- the processor is used to call and run the computer program stored in the memory to execute the corresponding operation and/or process performed by the network device in the routing information diffusion method provided by any implementation manner corresponding to FIG. 2-14.
- the chip further includes a memory, the memory and the processor are connected to the memory through a circuit or a wire, and the processor is used to read and execute the computer program in the memory.
- the chip further includes a communication interface, and the processor is connected to the communication interface.
- the communication interface is used to receive data and/or information that needs to be processed, and the processor obtains the data and/or information from the communication interface, and processes the data and/or information.
- the communication interface can be an input and output interface.
- the above embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
- software it can be implemented in the form of a computer program product in whole or in part.
- the computer program product includes one or more computer instructions.
- the computer program instructions When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application are generated in whole or in part.
- the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
- Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
- computer instructions can be transmitted from a website, computer, server, or data center through a cable (such as , Coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL) or wireless (for example, infrared, wireless, microwave, etc.) transmission to another website site, computer, server or data center.
- the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media.
- the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).
- the functions described in the embodiments of the present application may be implemented by hardware, software, firmware, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on the computer-readable medium.
- the computer-readable medium includes a computer storage medium and a communication medium, where the communication medium includes any medium that facilitates the transfer of a computer program from one place to another.
- the storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
本发明实施例公开了一种路由信息扩散方法、装置和存储介质,通过获取网络计算节点的路由信息,确定路由信息在路由网络中的第一目标扩散范围,其中,路由网络包括目标路由节点,根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。由于确定了路由信息扩散的最优路由扩散范围,即第一目标扩散范围,使路由信息在扩散的过程中,不再向所有可能的路由节点扩散信息,而是向最优范围内的路由节点扩散信息,从而解决带宽资源浪费和网络收敛慢的问题,提高路由信息扩散效率,降低网络延迟。
Description
本申请要求于2020年4月21日提交中国专利局、申请号为202010317910.8、申请名称为“路由信息扩散方法、装置和存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及网络通讯技术领域,更为具体地,涉及一种路由信息扩散方法、装置和存储介质。
目前互联网存在着巨大数量的智能终端和边缘网络设备,它们将提供广泛存在的计算能力,从而促进了边缘计算(edge computing)的产生和发展。在边缘计算的背景下,网络中能提供计算服务的计算节点需要把自己的计算能力,例如CPU、存储能力,作为路由信息的一部分,通过泛洪(flooding)等网络信息扩散技术发布出去,让网络中其他有可能需要计算服务的节点得知计算节点的存在和地址,从而去请求该计算服务。
然而,在网络中通过泛洪进行路由信息扩散时,会浪费带宽资源,造成网络收敛速度慢和高延迟的问题。
发明内容
本申请的目的在于提供一种路由信息扩散方法、装置和存储介质。通过获取网络计算节点的路由信息,并根据路由信息确定最优的路由扩散范围,向最优的路由扩散范围内的路由节点扩散信息,可以解决网络收敛慢,带宽资源浪费的问题,提高路由扩散效率,降低网络延迟。
第一方面,本申请公开了一种路由信息扩散方法,包括:
获取网络计算节点的路由信息;确定该路由信息在路由网络中的第一目标扩散范围,其中,路由网络包括目标路由节点;根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。
基于上述技术内容,通过获取网络计算节点的路由信息,并根据路由信息确定最优的路由扩散范围,即第一目标扩散范围,使路由信息在扩散的过程中,不再向所有可能的路由节点扩散信息,而是向最优范围内的路由节点扩散信息,从而解决带宽资源浪费和网络收敛慢的问题,提高路由信息扩散效率,降低网络延迟。
在一种实现方式中,确定路由信息在路由网络中的第一目标扩散范围,包括:获取第一扩散效益函数;该第一扩散效益函数用于表征扩散范围与扩散效益的映射关系;根据该第一扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。
通过第一扩散效益函数能够准确的表征扩散范围与扩散效益之间的关系,随着路由信息扩散范围的增大,会逐渐提高路由信息被目标路由接收到的概率,但同时网络延迟也会逐渐升高,因此,通过将第一扩散效益函数中扩散效益最大值对应的扩散范围,确认为第 一目标扩散范围,能够准确合理的确定最优的路由信息扩散范围,进一步提高路由信息的扩散效率和有效性。
在一种实现方式中,获取第一扩散效益函数,包括:获取第一扩散收益函数,该第一扩散收益函数用于表征不同扩散范围内存在目标路由节点的概率;获取第一扩散成本函数,该第一扩散成本函数用于表征不同扩散范围内路由网络的累积延迟;根据第一扩散收益函数与第一扩散成本函数的累计差,确定第一扩散效益函数。
通过将第一扩散效益函数分解为第一扩散收益函数和第一扩散成本函数两个具体的函数来表征,提高函数变化的可观测性,且随着扩散范围的增加,第一扩散效益函数和第一扩散收益函数具有独立的变化规律,可以更好地表征扩散范围分别与扩散收益、扩散成本之间的变化关系,进一步地提高第一扩散效益函数的计算精确度和有效性。
在一种实现方式中,路由网络中包括多个路由节点,获取第一扩散收益函数,包括:获取预设的第一目标概率,该第一目标概率用于表征路由节点为目标路由节点的概率;根据该第一目标概率,确定第一扩散收益函数。
在一种实现方式中,第一扩散收益函数为:gain=1-(1-p)
n,其中,gain为扩散收益,p为第一目标概率,n为扩散范围。
在一种实现方式中,获取第一扩散成本函数,包括:获取预设的第一延迟参数,该第一延迟参数包括:第一节点间单向网络延迟和第一最大单向网络延迟;根据该第一延迟参数,确定第一扩散成本函数。
在一种实现方式中,第一扩散成本函数为:cost=n*c/dmax,其中,cost为扩散成本,c为第一节点间单向网络延迟,dmax为第一最大单向网络延迟,n为扩散范围,*表示点乘。
通过对第一扩散收益函数和第一扩散成本函数具体实现方式的限定,本申请实施例提供了一种具体的第一扩散效益函数的实现方法,能够有效的评估随着扩散范围的增加,路由信息的扩散所带来的效益的变化,进而实现确定最大效益对应的最优扩散范围,进一步提高路由信息的扩散效率和有效性。
在一种实现方式中,获取第一扩散成本函数,包括:获取预设的第一延迟参数,该第一延迟参数包括:第一最大扩散跳数;根据不同扩散范围与第一最大扩散跳数的比值,确定第一扩散成本函数。
由于第一最大扩散跳数为预设值,通过扩散范围与第一最大扩散跳数的比值,确定第一扩散成本函数的实现方式更简便有效,且不会受到具体的网络连接状况影响,使第一扩散成本函数具有更好地鲁棒性。
在一种实现方式中,根据第一扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围,包括:获取预设的一个或多个扩散范围;将使第一扩散收益函数的函数值与第一扩散成本函数的函数值的差值小于或等于预设阈值的扩散范围,确定为第一目标扩散范围。
在一种实现方式中,路由信息中包括生存时间信息,根据第一目标扩散范围,向路由网络发送路由信息,包括:根据第一目标扩散范围,设置生存时间信息;向路由网络发送包含该生存时间信息的路由信息。
在一种实现方式中,生存时间信息为生存时间值(Time to Live,TTL)。
在一种实现方式中,根据第一目标扩散范围,向路由网络发送路由信息,使目标路由 节点获得路由信息之后,还包括:对第一目标扩散范围进行更新,获得第二目标扩散范围;根据该第二目标扩散范围,向路由网络发送路由信息。
由于路由网络的状态可以会发生变化,因此,在确定第一目标扩散范围后,通过对第一目标扩散范围进行更新,而获得第二目标扩散范围,并根据第二目标扩散范围向路由网络发送路由信息,从而进一步提高路由信息扩散控制的实时性,进一步提高路由信息扩散效果。
在一种实现方式中,对第一目标扩散范围进行更新,获得第二目标扩散范围,包括:根据目标路由节点对路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数;根据第二扩散收益函数与第一扩散成本函数的累计差,确定第二扩散效益函数;根据该第二扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。
在一种实现方式中,根据目标路由节点对路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数,包括:获取预设时间内,响应路由信息的目标路由节点个数;将该目标路由节点个数与第一目标扩散范围的比值,确定为第二目标概率;根据第二目标概率,确定第二扩散收益函数。
在一种实现方式中,对第一目标扩散范围进行更新,获得第二目标扩散范围,包括:根据路由网络中路由节点的变化情况,对第一扩散成本函数进行更新,获得第二扩散成本函数;根据第一扩散收益函数与第二扩散成本函数的累计差,确定第二扩散效益函数;根据该第二扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。
在一种实现方式中,根据路由网络中路由节点的变化情况,对第一扩散成本函数进行更新,获得第二扩散成本函数,包括:获取当前路由网络中路由节点的拓扑结构;根据拓扑结构,对第一延迟参数进行更新,获取第二延迟参数;根据该第二延迟参数,确定第二扩散成本函数。
第二方面,本申请公开了一种路由信息扩散装置,包括:
获取模块,用于获取网络计算节点的路由信息;确定模块,用于确定路由信息在路由网络中的第一目标扩散范围,其中,该路由网络包括目标路由节点;发送模块,用于根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。
本申请中,通过获取网络计算节点的路由信息,并根据路由信息确定最优的路由扩散范围,即第一目标扩散范围,使路由信息在扩散的过程中,不再向所有可能的路由节点扩散信息,而是向最优范围内的路由节点扩散信息,从而解决带宽资源浪费和网络收敛慢的问题,提高路由信息扩散效率,降低网络延迟。
在一种实现方式中,确定模块,具体用于:用于获取第一扩散效益函数;该第一扩散效益函数用于表征扩散范围与扩散效益的映射关系;根据该第一扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。
通过第一扩散效益函数能够准确的表征扩散范围与扩散效益之间的关系,随着路由信息扩散范围的增大,会逐渐提高路由信息被目标路由接收到的概率,但同时网络延迟也会逐渐升高,因此,通过将第一扩散效益函数中扩散效益最大值对应的扩散范围,确认为第一目标扩散范围,能够准确合理的确定最优的路由信息扩散范围,进一步提高路由信息的扩散效率和有效性。
在一种实现方式中,确定模块,包括:扩散收益子模块,用于获取第一扩散收益函数,该第一扩散收益函数用于表征不同扩散范围内存在目标路由节点的概率;扩散成本子模块,用于获取第一扩散成本函数,该第一扩散成本函数用于表征不同扩散范围内路由网络的累积延迟;计算子模块,用于根据第一扩散收益函数与第一扩散成本函数的累计差,确定第一扩散效益函数。确定子模块,用于根据扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。
通过将第一扩散效益函数分解为第一扩散收益函数和第一扩散成本函数两个具体的函数来表征,提高函数变化的可观测性,且随着扩散范围的增加,第一扩散效益函数和第一扩散收益函数具有独立的变化规律,可以更好地表征扩散范围分别与扩散收益、扩散成本之间的变化关系,进一步提高第一扩散效益函数的计算精确度和有效性。
在一种实现方式中,路由网络中包括多个路由节点,扩散收益子模块,具体用于:获取预设的第一目标概率,该第一目标概率用于表征路由节点为目标路由节点的概率;根据第一目标概率,确定第一扩散收益函数。
在一种实现方式中,第一扩散收益函数为:gain=1-(1-p)
n,其中,gain为扩散收益,p为第一目标概率,n为扩散范围。
在一种实现方式中,扩散成本子模块,具体用于:获取预设的第一延迟参数,该第一延迟参数包括:第一节点间单向网络延迟和第一最大单向网络延迟;根据该第一延迟参数,确定第一扩散成本函数。
在一种实现方式中,第一扩散成本函数为:cost=n*c/dmax,其中,cost为扩散成本,c为第一节点间单向网络延迟,dmax为第一最大单向网络延迟,n为扩散范围。
通过对第一扩散收益函数和第一扩散成本函数具体实现方式的限定,本申请实施例提供了一种具体的第一扩散效益函数的实现方法,能够有效的评估随着扩散范围的增加,路由信息的扩散所带来的效益的变化,进而实现确定最大效益对应的最优扩散范围,进一步提高路由信息的扩散效率和有效性。
在一种实现方式中,扩散成本子模块,具体用于:获取预设的第一延迟参数,该第一延迟参数包括:第一最大扩散跳数;根据不同扩散范围与第一最大扩散跳数的比值,确定第一扩散成本函数。
由于第一最大扩散跳数为预设值,通过扩散范围与第一最大扩散跳数的比值,确定第一扩散成本函数的实现方式更简便有效,且不会受到具体的网络连接状况影响,使第一扩散成本函数具有更好地鲁棒性,进一步提高路由信息的扩散效率和有效性。
在一种实现方式中,确定子模块,具体用于:获取预设的一个或多个扩散范围;将使第一扩散收益函数的函数值与第一扩散成本函数的函数值的差值小于或等于预设阈值的扩散范围,确定为第一目标扩散范围。
在一种实现方式中,路由信息中包括生存时间信息,发送模块,具体用于:根据第一目标扩散范围,设置生存时间信息;向路由网络发送包含该生存时间信息的路由信息。
在一种实现方式中,装置还包括:更新模块,该更新模块用于对第一目标扩散范围进行更新,获得第二目标扩散范围;发送模块,还用于根据第二目标扩散范围,向路由网络发送路由信息。
由于路由网络的状态可以会发生变化,因此,在确定第一目标扩散范围后,通过对第 一目标扩散范围进行更新,而获得第二目标扩散范围,并根据第二目标扩散范围向路由网络发送路由信息,从而提高路由信息扩散控制的实时性,进一步提高路由信息扩散效果。
在一种实现方式中,更新模块,具体用于:根据目标路由节点对路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数;根据第二扩散收益函数与第一扩散成本函数的累计差,确定第二扩散效益函数;根据第二扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。
在一种实现方式中,更新模块在根据目标路由节点对路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数时,具体用于:获取预设时间内,响应路由信息的目标路由节点个数;将目标路由节点个数与第一目标扩散范围的比值,确定为第二目标概率;根据第二目标概率,确定第二扩散收益函数。
在一种实现方式中,更新模块,具体用于:根据路由网络中路由节点的变化情况,对第一扩散成本函数进行更新,获得第二扩散成本函数;根据第一扩散收益函数与第二扩散成本函数的累计差,确定第二扩散效益函数;根据第二扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。
在一种实现方式中,更新模块在根据路由网络中路由节点的变化情况,对第一扩散成本函数进行更新,获得第二扩散成本函数时,具体用于:获取当前路由网络中路由节点的拓扑结构;根据该拓扑结构,对第一延迟参数进行更新,获取第二延迟参数;根据第二延迟参数,确定第二扩散成本函数。
第三方面,本申请实施例提供一种网络设备,网络设备包括:发送器、接收器、存储器和处理器;
存储器用于存储计算机指令;处理器用于运行存储器存储的计算机指令执行以上第一方面的任一实现方式提供的方法。
本申请中,通过获取网络计算节点的路由信息,并根据路由信息确定最优的路由扩散范围,即第一目标扩散范围,使路由信息在扩散的过程中,不再向所有可能的路由节点扩散信息,而是向最优范围内的路由节点扩散信息,从而解决带宽资源浪费和网络收敛慢的问题,提高路由信息扩散效率,降低网络延迟。
第四方面,本申请实施例提供一种网络设备,包括:处理器、存储器和收发器;
处理器用于控制收发器收发信号;存储器用于存储计算机程序;处理器还用于调用并运行存储器中存储的计算机程序,使得该网络设备执行以上第一方面的任一实现方式提供的方法。
第五方面,本申请实施例提供一种网络装置,包括处理器,处理器用于执行计算机程序,以执行以上第一方面的任一实现方式提供的方法;网络装置还包括通信接口;处理器与通信接口连接。
第六方面,本申请实施例提供一种计算机可读存储介质,包括计算机代码,当其在计算机上运行时,使得计算机执行以上第一方面的任一实现方式提供的方法。
第七方面,本申请实施例提供一种计算机程序产品,包括程序代码,当计算机运行计算机程序产品时,该程序代码执行以上第一方面的任一实现方式提供的方法。
第八方面,本申请还提供一种芯片,包括处理器。该处理器用于调用并运行存储器中存储的计算机程序,以执行本申请实施例的路由信息扩散方法中由网络设备执行的相应操 作和/或流程。可选地,该芯片还包括存储器,该存储器与该处理器通过电路或电线与存储器连接,处理器用于读取并执行该存储器中的计算机程序。进一步可选地,该芯片还包括通信接口,处理器与该通信接口连接。通信接口用于接收需要处理的数据和/或信息,处理器从该通信接口获取该数据和/或信息,并对该数据和/或信息进行处理。该通信接口可以是输入输出接口。
结合上述技术方案,本申请通过获取网络计算节点的路由信息,确定路由信息在路由网络中的第一目标扩散范围,其中,路由网络包括目标路由节点,根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。由于确定了路由信息扩散的最优路由扩散范围,即第一目标扩散范围,使路由信息在扩散的过程中,不再向所有可能的路由节点扩散信息,而是向最优范围内的路由节点扩散信息,从而解决带宽资源浪费和网络收敛慢的问题,提高路由信息扩散效率,降低网络延迟。
图1为本申请实施例提供的一种应用场景示意图;
图2为本申请实施例提供的一种路由信息扩散示意图;
图3为本申请实施例提供的一种路由信息扩散方法的流程图;
图4为本申请实施例提供的一种根据第一目标扩散范围向路由网络发送路由信息的示意图;
图5为本申请实施例提供的另一种路由信息扩散方法的流程图;
图6为图5所示实施例中步骤S202的一种实施方式的流程图;
图7为本申请实施例提供的一种路由网络结构示意图;
图8为本申请实施例提供的另一种路由网络结构示意图;
图9为图5所示实施例中步骤S203的一种实施方式的流程图;
图10为图5所示实施例中步骤S203的另一种实施方式的流程图;
图11为本申请实施例提供的一种扩散收益与扩散成本差值函数的曲线示意图;
图12为图5所示实施例中步骤S205的一种实施方式的流程图;
图13为本申请实施例提供的一种第一扩散收益函数与第一扩散成本函数的变化曲线示意图;
图14为本申请实施例提供的又一种路由信息扩散方法的流程示意图;
图15为图14所示实施例中步骤S307的另一种实施方式的流程图;
图16为本申请实施例提供的一种路由信息扩散装置的示意性框图;
图17为本申请实施例提供的另一种路由信息扩散装置的示意性框图;
图18为本申请实施例提供的一种网络设备的结构示意性框图;
图19为本申请实施例提供的另一种网络设备的结构示意性框图。
本申请实施例描述的网络架构以及业务场景是为了更加清楚的说明本申请实施例的技术方案,并不构成对于本申请实施例提供的技术方案的限定,本领域普通技术人员可知,随着网络架构的演变和新业务场景的出现,本申请实施例提供的技术方案对于类似的技术 问题,同样适用。
本申请实施例可以应用于无线通信系统,需要说明的是,本申请实施例提及的无线通信系统包括但不限于:无线局域网通信(wireless local area network,WLAN)系统,通用分组无线业务(general packet radio service,GPRS),LTE频分双工(frequency division duplex,FDD)系统,LTE时分双工(time division duplex,TDD)、通用移动通信系统(universal mobile telecommunication system,UMTS)、全球互联微波接入(worldwide interoperability for microwave access,WiMAX)通信系统,窄带物联网系统(Narrow Band-Internet of Things,NB-IoT)、全球移动通信系统(Global System for Mobile Communications,GSM)、增强型数据速率GSM演进系统(Enhanced Data rate for GSM Evolution,EDGE)、宽带码分多址系统(Wideband Code Division Multiple Access,WCDMA)、码分多址2000系统(Code Division Multiple Access,CDMA2000)、时分同步码分多址系统(Time Division-Synchronization Code Division Multiple Access,TD-SCDMA),长期演进系统(Long Term Evolution,LTE)以及下一代5G移动通信系统NR。
以下对本申请中的部分用语进行解释说明,以便于本领域技术人员理解。需要说明的是,当本申请实施例的方案应用于5G系统、或者现有的系统、或未来可能出现的其他系统时,网络设备和终端设备的名称可能发生变化,但这并不影响本申请实施例方案的实施。
1)边缘计算,是指在靠近物或数据源头的一侧,采用网络、计算、存储、应用核心能力为一体的开放平台,就近提供最近端服务。其应用程序在边缘侧发起,产生更快的网络服务响应,满足行业在实时业务、应用智能、安全与隐私保护等方面的基本需求。边缘计算处于物理实体和工业连接之间,或处于物理实体的顶端。而云端计算,仍然可以访问边缘计算的历史数据。其中,提供边缘计算能力的设备为网络计算节点,网络中的边缘计算设备、智能终端或其他具有计算能力的网络设备,均可以作为网络计算节点。
2)终端设备,又称为终端、用户设备,是一种向用户提供语音和/或数据连通性的设备,例如,具有无线连接功能的手持式设备、车载设备等;终端设备也可以是检测数据的设备,例如,传感器等;终端设备也可以是智能设备,例如,部署于室内的智能家居设备、可穿戴设备等。常见的终端设备例如包括:空气质量监测传感器、温度传感器、烟雾传感器手机、平板电脑、笔记本电脑、掌上电脑、移动互联网设备(mobile internet device,MID)、可穿戴设备,其中,可穿戴设备例如包括:智能手表、智能手环、计步器等。终端设备为现在和未来可能的无线通信的终端设备或有限通信的终端设备。
3)网络设备,又称为无线接入网(radio access network,RAN)设备是一种将终端设备接入到无线网络的设备,其包括各种通信制式中的设备,例如网络设备包括但不限于:传输点(transmission reception point,TRP)、基站(如,gNB)、无线网络控制器(radio network controller,RNC)、节点B(Node B,NB)、基站控制器(base station controller,BSC)、BTS(base transceiver station)、HeNB(home evolved NodeB),或HNB(home Node B)、基带单元(baseband uit,BBU)等。
4)“多个”是指两个或两个以上,其它量词与之类似。“和/或”,描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
5)“对应”可以指的是一种关联关系或绑定关系,A与B相对应指的是A与B之间是 一种关联关系或绑定关系。
需要指出的是,本申请实施例中涉及的名词或术语可以相互参考,不再赘述。
图1为本申请实施例提供的一种应用场景示意图,如图1所示,该示意图为智慧城市视频监测的应用场景,其中,本申请实施例的方案,可以应用到图1所示的网路计算节点11中,示例性地,网路计算节点为边缘计算设备。网络设备连接一个或多个视频采集终端12,并接收视频采集终端12传输的视频图像数据,边缘计算设备例如为边缘计算服务器,边缘计算服务器与网络设备N通信连接,并经网络设备N接入至路由网络中,并提供计算能力对视频图像数据进行处理。云服务器与路由网络通信连接,可以获取视频图像数据或对视频处理图像数据的处理结果。
目前互联网存在着巨大数量的智能终端和边缘计算设备,它们作为网络计算节点,将提供广泛存在的计算能力,从而促进了边缘计算的产生和发展。在边缘计算的背景下,网络中能提供计算服务的网络计算节点需要把自己的计算能力,例如CPU、存储能力,作为路由信息的一部分,通过泛洪等网络信息扩散技术发布出去,让网络中其他有可能需要计算服务的节点得知计算节点的存在和地址,从而去请求该计算服务。
图2为本申请实施例提供的一种路由信息扩散示意图,如图2所示,相关技术中,在路由网络中通过泛洪进行路由信息扩散时,随着扩散范围的增加,会提高网络计算节点的路由信息被需要使用该计算资源的路由节点接收的概率,但同时,也会使相互通信的路由节点的数量越来越多,路由网络的规模逐渐变大,进而造成带宽资源的浪费,以及网络收敛速度慢和网络高延迟的问题。
下面以具体地实施例对本申请的技术方案以及本申请的技术方案如何解决上述技术问题进行详细说明。下面这几个具体的实施例可以相互结合,对于相同或相似的概念或过程可能在某些实施例中不再赘述。下面将结合附图,对本申请的实施例进行描述。
图3为本申请实施例提供的一种路由信息扩散方法的流程示意图,如图3所示,该方法包括:
S101、获取网络计算节点的路由信息。
示例性地,本申请实施例的执行主体可以为边缘计算设备,例如服务器;或者智能终端设备,例如智能手机、个人电脑等;或者网络设备,例如路由器;或者其他可以执行本申请实施例的装置或设备。
具体地,路由信息可以为网络计算节点向路由网络待发送的路由信息报文,路由信息报文中包含有网络计算节点的计算能力,例如CPU计算能力、存储空间大小、链路带宽等。路由网络中的路由节点,可以通过路由信息,根据需要去请求该网络计算节点的计算能力。
S102、确定路由信息在路由网络中的第一目标扩散范围,其中,路由网络包括目标路由节点。
路由信息通过泛洪技术在路由网络中无目标的扩散,会导致带宽资源的浪费,因此,可以通过确定网络计算节点的路由信息在路由网络中扩散的最优扩散范围,即第一目标扩散范围,而实现路由信息的有限扩散。目标路由节点是指需要请求该网络计算节点的计算能力的路由节点,例如,网络中连接有一台需要请求网络计算节点的计算能力,对视频图像进行处理的视频采集设备,该视频采集设备对应的路由节点,即目标路由节点。目标路由节点处于第一目标扩散范围的覆盖范围内,即通过第一目标扩散范围进行路由信息扩散, 可以使目标路由节点接收到该路由信息,从而实现对该路由信息对应的计算能力的请求和使用。
示例性地,确定第一目标扩散范围的方法包括,获取第一扩散效益函数;第一扩散效益函数用于表征扩散范围与扩散效益的映射关系。根据第一扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。
具体地,第一扩散效益函数为表征扩散范围与扩散效益之间的映射关系,随着路由信息扩散范围的增大,会逐渐提高路由信息被目标路由接收到的概率,但同时网络延迟也会逐渐升高,扩散效益即为随着扩散范围的增加而获得的综合效益。其中,第一扩散效益函数中的扩散效益,在不同的应用场景中,其具体的表现方式是不同。示例性地,在一些时延敏感的应用场景中,例如,在线游戏、自动驾驶等,随着扩散范围的增加,其扩散效益会迅速下降,而在一些非时延性敏感的应用场景中,例如非实时数据处理,模型训练等,随着扩散范围的增加,其扩散效益会缓慢下降。因此,可以根据具体的使用需求,确定对应的第一扩散效益函数,例如,在用于在线游戏的场景中,使用第一扩散效益函数func_A确定第一目标扩散范围;在用于智慧城市视频监测的场景下,使用第一扩散效益函数func_B确定第一目标扩散范围,此处不对第一扩散效益函数的具体形式进行限定。
进一步地,在确定第一扩散效益函数后,将第一扩散效益函数中扩散效益最大值对应的扩散范围,确认为第一目标扩散范围。示例性地,第一扩散效益函数为一个二次函数,在扩散范围的变量区间内,存在一个全局最大值,将该全局最大值对应的扩散范围,确定为第一目标扩散范围。示例性地,第一扩散效益函数还可以为在扩散范围的变量区间内,存在多个全局最大值的高次函数,此种情况下,可以根据具体的需求,选择其中一个局部最大值对应的扩散范围,确定为第一目标扩散范围。
S103、根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。
图4为本申请实施例提供的一种根据第一目标扩散范围向路由网络发送路由信息的示意图,如图4所示,在确定第一目标扩散范围后,根据第一目标扩散范围,向路由网络发送路由信息,在第一目标扩散范围内的路由节点,均可以接收到网络计算节点的路由信息。其中,示例性地,据第一目标扩散范围为,向路由网络发送路由信息,包括:第一目标扩散范围为路由信息扩散的路由节点数量,根据路由信息扩散的路由节点数量,设定待发送的路由信息报文头部的TTL,通过TTL来实现网络计算节点的路由信息在第一目标扩散范围内扩散。其中,通过TTL扩散路由信息的方法,为本领域现有技术手段,此处不再进行赘述。
本申请中,通过获取网络计算节点的路由信息,确定路由信息在路由网络中的第一目标扩散范围,其中,路由网络包括目标路由节点,根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。由于确定了路由信息扩散的最优路由扩散范围,即第一目标扩散范围,使路由信息在扩散的过程中,不再向所有可能的路由节点扩散信息,而是向最优范围内的路由节点扩散信息,从而解决带宽资源浪费和网络收敛慢的问题,提高路由信息扩散效率,降低网络延迟。
图5为本申请实施例提供的另一种路由信息扩散方法的流程示意图,如图5所示,本实施例提供的路由信息扩散方法在图3所示实施例提供的路由信息扩散方法的基础上,对 步骤S102进一步细化,该方法包括:
S201、获取网络计算节点的路由信息,路由信息中包括生存时间信息。
S202、获取第一扩散收益函数,第一扩散收益函数用于表征不同扩散范围内存在目标路由节点的概率。
示例性地,第一扩散收益函数是表征不同扩散范围与该扩散范围内存在目标路由节点的概率之间的变化关系的函数。当扩散范围逐渐增大时,网络计算节点的路由信息被其他路由节点所接受到的概率越大,也即扩散收益越大。根据扩散范围与扩散收益之间的关系,可以确定第一扩散收益函数。
示例性地,如图6所示,在一种可行的实施方案中,路由网络中包括多个路由节点,S202包括S2021、S2022两个具体的实现步骤:
S2021、获取预设的第一目标概率,第一目标概率用于表征路由节点为目标路由节点的概率。
第一目标概率用于表征路由节点为目标路由节点的概率,示例性地,路由节点为目标路由节点的概率,可以是通过计算各路由信息接入终端设备的历史数据而确定的,也可以是根据具体的应用场景下路由网络中的路由节点数量而预设的,此处不对获取第一目标概率的具体方式进行限定。
更加具体地,例如,在一个具有10个路由节点的路由网络中,若10个路由节点相互独立的接入需要使用网络计算节点的计算能力的设备,各路由节点为目标路由节点的平均概率为20%,该平均概率的数值为根据日常统计而获得的,此时,第一目标概率可以为一个数值,即0.2。再例如,在一个具有10个路由节点的路由网络中,其中路由节点a接入需要使用网络计算节点的计算能力的设备的概率为50%,路由节点b接入需要使用网络计算节点的计算能力的设备的概率为30%,其他路由节点接入需要使用网络计算节点的计算能力的设备的概率为20%,则第一目标概率可以为一个长度为10的数组,数组中路由节点a对应的值为0.5,数组中路由节点b对应的值为0.3,数组中其他8个数值为0.2。
S2022、根据第一目标概率,确定第一扩散收益函数。
示例性的,第一扩散收益函数用于表征在在扩散范围内至少有一个路由节点为目标路由节点的概率,具体地,扩散范围的实现方式可以为扩散节点数。在确定第一目标概率,即路由节点为目标路由节点的概率后,相应地,可以确定路由节点不为目标路由节点的概率,进而可以确定路由信息经过N个扩散节点后,至少有一个路由节点为目标路由节点的概率。
示例性地,当第一目标概率p为数值时,第一扩散收益函数为如式(1)所示:
gain(n)=1-(1-p)
n (1)
其中,gain(n)为扩散范围为n时的扩散收益,p为第一目标概率,n为扩散范围。
图7为本申请实施例提供的一种路由网络结构示意图,如图7所示,从网络计算节点0开始向外扩散路由信息,预设的第一目标概率p为0.4,则当n=1时,第一扩散收益函数为0.4;则当n=2时,第一扩散收益函数为0.64;则当n=3时,第一扩散收益函数为0.78;则当n=4时,第一扩散收益函数为0.87。
示例性地,当第一目标概率p为数组时,第一扩散收益函数如式(2)所示:
其中,gain(n)为扩散范围为n时的扩散收益,pi为第一目标概率p中的第i个数值,n为扩散范围。
图8为本申请实施例提供的另一种路由网络结构示意图,如图8所示,从网络计算节点0开始向多个路径扩散路由信息,预设的第一目标概率p为一个概率数组[p1,p2,p3],其中,包括其中,p1,p2,p3分别为扩散范围为n=1、n=2、n=3时,多个路径的扩散范围内至少有一个路由节点为目标路由节点的综合概率,例如:
当n=1时,p1=0.25,则得到第一扩散收益函数为0.25。
当n=2时,p2=0.5,则得到第一扩散收益函数为0.625。
当n=3时,p3=0.5,则得到第一扩散收益函数为0.813。
本实施例步骤中,提供了一种具体的第一扩散收益函数的实现方法,能够有效的评估随着扩散范围的增加,路由信息的扩散所带来的收益变化,即在扩散范围内至少有一个路由节点为目标路由节点的概率,实现对路由信息扩散收益的准确评估,并且,通过预先设置数值形式的第一目标概率,对不同扩散范围,对应不同的第一目标概率值,进一步提高路由信息扩散收益评估的精确度,提高路由信息扩散控制的效果。
S203、获取第一扩散成本函数,第一扩散成本函数用于表征不同扩散范围内路由网络的累积延迟。
示例性地,第一扩散成本函数是表征不同扩散范围与路由网络总体扩散成本之间的变化关系的函数。当扩散范围逐渐增大时,随着路由信息经过的路由节点数的增加,路由网络总体扩散成本也会相应增加,例如网络传输延迟增加,网络收敛时间增加,即扩散成本越大。根据扩散范围与扩散成本之间的关系,可以确定第一扩散成本函数。
示例性地,如图9所示,在一种可行的实施方案中,S203包括S2031、S2032两个具体的实现步骤:
S2031、获取预设的第一延迟参数,第一延迟参数包括:第一节点间单向网络延迟和第一最大单向网络延迟。
示例性地,第一节点间单向网络延迟指不同的路由节点间,进行路由信息传递时的延迟量,该延迟量与具体的路由节点性能及路由节点间的网络状态决定;第一最大单向网络延迟是指路由信息从最初的网络计算节点发出后,遍历路由网络中的所有路由节点所需要的延迟,即最大延迟量。第一最大单向网络延迟与具体的路由网络的规模和结构有关。
更加具体地,在一个具有10个路由节点的路由网络中,其中路由节点a与路由节点b之间的单向网络延迟为30个延迟单位,路由节点b与其他路由节点,以及其他路由节点之间的单向网络延迟为10个延迟单位,则第一单向网络延迟可以为一个长度为10的数组,数组中路由节点a对应的值为30,数组中其他9个数值为10。
S2032、根据第一延迟参数,确定第一扩散成本函数。
根据第一延迟参数中的第一节点间单向网络延迟与第一最大单向网络延迟的比值,可以确定在路由信息传递路径上的每个路由节点间的归一化延迟量,进而,该归一化延迟量与扩散范围的乘积,扩散范围内路由网络的总体延迟量,即路由网络总体扩散成本。
示例性地,在一种可能的实现方式中,当第一单向网络延迟为一个数组时,第一扩散成本函数如式(3)所示:
其中,cost(n)为扩散范围为n时的扩散成本,ci为第i个路由节点对应的第一节点间单向网络延迟,dmax为第一最大单向网络延迟,n为扩散范围。
示例性地,如图7所示的路由网络结构中,从网络计算节点0开始向外扩散路由信息,最大扩散范围为n=4,对应的第一最大单向网络延迟为100。第一节点间单向网络延迟c1为10,则当n=1时,第一扩散成本函数为0.1;第一节点间单向网络延迟c2为30,则当n=2时,第一扩散成本函数为0.4;第一节点间单向网络延迟c3为30,则当n=3时,第一扩散成本函数为0.7;第一节点间单向网络延迟c4为30,则当n=4时,第一扩散成本函数为1。
示例性地,如图8所示的路由网络结构中,从网络计算节点0开始向多个路径扩散路由信息,最大扩散范围为n=3,对应的第一最大单向网络延迟为100。第一节点间单向网络延迟c1为20,则当n=1时,第一扩散成本函数为0.2;第一节点间单向网络延迟c2为40,则当n=2时,第一扩散成本函数为0.6;第一节点间单向网络延迟c3为40,则当n=3时,第一扩散成本函数为1。
示例性地,如图10所示,在另一种可行的实施方案中,S203包括S2033、S2034两个具体的实现步骤:
S2033、获取预设的第一延迟参数,第一延迟参数包括:第一最大扩散跳数。
具体地,第一最大扩散跳数为路由网络中,最大扩散范围对应的路由节点数,示例性地,如路由网络最大扩散范围为4个路由节点,则第一最大扩散跳数为4。
S2034、根据不同扩散范围与第一最大扩散跳数的比值,确定第一扩散成本函数。
若在路由网络中,各路由节点间单向网络延迟相同,例如确定单向网络延迟为平均单向网络延迟。则第一扩散成本函数可以根据扩散范围与第一最大扩散跳数的比值确定。
示例性地,在一种可能的实现方式中,当第一单向网络延迟为平均单向网络延迟,第一扩散成本函数如式(4)所示:
cost(n)=n/t
max (4)
其中,cost(n)为扩散范围为n时的扩散成本,tmax为第一最大扩散跳数,n为扩散范围。
示例性地,如图7所示的路由网络结构中,从网络计算节点0开始向外扩散路由信息,第一最大扩散跳数为n=4,则当n=1时,第一扩散成本函数为0.25;当n=2时,第一扩散成本函数为0.5;当n=3时,第一扩散成本函数为0.75;当n=4时,第一扩散成本函数为1。
S204、根据第一扩散收益函数与第一扩散成本函数的累计差,确定第一扩散效益函数。
具体地,随着第一扩散收益函数与第一扩散成本函数中扩散范围的变化,第一扩散收益函数与第一扩散成本函数的函数值也相应的发生变化,而第一扩散收益函数与第一扩散成本函数的差值的累积,可以反映路由网络的效益变化,即第一扩散效益函数。示例性地,第一扩散效益函数如式(5)所示:
utility(n)=∑(w
1×gain(n)-w
2×cost(n)) (5)
其中,utility(n)为扩散范围为n时的扩散效益;gain(n)为扩散范围为n时的扩散收益;cost(n)为扩散范围为n时的扩散成本,w1为第一权重系数;w2为第二权重系数;w1和w2用于调节第一扩散收益函数和第一扩散成本函数的权重。
S205、根据第一扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第一目 标扩散范围。
示例性地,图11为本申请实施例提供的一种扩散收益与扩散成本的差值函数的曲线示意图,如图11所示,图中横轴为扩散范围,纵轴为扩散收益与扩散成本的差值;随着扩散范围的增加,第一扩散效益函数中的第一扩散收益函数与第一扩散成本函数均会增加,但是在扩散范围较小时,扩散收益大于扩散成本,二者差值大于零,随着扩散范围的增加,扩散收益与扩散成本的差值的累积量始终增加,因此,第一扩散效益函数的函数值随之增加。但在超过扩散范围nop后,扩散收益小于成本函数,二者差值小于零,随着扩散范围的增加,扩散收益与扩散成本的差值的累积量逐渐减小,进而,第一扩散效益函数的函数值逐渐变小,因此,可以将第一扩散效益函数的最大函数值对应的自变量,即扩散范围nop,确定为第一目标扩散范围。
示例性地,如图12所示,在一种可行的实施方案中,S205包括S2051、S2052两个具体的实现步骤:
S2051、获取预设的一个或多个扩散范围。
示例性地,获得一个预设的扩散范围序列,例如为n_list=[1,2,3,4],扩散范围序列中的值,依次对应扩散范围为n_list(1)=1;扩散范围为n_list(1)=2;扩散范围为n_list(1)=3;扩散范围为n_list(1)=4。
S2052、将使第一扩散收益函数的函数值与第一扩散成本函数的函数值的差值小于或等于预设阈值的扩散范围,确定为第一目标扩散范围。
示例性地,预设阈值可以为预设误差阈值,将扩散范围序列n_list中的扩散范围值,依次输入如式(6)所示的判断函数:
|w
1×gain(n)-w
2×cost(n)|≤ε (6)
其中,ε为预设误差阈值,由具体的路由网络参数确定。
当n_list中的扩散范围值满足式(6)所示的判断条件时,则将对应的扩散范围值确定为第一目标扩散范围。
图13为第一扩散收益函数与第一扩散成本函数的变化曲线示意图,如图13所示,随着扩散范围的增加,第一扩散收益函数与第一扩散成本函数均开始增加,当n=nop时,满足式(6)所示的判断条件,即|gain(n
op)-cost(n
op)|≤ε,其中,nop为正整数。示例性地,ε为0.1,即10%的误差范围。示例性地,若满足条件的nop个数大于一个,则选择所有nop中最大的作为第一目标扩散范围。
通过对第一扩散收益函数和第一扩散成本函数具体实现方式的限定,本申请实施例提供了一种具体的第一扩散效益函数的实现方法,能够有效的评估随着扩散范围的增加,路由信息的扩散所带来的效益的变化,进而实现确定最大效益对应的最优扩散范围。
同时,通过将第一扩散效益函数分解为第一扩散收益函数和第一扩散成本函数两个具体的函数来表征,提高函数变化的可观测性和灵活性。通过调第一扩散效益函数和第一扩散成本函数的权重系数,能够使第一扩散效益函数应用于时延敏感型或者非延时敏感型应用场景,例如,在时延敏感型应用场景,通过相对调高第一扩散成本函数的权重系数,可以确定一个较小的最优扩散范围,满足该应用场景下的低延迟要求;在非时延敏感应用场景下,可以相对调高第一扩散收益函数的权重系数,确定一个较大的最优扩散范围,使网络计算节点的计算能力能够被更多的设备利用,提高网络系统的经济性,同时提高第一扩 散效益函数的计算精确度和有效性。
S206、根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。
本实施例中,S201和S206的实现方式与本发明图3所示实施例中的S101、S103的实现方式相同,在此不再一一赘述。
图14为本申请实施例提供的又一种路由信息扩散方法的流程示意图,如图14所示,本实施例提供的路由信息扩散方法在图5所示实施例提供的路由信息扩散方法的基础上,在S206之后,增加了对第一目标扩散范围进行更新的步骤,该方法包括:
S301、获取网络计算节点的路由信息,路由信息中包括生存时间信息。
S302、获取第一扩散收益函数,第一扩散收益函数用于表征不同扩散范围内存在目标路由节点的概率。
S303、获取第一扩散成本函数,第一扩散成本函数用于表征不同扩散范围内路由网络的累积延迟。
S304、根据第一扩散收益函数与第一扩散成本函数的累计差,确定第一扩散效益函数。
S305、根据第一扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。
S306、根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。
S307、对第一扩散收益函数,和/或,第一扩散成本函数进行更新,获得第二目标扩散范围。
由于路由网络中的各种接入设备以及负载情况是动态变化的,因此,在根据第一目标扩散范围,向路由网络发送路由信息后,可以根据路由网络的具体情况,对路由信息的扩散范围进行实时的调整和更新,更新的时机可以是预设的更新间隔,例如为2小时;也可以为当检测到路由网络发送变化时,进行更新。
示例性地,如图15所示,在一种可行的实施方案中,S207包括S2071、S2072和S2073三个具体的步骤方式:
S3071、根据目标路由节点对路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数,和/或,根据路由网络中路由节点的变化情况,对第一扩散成本函数进行更新,获得第二扩散成本函数。
其中,示例性地,第一扩散收益函数进行更新,获得第二扩散收益函数的方法包括:
获取预设时间内,响应路由信息的目标路由节点个数,将目标路由节点个数与第一目标扩散范围的比值,确定为第二目标概率。
例如,在预设时间内,响应路由信息的目标路由节点为5个,第一目标扩散范围对应的目标路由节点为10个,则在第一目标扩散范围内,对路由信息的平均响应概率为0.5,即第二目标概率。
根据第二目标概率,确定第二扩散收益函数。
根据第二目标概率,对如式(1)或式(2)所示第一扩散收益函数中的第一目标概率进行替换,可以获得新的扩散收益函数,即第二扩散收益函数。
示例性地,第一扩散成本函数进行更新,获得第二扩散成本函数的方法包括:
获取当前路由网络中路由节点的拓扑结构;根据拓扑结构,对第一延迟参数进行更新,获取第二延迟参数。
根据第二延迟参数,确定第二扩散成本函数。
当路由网络中的路由节点数量发生变化时,例如接入新的路由节点,或者删除现有的路由节点时,路由网络中的拓扑结构也会相应发生变化,相应地,会导致例如节点间单向网络延迟、最大单向网络延迟、最大扩散跳数等延迟参数发生变化,即形成包括第二节点间单向网络延迟、第二最大单向网络延迟或第二最大扩散跳数的第二延迟参数。根据第二延迟参数,对如式(3)或式(4)所示第一扩散成本函数中的第一节点间单向网络延迟、第一最大单向网络延迟或第一最大扩散跳数进行替换,可以获得新的扩散成本函数,即第二扩散成本函数。
S3072、根据第二扩散收益函数,和/或第二扩散成本函数,确定第二扩散效益函数。
根据第二扩散收益函数,和/或第二扩散成本函数,对如式(5)所示的第一扩散效益函数进行更新,形成新的用于表征扩散效益和扩散范围的函数,即第二扩散效益函数。
S3073、根据第二扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。
S3073具体地实施方法及技术效果同与图5所示实施例中S205相同,此处不再赘述。
S308、根据第二目标扩散范围,向路由网络发送路由信息。
由于路由网络的状态可以会发生变化,因此,在确定第一目标扩散范围后,可以对第一目标扩散范围进行更新,而获得第二目标扩散范围,并根据第二目标扩散范围向路由网络发送路由信息,从而提高路由信息扩散控制的实时性,提高路由信息扩散效果。
本实施例中,S301-S306的实现方式与本发明图5所示实施例中的S201-S206的实现方式相同,S308的实现方式与本发明图5所示实施例中的S206的实现方式相同,在此不再一一赘述。
上文中详细描述了本申请实施例的路由信息扩散方法,下面将描述本申请实施例的路由信息扩散装置。
在一个示例中,图16为本申请实施例提供的一种路由信息扩散装置的示意性框图。本申请实施例的路由信息扩散装置4可以是上述方法实施例中的网络计算节点或网络设备,也可以是网络计算节点或网络设备内的一个或多个芯片。该路由信息扩散装置4可以用于执行上述方法实施例中的网络计算节点或网络设备的部分或全部功能。该路由信息扩散装置4可以包括下述模块。
获取模块41,用于获取网络计算节点的路由信息;此时,获取模块41可以执行图2所示方法的步骤S101;或者可以执行图5所示方法的步骤S201;或者可以执行图14所示方法的步骤S301。
确定模块42,用于确定路由信息在路由网络中的第一目标扩散范围,其中,路由网络包括目标路由节点。此时,确定模块42可以执行图2所示方法的步骤S102。
发送模块43,用于根据第一目标扩散范围,向路由网络发送路由信息,使目标路由节点获得路由信息。此时,发送模块43可以执行图2所示方法的步骤S103,或者可以执行图5所示方法的步骤S206。
图16所示实施例的路由信息扩散装置可用于执行上述方法中图2所示实施例的技术 方案,其实现原理和技术效果类似,此处不再赘述。
在另一个示例中,图17为本申请实施例提供的另一种路由信息扩散装置的示意性框图。在图16所示装置的基础上,如图17所示,该装置中,确定模块42,包括:
扩散收益子模块421,用于获取第一扩散收益函数,第一扩散收益函数用于表征不同扩散范围内存在目标路由节点的概率。扩散收益子模块421可以执行图5所示方法的步骤S202;或者可以执行图14所示方法的步骤S302。
扩散成本子模块422,用于获取第一扩散成本函数,第一扩散成本函数用于表征不同扩散范围内路由网络的累积延迟;扩散成本子模块422可以执行图5所示方法的步骤S203;或者可以执行图14所示方法的步骤S303。
计算子模块423,用于根据第一扩散收益函数与第一扩散成本函数的累计差,确定第一扩散效益函数。计算子模块423可以执行图5所示方法的步骤S204;或者可以执行图14所示方法的步骤S304。
确定子模块424,用于根据扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。确定子模块424可以执行图5所示方法的步骤S205;或者可以执行图14所示方法的步骤S305。
示例性地,确定模块42,具体用于:
用于获取第一扩散效益函数;第一扩散效益函数用于表征扩散范围与扩散效益的映射关系。根据第一扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。此时,确定模块42可以执行图2所示方法的步骤S102。
通过第一扩散效益函数能够准确的表征扩散范围与扩散效益之间的关系,随着路由信息扩散范围的增大,会逐渐提高路由信息被目标路由接收到的概率,但同时网络延迟也会逐渐升高,因此,通过将第一扩散效益函数中扩散效益最大值对应的扩散范围,确认为第一目标扩散范围,能够准确合理的确定最优的路由信息扩散范围,提高路由信息的扩散效率和有效性。
在一种可能的实现方式中,路由网络中包括多个路由节点,扩散收益子模块421,具体用于:
获取预设的第一目标概率,第一目标概率用于表征路由节点为目标路由节点的概率。此时,扩散收益子模块421可以执行图5所示方法的步骤S2021。
根据第一目标概率,确定第一扩散收益函数。此时,扩散收益子模块421可以执行图5所示方法的步骤S2022。
在一种可能的实现方式中,第一扩散收益函数为:gain=1-(1-p)
n,其中,gain为扩散收益,p为第一目标概率,n为扩散范围。
在一种可能的实现方式中,扩散成本子模块422,具体用于:
获取预设的第一延迟参数,第一延迟参数包括:第一节点间单向网络延迟和第一最大单向网络延迟。此时,扩散成本子模块422可以执行图5所示方法的步骤S2031。
根据第一延迟参数,确定第一扩散成本函数。此时,扩散成本子模块422可以执行图5所示方法的步骤S2032。
在一种可能的实现方式中,第一扩散成本函数为:cost=n*c/dmax,其中,cost为扩散成本,c为第一节点间单向网络延迟,dmax为第一最大单向网络延迟,n为扩散范围。
在一种可能的实现方式中,扩散成本子模块422,具体用于:
获取预设的第一延迟参数,第一延迟参数包括:第一最大扩散跳数。此时,扩散成本子模块422可以执行图5所示方法的步骤S2033。
根据不同扩散范围与第一最大扩散跳数的比值,确定第一扩散成本函数。此时,扩散成本子模块422可以执行图5所示方法的步骤S2034。
在一种可能的实现方式中,确定子模块424,具体用于:
获取预设的一个或多个扩散范围。此时,确定子模块424可以执行图5所示方法的步骤S2051。
在一种可能的实现方式中,路由信息中包括生存时间信息,发送模块43,具体用于:
根据第一目标扩散范围,设置生存时间信息。此时,发送模块43可以执行图5所示方法的步骤S206,或者,可以执行图14所示方法的步骤S306。
向路由网络发送包含生存时间信息的路由信息。此时,发送模块43可以执行图5所示方法的步骤S206,或者,可以执行图14所示方法的步骤S306。
在一种可能的实现方式中,装置还包括:更新模块44,更新模块44用于对第一目标扩散范围进行更新,获得第二目标扩散范围。更新模块44可以执行图14所示方法的步骤S307。
发送模块43,还用于根据第二目标扩散范围,向路由网络发送路由信息。此时,发送模块43可以执行图14所示方法的步骤S308。
由于路由网络的状态可以会发生变化,因此,在确定第一目标扩散范围后,可以对第一目标扩散范围进行更新,而获得第二目标扩散范围,并根据第二目标扩散范围向路由网络发送路由信息,从而提高路由信息扩散控制的实时性,提高路由信息扩散效果。
在一种可能的实现方式中,更新模块44,具体用于:
根据目标路由节点对路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数。此时,更新模块44可以执行图14所示方法的步骤S3071。
根据第二扩散收益函数与第一扩散成本函数的累计差,确定第二扩散效益函数。此时,更新模块44可以执行图14所示方法的步骤S3071。
根据第二扩散收益函数与第一扩散成本函数的累计差,确定第二扩散效益函数。此时,更新模块44可以执行图14所示方法的步骤S3072。
根据第二扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。此时,更新模块44可以执行图14所示方法的步骤S3073。
在一种可能的实现方式中,更新模块44在根据目标路由节点对路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数时,具体用于:
获取预设时间内,响应路由信息的目标路由节点个数,将目标路由节点个数与第一目标扩散范围的比值,确定为第二目标概率,根据第二目标概率,确定第二扩散收益函数。此时,更新模块44可以执行图14所示方法的步骤S3071。
在一种可能的实现方式中,更新模块44,具体用于:
根据路由网络中路由节点的变化情况,对第一扩散成本函数进行更新,获得第二扩散成本函数,根据第一扩散收益函数与第二扩散成本函数的累计差,确定第二扩散效益函数,根据第二扩散效益函数,将扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。 此时,更新模块44可以执行图14所示方法的步骤S3072。
在一种可能的实现方式中,更新模块44在根据路由网络中路由节点的变化情况,对第一扩散成本函数进行更新,获得第二扩散成本函数时,具体用于:
获取当前路由网络中路由节点的拓扑结构;根据拓扑结构,对第一延迟参数进行更新,获取第二延迟参数;根据第二延迟参数,确定第二扩散成本函数。此时,更新模块44可以执行图14所示方法的步骤S3071。
图17所示实施例的路由信息扩散装置可用于执行上述方法中图5或图14所示实施例中任一项的技术方案,其实现原理和技术效果类似,此处不再赘述。
并且,本实施例的实施不依赖于图16所示的实施例是否实施,本实施例可以独立实施。
图18为本申请实施例提供的一种网络设备的结构示意性框图。如图18所示,该网络设备包括发送器51、接收器52和处理器53。
其中,处理器53用于执行图2的各步骤,或者,处理器53用于执行图5的各步骤,或者,处理器53用于执行图14的各步骤。处理器53用于实现图16和图17的各模块。
图18所示实施例的网络设备可用于执行上述方法实施例的技术方案,或者图16、图17所示实施例各个模块的程序,处理器53调用该程序,执行以上方法实施例的操作,以实现图16、图17所示的各个模块。
其中,处理器53也可以为控制器,图18中表示为“控制器/处理器53”。发送器51和接收器52用于支持网络设备与上述实施例中的网络环境中的各设备之间收发信息,以及支持网络设备与上述实施例中的网络环境中的各设备之间进行通信。
进一步的,网络设备还可以包括存储器54,存储器54用于存储网络设备的程序代码和数据。进一步的,网络设备还可以包括通信接口55。
处理器53例如中央处理器(Central Processing Unit,CPU),还可以是被配置成实施以上方法的一个或多个集成电路,例如:一个或多个特定集成电路(Application Specific Integrated Circuit,ASIC),或,一个或多个微处理器(digital singnal processor,DSP),或,一个或者多个现场可编程门阵列(Field Programmable Gate Array,FPGA)等。存储器54可以是一个存储器,也可以是多个存储元件的统称。
需要说明的是,本申请实施例提供的图18的网络设备所包含的发送器51对应前述方法实施例中可以执行发送动作,处理器53执行处理动作,接收器可以执行接收动作。具体可参考前述方法实施例。
示例性地,图19为本申请实施例提供的另一种网络设备的结构示意性框图,如图19所示,本实施例提供的网络设备包括:收发器61,存储器62,处理器63以及计算机程序。
其中,处理器63用于控制收发器61收发信号,计算机程序存储在存储器62中,并被配置为由处理器63执行以实现本发明图2-14所对应的任一实现方式提供的方法。
其中,收发器61,存储器62,处理器63通过总线64连接。
相关说明可以对应参见图2-图4所对应的实施例中的步骤所对应的相关描述和效果进行理解,此处不做过多赘述。
本申请实施例还提供一种网络装置,包括处理器,处理器用于执行计算机程序,以执行以上如图2-14所对应的任一实现方式提供的方法;网络装置还包括通信接口;处理器与 通信接口连接。
本申请实施例还提供一种计算机可读存储介质,包括计算机代码,当其在计算机上运行时,使得计算机执行如图2-14所对应的任一实现方式提供的方法。
本申请实施例还提供一种计算机程序产品,包括程序代码,当计算机运行计算机程序产品时,该程序代码执行如图2-14所对应的任一实现方式提供的方法。
本申请实施例还提供一种芯片,包括处理器。该处理器用于调用并运行存储器中存储的计算机程序,以执行如图2-14所对应的任一实现方式提供的路由信息扩散方法中由网络设备执行的相应操作和/或流程。可选地,该芯片还包括存储器,该存储器与该处理器通过电路或电线与存储器连接,处理器用于读取并执行该存储器中的计算机程序。进一步可选地,该芯片还包括通信接口,处理器与该通信接口连接。通信接口用于接收需要处理的数据和/或信息,处理器从该通信接口获取该数据和/或信息,并对该数据和/或信息进行处理。该通信接口可以是输入输出接口。在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时,全部或部分地产生按照本申请实施例的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如,同轴电缆、光纤、数字用户线(Digital Subscriber Line,DSL))或无线(例如,红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如,固态硬盘(Solid State Disk,SSD))等。
本领域技术人员应该可以意识到,在上述一个或多个示例中,本申请实施例所描述的功能可以用硬件、软件、固件或它们的任意组合来实现。当使用软件实现时,可以将这些功能存储在计算机可读介质中或者作为计算机可读介质上的一个或多个指令或代码进行传输。计算机可读介质包括计算机存储介质和通信介质,其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是通用或专用计算机能够存取的任何可用介质。
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到的变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以所述权利要求的保护范围为准。
Claims (31)
- 一种路由信息扩散方法,其特征在于,所述方法包括:获取网络计算节点的路由信息;确定所述路由信息在路由网络中的第一目标扩散范围,其中,所述路由网络包括目标路由节点;根据所述第一目标扩散范围,向所述路由网络发送所述路由信息,使所述目标路由节点获得所述路由信息。
- 根据权利要求1所述的方法,其特征在于,确定所述路由信息在路由网络中的第一目标扩散范围,包括:获取第一扩散效益函数;所述第一扩散效益函数用于表征扩散范围与扩散效益的映射关系;根据所述第一扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。
- 根据权利要求2所述的方法,其特征在于,所述获取第一扩散效益函数,包括:获取第一扩散收益函数,所述第一扩散收益函数用于表征不同扩散范围内存在目标路由节点的概率;获取第一扩散成本函数,所述第一扩散成本函数用于表征不同扩散范围内路由网络的累积延迟;根据所述第一扩散收益函数与所述第一扩散成本函数的累计差,确定所述第一扩散效益函数。
- 根据权利要求3所述的方法,其特征在于,所述路由网络中包括多个路由节点,所述获取第一扩散收益函数,包括:获取预设的第一目标概率,所述第一目标概率用于表征所述路由节点为目标路由节点的概率;根据所述第一目标概率,确定所述第一扩散收益函数。
- 根据权利要求3或4所述的方法,其特征在于,所述获取第一扩散成本函数,包括:获取预设的第一延迟参数,所述第一延迟参数包括:第一节点间单向网络延迟和第一最大单向网络延迟;根据所述第一延迟参数,确定所述第一扩散成本函数。
- 根据权利要求3或4所述的方法,其特征在于,所述获取第一扩散成本函数,包括:获取预设的第一延迟参数,所述第一延迟参数包括:第一最大扩散跳数;根据不同扩散范围与所述第一最大扩散跳数的比值,确定所述第一扩散成本函数。
- 根据权利要求2-6任一项所述的方法,其特征在于,根据所述第一扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围,包括:获取预设的一个或多个扩散范围;将使第一扩散收益函数的函数值与第一扩散成本函数的函数值的差值小于或等于预设阈值的扩散范围,确定为所述第一目标扩散范围。
- 根据权利要求1-7任一项所述的方法,其特征在于,所述路由信息包括生存时间信息,根据所述第一目标扩散范围,向所述路由网络发送所述路由信息,包括:根据所述第一目标扩散范围,设置所述生存时间信息;向所述路由网络发送包含所述生存时间信息的所述路由信息。
- 根据权利要求3-8任一项所述的方法,其特征在于,根据所述第一目标扩散范围,向所述路由网络发送所述路由信息,使所述目标路由节点获得所述路由信息之后,还包括:对所述第一目标扩散范围进行更新,获得第二目标扩散范围;根据所述第二目标扩散范围,向所述路由网络发送所述路由信息。
- 根据权利要求9所述的方法,其特征在于,对所述第一目标扩散范围进行更新,获得第二目标扩散范围,包括:根据所述目标路由节点对所述路由信息的响应概率,对第一扩散收益函数进行更新,获得第二扩散收益函数;根据所述第二扩散收益函数与所述第一扩散成本函数的累计差,确定第二扩散效益函数;根据所述第二扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为所述第二目标扩散范围。
- 根据权利要求10所述的方法,其特征在于,根据所述目标路由节点对所述路由信息的响应概率,对所述第一扩散收益函数进行更新,获得第二扩散收益函数,包括:获取预设时间内,响应所述路由信息的目标路由节点个数;将所述目标路由节点个数与所述第一目标扩散范围的比值,确定为第二目标概率;根据所述第二目标概率,确定所述第二扩散收益函数。
- 根据权利要求9所述的方法,其特征在于,对所述第一目标扩散范围进行更新,获得第二目标扩散范围,包括:根据所述路由网络中路由节点的变化情况,对所述第一扩散成本函数进行更新,获得第二扩散成本函数;根据所述第一扩散收益函数与所述第二扩散成本函数的累计差,确定第二扩散效益函数;根据所述第二扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为所述第二目标扩散范围。
- 根据权利要求12所述的方法,其特征在于,根据所述路由网络中路由节点的变化情况,对所述第一扩散成本函数进行更新,获得第二扩散成本函数,包括:获取当前路由网络中路由节点的拓扑结构;根据所述拓扑结构,对第一延迟参数进行更新,获取第二延迟参数;根据所述第二延迟参数,确定所述第二扩散成本函数。
- 一种路由信息扩散装置,其特征在于,所述装置包括:获取模块,用于获取网络计算节点的路由信息;确定模块,用于确定所述路由信息在路由网络中的第一目标扩散范围,其中,所述路由网络包括目标路由节点;发送模块,用于根据所述第一目标扩散范围,向所述路由网络发送所述路由信息,使所述目标路由节点获得所述路由信息。
- 根据权利要求14所述的装置,其特征在于,所述确定模块,具体用于:获取第一扩散效益函数;所述第一扩散效益函数用于表征扩散范围与扩散效益的映射关系;根据所述第一扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围。
- 根据权利要求15所述的装置,其特征在于,所述确定模块,包括:扩散收益子模块,用于获取第一扩散收益函数,所述第一扩散收益函数用于表征不同扩散范围内存在目标路由节点的概率;扩散成本子模块,用于获取第一扩散成本函数,所述第一扩散成本函数用于表征不同扩散范围内路由网络的累积延迟;计算子模块,用于根据所述第一扩散收益函数与所述第一扩散成本函数的累计差,确定所述第一扩散效益函数。
- 根据权利要求16所述的装置,其特征在于,所述路由网络中包括多个路由节点,所述扩散收益子模块,具体用于:获取预设的第一目标概率,所述第一目标概率用于表征所述路由节点为目标路由节点的概率;根据所述第一目标概率,确定所述第一扩散收益函数。
- 根据权利要求16或17所述的装置,其特征在于,所述扩散成本子模块,具体用于:获取预设的第一延迟参数,所述第一延迟参数包括:第一节点间单向网络延迟和第一最大单向网络延迟;根据所述第一延迟参数,确定所述第一扩散成本函数。
- 根据权利要求16或17所述的装置,其特征在于,所述扩散成本子模块,具体用于:获取预设的第一延迟参数,所述第一延迟参数包括:第一最大扩散跳数;根据不同扩散范围与所述第一最大扩散跳数的比值,确定所述第一扩散成本函数。
- 根据权利要求16-19任一项所述的装置,其特征在于,所述确定模块在根据所述第一扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为第一目标扩散范围时,具体用于:获取预设的一个或多个扩散范围;将使第一扩散收益函数的函数值与第一扩散成本函数的函数值的差值小于或等于预设阈值的扩散范围,确定为所述第一目标扩散范围。
- 根据权利要求14-20任一项所述的装置,其特征在于,所述路由信息中包括生存时间信息,所述发送模块,具体用于:根据所述第一目标扩散范围,设置所述生存时间信息;向所述路由网络发送包含所述生存时间信息的路由信息。
- 根据权利要求16-21任一项所述的装置,其特征在于,所述装置还包括:更新模块,所述更新模块用于对所述第一目标扩散范围进行更新,获得第二目标扩散范围;所述发送模块,还用于根据所述第二目标扩散范围,向所述路由网络发送所述路由信息。
- 根据权利要求22所述的装置,其特征在于,所述更新模块,具体用于:根据所述目标路由节点对所述路由信息的响应概率,对所述第一扩散收益函数进行更新,获得第二扩散收益函数;根据所述第二扩散收益函数与所述第一扩散成本函数的累计差,确定第二扩散效益函数;根据所述第二扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为第二目标扩散范围。
- 根据权利要求23所述的装置,其特征在于,所述更新模块在根据目标路由节点对所述路由信息的响应概率,对所述第一扩散收益函数进行更新,获得第二扩散收益函数时,具体用于:获取预设时间内,响应所述路由信息的目标路由节点个数;将所述目标路由节点个数与所述第一目标扩散范围的比值,确定为第二目标概率;根据所述第二目标概率,确定所述第二扩散收益函数。
- 根据权利要求22所述的装置,其特征在于,所述更新模块,具体用于:根据所述路由网络中路由节点的变化情况,对所述第一扩散成本函数进行更新,获得第二扩散成本函数;根据所述第一扩散收益函数与所述第二扩散成本函数的累计差,确定第二扩散效益函数;根据所述第二扩散效益函数,将所述扩散效益的最大值对应的扩散范围,确定为所述第二目标扩散范围。
- 根据权利要求25所述的装置,其特征在于,所述更新模块在根据所述路由网络中路由节点的变化情况,对所述第一扩散成本函数进行更新,获得第二扩散成本函数时,具体用于:获取当前路由网络中路由节点的拓扑结构;根据所述拓扑结构,对第一延迟参数进行更新,获取第二延迟参数;根据所述第二延迟参数,确定所述第二扩散成本函数。
- 一种网络设备,其特征在于,所述网络设备包括:处理器、存储器和收发器;所述处理器用于控制所述收发器收发信号;所述存储器用于存储计算机程序;所述处理器还用于调用并运行所述存储器中存储的计算机程序,使得所述网络设备执行所述权利要求1-13中任一项方法。
- 一种网络装置,其特征在于,包括处理器,所述处理器用于执行计算机程序,以执行所述权利要求1至13中任一项所述的方法;所述网络装置还包括通信接口;所述处理器与所述通信接口连接。
- 一种计算机可读存储介质,其特征在于,包括计算机代码,当其在计算机上运行时,使得计算机执行所述权利要求1至13中任一项所述的方法。
- 一种计算机程序产品,包括程序代码,当计算机运行计算机程序产品时,该程序代码执行所述权利要求1至13中任一项所述的方法。
- 一种芯片,包括处理器,该处理器用于调用并运行存储器中存储的计算机程序,以执行所述权利要求1至13中任一项所述的方法。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010317910.8A CN113542132A (zh) | 2020-04-21 | 2020-04-21 | 路由信息扩散方法、装置和存储介质 |
CN202010317910.8 | 2020-04-21 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021212982A1 true WO2021212982A1 (zh) | 2021-10-28 |
Family
ID=78093897
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2021/076406 WO2021212982A1 (zh) | 2020-04-21 | 2021-02-09 | 路由信息扩散方法、装置和存储介质 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN113542132A (zh) |
WO (1) | WO2021212982A1 (zh) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114205782A (zh) * | 2022-02-18 | 2022-03-18 | 中国电子技术标准化研究院 | 基于云边协同的时延最优缓存和路由方法、装置及系统 |
CN114826930A (zh) * | 2022-04-20 | 2022-07-29 | 山东云海国创云计算装备产业创新中心有限公司 | 一种实现扁平式蝴蝶型网络拓扑的系统及方法 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103248626A (zh) * | 2013-05-07 | 2013-08-14 | 中国科学技术大学 | 一种信息传播方法及系统 |
CN107809363A (zh) * | 2016-08-30 | 2018-03-16 | 腾讯科技(深圳)有限公司 | 一种网络信息传播控制方法和装置 |
US20200082684A1 (en) * | 2017-07-05 | 2020-03-12 | Oneevent Technologies, Inc. | Evacuation system |
CN110932909A (zh) * | 2019-12-05 | 2020-03-27 | 中国传媒大学 | 信息传播预测方法、系统及存储介质 |
-
2020
- 2020-04-21 CN CN202010317910.8A patent/CN113542132A/zh active Pending
-
2021
- 2021-02-09 WO PCT/CN2021/076406 patent/WO2021212982A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103248626A (zh) * | 2013-05-07 | 2013-08-14 | 中国科学技术大学 | 一种信息传播方法及系统 |
CN107809363A (zh) * | 2016-08-30 | 2018-03-16 | 腾讯科技(深圳)有限公司 | 一种网络信息传播控制方法和装置 |
US20200082684A1 (en) * | 2017-07-05 | 2020-03-12 | Oneevent Technologies, Inc. | Evacuation system |
CN110932909A (zh) * | 2019-12-05 | 2020-03-27 | 中国传媒大学 | 信息传播预测方法、系统及存储介质 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114205782A (zh) * | 2022-02-18 | 2022-03-18 | 中国电子技术标准化研究院 | 基于云边协同的时延最优缓存和路由方法、装置及系统 |
CN114205782B (zh) * | 2022-02-18 | 2022-06-07 | 中国电子技术标准化研究院 | 基于云边协同的时延最优缓存和路由方法、装置及系统 |
CN114826930A (zh) * | 2022-04-20 | 2022-07-29 | 山东云海国创云计算装备产业创新中心有限公司 | 一种实现扁平式蝴蝶型网络拓扑的系统及方法 |
CN114826930B (zh) * | 2022-04-20 | 2024-02-23 | 山东云海国创云计算装备产业创新中心有限公司 | 一种实现扁平式蝴蝶型网络拓扑的系统及方法 |
Also Published As
Publication number | Publication date |
---|---|
CN113542132A (zh) | 2021-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3720052B1 (en) | Service identification method and device, and network device | |
WO2020020263A1 (zh) | 一种数据收集方法、设备及系统 | |
WO2021212982A1 (zh) | 路由信息扩散方法、装置和存储介质 | |
WO2021077419A1 (zh) | 用于传输信道状态信息的方法和设备 | |
WO2018228544A1 (zh) | 一种功率确定方法、设备及系统 | |
WO2020125539A1 (zh) | 一种节点设备的选择方法及其相关设备 | |
WO2022121804A1 (zh) | 半异步联邦学习的方法和通信装置 | |
WO2022226713A1 (zh) | 策略确定的方法和装置 | |
TWI531186B (zh) | 多重介面網路裝置與網路封包傳送選擇方法 | |
WO2022063261A1 (zh) | 一种上行参考信号的关联方法及通信装置 | |
CN111740768A (zh) | 一种通信方法及设备 | |
WO2022027345A1 (zh) | 无线通信方法和设备 | |
CN111200821A (zh) | 一种容量规划方法及装置 | |
WO2020114030A1 (en) | Methods, nodes and computer readable media for phr | |
WO2021254211A1 (zh) | 用于无线通信的电子设备和方法、计算机可读存储介质 | |
US11329926B2 (en) | Measuring transmission delay | |
WO2021209058A1 (zh) | 天线选择方法及相关设备 | |
CN110536398B (zh) | 基于多维有效容量的平均时延保障功率控制方法及系统 | |
WO2020155979A1 (zh) | 一种通信方法、网元、系统及存储介质 | |
CN113473505B (zh) | 一种多链路同步接入吞吐量优化方法、系统终端及介质 | |
WO2022155924A1 (zh) | 无线通信方法、终端设备和网络设备 | |
US20240056989A1 (en) | Precoding and power allocation for access points in a cell-free communication system | |
CN114125931A (zh) | 流量调节方法、装置和网络设备 | |
WO2019100808A1 (zh) | 捆绑大小确定方法、用户终端和网络侧设备 | |
WO2024148523A1 (zh) | 信息交互方法以及装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21791751 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21791751 Country of ref document: EP Kind code of ref document: A1 |