WO2022237670A1 - 基于5g的边缘节点调度方法、装置、介质及设备 - Google Patents
基于5g的边缘节点调度方法、装置、介质及设备 Download PDFInfo
- Publication number
- WO2022237670A1 WO2022237670A1 PCT/CN2022/091392 CN2022091392W WO2022237670A1 WO 2022237670 A1 WO2022237670 A1 WO 2022237670A1 CN 2022091392 W CN2022091392 W CN 2022091392W WO 2022237670 A1 WO2022237670 A1 WO 2022237670A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- node
- edge
- target node
- address
- scheduling
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004891 communication Methods 0.000 claims description 32
- 230000036541 health Effects 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 8
- 238000007726 management method Methods 0.000 description 62
- 230000004044 response Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 13
- 238000004458 analytical method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000036449 good health Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0659—Management of faults, events, alarms or notifications using network fault recovery by isolating or reconfiguring faulty entities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0894—Policy-based network configuration management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
Definitions
- Embodiments of the present disclosure relate to but are not limited to a 5G-based edge node scheduling method, device, medium, and equipment.
- the access address of the server obtained by the UPF network element from the access address list according to the data request of the access target application is relatively fixed.
- the server cannot support the service, Unable to adjust flexibly in time.
- the update of the access address list needs to open a corresponding interface on the operator side, and the update steps are relatively cumbersome. Therefore, how to ensure the response success rate of the data request and reduce the complexity of updating the address list has become a technical problem to be solved urgently.
- the present disclosure provides a 5G-based edge node scheduling method, device, medium and equipment.
- a 5G-based edge node scheduling method is provided, and the 5G-based edge node scheduling method is applied to an edge management node, including:
- the UPF network element before receiving the data request forwarded by the UPF network element and carrying the target node identifier, it further includes:
- Said generating a parsing request for said target node identification includes:
- a 5G-based edge node scheduling method is provided, which is applied to scheduling nodes including:
- the resolution request sent by the edge management node for the target node identifier is generated by the edge management node according to the data request carrying the target node identifier, and the data request is sent by the UPF network element according to the service provider's
- the network address IP segment corresponding to the autonomous domain is forwarded to the edge management node;
- the target node identifier determine the IP address of the target node corresponding to the target node identifier
- the determining the IP address of the target node corresponding to the target node ID according to the target node ID includes:
- the edge node list after detecting the health values of the edge nodes in the edge node list, it further includes:
- the edge management node before receiving the parsing request for the target node identifier sent by the edge management node, it further includes:
- Route announcements are made to the public network according to the network address IP segment corresponding to the autonomous domain of the service provider.
- the method before determining the IP address of the target node corresponding to the target node ID according to the target node ID, the method further includes:
- the IP address of the newly accessed edge node is added to the IP address record of the corresponding network address IP segment.
- a 5G-based edge node scheduling device is provided, and the 5G-based edge node scheduling device is applied to an edge management node, including:
- the data request receiving module receives the data request forwarded by the UPF network element and carries the target node identifier, and the data request is forwarded by the UPF network element according to the network address IP segment corresponding to the autonomous domain of the service provider;
- a scheduling module configured to generate a parsing request for the target node identifier, and send the parsing request to a scheduling node;
- the scheduling result receiving module is configured to receive the IP address of the target node fed back by the scheduling node, and the target node is determined by the scheduling node according to the target node identifier;
- the first feedback module is configured to feed back the IP address of the target node to the UPF network element.
- a 5G-based edge node scheduling device which is applied to a scheduling node, including:
- the parsing request receiving module is configured to receive a parsing request for the target node identifier sent by the edge management node, the parsing request is generated by the edge management node according to the data request carrying the target node identifier, and the data request is generated by The UPF network element forwards to the edge management node according to the network address IP segment corresponding to the service provider's autonomous domain;
- the parsing module is configured to determine the IP address of the target node corresponding to the target node ID according to the target node ID;
- the second feedback module is configured to feed back the IP address of the target node to the edge management node.
- a computer-readable storage medium on which a computer program is stored, and when the computer program is executed, the steps of the above method are implemented.
- a computer device including a processor, a memory, and a computer program stored on the memory, and the processor implements the steps of the above method when executing the computer program.
- This disclosure provides a 5G-based edge node scheduling method.
- the edge management node receives the data request carrying the target node ID forwarded by the UPF network element, generates a resolution request for the target node ID, and sends the resolution request to the scheduling node.
- the node determines the IP address of the target node, so that when the client requests data through the UPF network element, the scheduling node of the service provider selects the target node to provide services for the client.
- the server fails, the access address can be adjusted flexibly in time.
- the troubleshooting server ensures a timely response; and the update of the access address list does not require the corresponding interface to be opened on the 5G operator side, ensuring the safety and reliability of the 5G communication network system.
- Fig. 1 is a flowchart showing a 5G-based edge node scheduling method according to an exemplary embodiment.
- Fig. 2 is a flowchart showing a 5G-based edge node scheduling method according to an exemplary embodiment.
- Fig. 3 is a flowchart showing a 5G-based edge node scheduling method according to an exemplary embodiment.
- Fig. 4 is a schematic diagram of a scheduling method of a 5G-based edge node scheduling method according to an exemplary embodiment of the present disclosure.
- Fig. 5 is a block diagram of a 5G-based edge node scheduling device according to an exemplary embodiment.
- Fig. 6 is a block diagram of a 5G-based edge node scheduling device according to an exemplary embodiment.
- Fig. 7 is a block diagram of a computer device according to an exemplary embodiment.
- the UPF User Plane Function
- SMF Session Management Function, session management function
- user plane function network element offload strategy, offload the corresponding access requests in the communication network to the MEC (Mobile Edge Computing, edge computing technology) edge cloud, and improve the data response speed.
- MEC Mobile Edge Computing, edge computing technology
- the MEC edge cloud needs to pre-set the access address of each target application, so that the access address obtained by the UPF network element to access the target application is relatively fixed. Once a node in the data network fails or the interface is abnormal, the UPF network element cannot The timely adjustment of the access address of the target application will inevitably affect the response speed of the data, and even cause the failure to obtain the target data, affecting the user experience.
- the present disclosure provides a 5G-based edge node scheduling method.
- Fig. 1 shows a flowchart of a 5G-based edge node scheduling method according to an exemplary embodiment of the present disclosure.
- the 5G-based edge node scheduling method is applied to the edge management node.
- the 5G-based edge node scheduling method includes at least step S11 to step S14, which are described in detail as follows:
- step S11 the data request carrying the target node identifier forwarded by the UPF network element is received, and the data request is forwarded by the UPF network element according to the IP segment of the network address corresponding to the autonomous domain of the service provider.
- the target node may be an edge node that provides the data service required by the user (for example, the data service may be data storage, data acquisition, or application program support, etc.). It should be noted that an edge node can provide a single data service or multiple data services, so the number of edge nodes can be one, or any number of two or more, which is not specifically limited in this disclosure .
- the target node identifier may be identification information associated with the target node, and the corresponding target node can be determined according to the target node identifier. It should be noted that the target node identifier described in this disclosure is not only able to uniquely determine a certain edge node, but also can be the common attribute information of multiple edge nodes, such as having the same IP segment, corresponding to the same domain name, Be in the same region or support the same data service, etc.
- the data request may be information used to request a corresponding data service, such as an application access request.
- the user may click a specific area in the terminal interface (such as a "confirm access" button, etc.) to generate a corresponding data request, and the data request may include the target node identifier.
- the terminal device may transmit the data request in the 5G communication network, so as to determine the target node corresponding to the target node identifier.
- the client is connected to the 5G network through the base station, and the data request is sent to a UPF (User Plane Function, user plane function) network element.
- the 5G operator sets the UPF offloading strategy through the SMF (Session Management Function, session management function) network element in advance.
- the UPF network element can forward the data request carrying the target node identifier to the corresponding edge management node, and forward the data request without the target node identifier to the 5G core network.
- the network service provider may cooperate with the 5G communication network operator to realize the integration of the communication network and the data network.
- the target node identifier can be the domain name, IP segment, and region where the client is located in the preset edge node service in the edge management node, or it can be the type of content stored in the edge node, the function it has, and so on.
- the service provider sets up edge nodes in the IP segment of the network address corresponding to the autonomous domain to provide services for the domain name A.
- the 5G operator configures the UPF distribution policy through the SMF network element in the 5G communication network.
- the UPF receives the data request, when the data request carries the target node identifier "domain name A"
- the UPF determines that the access request is from the network corresponding to the service provider's autonomous domain.
- the edge node in the IP segment of the address provides services, so the access request is forwarded to the edge management node.
- step S12 a resolution request for the target node identifier is generated, and the resolution request is sent to the scheduling node.
- the resolution request may be information for requesting to determine the IP address of the target node.
- the parsing request may include the target node identifier, so that the IP address of the corresponding target node may be determined according to the target node identifier included in the parsing request.
- the scheduling node may be a service provider's network device, and the scheduling node may be a processing node with a node allocation function. After receiving the resolution request, it may determine the IP address of the corresponding target node according to the target node identifier contained in the resolution request. , and feed back the IP address of the target node to the edge management node. It should be understood that one target node ID may correspond to multiple edge nodes, therefore, the scheduling node may determine multiple edge nodes corresponding to the target node ID according to the target node ID, and then select one of the multiple edge nodes from the multiple edge nodes - Feedback as a target node, for example, the target node can be determined according to the optimal route or node health value.
- the edge management node generates a resolution request for the target node ID according to the target node ID in the received data request, and sends the resolution request to the scheduling node, and the scheduling node parses out the target node IP address. For example, if the target node is identified as a domain name, a resolution request for the domain name is generated, so that the scheduling node determines an edge node serving the domain name. If the target node is identified as the area where the client is located, a resolution request for the area is generated, so that the scheduling node determines the edge node serving the area.
- the target node If the target node is identified as a combination of the domain name and the area where the client is located, generate a resolution request for the domain name carrying the area information of the client, so that the scheduling node can determine the edge that serves the domain name accessed by the client in the area node.
- step S13 the IP address of the target node fed back by the scheduling node is received, and the target node is determined by the scheduling node according to the target node identifier.
- the scheduling node determines the target node according to the received resolution request, and the target node corresponds to the target node identifier included in the resolution request, and then feeds back the IP address of the target node to the edge management node.
- the resolution request is a resolution request for the access area
- the scheduling node can determine the edge node in the same area as the target node according to the area where the client is located, and feed back the IP address of the target node to the edge management node.
- step S14 the IP address of the target node is fed back to the UPF network element.
- the edge management node may feed back the IP address of the target node fed back by the scheduling node to the UPF network element, and the UPF network element sends the IP address of the target node to the client used by the user, So that the client can establish a connection with the target node, so as to obtain the corresponding data service.
- the edge management node generates a parsing request for the target node identifier in the data request, and the scheduling node parses and determines the IP address of the target node.
- Scheduling nodes can be scheduled in the existing edge nodes, from which the target node can be determined, solving the problem that the access address of the server accessing the target application in the existing 5G communication network is relatively fixed, ensuring the robustness of the service and the response to the data request Success rate.
- the UPF network element forwards according to the network address IP segment corresponding to the service provider's autonomous domain, without modifying the specific access address list in the communication network, and without the need for the 5G operator to open the address interface, which not only ensures the safety and reliability of the 5G communication network system, At the same time, the trouble of updating the address list is also reduced. In addition, the transmission of this part of data does not need to pass through the 5G core network, which improves the data response speed and reduces the occupation of 5G core network resources.
- the 5G-based edge node scheduling method before receiving the data request forwarded by the UPF network element and carrying the target node identifier, the 5G-based edge node scheduling method further includes:
- the service provider may be a CDN service provider or an edge cloud computing service provider, and they may have a large number of edge nodes for caching data in the network/computing and providing target data to users nearby.
- a service provider can have its own autonomous domain, which has a corresponding network address IP segment. Before providing network services, it is necessary to advertise the routes of the autonomous domain and its corresponding network address IP segment to establish connections with devices in other domains.
- 5G communication network operators cooperate with network service providers, and can use a large number of edge nodes of service providers as MEC edge clouds to provide high-speed data services for end users accessing 5G communication networks.
- 5G communication network operators need to obtain the IP segment of the network address corresponding to the autonomous domain of the service provider, and register the IP segment of the network address corresponding to the autonomous domain of the service provider into the 5G communication network, for example, add the IP segment of the network address to the 5G communication record In the table, the IP address in the IP segment of the network address can be accessed by the 5G communication network.
- Edge nodes with IP addresses in the network address IP segment can provide MEC edge cloud services for the 5G communication network, and clients can obtain data from these edge nodes.
- Said generating a parsing request for said target node identification includes:
- the edge management node may obtain the IP address of the scheduling node system, and when generating the resolution request, set the resolution address corresponding to the resolution request as the IP address of the scheduling node. Therefore, the edge management node can send the analysis request to the scheduling node for analysis, and the service provider side can perform the analysis, thereby improving the flexibility of analysis.
- Fig. 2 shows a flowchart of a 5G-based edge node scheduling method according to another exemplary embodiment of the present disclosure.
- the 5G-based edge node scheduling method is applied to the scheduling node, and the 5G-based edge node scheduling method includes at least step S21 to step S23, which are described in detail as follows:
- step S21 the resolution request for the target node identifier sent by the edge management node is received, the resolution request is generated by the edge management node according to the data request carrying the target node identifier, and the data request is sent by the UPF network
- the element is forwarded to the edge management node according to the IP segment of the network address corresponding to the autonomous domain of the service provider.
- the scheduling node receives the parsing request for the target node identifier sent by the edge management node.
- step S22 the IP address of the target node corresponding to the target node identifier is determined according to the target node identifier.
- the IP address of the target node corresponding to the target node identifier is resolved by the scheduling node.
- the scheduling node may search for an edge node corresponding to the target node ID according to the target node ID, and then determine the IP address of the corresponding target node from the edge node. For example, if the target node is identified as a domain name, the scheduling node determines that the edge node serving the domain name is the target node; if the target node is identified as the area where the client is located, the scheduling node determines that the edge node serving the area is the target node.
- step S23 the IP address of the target node is fed back to the edge management node.
- the scheduling node feeds back the IP address of the target node to the edge management node.
- the edge management node feeds back the IP address of the target node to the client according to the path of receiving the request, so that the client can connect with the target node and obtain the data content.
- the scheduling node receives the resolution request generated by the edge management node for the target node identifier in the data request, parses the resolution request, and determines the IP address of the target node. Scheduling nodes can be scheduled in the existing edge nodes, from which the target node can be determined, solving the problem that the access address of the server accessing the target application in the existing 5G communication network is relatively fixed, ensuring the robustness of the service and the response to the data request Success rate.
- the service provider can flexibly determine the target node according to the actual situation, without 5G updating the address list, and 5G operators do not need to open the address interface, which not only ensures the safety and reliability of the 5G communication network system, but also reduces the cumbersome update of the address list.
- the target node responds to the data request, and the transmission of the data request and response data does not need to pass through the 5G core network, which improves the data response speed and reduces the occupation of 5G core network resources.
- the 5G-based edge node scheduling method before receiving the parsing request for the target node identifier sent by the edge management node, the 5G-based edge node scheduling method further includes:
- Route announcements are made to the public network according to the network address IP segment corresponding to the autonomous domain of the service provider.
- the service provider in order to enable the IP address in the IP segment of the network address corresponding to the service provider’s autonomous domain to be accessible by the 5G communication network, the service provider needs to issue routing announcements and broadcasts so that the 5G communication network can obtain the service provider’s autonomous domain The corresponding network address IP segment, and register the network address IP segment corresponding to the service provider's autonomous domain into the 5G communication network. Then, the edge node with the IP address in the IP segment of the network address corresponding to the service provider's autonomous domain can be discovered by other devices in the network and establish a connection.
- Fig. 3 shows a flowchart of a 5G-based edge node scheduling method according to another exemplary embodiment of the present disclosure.
- determining the IP address of the target node includes steps S221 to S223, which are described in detail as follows:
- step S221 according to the target node identifier, an edge node list corresponding to the target node identifier is obtained.
- the target node identifier may be identification information associated with the target node, and an edge node associated with the target node identifier may be determined according to the target node identifier. For example, when the target node is a domain name, it may be determined that an edge node serving the domain name is an associated edge node. When there are many clients accessing the domain name, multiple edge nodes can be set to serve the domain name at the same time. At this time, multiple edge nodes can be obtained according to the target node ID. In order to facilitate subsequent determination of the target edge node from multiple edge nodes, you can Establish an edge node list for the IP addresses of multiple edge nodes serving the same domain name, and establish a correspondence between the domain name and the edge node list. When the scheduling node receives a data request for a domain name, it can quickly determine the corresponding edge node list.
- step S222 the health values of the edge nodes in the edge node list are detected, and edge nodes whose health values are greater than or equal to a predetermined threshold are selected as candidate edge nodes.
- the scheduling node can detect the edge nodes in the edge node list one by one by traversing the IP addresses of the edge node list, and detect the health value of each edge node.
- the health value of the edge node can be numerical information used to represent the service capability of the edge node, which can be determined according to the business indicators of the edge node: such as throughput, response time, concurrency, business success rate and other factors, for example, monitoring the edge node unit
- the value of various factors such as throughput, concurrency, response time, and business success rate within a certain period of time is compared with the preset value, and the score is calculated comprehensively as the health value of the edge node; it can also be based on the resources of the edge node Indicators: determine the consumption of CPU, memory, I/O and other resources, for example, detect the consumption of CPU, memory, I/O and other resources of the edge node, calculate the remaining resource score, and use it as the health value of the edge node; or The health value determined according to the business index and
- presetting the health value threshold only the edge nodes whose health value is greater than the threshold can provide good service, and the edge nodes whose health value is greater than the predetermined threshold are considered as candidate edge nodes.
- step S223 the edge node having the optimal route with the edge management node is determined as the target node from the candidate edge nodes.
- an edge node can be randomly selected as the target node among the candidate edge nodes, and the IP address of the target node is fed back to the client, so that the client can establish a connection with the target node, And the target node provides services for the client.
- the scheduling node in order to further improve the response speed, the scheduling node further performs route detection on the candidate edge nodes, and takes the edge node having the optimal route with the edge management node as the target node. For example, the edge node with the least time-consuming information transmission can be determined as the target node, and so on.
- Selecting the target node through the above method can not only ensure that the parsed target node has good health and can provide services for the client, but also has the optimal route between the target node and the edge management node, and can respond with the fastest speed. , to serve clients.
- the edge node list after detecting the health values of the edge nodes in the edge node list, it further includes:
- the failed edge node may be added to the failure list.
- the IP address of the failed edge node may be deleted from the edge node list.
- scheduling nodes to resolve it will traverse the edge node list and determine the candidate edge nodes. After deleting the IP address of the failed edge node from the edge node list, the failed edge node will no longer be resolved; or,
- the scheduling node traverses the IP addresses of the edge node list, it compares the edge node list with the fault list, and skips the IP addresses in the fault list, so as to ensure that the faulty edge nodes will not be resolved again, and the terminal will not request the faulty ones. edge nodes.
- timely adjustments are made on the service provider side without any adjustment on the operator side, which ensures the flexibility and timeliness of scheduling.
- the target node ID before determining the IP address of the target node corresponding to the target node ID according to the target node ID, it further includes:
- the IP address of the newly accessed edge node is added to the IP address record of the corresponding network address IP segment.
- the service provider configures a new edge node
- it in order to enable the new edge node to provide services for users using the 5G network, it only needs to set the IP address of the new edge node as the network address IP segment
- the IP address of the newly added edge node can be accessed by the 5G communication network.
- the IP address of the newly added edge node needs to be added to the edge node list. The above process does not require any adjustments by the 5G operator, eliminating the need to modify the operator's address list multiple times.
- Fig. 4 shows a schematic diagram of a scheduling method of a 5G-based edge node scheduling method according to an exemplary embodiment of the present disclosure.
- 5G operator A has established a 5G network in a certain city to provide 5G services to citizens.
- Operator A cooperates with service provider B, and uses service provider B's edge node cluster as an EMC edge cloud (46).
- Service provider B sets up multiple edge nodes in the city, where edge node 1 - edge node 10 provide services for domain name a.
- Operator A divides the city into two areas, and sets the edge management node (44); corresponding to the two areas, sets the edge management node 1 (441) in area 1, sets the access address list, and in the access address list Including edge node 1 and edge node 2; set an edge management node (442) in area 2, set an access address list, and the access address list includes edge node 5 and edge node 6.
- the user (411) in area 1 accesses the 5G network through the 5G base station and initiates a data request.
- the UPF network element (43) receives the data request, if the domain name of the data request is not the domain name served by the edge node, the data request is forwarded to the 5G core network (47), and the user communicates with the source station or the public network through the 5G core network (47) (48) Connect and get data. If the domain name of the data request is the domain name served by the edge node, forward the data request to the edge management node (44).
- the target node identifier carried in the request contains area information, indicating that it comes from area 1, the user's data request is forwarded to edge management node 1 (441), and edge management node 1 (441) determines that the edge node belonging to area 1 1 or edge node 2 to respond to user access requests.
- edge management node 1 fails, operator A needs to modify the access address list of the edge management node 1, which cannot be adjusted in time. In this process, a large number of users will be unable to access.
- operator A After negotiation between service provider B and operator A, operator A registers the network address IP segment corresponding to service provider B's autonomous domain to the 5G communication network, and sets the network address IP segment corresponding to service provider B's autonomous domain for edge nodes. IP address, so that edge nodes with IP addresses in this IP segment can provide edge cloud services for users of the 5G communication network. At the same time, the IP address of the scheduling node (45) is obtained.
- edge management node 1 Assuming that edge node 1 and edge node 5 fail, edge management node 1 generates a resolution request for domain name a after receiving a data request from a user (411) in area 1 to access domain name a, and sends the resolution request to service provider B’s Scheduling node (45), the scheduling node (45) queries the list of edge nodes according to the domain name a in the request, and determines that the domain name a is provided by the edge node 1-edge node 10, and the scheduling node (45) successively sends the edge node 1-edge Node 10 performs detection, wherein the health values of edge node 3, edge node 4, edge node 6, and edge node 7 are greater than the preset threshold, and the scheduling node further detects the route from the above edge node to edge management node 1, and finally determines The route from edge node 4 to edge management node 1 is the shortest, and edge node 4 is selected as the target node to provide services to users (411) in area 1.
- edge node 1 and edge node 5 are added to the failure list, and edge node 1 and edge node 5 are deleted from the edge node list.
- the edge management node 2 (442) When the edge management node 2 (442) receives a request from a user (412) in area 2 to access domain name a, it generates a resolution request for domain name a, and sends the resolution request to the scheduling node (45) of service provider B, and the scheduling node (45) According to the domain name a in the request, query the list of edge nodes, and determine that there are 8 edge nodes from edge node 2 to edge node 4, edge node 6 to edge node 10 to provide services, and the scheduling node sequentially performs the above-mentioned 8 edge nodes Detection, wherein the health values of edge node 3, edge node 4, edge node 6, and edge node 7 are greater than a preset threshold, and the scheduling node (45) further detects the route from the edge node to the edge management node 2 (442) Finally, it is determined that the route from edge node 7 to edge management node 2 (442) is the shortest, and edge node 7 is selected as the target
- the operator registers the IP segment of the service provider's network address to the 5G communication network, and can use a large number of edge nodes of the service provider as MEC edge cloud to provide services, speed up the data response speed, and at the same time, the scheduling node of the service provider provides analysis Service, when the edge node fails, the intelligent scheduling node can adjust the analysis result in time, and the operator side does not need to open the corresponding interface.
- This method does not need to adjust the settings of the 5G core network, there is no security risk on the operator side, and the service is guaranteed to be stable; the edge node with the shortest route can be selected to provide services, and the response timeliness is improved.
- Fig. 5 shows a block diagram of a 5G-based edge node scheduling device according to an exemplary embodiment of the present disclosure.
- the 5G-based edge node scheduling device is applied to the edge management node, including: a data request receiving module 501 , a scheduling module 502 , a scheduling result receiving module 503 , and a first feedback module 504 .
- the data request receiving module 501 is configured to receive a data request carrying a target node identifier forwarded by a UPF network element, where the data request is forwarded by the UPF network element according to the IP segment of the network address corresponding to the autonomous domain of the service provider.
- the scheduling module 502 is configured to generate a resolution request for the target node identifier, and send the resolution request to the scheduling node.
- the scheduling result receiving module 503 is configured to receive the IP address of the target node fed back by the scheduling node, and the target node is determined by the scheduling node according to the target node identifier.
- the first feedback module 504 is configured to feed back the IP address of the target node to the UPF network element.
- Scheduling module 502 is also configured to:
- Fig. 6 shows a block diagram of a 5G-based edge node scheduling device according to an exemplary embodiment of the present disclosure.
- the 5G-based edge node scheduling device is applied to a scheduling node, including: an analysis request receiving module 601 , an analysis module 602 , and a second feedback module 603 .
- the resolution request receiving module 501 is configured to receive a resolution request sent by an edge management node for a target node identifier, the resolution request is generated by the edge management node according to a data request carrying the target node identifier, and the data The request is forwarded by the UPF network element to the edge management node according to the IP segment of the network address corresponding to the autonomous domain of the service provider.
- the parsing module 502 is configured to determine the IP address of the target node corresponding to the target node identifier according to the target node identifier.
- the second feedback module 503 is configured to feed back the IP address of the target node to the edge management node.
- the parsing module 502 determines the IP address of the target node according to the target node identifier, including:
- the detection of the health values of the edge nodes in the edge node list it also includes:
- the IP address of the newly accessed edge node is added to the IP address record of the corresponding network address IP segment.
- Fig. 7 shows a block diagram of a computer device 700 for 5G scheduling according to an exemplary embodiment of the present disclosure.
- computer device 700 may be provided as a server.
- a computer device 700 includes a processor 701 , and the number of processors can be set to one or more as required.
- the computer device 700 also includes a memory 702 for storing instructions executable by the processor 701 , such as application programs.
- the number of memories can be set to one or more as required. It can store one or more applications.
- the processor 701 is configured to execute instructions to execute the above-mentioned 5G-based edge node scheduling method.
- the embodiments of the present disclosure may be provided as a method, an apparatus (device), or a computer program product. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein.
- Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data , including but not limited to RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, tape, magnetic disk storage or other magnetic storage devices, or can be used in Any other medium, etc. that stores desired information and can be accessed by a computer.
- communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .
- These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions
- the device realizes the function specified in one or more processes of the flowchart and/or one or more blocks of the block diagram
- a 5G-based edge node scheduling method receives the data request carrying the target node ID forwarded by the UPF network element, generates a resolution request for the target node ID, and sends the resolution request to the scheduling node.
- the scheduling node determines the IP address of the target node, so that when the client requests data through the UPF network element, the scheduling node of the service provider selects the target node to provide services for the client.
- the access address can be adjusted flexibly in time , the troubleshooting server to ensure timely response; and the update of the access address list does not require the corresponding interface to be opened on the 5G operator side to ensure the safety and reliability of the 5G communication network system.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
本公开是关于一种基于5G的边缘节点调度方法、装置、介质及设备,基于5G的边缘节点调度方法应用于边缘管理节点,包括:接收UPF网元转发的携带有目标节点标识的数据请求;生成针对目标节点标识的解析请求,并将解析请求发送至调度节点;接收由调度节点反馈的目标节点的IP地址,目标节点为调度节点根据目标节点标识确定;向UPF网元反馈所述目标节点的IP地址。
Description
本公开基于2021年05月14日提交中国专利局、申请号为202110529396.9,发明名称为“基于5G的边缘节点调度方法、装置、介质及设备”的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本公开作为参考。
本公开实施例涉及但不限于一种基于5G的边缘节点调度方法、装置、介质及设备。
相关技术中,数据在5G通信网络中传输时,UPF网元根据访问目标应用的数据请求从接入地址列表中获取到的服务端的接入地址相对固定,然而当该服务端无法支持服务时,无法及时灵活调整。且接入地址列表的更新需要运营商侧开放相应的接口,更新步骤较为繁琐。由此,如何保证数据请求的响应成功率,且减少地址列表更新的繁琐成为了亟待解决的技术问题。
发明内容
以下是对本公开详细描述的主题的概述。本概述并非是为了限制权利要求的保护范围。
为克服相关技术中存在的问题,本公开提供一种基于5G的边缘节点调度方法、装置、介质及设备。
根据本公开的第一方面,提供一种基于5G的边缘节点调度方法,基于5G的边缘节点调度方法应用于边缘管理节点,包括:
接收UPF网元转发的携带有目标节点标识的数据请求,所述数据请求为所述UPF网元根据服务商的自治域对应的网络地址IP段进行转发;
生成针对所述目标节点标识的解析请求,并将所述解析请求发送至调度节 点;
接收由所述调度节点反馈的目标节点的IP地址,所述目标节点为所述调度节点根据所述目标节点标识确定;
向所述UPF网元反馈所述目标节点的IP地址。
在本公开一些示例性的实施例中,在所述接收UPF网元转发的携带有目标节点标识的数据请求之前,还包括:
获取服务商的自治域对应的网络地址IP段;
将所述服务商的自治域对应的网络地址IP段注册到5G通信网络。
在本公开一些示例性的实施例中,
所述生成针对所述目标节点标识的解析请求,包括:
获取所述调度节点的IP地址;
生成针对所述目标节点标识的解析请求,其中,所述解析请求的解析地址为所述调度节点的IP地址。
根据本公开的第二方面,提供一种基于5G的边缘节点调度方法,应用于调度节点包括:
接收边缘管理节点发送的针对目标节点标识的解析请求,所述解析请求为所述边缘管理节点根据携带有所述目标节点标识的数据请求而生成,所述数据请求由UPF网元根据服务商的自治域对应的网络地址IP段转发至所述边缘管理节点;
根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址;
将所述目标节点的IP地址反馈给所述边缘管理节点。
在本公开一些示例性的实施例中,所述根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址,包括:
根据所述目标节点标识,获取与所述目标节点标识对应的边缘节点列表;
探测所述边缘节点列表中的边缘节点的健康值,将所述健康值大于或等于预定阈值的边缘节点识别为备选边缘节点;
从所述备选边缘节点中确定与所述边缘管理节点之间具有最优路由的备选边缘节点为目标节点。
在本公开一些示例性的实施例中,在所述探测所述边缘节点列表中的边缘节点的健康值之后,还包括:
将所述健康值小于所述预定阈值的边缘节点加入故障列表。
在本公开一些示例性的实施例中,在所述接收边缘管理节点发送的针对目标节点标识的解析请求之前,还包括:
根据所述服务商的自治域对应的网络地址IP段向公共网络进行路由宣告。
在本公开一些示例性的实施例中,在所述根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址之前,还包括:
当检测到新的边缘节点接入时,将新接入的所述边缘节点的IP地址添加至对应的网络地址IP段的IP地址记录中。
根据本公开的第三方面,提供一种基于5G的边缘节点调度装置,基于5G的边缘节点调度装置应用于边缘管理节点,包括:
数据请求接收模块,接收UPF网元转发的携带有目标节点标识的数据请求,所述数据请求为所述UPF网元根据服务商的自治域对应的网络地址IP段进行转发;
调度模块,设置为生成针对所述目标节点标识的解析请求,并将所述解析请求发送至调度节点;
调度结果接收模块,设置为接收由所述调度节点反馈的目标节点的IP地址,所述目标节点为所述调度节点根据所述目标节点标识确定;
第一反馈模块,设置为向所述UPF网元反馈所述目标节点的IP地址。
根据本公开的第四方面,提供一种基于5G的边缘节点调度装置,应用于调度节点,包括:
解析请求接收模块,设置为接收边缘管理节点发送的针对目标节点标识的解析请求,所述解析请求为所述边缘管理节点根据携带有所述目标节点标识的数据请求而生成,所述数据请求由UPF网元根据服务商的自治域对应的网络地 址IP段转发至所述边缘管理节点;
解析模块,设置为根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址;
第二反馈模块,设置为将所述目标节点的IP地址反馈给所述边缘管理节点。
根据本公开的第五方面,提供一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序被执行时实现如上所述方法的步骤。
根据本公开的第六方面,提供一种计算机设备,包括处理器、存储器和存储于所述存储器上的计算机程序,所述处理器执行所述计算机程序时实现如上所述方法的步骤。
本公开通过提供一种基于5G的边缘节点调度方法,边缘管理节点接收UPF网元转发的携带有目标节点标识的数据请求,针对目标节点标识生成解析请求,将解析请求发送至调度节点,由调度节点确定目标节点的IP地址,以实现客户端通过UPF网元请求数据时,由服务商的调度节点选择目标节点为客户端提供服务,当服务端出现故障时,能够及时灵活调整接入地址,排除故障的服务端,保证响应及时;且接入地址列表的更新不需要5G运营商侧开放相应的接口,保障5G通信网络***安全可靠。
应当理解的是,以上的一般描述和后文的细节描述仅是示例性和解释性的,并不能限制本公开。在阅读并理解了附图和详细描述后,可以明白其他方面。
构成本公开的一部分的附图用来提供对本公开的进一步理解,本公开的示例性实施例及其说明用于解释本公开,并不构成对本公开的不当限定。在附图中:
图1是根据一示例性实施例示出的一种基于5G的边缘节点调度方法的流程图。
图2是根据一示例性实施例示出的一种基于5G的边缘节点调度方法的流程图。
图3是根据一示例性实施例示出的一种基于5G的边缘节点调度方法的流程 图。
图4是根据本公开一示例性实施例的基于5G的边缘节点调度方法的调度示意图。
图5是根据一示例性实施例示出的一种基于5G的边缘节点调度装置的框图。
图6是根据一示例性实施例示出的一种基于5G的边缘节点调度装置的框图。
图7是根据一示例性实施例示出的一种计算机设备的框图。
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本公开一部分实施例,而不是全部的实施例。基于本公开中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本公开保护的范围。需要说明的是,在不冲突的情况下,本公开中的实施例及实施例中的特征可以相互任意组合。
随着5G时代的到来,在5G网络中,数据传输速度大幅提高,以通信网SMF/架构为例,当前技术中,通过SMF(Session Management Function,会话管理功能)网元设置UPF(User Plane Function,用户面功能)网元分流策略,将通信网络中对应的访问请求分流至MEC(Mobile Edge Computing,边缘计算技术)边缘云,提高数据响应速度。然而,MEC边缘云需要预先设置好各个目标应用的接入地址,导致UPF网元获取到访问目标应用的接入地址相对固定,一旦数据网络中的节点发生故障或者接口异常,UPF网元无法对目标应用的接入地址进行及时调整,势必影响数据的响应速度,甚至造成无法获取目标数据,影响用户体验。
为解决以上问题,本公开提供一种基于5G的边缘节点调度方法。
图1示出了根据本公开一示例性实施例的基于5G的边缘节点调度方法的流程图。参考图1,基于5G的边缘节点调度方法应用于边缘管理节点,该基于5G的边缘节点调度方法至少包括步骤S11至步骤S14,详细介绍如下:
在步骤S11中,接收UPF网元转发的携带有目标节点标识的数据请求,所述数据请求为所述UPF网元根据服务商的自治域对应的网络地址IP段进行转发。
其中,目标节点可以是提供用户所需的数据服务(例如数据服务可以为数据存储、数据获取或者应用程序支持等)的边缘节点。需要说明的,一个边缘节点可以提供单一数据服务,也可以提供多种数据服务,所以边缘节点的数量可以是一个,也可以是两个或者两个以上的任意数量,本公开对此不作特殊限定。
目标节点标识可以是与目标节点相关联的标识信息,根据目标节点标识即可确定对应的目标节点。需要说明的,本公开所述的目标节点标识并不仅是可以唯一确定某一边缘节点,其也可以是多个边缘节点所具有的共同属性信息,例如具有相同的IP段、对应于同一域名、处于同一区域或者支持同一数据服务等等。
数据请求可以是用以请求对应数据服务的信息,如可以是应用访问请求。在一示例中,用户可以点击终端界面中的特定区域(例如“确认访问”按键等)以生成对应的数据请求,该数据请求可以包含目标节点标识。终端设备可以将该数据请求在5G通信网络中进行传输,以确定与该目标节点标识对应的目标节点。
在本公开一示例性实施例中,客户端通过基站连接到5G网络,数据请求发送到UPF(User Plane Fuction,用户面功能)网元。5G运营商预先通过SMF(Session Management Function,会话管理功能)网元设置UPF分流策略。根据该分流策略,UPF网元可以将携带有目标节点标识的数据请求转发至对应的边缘管理节点,将未携带目标节点标识的数据请求转发到5G核心网络。需要说明的,为了实现本公开提供的基于5G的边缘节点调度方法,网络服务商可以与5G通信网运营商进行合作,以实现通信网与数据网的融合。
目标节点标识可以是边缘管理节点中预设的边缘节点服务的域名、IP段、客户端所处区域,也可以是边缘节点所存储的内容的类型、所具有的功能等等。例如,服务商设置自治域对应的网络地址IP段内的边缘节点,用于对域名A提供服务。5G运营商通过5G通信网中的SMF网元配置UPF分流策略,UPF接收到数据请求,当数据请求中携带目标节点标识“域名A”,UPF确定该访问请求由 服务商的自治域对应的网络地址IP段中的边缘节点提供服务,所以将访问请求转发到边缘管理节点。
在步骤S12中,生成针对所述目标节点标识的解析请求,并将所述解析请求发送至调度节点。
其中,解析请求可以是用以请求确定目标节点的IP地址的信息。在一示例中,该解析请求中可以包含目标节点标识,从而可以根据解析请求所包含的目标节点标识确定对应的目标节点的IP地址。
调度节点可以是服务商的网络设备,调度节点可以是具有节点分配功能的处理节点,其可以在接收到解析请求之后,根据解析请求中所包含的目标节点标识,确定对应的目标节点的IP地址,并将该目标节点的IP地址向边缘管理节点进行反馈。应该理解的,一个目标节点标识可以对应于多个边缘节点,因此,调度节点可以根据该目标节点标识,确定与该目标节点标识对应的多个边缘节点,再从该多个边缘节点中选择其一作为目标节点进行反馈,例如可以根据最优路由或者节点健康值确定目标节点等等。
在本公开一示例性实施例中,边缘管理节点根据接收到的数据请求中的目标节点标识,生成针对目标节点标识的解析请求,并将解析请求发送至调度节点,由调度节点解析出目标节点的IP地址。例如,如果目标节点标识为域名,则生成针对域名的解析请求,以使调度节点确定服务于该域名的边缘节点。如果目标节点标识为客户端所处区域,则生成针对该区域的解析请求,以使调度节点确定服务于该区域的边缘节点。如果目标节点标识为域名和客户端所处区域的组合,则生成携带客户端所处区域信息的针对域名的解析请求,以使调度节点确定服务于该区域客户端所访问的该域名的的边缘节点。
在步骤S13中,接收由所述调度节点反馈的目标节点的IP地址,所述目标节点为所述调度节点根据目标节点标识确定。
在本公开一示例性实施例中,调度节点根据接收到的解析请求,确定目标节点,该目标节点与解析请求中所包含的目标节点标识相对应,再将目标节点的IP地址反馈给边缘管理节点。例如,解析请求是针对访问区域的解析请求,调度节点可以根据客户端所处区域,确定同区域的边缘节点为目标节点,将目标节点的IP地址反馈至边缘管理节点。
在步骤S14中,向所述UPF网元反馈所述目标节点的IP地址。
在本公开一示例性实施例中,边缘管理节点可以将调度节点反馈的目标节点的IP地址向UPF网元进行反馈,UPF网元则将该目标节点的IP地址向用户使用的客户端发送,以使该客户端能够与目标节点建立连接,从而获取对应的数据服务。
在图1所示的实施例中,边缘管理节点针对数据请求中的目标节点标识,生成解析请求,由调度节点进行解析,并确定目标节点的IP地址。调度节点可以在已有的边缘节点中进行调度,从中确定目标节点,解决现有5G通信网络中访问目标应用的服务端的接入地址相对固定的问题,保障服务的稳健性,保证数据请求的响应成功率。且UPF网元根据服务商的自治域对应的网络地址IP段进行转发,无需修改通信网络中的具体接入地址列表,也无需5G运营商开放地址接口,既保障了5G通信网络***安全可靠,同时也减少了地址列表更新的繁琐。另外,这部分数据的传输不需要经过5G核心网,提高数据响应速度的同时,也减少了对5G核心网资源的占用。
基于图1所示的实施例,在本公开一示例性实施例中,在所述接收UPF网元转发的携带有目标节点标识的数据请求之前,该基于5G的边缘节点调度方法还包括:
获取服务商的自治域对应的网络地址IP段;
将服务商的自治域对应的网络地址IP段注册到5G通信网络。
在该实施例中,服务商可以是CDN服务商或边缘云计算服务商,他们可以拥有大量边缘节点,用于缓存网络/计算中的数据,就近向用户提供目标数据。服务商可以拥有自己的自治域,该自治域具有对应的网络地址IP段。在提供网络服务前,需要将自治域和及其对应的网络地址IP段向外宣告路由,才能和其他域中的设备建立连接。
5G通信网运营商和网络服务商进行合作,可以使用服务商的大量边缘节点作为MEC边缘云,为接入5G通信网的终端用户提供高速数据服务。5G通信网运营商需要获取服务商的自治域对应的网络地址IP段,并将服务商的自治域对应的网络地址IP段注册到5G通信网络中,例如,将网络地址IP段加入5G通信记录表中,使得网络地址IP段中的IP地址,能够被5G通信网访问到。具有该网络地址IP段内的IP地址的边缘节点,可以为5G通信网提供MEC边缘云服务,客户端可以从这些边缘节点处获取数据。
基于图1所示的实施例,在本公开一示例性实施例中,
所述生成针对所述目标节点标识的解析请求,包括:
获取所述调度节点的IP地址;
生成针对所述目标节点标识的解析请求,其中,所述解析请求的解析地址为所述调度节点的IP地址。
在该实施例中,边缘管理节点可以获取调度节点统的IP地址,并在生成解析请求时,将解析请求对应的解析地址设置为该调度节点的IP地址。由此,边缘管理节点可以将该解析请求发送至调度节点进行解析,由服务商侧进行解析,提高解析灵活性。
图2示出了根据本公开另一示例性实施例的基于5G的边缘节点调度方法的流程图。参考图2,基于5G的边缘节点调度方法应用于调度节点,该基于5G的边缘节点调度方法至少包括步骤S21至步骤S23,详细介绍如下:
在步骤S21中,接收边缘管理节点发送的针对目标节点标识的解析请求,所述解析请求为所述边缘管理节点根据携带有所述目标节点标识的数据请求而生成,所述数据请求由UPF网元根据服务商的自治域对应的网络地址IP段转发至所述边缘管理节点。
在该实施例中,与运营商侧的边缘管理节点的调度方法对应,在服务商一侧,调度节点接收边缘管理节点发送的针对目标节点标识的解析请求。
在步骤S22中,根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址。
在该实施例中,由调度节点解析出与目标节点标识对应的目标节点的IP地址。具体地,调度节点可以根据目标节点标识,查找与该目标节点标识对应的边缘节点,再从该边缘节点中确定对应的目标节点的IP地址。例如,如果目标节点标识为域名,调度节点确定服务于该域名的边缘节点为目标节点;如果目标节点标识为客户端所处区域,调度节点确定服务于该区域的边缘节点为目标节点。
在步骤S23中,将目标节点的IP地址反馈给边缘管理节点。
在该实施例中,调度节点将目标节点的IP地址反馈给边缘管理节点。边缘管理节点按接收请求的路径,将目标节点的IP地址反馈给客户端,以使客户端 与目标节点进行连接,并获取数据内容。
在图2所示的实施例中,由调度节点接收边缘管理节点针对数据请求中的目标节点标识生成的解析请求,对解析请求进行解析,并确定目标节点的IP地址。调度节点可以在已有的边缘节点中进行调度,从中确定目标节点,解决现有5G通信网络中访问目标应用的服务端的接入地址相对固定的问题,保障服务的稳健性,保证数据请求的响应成功率。服务商可以根据实际情况,灵活确定目标节点,无需5G对地址列表进行更新,也无需5G运营商开放地址接口,既保障了5G通信网络***安全可靠,同时也减少了地址列表更新的繁琐。另外,由目标节点对数据请求进行响应,数据请求和响应数据的传输不需要经过5G核心网,提高数据响应速度的同时,也减少了对5G核心网资源的占用。
在一示例性实施例中,接收边缘管理节点发送的针对目标节点标识的解析请求之前,基于5G的边缘节点调度方法,还包括:
根据所述服务商的自治域对应的网络地址IP段向公共网络进行路由宣告。
在该实施例中,为了使服务商自治域对应的网络地址IP段中的IP地址能够被5G通信网访问到,服务商需要发布路由宣告及广播,使得5G通信网能够获取服务商的自治域对应的网络地址IP段,并将服务商的自治域对应的网络地址IP段注册到5G通信网络中。然后,具有服务商自治域对应的网络地址IP段中的IP地址的边缘节点能够被网络中其他设备发现并建立连接。
图3示出了根据本公开另一示例性实施例的基于5G的边缘节点调度方法的流程图。参考图3,在一示例性实施例中,在步骤S22中,根据目标节点标识,确定目标节点的IP地址包括步骤S221至步骤S223,详细介绍如下:
在步骤S221中,根据目标节点标识,获取与所述目标节点标识对应的边缘节点列表。
在该实施例中,目标节点标识可以是与目标节点相关联的标识信息,根据目标节点标识,可以确定与目标节点标识关联的边缘节点。例如,当目标节点为域名时,可以确定服务于该域名的边缘节点为关联的边缘节点。当访问该域名的客户端较多时,可以设置多个边缘节点同时服务于该域名,此时根据目标节点标识可以获取多个边缘节点,为了便于后续从多个边缘节点中确定目标边缘节点,可以对服务于同一域名的多个边缘节点的IP地址建立边缘节点列表,并建立域名与边缘节点列表的对应关系。调度节点在接收到针对某一域名的数 据请求时,可以快速确定对应的边缘节点列表。
在步骤S222中,探测边缘节点列表中的边缘节点的健康值,选择健康值大于或等于预定阈值的边缘节点为备选边缘节点。
调度节点可以通过遍历边缘节点列表的IP地址的方式,对边缘节点列表中的边缘节点逐一进行探测,探测每个边缘节点的健康值。边缘节点的健康值可以是用于表示边缘节点服务能力的数值信息,其可以根据边缘节点的业务指标:如吞吐量、响应时间、并发数、业务成功率等因素确定,例如,监测边缘节点单位时间内的吞吐量、并发数、响应时间、业务成功率等各个因素的量值,与预设的量值进行比较,并综合计算得分,作为边缘节点的健康值;也可以根据边缘节点的资源指标:如CPU、内存、I/O等资源的消耗情况确定,例如,检测边缘节点的CPU、内存、I/O等资源的消耗情况,计算剩余资源分值,作为边缘节点的健康值;或者将根据业务指标确定的健康值和根据资源指标确定的健康值,分别乘以权重系数,综合确定。需要说明的,健康值越高,则边缘节点的服务能力越强,健康值越低,则边缘节点的服务能力越弱。本实施例中,通过预先设定健康值阈值,只有健康值大于阈值的边缘节点才能提供良好的服务,将健康值大于预定阈值的边缘节点为备选边缘节点。
在步骤S223中,从备选边缘节点中确定与边缘管理节点具有最优路由的边缘节点为目标节点。
在该实施例中,确定了备选边缘节点,可以在备选边缘节点中随机选择一个边缘节点为目标节点,将目标节点的IP地址反馈给客户端,以使客户端与目标节点建立连接,并由目标节点为客户端提供服务。在本实施例中,为进一步提高响应速度,调度节点进一步对备选边缘节点进行路由探测,将与边缘管理节点具有最优路由的边缘节点作为目标节点。例如可以将信息传输的耗时最小的边缘节点确定为目标节点,等等。
通过以上方法选取目标节点,不但可以保障解析出的目标节点具有良好的健康度,确保能够为客户端提供服务,而且,目标节点与边缘管理节点还具有最优路由,能够以最快的响应速度,为客户端提供服务。
在一示例性实施例中,在所述探测所述边缘节点列表中的边缘节点的健康值之后,还包括:
将所述健康值小于所述预定阈值的边缘节点加入故障列表。
在该实施例中,在边缘节点出现故障后,可以将出现故障的边缘节点加入故障列表。为了使出现故障的边缘节点不会被调度节点解析到,可以将出现故障的边缘节点的IP地址从边缘节点列表中删除。在调度节点进行解析时,会遍历边缘节点列表,并确定备选边缘节点,将出现故障的边缘节点的IP地址从边缘节点列表中删除后,故障的边缘节点不会再被解析到;或者,调度节点遍历边缘节点列表的IP地址时,将边缘节点列表和故障列表进行比较,并跳过故障列表中的IP地址,保障故障的边缘节点不会再被解析到,终端不会请求到故障的边缘节点。本实施例中,当节点发生故障时,在服务商侧进行及时调整,不需要运营商侧做任何调整,保障了调度的灵活性和及时性。
在一实施例中,在所述根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址之前,还包括:
当检测到新的边缘节点接入时,将新接入的所述边缘节点的IP地址添加至对应的网络地址IP段的IP地址记录中。
在该实施例中,当服务商配置了新的边缘节点时,为了使新增的边缘节点能够为使用5G网络的用户提供服务,只需将新增边缘节点的IP地址设置为网络地址IP段中的IP地址,即可使新增边缘节点能够被5G通信网访问到,同时,为了使新增边缘节点能够调度节点解析到,还需要将新增的边缘节点的IP地址加入边缘节点列表。以上过程不需要5G运营商作任何调整,免去了多次修改运营商的地址列表的繁琐。
基于上述实施例的技术方案,以下介绍本公开实施例的一个具体应用场景:
图4示出了根据本公开一示例性实施例的基于5G的边缘节点调度方法的调度示意图。
参考图4,5G运营商A在某个城市建立了5G网络,向市民提供5G服务。运营商A和服务商B合作,使用服务商B的边缘节点集群作为EMC边缘云(46)。服务商B在该城市设置了多个边缘节点,其中,边缘节点1-边缘节点10为域名a提供服务。运营商A将该城市划分为两个区域,并设置边缘管理节点(44);对应两个区域,在区域1中设置边缘管理节点1(441),设置接入地址列表,接入地址列表中包括边缘节点1、边缘节点2;在区域2中设置边缘管理节点(442),设置接入地址列表,接入地址列表中包括边缘节点5、边缘节点6。
区域1中的用户(411),通过5G基站,接入5G网络,发起数据请求。UPF 网元(43)接收到数据请求后,如果数据请求的域名不是边缘节点服务的域名,将数据请求转发到5G核心网(47),用户通过5G核心网(47)与源站或公网(48)连接并获取数据。如果数据请求的域名为边缘节点服务的域名,将数据请求转发到边缘管理节点(44)。其中,由于请求携带的目标节点标识包含了区域信息表示来源于区域1,将用户的数据请求转发到边缘管理节点1(441),边缘管理节点1(441)确定由同属于区域1的边缘节点1或边缘节点2来响应用户的访问请求。当边缘节点1出现故障后,需要由运营商A修改边缘管理节点1的接入地址列表,无法及时做出调整。而在这个过程中,大量用户将出现无法访问的情况。
服务商B与运营商A协商后,运营商A将服务商B的自治域对应的网络地址IP段注册到5G通信网,并为边缘节点设置服务商B的自治域对应的网络地址IP段中的IP地址,使得拥有该IP段内IP地址的边缘节点都可以为5G通信网的用户提供边缘云服务。同时获取调度节点(45)的IP地址。
假设边缘节点1、边缘节点5出现故障,边缘管理节点1接收到区域1中的用户(411)访问域名a的数据请求后,生成针对域名a的解析请求,将解析请求发送给服务商B的调度节点(45),调度节点(45)根据请求中的域名a,查询边缘节点列表,确定由边缘节点1-边缘节点10为域名a提供服务,调度节点(45)依次对边缘节点1-边缘节点10进行探测,其中,边缘节点3、边缘节点4、边缘节点6、边缘节点7的健康值大于预设的阈值,调度节点进一步对上述边缘节点到边缘管理节点1的路由进行探测,最终确定边缘节点4到边缘管理节点1的路由最短,选择边缘节点4为目标节点,向区域1中用户(411)提供服务。根据探测结果,边缘节点1、边缘节点5的健康值小于预定阈值,将边缘节点1、边缘节点5加入故障列表,并从边缘节点列表中删除边缘节点1、边缘节点5。当边缘管理节点2(442)接收到区域2中的用户(412)访问域名a的请求后,生成针对域名a的解析请求,将解析请求发送给服务商B的调度节点(45),调度节点(45)根据请求中的域名a,查询边缘节点列表,确定由边缘节点2-边缘节点4、边缘节点6-边缘节点10共8个边缘节点提供服务,调度节点依次对上述8个边缘节点进行探测,其中,边缘节点3、边缘节点4、边缘节点6、边缘节点7的健康值大于预设的阈值,调度节点(45)进一步对上述边缘节点到边缘管理节点2(442)的路由进行探测,最终确定边缘节点7到边缘管理节点2(442)的路由最短,选择边缘节点7为目标节点,向区域2中用户(412) 提供服务。
通过上述实施例,运营商将服务商的网络地址IP段注册到5G通信网,可以使用服务商的大量边缘节点作为MEC边缘云提供服务,加速数据响应速度,同时由服务商的调度节点提供解析服务,当边缘节点出现故障后,智能调度节点能够对解析结果及时调整,运营商侧不需要开放相应接口。该方法不需要调整5G核心网的设置,运营商侧不存在安全性风险,保障服务稳健;能够选择最短路由的边缘节点提供服务,提高响应及时性。
图5示出了根据本公开一示例性实施例的基于5G的边缘节点调度装置的框图。参考图5,基于5G的边缘节点调度装置应用于边缘管理节点,包括:数据请求接收模块501,调度模块502,调度结果接收模块503,第一反馈模块504。
该数据请求接收模块501被配置为接收UPF网元转发的携带有目标节点标识的数据请求,所述数据请求为所述UPF网元根据服务商的自治域对应的网络地址IP段进行转发。
该调度模块502被配置为生成针对所述目标节点标识的解析请求,并将所述解析请求发送至调度节点。
该调度结果接收模块503被配置为接收由所述调度节点反馈的目标节点的IP地址,所述目标节点为所述调度节点根据所述目标节点标识确定。
该第一反馈模块504被配置为向所述UPF网元反馈目标节点的IP地址。
调度模块502还设置为:
获取调度节点的IP地址;
生成针对所述目标节点标识的解析请求,其中,所述解析请求的解析地址为所述调度节点的IP地址。
图6示出了根据本公开一示例性实施例的基于5G的边缘节点调度装置的框图。参考图6,基于5G的边缘节点调度装置应用于调度节点,包括:解析请求接收模块601,解析模块602,第二反馈模块603。
该解析请求接收模块501被配置为接收边缘管理节点发送的针对目标节点标识的解析请求,所述解析请求为所述边缘管理节点根据携带有所述目标节点标识的数据请求而生成,所述数据请求由UPF网元根据服务商的自治域对应的网络地址IP段转发至所述边缘管理节点。
该解析模块502被配置为根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址。
该第二反馈模块503被配置为将目标节点的IP地址反馈给所述边缘管理节点。
解析模块502根据目标节点标识,确定目标节点的IP地址包括:
根据所述目标节点标识,获取与所述目标节点标识对应的边缘节点列表;
探测所述边缘节点列表中的边缘节点的健康值,将所述健康值大于或等于预定阈值的边缘节点识别为备选边缘节点;
从所述备选边缘节点中确定与所述边缘管理节点之间具有最优路由的备选边缘节点为目标节点。
在所述探测所述边缘节点列表中的边缘节点的健康值之后,还包括:
将所述健康值小于所述预定阈值的边缘节点加入故障列表。
当检测到新的边缘节点接入时,将新接入的所述边缘节点的IP地址添加至对应的网络地址IP段的IP地址记录中。
图7示出了根据本公开一示例性实施例的一种用于5G调度的计算机设备700的框图。例如,计算机设备700可以被提供为一服务器。参照图7,计算机设备700包括处理器701,处理器的个数可以根据需要设置为一个或者多个。计算机设备700还包括存储器702,用于存储可由处理器701的执行的指令,例如应用程序。存储器的个数可以根据需要设置一个或者多个。其存储的应用程序可以为一个或者多个。处理器701被配置为执行指令,以执行上述基于5G的边缘节点调度方法。
本领域技术人员应明白,本公开的实施例可提供为方法、装置(设备)、或计算机程序产品。因此,本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质上实施的计算机程序产品的形式。计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质,包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或 其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质等。此外,本领域普通技术人员公知的是,通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据,并且可包括任何信息递送介质。
本公开是参照根据本公开实施例的方法、装置(设备)和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在本公开中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括……”限定的要素,并不排除在包括所述要素的物品或者设备中还存在另外的相同要素。
尽管已描述了本公开的优选实施例,但本领域内的技术人员一旦得知了基本创造性概念,则可对这些实施例作出另外的变更和修改。所以,所附权利要求意欲解释为包括优选实施例以及落入本公开范围的所有变更和修改。
显然,本领域的技术人员可以对本公开进行各种改动和变型而不脱离本公开的精神和范围。这样,倘若本公开的这些修改和变型属于本公开权利要求及其等同技术的范围之内,则本公开的意图也包含这些改动和变型在内。
本公开中通过提供一种基于5G的边缘节点调度方法,边缘管理节点接收UPF网元转发的携带有目标节点标识的数据请求,针对目标节点标识生成解析请求,将解析请求发送至调度节点,由调度节点确定目标节点的IP地址,以实现客户端通过UPF网元请求数据时,由服务商的调度节点选择目标节点为客户端提供服务,当服务端出现故障时,能够及时灵活调整接入地址,排除故障的服务端,保证响应及时;且接入地址列表的更新不需要5G运营商侧开放相应的接口,保障5G通信网络***安全可靠。
Claims (12)
- 一种基于5G的边缘节点调度方法,应用于边缘管理节点,包括:接收UPF网元转发的携带有目标节点标识的数据请求,所述数据请求为所述UPF网元根据服务商的自治域对应的网络地址IP段进行转发;生成针对所述目标节点标识的解析请求,并将所述解析请求发送至调度节点;接收由所述调度节点反馈的目标节点的IP地址,所述目标节点为所述调度节点根据所述目标节点标识确定;向所述UPF网元反馈所述目标节点的IP地址。
- 如权利要求1所述的基于5G的边缘节点调度方法,其中,在所述接收UPF网元转发的携带有目标节点标识的数据请求之前,还包括:获取服务商的自治域对应的网络地址IP段;将所述服务商的自治域对应的网络地址IP段注册到5G通信网络。
- 如权利要求1所述的基于5G的边缘节点调度方法,其中,所述生成针对所述目标节点标识的解析请求,包括:获取所述调度节点的IP地址;生成针对所述目标节点标识的解析请求,其中,所述解析请求的解析地址为所述调度节点的IP地址。
- 一种基于5G的边缘节点调度方法,应用于调度节点,包括:接收边缘管理节点发送的针对目标节点标识的解析请求,所述解析请求为所述边缘管理节点根据携带有所述目标节点标识的数据请求而生成,所述数据请求由UPF网元根据服务商的自治域对应的网络地址IP段转发至所述边缘管理节点;根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址;将所述目标节点的IP地址反馈给所述边缘管理节点。
- 如权利要求4所述的基于5G的边缘节点调度方法,其中,所述根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址,包括:根据所述目标节点标识,获取与所述目标节点标识对应的边缘节点列表;探测所述边缘节点列表中的边缘节点的健康值,将所述健康值大于或等于预定阈值的边缘节点识别为备选边缘节点;从所述备选边缘节点中确定与所述边缘管理节点之间具有最优路由的备选边缘节点为目标节点。
- 如权利要求5所述的基于5G的边缘节点调度方法,其中,在所述探测所述边缘节点列表中的边缘节点的健康值之后,还包括:将所述健康值小于所述预定阈值的边缘节点加入故障列表。
- 如权利要求4所述的基于5G的边缘节点调度方法,其中,在所述接收边缘管理节点发送的针对目标节点标识的解析请求之前,还包括:根据所述服务商的自治域对应的网络地址IP段向公共网络进行路由宣告。
- 如权利要求7所述的基于5G的边缘节点调度方法,其中,在所述根据所述目标节点标识,确定与所述目标节点标识对应的目标节点的IP地址之前,还包括:当检测到新的边缘节点接入时,将新接入的所述边缘节点的IP地址添加至对应的网络地址IP段的IP地址记录中。
- 一种基于5G的边缘节点调度装置,应用于边缘管理节点,包括:数据请求接收模块,接收UPF网元转发的携带有目标节点标识的数据请求,所述数据请求为所述UPF网元根据服务商的自治域对应的网络地址IP段进行转发;调度模块,设置为生成针对所述目标节点标识的解析请求,并将所述解析请求发送至调度节点;调度结果接收模块,设置为接收由所述调度节点反馈的目标节点的IP地址,所述目标节点为所述调度节点根据所述目标节点标识确定;第一反馈模块,设置为向所述UPF网元反馈所述目标节点的IP地址。
- 一种基于5G的边缘节点调度装置,应用于调度节点,包括:解析请求接收模块,设置为接收边缘管理节点发送的针对目标节点标识的解析请求,所述解析请求为所述边缘管理节点根据携带有所述目标节点标识的数据请求而生成,所述数据请求由UPF网元根据服务商的自治域对应的网络地址IP段转发至所述边缘管理节点;解析模块,设置为根据所述目标节点标识,确定与所述目标节点标识对应 的目标节点的IP地址;第二反馈模块,设置为将所述目标节点的IP地址反馈给所述边缘管理节点。
- 一种计算机可读存储介质,其上存储有计算机程序,其中,所述计算机程序被执行时实现如权利要求1-8中任意一项所述方法的步骤。
- 一种计算机设备,包括处理器、存储器和存储于所述存储器上的计算机程序,其中,所述处理器执行所述计算机程序时实现如权利要求1-8中任意一项所述方法的步骤。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110529396.9 | 2021-05-14 | ||
CN202110529396.9A CN115426413B (zh) | 2021-05-14 | 2021-05-14 | 基于5g的边缘节点调度方法、装置、介质及设备 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022237670A1 true WO2022237670A1 (zh) | 2022-11-17 |
Family
ID=84027971
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/091392 WO2022237670A1 (zh) | 2021-05-14 | 2022-05-07 | 基于5g的边缘节点调度方法、装置、介质及设备 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN115426413B (zh) |
WO (1) | WO2022237670A1 (zh) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110198363A (zh) * | 2019-05-10 | 2019-09-03 | 深圳市腾讯计算机***有限公司 | 一种移动边缘计算节点的选择方法、装置及*** |
CN110535930A (zh) * | 2019-08-22 | 2019-12-03 | 网宿科技股份有限公司 | 一种边缘cdn节点的调度方法和*** |
WO2021078936A1 (en) * | 2019-10-23 | 2021-04-29 | Telefonaktiebolaget Lm Ericsson (Publ) | Edge nodes, ue and methods performed therein |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
ES2964062T3 (es) * | 2018-06-01 | 2024-04-03 | Univ Catalunya Politecnica | Método y sistema de traspaso para redes 5g |
CN112512090B (zh) * | 2019-03-15 | 2022-07-19 | 腾讯科技(深圳)有限公司 | 通信处理方法、装置、计算机可读介质及电子设备 |
CN110582090A (zh) * | 2019-08-22 | 2019-12-17 | 网宿科技股份有限公司 | 一种cdn调度方法、调度***和mec网元 |
CN110572377B (zh) * | 2019-08-22 | 2022-02-22 | 网宿科技股份有限公司 | 一种数据转发方法、插件和域名服务器 |
CN110636007B (zh) * | 2019-09-11 | 2021-05-18 | 北京智芯微电子科技有限公司 | 边缘计算网络的路由编排方法、路由编排器及*** |
CN110769039B (zh) * | 2019-10-09 | 2021-12-10 | 腾讯科技(深圳)有限公司 | 资源调度方法及装置、电子设备和计算机可读存储介质 |
CN111638935B (zh) * | 2020-04-15 | 2022-07-01 | 阿里巴巴集团控股有限公司 | 镜像管理方法、网络***、设备以及存储介质 |
CN111629030A (zh) * | 2020-04-24 | 2020-09-04 | 腾讯科技(深圳)有限公司 | 基于边缘计算平台的通信处理方法、装置、介质及设备 |
CN111586114A (zh) * | 2020-04-24 | 2020-08-25 | 腾讯科技(深圳)有限公司 | 业务协同处理方法及相关设备 |
-
2021
- 2021-05-14 CN CN202110529396.9A patent/CN115426413B/zh active Active
-
2022
- 2022-05-07 WO PCT/CN2022/091392 patent/WO2022237670A1/zh active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110198363A (zh) * | 2019-05-10 | 2019-09-03 | 深圳市腾讯计算机***有限公司 | 一种移动边缘计算节点的选择方法、装置及*** |
CN110535930A (zh) * | 2019-08-22 | 2019-12-03 | 网宿科技股份有限公司 | 一种边缘cdn节点的调度方法和*** |
US20210058363A1 (en) * | 2019-08-22 | 2021-02-25 | Wangsu Science & Technology Co., Ltd. | Method and system for scheduling edge cdn node |
WO2021078936A1 (en) * | 2019-10-23 | 2021-04-29 | Telefonaktiebolaget Lm Ericsson (Publ) | Edge nodes, ue and methods performed therein |
Also Published As
Publication number | Publication date |
---|---|
CN115426413B (zh) | 2024-03-12 |
CN115426413A (zh) | 2022-12-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10264062B2 (en) | Request routing using a popularity identifier to identify a cache component | |
US20190182340A1 (en) | Selecting a content providing server in a content delivery network | |
US20180205697A1 (en) | Managing content delivery network service providers by a content broker | |
US9160703B2 (en) | Request routing management based on network components | |
US9444759B2 (en) | Service provider registration by a content broker | |
US8688837B1 (en) | Dynamically translating resource identifiers for request routing using popularity information | |
US20160212066A1 (en) | Software-Defined Information Centric Network (ICN) | |
CN107528862B (zh) | 域名解析的方法及装置 | |
WO2021057369A1 (zh) | HttpDNS调度方法、装置、介质及设备 | |
US11212329B2 (en) | Method, apparatus, device and storage medium for pushing video stream | |
CN112825524B (zh) | 网络服务节点的确定方法、装置和*** | |
US20150156259A1 (en) | Load balancing apparatus, information processing system, method and medium | |
US20200186463A1 (en) | Method and system for name-based in-networking processing | |
US20090300182A1 (en) | Computer-readable storage medium storing event control program, event control method, and event controller | |
WO2022237670A1 (zh) | 基于5g的边缘节点调度方法、装置、介质及设备 | |
US20170195426A1 (en) | Maintaining session across plural providing devices | |
CN111600929A (zh) | 传输线路探测方法、路由策略生成方法及代理服务器 | |
US20230102122A1 (en) | Methods, systems, and computer readable media for identifying alternate delivery endpoints for mobile originated data and monitoring reports in a communications network | |
CN114039906B (zh) | 流量引导方法、电子设备及可读存储介质 | |
US11095605B1 (en) | Request routing utilizing encoded DNS-based messaging parameters | |
US20140181307A1 (en) | Routing apparatus and method | |
US10574526B2 (en) | Control method for application feature rules and application feature server | |
WO2021017970A1 (zh) | 一种调度访问请求的方法、装置、介质及设备 | |
US20230421533A1 (en) | Network Traffic Management | |
CN115701067A (zh) | 切换用户端的边缘节点的方法、装置和*** |
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: 22806636 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: 22806636 Country of ref document: EP Kind code of ref document: A1 |