A relay forwarding node selection method and system for a terminal computing power network

Abstract

The application particularly relates to a relay forwarding node selection method and system for a terminal computing power network. The relay forwarding node selection method for the terminal computing power network comprises the following steps: searching for a distributed hash table (DHT) retrieval relay forwarding node list according to network resource demand information of a deployed service, and performing preliminary screening; performing secondary screening based on available bandwidth and the number of connections, and performing DHT retrieval again to obtain associated address information multiaddr; performing connection testing, filtering relay forwarding nodes that cannot meet the demand, and establishing a relay connection; monitoring performance data of the relay connection, and re-searching for applicable relay forwarding nodes if the network resource demand is not met. The relay forwarding node selection method and system for the terminal computing power network can update connection resource information of relay forwarding nodes providing relay services in a timely manner, meet network resource demand, realize communication between a service providing node and a service consuming node, and guarantee connection quality of the service.

Description

Technical Field

[0001] This invention relates to the field of computing power scheduling technology, and in particular to a method and system for selecting relay forwarding nodes for terminal computing power networks. Background Technology

[0002] Computing power networks have emerged as a new research topic, aiming to solve the problem of coordinated scheduling of ubiquitous computing power and networks. Currently, most research and technical directions focus on the coordination and optimization of bearer networks with edge computing and cloud computing. Terminal computing power networks for broadband access networks, as a typical application scenario with high computing idle rates and uneven network resource allocation, have received less research investment and lack relevant technical solutions. Especially in constructing the network connection layer of terminal computing power networks, existing P2P connection technologies are often used. However, these technologies only solve the problem of network connectivity, and still have shortcomings in transmission quality and performance.

[0003] In complex scenarios involving terminal computing networks, these networks are large-scale, widely distributed, structurally complex, and comprised of diverse terminal devices. Furthermore, due to the complex Network Address Translation (NAT) configurations in IPv4 networks and the limitations of stateful firewalls in IPv6 networks within broadband access networks, achieving direct communication between these nodes using techniques such as NAT traversal and firewall traversal becomes a reasonable solution. However, the actual network environment of nodes is highly complex, and the aforementioned techniques cannot guarantee direct communication between peers. Therefore, relay servers are still needed to provide relay links to enable connections between peers.

[0004] For terminal devices that lack static public IP addresses and have complex firewall and NAT configurations, and that provide computing power services or use external computing power services through relay connections, a relay forwarding node selection method and system for terminal computing power networks is proposed. Summary of the Invention

[0005] To overcome the shortcomings of existing technologies, this invention provides a simple and efficient method and system for selecting relay forwarding nodes in terminal computing power networks.

[0006] This invention is achieved through the following technical solution:

[0007] A relay forwarding node selection method for terminal computing power networks, characterized by the following steps:

[0008] Step S1: Obtain network resource requirements information for deployed services;

[0009] First, obtain the network resource requirements of the services already deployed on the service provider nodes, including but not limited to minimum bandwidth requirements, maximum latency requirements, and connection requirements, for reference in the subsequent selection process of relay forwarding nodes;

[0010] Step S2: Search the Distributed Hash Table (DHT) to retrieve the list of relay forwarding nodes and perform preliminary filtering;

[0011] The service provides node lookup and retrieval of the Distributed Hash Table (DHT) to obtain a list of available relay nodes, and filters them based on tunnel protocol type and encryption type to obtain a preliminary list of relay nodes.

[0012] In step S2, a custom periodic timer is used to update the available connection resource information of the relay forwarding node to the distributed hash table DHT at a custom period.

[0013] The available connection resource information of the relay forwarding node includes, but is not limited to, available bandwidth, number of available connections, supported relay tunnel protocols, and supported encryption methods;

[0014] Based on the relay tunnel protocols and encryption methods supported by the service provider nodes, a preliminary list of relay forwarding nodes is formed.

[0015] Step S3: Perform secondary filtering based on available bandwidth and number of connections;

[0016] The service provider node further filters the relay forwarding node list based on the initial screening, filtering out relay forwarding nodes whose available bandwidth and number of available connections do not meet the requirements of the services already deployed on the service provider node, thus forming a relay forwarding node list after secondary screening.

[0017] Step S4: Perform the Distributed Hash Table (DHT) search again to obtain the associated address information multiaddr;

[0018] The service provider node performs a distributed hash table (DHT) search again based on the Peer ID of the node identifier in the relay forwarding node list after secondary filtering to find its corresponding associated address information multiaddr.

[0019] Step S5: Perform connection tests, obtain connection performance data, filter out relay forwarding nodes that cannot meet the service requirements of the service provider node, and form a relay forwarding node list after three rounds of filtering.

[0020] If the list of relay forwarding nodes after three rounds of filtering formed by the connection test is not empty, then establish a relay connection with at least one of the relay forwarding nodes; otherwise, output a network connection alarm message.

[0021] In step S5, after the connection test is completed, the latency, packet loss and jitter information of each tested relay forwarding node is recorded, and relay forwarding nodes that cannot meet the maximum latency requirements of the service provider node are filtered out, forming a relay forwarding node list after three filtering steps.

[0022] The service provider node selects at least one relay forwarding node from the list of relay forwarding nodes after three rounds of filtering, based on a random algorithm and / or IP address information, to establish a relay connection.

[0023] Even better, the service provider node selects at least two relay nodes to establish a relay connection to avoid a single point of failure that would render the service provider node inaccessible.

[0024] Step S6: The service provider node monitors the performance data of the established relay connection to determine whether the relay connection meets the network resource requirements of the services deployed on the service provider node.

[0025] If the conditions are met, the connection will be maintained and monitoring will continue.

[0026] If the conditions are not met, proceed to step S2 to find a suitable relay forwarding node;

[0027] In step S6, all relay connections of the relay forwarding node are monitored in real time, and a custom periodic timer is used to monitor the performance data of the established relay connections at a custom period.

[0028] The performance data of the established relay connection includes, but is not limited to, latency, packet loss and jitter information to the relay forwarding node and available bandwidth information;

[0029] When some relay connection quality degradation is detected, the appropriate relay forwarding node is searched again according to steps S2 to S5. When all relay connection quality degradation is detected, the corresponding network connection alarm information is output.

[0030] Step S7: After establishing a relay connection with the service provider node, the relay forwarding node reserves available bandwidth and connection number equal to the minimum bandwidth requirement for the corresponding service provider node, and prioritizes forwarding the uplink and downlink traffic of the service provider node to ensure service quality.

[0031] After the relay forwarding node completes the reservation of available bandwidth, it updates the available connection resource information of the relay forwarding node to the distributed hash table DHT, where the available bandwidth and the number of available connections are reduced by the amount of reserved resources.

[0032] A relay forwarding node selection system for terminal computing power networks includes:

[0033] The Distributed Hash Table (DHT) maintenance module is responsible for using a custom periodic timer to update the DHT with information on available connection resources for relay nodes at a custom interval. This information includes, but is not limited to, available bandwidth, number of available connections, supported relay tunnel protocols, and supported encryption methods.

[0034] The network resource requirements module is responsible for obtaining network resource requirements information of services already deployed on the service provider nodes, including but not limited to minimum bandwidth requirements, maximum latency requirements, and connection requirements, for reference in the subsequent selection process of relay forwarding nodes.

[0035] The preliminary screening module is responsible for searching and retrieving the Distributed Hash Table (DHT) to obtain a list of available relay nodes, and for filtering based on the relay tunnel protocols and encryption methods supported by the nodes, thus obtaining a preliminary list of relay nodes.

[0036] The secondary filtering module is responsible for further filtering based on the initial filtering list of relay forwarding nodes, filtering out relay forwarding nodes whose available bandwidth and number of available connections do not meet the requirements of the services already deployed on the service provider nodes, thus forming a secondary filtering list of relay forwarding nodes.

[0037] The second retrieval module is responsible for performing a distributed hash table (DHT) retrieval again based on the node identifier Peer ID in the relay forwarding node list after the second filtering, to find its corresponding associated address information multiaddr.

[0038] The connection testing module is responsible for performing connection tests, obtaining connection performance data, filtering out relay forwarding nodes that cannot meet the service requirements of the service provider node, and forming a relay forwarding node list after three rounds of filtering.

[0039] If the list of relay forwarding nodes after three rounds of filtering formed by the connection test is not empty, then establish a relay connection with at least one of the relay forwarding nodes; otherwise, output a network connection alarm message.

[0040] After completing the connection test, the connection test module records the latency, packet loss and jitter information of each tested relay forwarding node, filters out relay forwarding nodes that cannot meet the maximum latency requirements of the services deployed by the service provider node, and forms a relay forwarding node list after three filtering steps.

[0041] The service provider node selects at least one relay forwarding node from the list of relay forwarding nodes after three rounds of filtering, based on a random algorithm and / or IP address information, to establish a relay connection.

[0042] Even better, the service provider node selects at least two relay nodes to establish a relay connection to avoid a single point of failure that would render the service provider node inaccessible.

[0043] The relay connection monitoring module is responsible for monitoring the performance data of established relay connections and determining whether the relay connections meet the network resource requirements of the services deployed on the service provider nodes.

[0044] If the conditions are met, the connection will be maintained and monitoring will continue.

[0045] If the conditions are not met, the preliminary screening module is triggered to search for suitable relay forwarding nodes again.

[0046] The relay connection monitoring module monitors all relay connections of the relay forwarding node in real time and uses a custom periodic timer to monitor the performance data of established relay connections at custom periods.

[0047] The performance data of the established relay connection includes, but is not limited to, latency, packet loss and jitter information to the relay forwarding node and available bandwidth information;

[0048] When some relay connection quality degradation is detected, a suitable relay forwarding node is re-searched. When all relay connection quality degradation is detected, the corresponding network connection alarm information is output.

[0049] The connection resource management module is responsible for reserving available bandwidth and connection number equal to the minimum bandwidth requirement for the corresponding service provider node after the relay forwarding node establishes a relay connection with the service provider node, and prioritizing the forwarding of the uplink and downlink traffic of the service provider node to ensure service quality.

[0050] After the relay forwarding node completes the reservation of available bandwidth, it updates the available connection resource information of the relay forwarding node to the distributed hash table DHT, where the available bandwidth and the number of available connections are reduced by the amount of reserved resources.

[0051] A readable storage medium, characterized in that: a computer program is stored on the readable storage medium, and the computer program, when executed by a processor, implements the method described above.

[0052] The beneficial effects of this invention are: the relay forwarding node selection method and system for terminal computing power networks can update the connection resource information of relay forwarding nodes that provide relay services in a timely manner, meet the network resource requirements of services already deployed on the service provider node, realize communication between the service provider node and the service consumer node, and ensure the connection quality of the service. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Appendix Figure 1 This is a schematic diagram of the relay forwarding node selection method for terminal computing power networks according to the present invention. Detailed Implementation

[0055] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions in the embodiments of this invention will be clearly and completely described below in conjunction with the embodiments of this invention. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0056] Currently, distributed hash tables (DHTs) are commonly used in P2P networks to retrieve nodes that can provide relay services and select one of them to perform relay forwarding. However, in scenarios involving terminal computing power networks, the demand for relay traffic is large, and the load and dynamism of the nodes providing relay forwarding services are high. Therefore, it is necessary to expand the connection resource status information of relay forwarding nodes in the distributed hash table (DHT) so that service-providing nodes can preferentially select relay forwarding nodes that meet their needs.

[0057] The service model of a terminal computing network typically contains three types of nodes: service provider nodes, relay nodes, and service consumer nodes. Since service provider nodes and service consumer nodes are located behind firewalls or NAT devices, they may not be able to communicate directly. Therefore, they need to communicate with relay nodes that have public IP addresses.

[0058] This relay forwarding node selection method for terminal computing power networks records and searches for relay forwarding nodes that can provide relay services through a distributed hash table (DHT), and extends the connection resource status information of the nodes. The service provider node selects a node from the found relay forwarding nodes to achieve communication with the service consumer node and ensure the connection quality of the service.

[0059] Specifically, the following steps are included:

[0060] Step S1: Obtain network resource requirements information for deployed services;

[0061] First, obtain the network resource requirements of the services already deployed on the service provider nodes, including but not limited to minimum bandwidth requirements, maximum latency requirements, and connection requirements, for reference in the subsequent selection process of relay forwarding nodes;

[0062] Step S2: Search the Distributed Hash Table (DHT) to retrieve the list of relay forwarding nodes and perform preliminary filtering;

[0063] The service provides node lookup and retrieval of the Distributed Hash Table (DHT) to obtain a list of available relay nodes, and filters them based on tunnel protocol type and encryption type to obtain a preliminary list of relay nodes.

[0064] In step S2, a custom periodic timer is used to update the available connection resource information of the relay forwarding node to the distributed hash table DHT at a custom period.

[0065] The available connection resource information of the relay forwarding node includes, but is not limited to, available bandwidth, number of available connections, supported relay tunnel protocols, and supported encryption methods;

[0066] Based on the relay tunnel protocols and encryption methods supported by the service provider nodes, a preliminary list of relay forwarding nodes is formed.

[0067] Step S3: Perform secondary filtering based on available bandwidth and number of connections;

[0068] The service provider node further filters the relay forwarding node list based on the initial screening, filtering out relay forwarding nodes whose available bandwidth and number of available connections do not meet the requirements of the services already deployed on the service provider node, thus forming a relay forwarding node list after secondary screening.

[0069] Step S4: Perform the Distributed Hash Table (DHT) search again to obtain the associated address information multiaddr;

[0070] The service provider node performs a distributed hash table (DHT) search again based on the Peer ID of the node identifier in the relay forwarding node list after secondary filtering to find its corresponding associated address information multiaddr.

[0071] Step S5: Perform connection tests, obtain connection performance data, filter out relay forwarding nodes that cannot meet the service requirements of the service provider node, and form a relay forwarding node list after three rounds of filtering.

[0072] If the list of relay forwarding nodes after three rounds of filtering formed by the connection test is not empty, then establish a relay connection with at least one of the relay forwarding nodes; otherwise, output a network connection alarm message.

[0073] In step S5, after the connection test is completed, the latency, packet loss and jitter information of each tested relay forwarding node is recorded, and relay forwarding nodes that cannot meet the maximum latency requirements of the service provider node are filtered out, forming a relay forwarding node list after three filtering steps.

[0074] The service provider node selects at least one relay forwarding node from the list of relay forwarding nodes after three rounds of filtering, based on a random algorithm and / or IP address information, to establish a relay connection.

[0075] Even better, the service provider node selects at least two relay nodes to establish a relay connection to avoid a single point of failure that would render the service provider node inaccessible.

[0076] Step S6: The service provider node monitors the performance data of the established relay connection to determine whether the relay connection meets the network resource requirements of the services deployed on the service provider node.

[0077] If the conditions are met, the connection will be maintained and monitoring will continue.

[0078] If the conditions are not met, proceed to step S2 to find a suitable relay forwarding node;

[0079] In step S6, all relay connections of the relay forwarding node are monitored in real time, and a custom periodic timer is used to monitor the performance data of the established relay connections at a custom period.

[0080] The performance data of the established relay connection includes, but is not limited to, latency, packet loss and jitter information to the relay forwarding node and available bandwidth information;

[0081] When some relay connection quality degradation is detected, the appropriate relay forwarding node is searched again according to steps S2 to S5. When all relay connection quality degradation is detected, the corresponding network connection alarm information is output.

[0082] Step S7: After establishing a relay connection with the service provider node, the relay forwarding node reserves available bandwidth and connection number equal to the minimum bandwidth requirement for the corresponding service provider node, and prioritizes forwarding the uplink and downlink traffic of the service provider node to ensure service quality.

[0083] After the relay forwarding node completes the reservation of available bandwidth, it updates the available connection resource information of the relay forwarding node to the distributed hash table DHT, where the available bandwidth and the number of available connections are reduced by the amount of reserved resources.

[0084] This relay forwarding node selection system for terminal computing power networks includes:

[0085] The Distributed Hash Table (DHT) maintenance module is responsible for using a custom periodic timer to update the DHT with information on available connection resources for relay nodes at a custom interval. This information includes, but is not limited to, available bandwidth, number of available connections, supported relay tunnel protocols, and supported encryption methods.

[0086] The network resource requirements module is responsible for obtaining network resource requirements information of services already deployed on the service provider nodes, including but not limited to minimum bandwidth requirements, maximum latency requirements, and connection requirements, for reference in the subsequent selection process of relay forwarding nodes.

[0087] The preliminary screening module is responsible for searching and retrieving the Distributed Hash Table (DHT) to obtain a list of available relay nodes, and for filtering based on the relay tunnel protocols and encryption methods supported by the nodes, thus obtaining a preliminary list of relay nodes.

[0088] The secondary filtering module is responsible for further filtering based on the initial filtering list of relay forwarding nodes, filtering out relay forwarding nodes whose available bandwidth and number of available connections do not meet the requirements of the services already deployed on the service provider nodes, thus forming a secondary filtering list of relay forwarding nodes.

[0089] The second retrieval module is responsible for performing a distributed hash table (DHT) retrieval again based on the node identifier Peer ID in the relay forwarding node list after the second filtering, to find its corresponding associated address information multiaddr.

[0090] The connection testing module is responsible for performing connection tests, obtaining connection performance data, filtering out relay forwarding nodes that cannot meet the service requirements of the service provider node, and forming a relay forwarding node list after three rounds of filtering.

[0091] If the list of relay forwarding nodes after three rounds of filtering formed by the connection test is not empty, then establish a relay connection with at least one of the relay forwarding nodes; otherwise, output a network connection alarm message.

[0092] After completing the connection test, the connection test module records the latency, packet loss and jitter information of each tested relay forwarding node, filters out relay forwarding nodes that cannot meet the maximum latency requirements of the services deployed by the service provider node, and forms a relay forwarding node list after three filtering steps.

[0093] The service provider node selects at least one relay forwarding node from the list of relay forwarding nodes after three rounds of filtering, based on a random algorithm and / or IP address information, to establish a relay connection.

[0094] Even better, the service provider node selects at least two relay nodes to establish a relay connection to avoid a single point of failure that would render the service provider node inaccessible.

[0095] The relay connection monitoring module is responsible for monitoring the performance data of established relay connections and determining whether the relay connections meet the network resource requirements of the services deployed on the service provider nodes.

[0096] If the conditions are met, the connection will be maintained and monitoring will continue.

[0097] If the conditions are not met, the preliminary screening module is triggered to search for suitable relay forwarding nodes again.

[0098] The relay connection monitoring module monitors all relay connections of the relay forwarding node in real time and uses a custom periodic timer to monitor the performance data of established relay connections at custom periods.

[0099] The performance data of the established relay connection includes, but is not limited to, latency, packet loss and jitter information to the relay forwarding node and available bandwidth information;

[0100] When some relay connection quality degradation is detected, a suitable relay forwarding node is re-searched. When all relay connection quality degradation is detected, the corresponding network connection alarm information is output.

[0101] The connection resource management module is responsible for reserving available bandwidth and connection number equal to the minimum bandwidth requirement for the corresponding service provider node after the relay forwarding node establishes a relay connection with the service provider node, and prioritizing the forwarding of the uplink and downlink traffic of the service provider node to ensure service quality.

[0102] After the relay forwarding node completes the reservation of available bandwidth, it updates the available connection resource information of the relay forwarding node to the distributed hash table DHT, where the available bandwidth and the number of available connections are reduced by the amount of reserved resources.

[0103] The readable storage medium stores a computer program that, when executed by a processor, implements the method described above.

[0104] The embodiments described above are merely one specific implementation of the present invention. Ordinary changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for selecting a relay forwarding node in a terminal computing power network, characterized in that: The method comprises the following steps: Step S1, obtaining network resource requirement information of a deployed service; First, obtain the network resource requirement information of the deployed service on the service providing node, including but not limited to minimum bandwidth requirement, maximum latency requirement and connection number requirement, for reference in the subsequent screening process of the relay forwarding node; Step S2, searching a distributed hash table (DHT) to retrieve a relay forwarding node list and performing preliminary screening; The service providing node searches the DHT to obtain a suitable relay forwarding node list, and performs screening based on the tunnel protocol type and the encryption type, to obtain a preliminary screened relay forwarding node list; Step S3, performing secondary screening based on available bandwidth and connection number; The service providing node further screens the preliminary screened relay forwarding node list, filters out the relay forwarding nodes that do not meet the requirements of the deployed service on the service providing node in terms of available bandwidth and available connection number, and forms a secondary screened relay forwarding node list; Step S4, searching the DHT again to obtain associated address information multiaddr; The service providing node searches the DHT again based on the node identifier Peer ID in the secondary screened relay forwarding node list, to find the corresponding associated address information multiaddr; Step S5, performing connection testing, obtaining connection performance data, filtering out the relay forwarding nodes that cannot meet the requirements of the deployed service on the service providing node, and forming a tertiary screened relay forwarding node list; If the tertiary screened relay forwarding node list formed by the connection testing is not empty, a relay connection is established with at least one of the relay forwarding nodes, otherwise network connection alarm information is output; Step S6, the service providing node monitors the performance data of the established relay connection, and determines whether the relay connection meets the network resource requirements of the deployed service on the service providing node: If yes, the connection is maintained and the monitoring is continuously performed; If no, go to step S2 to search for a suitable relay forwarding node; Step S7, after the relay forwarding node establishes a relay connection with the service providing node, the relay forwarding node reserves available bandwidth equal to the minimum bandwidth requirement and connection number for the corresponding service providing node, and preferentially forwards the uplink and downlink traffic of the service providing node, to guarantee the quality of service; After the relay forwarding node completes the reservation of available bandwidth, the relay forwarding node updates the available connection resource information of the relay forwarding node to the DHT, wherein the available bandwidth and the available connection number are both deducted by the reserved resource amount.

2. The method of claim 1, wherein the method further comprises: In step S2, a self-defined periodic timer is used to update the available connection resource information of the relay forwarding node to the DHT at a self-defined period; The available connection resource information of the relay forwarding node includes but is not limited to available bandwidth, available connection number, supported relay tunnel protocol and supported encryption method; The relay forwarding node list is screened based on the supported relay tunnel protocol and encryption method of the service providing node, to form a preliminary screened relay forwarding node list.

3. The method of claim 1, wherein the method further comprises: receiving a request from a first terminal device for a relay forwarding node; and sending a response to the first terminal device, the response including a list of relay forwarding nodes that are available to the first terminal device. In the step S5, after completing the connection test, the delay, packet loss and jitter information of each relay forwarding node is recorded, and the relay forwarding nodes that cannot meet the maximum delay requirement of the deployed services of the service providing node are filtered out to form the relay forwarding node list after three times of screening; The service providing node selects at least one relay forwarding node from the relay forwarding node list after three times of screening to establish a relay connection based on a random algorithm and / or IP home location information.

4. The method of claim 3, wherein: The service providing node selects at least two relay forwarding nodes to establish a relay connection to avoid single point failure leading to the service providing node being inaccessible.

5. The method of claim 1, wherein: In the step S6, all relay connections of the relay forwarding node are monitored in real time, and a self-defined periodic timer is used to monitor the performance data of the established relay connection at a self-defined period; The performance data of the established relay connection includes but is not limited to the delay, packet loss and jitter information and available bandwidth information to the relay forwarding node; When the quality of part of the relay connections is monitored to be degraded, the applicable relay forwarding nodes are searched again according to the steps S2-S5, and when the quality of all the relay connections is monitored to be degraded, corresponding network connection alarm information is output. 6.A system for selecting a relay forwarding node in a terminal-computing-power-oriented network, characterized in that: It comprises: A distributed hash table (DHT) maintenance module responsible for updating the available connection resource information of the relay forwarding node to the distributed hash table (DHT) at a self-defined period by using a self-defined periodic timer; The available connection resource information of the relay forwarding node includes but is not limited to available bandwidth, available connection number, supported relay tunnel protocol and supported encryption mode; A network resource demand module responsible for obtaining the network resource demand information of the deployed services on the service providing node, including but not limited to minimum bandwidth demand, maximum delay demand and connection number demand, for reference in the subsequent screening process of the relay forwarding node; A preliminary screening module responsible for searching the distributed hash table (DHT) to obtain the relay forwarding node list, and screening the relay forwarding node list based on the supported relay tunnel protocol and encryption mode of the service providing node to obtain the relay forwarding node list after preliminary screening; A secondary screening module responsible for further screening based on the relay forwarding node list after preliminary screening, filtering out the relay forwarding nodes whose available bandwidth and available connection number cannot meet the demand of the deployed services on the service providing node to form the relay forwarding node list after secondary screening; A re-searching module responsible for searching the distributed hash table (DHT) again based on the node identifier (Peer ID) in the relay forwarding node list after secondary screening to find the corresponding associated address information (multiaddr); A connection testing module responsible for performing connection test, obtaining connection performance data, filtering out the relay forwarding nodes that cannot meet the demand of the deployed services of the service providing node to form the relay forwarding node list after three times of screening; If the relay forwarding node list after three times of screening formed by the connection test is not empty, a relay connection is established with at least one relay forwarding node, otherwise network connection alarm information is output. A relay connection monitoring module responsible for monitoring the performance data of the established relay connection and judging whether the relay connection meets the network resource demand of the deployed services of the service providing node: If yes, maintain the connection and continue monitoring; If no, trigger the preliminary screening module to re-search for applicable relay forwarding nodes; The connection resource management module is responsible for reserving available bandwidth and connection number equal to the minimum bandwidth requirement of the corresponding service providing node after the relay forwarding node establishes a relay connection with the service providing node, and preferentially forwarding the uplink and downlink traffic of the service providing node to guarantee the quality of service. After the relay forwarding node completes the available bandwidth reservation, it updates the distributed hash table (DHT) with the available connection resource information of the relay forwarding node, wherein the available bandwidth and the available connection number are both deducted by the reserved resource amount.

7. The terminal-oriented computing power network relay forwarding node selection system according to claim 6, characterized in that: After completing the connection test, the connection test module records the latency, packet loss, and jitter information of each tested relay forwarding node, filters out the relay forwarding nodes that cannot meet the maximum latency requirement of the deployed services of the service providing node, and forms a list of relay forwarding nodes after three screenings. The service providing node selects at least one relay forwarding node from the list of relay forwarding nodes after three screenings to establish a relay connection based on a random algorithm and / or IP home location information. 8.The terminal-oriented computing power network relay forwarding node selection system according to claim 7, characterized in that: The service providing node selects at least two relay forwarding nodes to establish a relay connection to prevent a single point failure from causing the service providing node to be inaccessible. 9.The terminal-oriented computing power network relay forwarding node selection system according to claim 6, characterized in that: The relay connection monitoring module monitors all relay connections of the relay forwarding node in real time, defines a periodic timer, and monitors the performance data of the established relay connection at a self-defined period. The performance data of the established relay connection includes but is not limited to the latency, packet loss, and jitter information to the relay forwarding node and the available bandwidth information. When the quality of part of the relay connections deteriorates, the system re-searches for applicable relay forwarding nodes, and when the quality of all relay connections deteriorates, the system outputs corresponding network connection alarm information.

10. A readable storage medium, characterized by: The readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method of any one of claims 1 to 5.

Images