5G fusion network flow scheduling method and system, computer equipment and medium

Abstract

The invention relates to the technical field of communication, and provides a 5G convergence network flow scheduling method and system, computer equipment and a medium. The 5G convergence network flow scheduling method comprises the following steps: acquiring network data of a 5G convergence network and service flow data of at least one data flow; determining a path of each data flow according to the network data and each piece of service flow data; determining a first time slot of each data stream in each switch according to each path; and determining a routing scheduling result of each data stream according to each first time slot and a pre-constructed constraint condition. According to the invention, the requirements of the 5G fusion network are met, and the flow scheduling of the 5G fusion network is realized.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular, to a 5G converged network traffic scheduling method, system, computer device, and medium. Background Art

[0002] With the rapid development of 5G technology, 5G converged networks have become an important direction for future communication networks. 5G converged networks integrate 5G networks with other network technologies such as Time-Sensitive Networking (TSN) to provide more efficient and stable network services. However, in 5G converged networks, traffic scheduling is a complex and critical issue.

[0003] In traditional 5G networks, due to the lack of consideration for time sensitivity, problems such as data transmission delay and jitter may occur, and the requirements of some services with high real-time requirements cannot be met. Time-Sensitive Networking is a new type of network technology that can effectively reduce data transmission delay and jitter and improve network real-time performance by precisely controlling the time of network transmission.

[0004] However, when integrating 5G networks with TSN, etc., due to different technical characteristics, how to perform effective traffic scheduling has become an urgent problem to be solved. Traditional traffic scheduling methods may not meet the requirements of 5G converged networks, so a new 5G converged network traffic scheduling method needs to be studied. Summary of the Invention

[0005] To meet the requirements of 5G converged networks and achieve traffic scheduling for 5G converged networks, the present invention proposes a 5G converged network traffic scheduling method, system, computer device, and medium.

[0006] In a first aspect, the present invention provides a 5G converged network traffic scheduling method, which includes:

[0007] Obtain the network data of the 5G converged network and the service flow data of at least one data flow;

[0008] Determine the paths of each data flow according to the network data and each service flow data;

[0009] Determine the first time slot of each data flow in each switch according to each path;

[0010] Determine the routing and scheduling results of each data flow according to each first time slot and the pre-constructed constraint conditions.

[0011] Through the above method, using the network data of the 5G converged network and the service flow data of the data flow, determine the transmission path of each data flow in the 5G converged network, determine the first time slot of each data flow in each switch according to the path, and further, according to the first time slot and the constraint conditions, determine the routing and scheduling result of the data flow, meet the requirements of the 5G converged network, realize the traffic scheduling and end-to-end deterministic transmission of the 5G converged network, and ensure heterogeneous network adaptation and seamless cross-network high-reliability bearer.

[0012] In an alternative embodiment, the service flow data includes a source address and a terminal address. Determining the path of the data flow according to the network data and the service flow data includes:

[0013] Determine the path of the data flow according to the network data, the source address, the terminal address, and the minimum path algorithm.

[0014] Through the above embodiment, by combining the network data and the service flow data and optimizing the data flow path through the minimum path algorithm, network resources can be better utilized, congestion on certain paths can be avoided, thereby reducing network latency and data transmission time, and improving network performance and data transmission reliability.

[0015] In an alternative embodiment, the service flow data includes a deadline. Determining the first time slot of each data flow in each switch according to each path includes:

[0016] Sort each data flow according to each deadline to obtain a first sorting result;

[0017] Determine the first time slot of each data flow in each switch according to each path and the first sorting result.

[0018] Through the above embodiment, by sorting the data flow according to the deadline to obtain a first sorting result, and determining the first time slot of each data flow in the switch according to each path and the first sorting result, while reasonably allocating network resources according to the path, the data flows that need to be completed earlier are processed preferentially, thereby improving the overall efficiency of the network.

[0019] In an alternative embodiment, determining the first time slot of the data flow in the switch according to the path and the first sorting result includes:

[0020] Determine multiple second time slots of the data flow in the switch according to the path and the first sorting result;

[0021] Calculate the resource utilization rate of each second time slot;

[0022] Select the second time slot with the minimum resource utilization rate as the first time slot of the data flow in the switch.

[0023] Through the above implementation manners, by selecting the time slot with the minimum resource utilization rate according to the calculated resource utilization rates of each second time slot, the resources of the switch can be effectively utilized, the load of the switch can be balanced, and resource waste can be avoided, that is, the situation where some time slots are overloaded and some time slots are idle is avoided, thereby improving the overall performance of the network.

[0024] In an alternative implementation manner, the routing and scheduling result includes a scheduling order. According to each first time slot and the pre-constructed constraint conditions, the routing and scheduling result of each data stream is determined, including:

[0025] Regarding the first time slots that meet the constraint conditions as third time slots;

[0026] Determining the data streams corresponding to each third time slot;

[0027] Sorting the data streams corresponding to each third time slot according to the offsets of each third time slot to obtain the scheduling order of each data stream.

[0028] Through the above implementation manners, regarding the first time slots that meet the constraint conditions as third time slots ensures that the data streams meet the pre-constructed constraint conditions, thereby guaranteeing the security and stability of the network; determining the data streams corresponding to each third time slot and sorting the data streams according to the offsets of each third time slot can obtain the scheduling order of each data stream, thereby optimizing the routing and scheduling, improving the performance and reliability of the network, and providing more decision-making bases for better predicting the behavior and performance of the network.

[0029] In a second aspect, the present invention further provides a 5G converged network traffic scheduling system. The system includes: a network topology analysis module and a global routing and scheduling module;

[0030] The network topology analysis module is used to obtain the network data of the 5G converged network and the service flow data of at least one data stream; and send the network data and each service flow data to the global routing and scheduling module;

[0031] The global routing and scheduling module is used to determine the paths of each data stream according to the network data and each service flow data; determine the first time slots of each data stream in each switch according to each path; and determine the routing and scheduling result of each data stream according to each first time slot and the pre-constructed constraint conditions.

[0032] Through the above system, the global routing and scheduling module uses the network data of the 5G converged network and the service flow data of the data flows to determine the transmission paths of the respective data flows in the 5G converged network, determines the first time slots of the respective data flows in each switch according to the paths, and further determines the routing and scheduling results of the data flows according to the first time slots and the constraint conditions, so as to meet the requirements of the 5G converged network, realize the traffic scheduling of the 5G converged network, end-to-end deterministic transmission, and ensure heterogeneous network adaptation and seamless cross-network high-reliability bearer.

[0033] In an alternative embodiment, the system further includes: a network resource analysis module, a network connection management module, and an application program interface;

[0034] The network resource analysis module is connected to the network topology analysis module and is used to manage virtual network resources and provide resource scheduling information through the application program interface;

[0035] The network connection management module is connected to the global routing and scheduling module and is used to implement end-to-end service connections.

[0036] Through the above embodiment, the network resource analysis module manages virtual network resources and provides resource scheduling information through the application program interface, which enables the system to manage network resources more precisely and perform dynamic scheduling according to service requirements, improving the utilization efficiency of resources and network performance; the network connection management module is connected to the global routing and scheduling module to implement end-to-end service connections. This enables the system to better support various service requirements, provide stable and reliable connection services, and improve the availability and service quality of the network; by adding the network resource analysis module and the application program interface, the system can expand and manage network resources more flexibly. This enables the system to adapt to the changing network environment and service requirements, and improves the scalability and adaptability of the system.

[0037] In an alternative embodiment, the system further includes: a protocol management module;

[0038] The protocol management module is used to parse the protocols in the 5G converged network and implement the interaction between the 5G converged network, the network topology analysis module, the global routing and scheduling module, and the network connection management module.

[0039] Through the above embodiment, the protocol management module can parse the protocols in the 5G converged network to ensure the communication and interaction between the system and various network devices and application programs, which enables the system to be seamlessly integrated with the existing network infrastructure and realize protocol compatibility and interoperability; at the same time, the protocol management module can provide standardized interfaces and protocols, simplify the work of developers and network administrators, enable the system to be more conveniently integrated with other network devices and application programs, and reduce the cost and complexity of development and maintenance.

[0040] In a third aspect, the present invention further provides a computer device, including a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the steps of the 5G converged network traffic scheduling method according to the first aspect or any implementation manner of the first aspect.

[0041] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the 5G converged network traffic scheduling method according to the first aspect or any implementation manner of the first aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the specific implementation manners of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific implementation manners or the prior art. Obviously, the drawings in the following description are some implementation manners of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 is a flowchart of a 5G converged network traffic scheduling method according to an exemplary embodiment;

[0044] Figure 2 is a specific implementation flowchart of the 5G converged network traffic scheduling method in an example;

[0045] Figure 3 is a structural block diagram of a 5G converged network traffic scheduling system according to an exemplary embodiment;

[0046] Figure 4 is a specific structural schematic diagram of a 5G converged network traffic scheduling system in an example;

[0047] Figure 5 is a hardware structural schematic diagram of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The following will clearly and completely describe the technical solutions of the present invention with reference to the drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0049] In addition, the technical features involved in different implementation manners of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0050] To meet the requirements of the 5G converged network and achieve traffic scheduling for the 5G converged network, the present invention proposes a 5G converged network traffic scheduling method, system, computer device, and medium.

[0051] Figure 1 It is a flowchart of a 5G converged network traffic scheduling method proposed according to an exemplary embodiment. As Figure 1 shown, the 5G converged network traffic scheduling method includes the following steps S101 to S104.

[0052] Step S101: Obtain the network data of the 5G converged network and the service flow data of at least one data flow.

[0053] In an optional embodiment, the 5G converged network can be a network obtained by fusing the 5G network with the time-sensitive network, or a network obtained by fusing the 5G network with other network technologies, and no specific limitation is made here.

[0054] In an optional embodiment, the network data includes parameter information such as network topology, network status, flow transfer direction, transmission delay budget, priority, etc., as well as network management and configuration information.

[0055] In an optional embodiment, the service flow data includes but is not limited to source address, terminal address, data frame length, data transmission period, end-to-end delay upper bound (deadline), etc.

[0056] Step S102: Determine the paths of each data flow according to the network data and each service flow data.

[0057] In an optional embodiment, the path of the data flow refers to the path of the switches passed by the data flow during transmission. The path of a data flow includes at least one switch.

[0058] In an optional embodiment, according to the network data and each service flow data, use the routing scheduling algorithm to calculate the paths of each data flow in each switch.

[0059] Step S103: Determine the first time slot of each data flow in each switch according to each path.

[0060] In an optional embodiment, the first time slot of each data flow in the switch can be determined according to each path in combination with the deadline of the data flow to ensure that the data flow can be reasonably processed and scheduled.

[0061] Step S104: Determine the routing scheduling result of each data flow according to each first time slot and the pre-constructed constraint conditions.

[0062] In an alternative embodiment, the constraint conditions can be determined based on network bandwidth, switch capacity, time slot availability, and data flow priority.

[0063] In an alternative embodiment, when the first time slot meets the pre-constructed constraint conditions, routing and scheduling are performed on the data flow corresponding to the first time slot.

[0064] In an alternative embodiment, the routing and scheduling results include the scheduling order, scheduling time, etc. of the data flow, which are not specifically limited herein.

[0065] Through the above method, using the network data of the 5G converged network and the service flow data of the data flow, the transmission paths of each data flow in the 5G converged network are determined. According to the paths, the first time slots of each data flow in each switch are determined. Further, according to the first time slots and the constraint conditions, the routing and scheduling results of the data flow are determined, meeting the requirements of the 5G converged network, realizing traffic scheduling and end-to-end deterministic transmission of the 5G converged network, and ensuring heterogeneous network adaptation and seamless cross-network highly reliable bearer.

[0066] In an example, the service flow data includes the source address and the terminal address. Among them, the source address refers to the starting address of the data flow, and the terminal address is the destination address of the data flow. In the above step S102, according to the network data, source address, terminal address, and the minimum path algorithm, the path of the data flow is determined.

[0067] In an alternative embodiment, a minimum path algorithm, such as Dijkstra's Algorithm or Bellman-Ford Algorithm, etc., is used to process the network data. Through the minimum path algorithm, according to the source address, terminal address, and network data, the minimum path from the source to the terminal is calculated.

[0068] In an alternative embodiment, the 5G converged network is a network obtained by fusing a 5G network and a TSN network. The 5G converged network topology is abstracted as an undirected graph G=(V, E), where V represents the set of all nodes in the 5G network and also represents the set of switches and network terminal stations in the TSN domain. The minimum path algorithm can perform V-1 relaxation operations on G=(V, E) to obtain the shortest path of the data flow.

[0069] In the embodiments of the present invention, by combining network data and service flow data and optimizing the data flow path through the minimum path algorithm, network resources can be better utilized, congestion on certain paths can be avoided, thereby reducing network latency and data transmission time, and improving network performance and data transmission reliability. Combining the traffic scheduling success rate algorithm based on the injection time algorithm with a relaxation operation algorithm based on the single-source shortest path problem has better performance in traffic scheduling. Under the action of the optimization mechanism, the optimal values of the traffic scheduling success rate for low workloads and high workloads are both improved, significantly enhancing the schedulability.

[0070] In one example, the service flow data includes a deadline. In step S103 above, the first time slot of each data flow in each switch is determined through the following steps:

[0071] Step a1: Sort each data flow according to each deadline to obtain a first sorting result.

[0072] In an alternative embodiment, each data flow is sorted in ascending order of the deadline.

[0073] In an alternative embodiment, the service flow data further includes path length, data flow message size, cycle size, etc. In the embodiments of the present invention, each data flow can also be sorted according to path length, data flow message size, cycle size, etc.

[0074] Step a2: Determine the first time slot of each data flow in each switch according to each path and the first sorting result.

[0075] In an alternative embodiment, for the data flows sorted earlier in the first sorting result, their time slots in the switch will be preferentially allocated.

[0076] In the embodiments of the present invention, a first sorting result is obtained by sorting the data flows according to the deadline. According to each path and the first sorting result, the first time slot of each data flow in the switch is determined. While reasonably allocating network resources according to the path, those data flows that need to be completed earlier are preferentially processed, thereby improving the overall efficiency of the network.

[0077] In an alternative embodiment, in step a2 above, the first time slot of the data flow in the switch is determined in the following manner:

[0078] First, determine multiple second time slots of the data flow in the switch according to the path and the first sorting result. Exemplarily, for each switch in the path, multiple second time slots of the data flow in the switch are determined according to the first sorting result.

[0079] Then, calculate the resource utilization rate of each second time slot. Among them, the resource utilization rate can be determined by the number of data streams scheduled in the second time slot, or can be determined by the ratio of the number of data streams scheduled in the second time slot to the total number of data streams transmitted in the 5G converged network.

[0080] Finally, select the second time slot with the minimum resource utilization rate as the first time slot of the data stream in the switch.

[0081] In the embodiment of the present invention, according to the calculated resource utilization rate of each second time slot, select the time slot with the minimum resource utilization rate, which can effectively utilize the resources of the switch, balance the load of the switch, avoid resource waste, that is, avoid the situation that some time slots are overloaded and some time slots are idle, thereby improving the overall performance of the network.

[0082] In an example, the routing and scheduling result includes a scheduling order. In the above step S104, the routing and scheduling results of each data stream are determined in the following manner:

[0083] First, use the first time slot that meets the constraint conditions as the third time slot. Exemplarily, the constraint conditions can be frame transmission offset constraints, network resource constraints, etc. Find available time slots as coherent time slots (the third time slot) in the switches on the path through the constraint conditions.

[0084] Then, determine the data streams corresponding to each third time slot.

[0085] Finally, sort the data streams corresponding to each third time slot according to the offset of each third time slot to obtain the scheduling order of each data stream. In the embodiment of the present invention, for the third time slots that meet the constraint conditions, sort each data stream in descending order of the offset of the third time slot, so as to obtain the scheduling order of each data stream.

[0086] In an alternative embodiment, for the first time slot that does not meet the constraint conditions, do not schedule the data stream corresponding to the first time slot.

[0087] In the embodiment of the present invention, using the first time slot that meets the constraint conditions as the third time slot ensures that the data stream meets the pre-constructed constraint conditions, thereby ensuring the security and stability of the network; determining the data streams corresponding to each third time slot and sorting the data streams according to the offset of each third time slot can obtain the scheduling order of each data stream, thereby optimizing the routing and scheduling, improving the performance and reliability of the network, and providing more decision-making basis for better predicting the behavior and performance of the network.

[0088] In an alternative embodiment, each switch needs to be initialized at the initial moment of the system. Exemplarily, each switch is initialized using bandwidth and cache resources. Each switch in the data flow path checks the status of its bandwidth and cache resources to find sufficient time slots for bandwidth and cache for each switch in the path.

[0089] In one example, the constraints include at least one or more of frame transmission offset constraints, network resource constraints, end-to-end delay constraints, switch queue resource constraints, and receive window constraints.

[0090] In an alternative embodiment, on the switch, the number of time slots injected by each data flow should not exceed the number of time slots in each scheduling period in the 5G converged network. In this converged network, since the transmission of periodic data flows is periodic, the least common multiple of the periods of all data flows can be used as the scheduling period T.

[0091] Otherwise, when the offset is too large, the next data flow has been generated and the previous data flow has not been sent yet. A large amount of data flows need to be cached on the terminal, reducing the storage utilization rate on the terminal. When the switch takes reasonable offset time slots, resources can be allocated more reasonably, thereby improving the success rate of service flow scheduling. Therefore, the frame transmission offset constraint C1 is expressed as follows:

[0092]

[0093] where f i inject represents the end-to-end delay allowed for the data flow, f i period represents the scheduling period of the data flow, and t slot represents the minimum scheduling duration.

[0094] In an alternative embodiment, the network resource constraint means that when the upstream switch transmits a data flow, the downstream switch has sufficient network resources to accept the data flow, that is, the network resource threshold of the downstream switch is greater than or equal to the network resource threshold of the upstream switch. Among them, the network resources are characterized by the time slots per hop of the switch. The time slots for the downstream switch to accept the data packet should be the same as the time slots for the upstream switch to send the data packet. Thus, the network resource constraint C2 is expressed as follows:

[0095] C2: T slot = f i path (S k ) + f i inject

[0096] T slot ' ≥ T slot

[0097] Among them, for time-sensitive flows, f i path(S k ) represents the number of hops of the data stream on the upstream switch f i path Then T slot is the time slot per hop of the upstream switch, and T slot ' is the time slot per hop of the downstream switch.

[0098] In an alternative embodiment, the end-to-end delay constraint includes that the transmission time from the source switch to the destination switch should be less than or equal to the deadline of the data stream. The end-to-end delay constraint C3 is expressed as follows:

[0099] C3:

[0100] Among them, T is the transmission time from the source switch to the destination switch, represents the total number of hops in the switches on the flow path.

[0101] In an alternative embodiment, the 5G converged network is obtained by the convergence of the 5G network and TSN. In TSN, Cyclic Queuing and Forwarding (CQF) is adopted. As one of the TSN synchronous traffic shaping mechanisms, the CQF algorithm provides a new idea for the deterministic transmission of traffic in the converged network architecture. The CQF algorithm is based on ping-pong queues and performs packet scheduling alternately according to odd and even time slots. It can not only ensure the deterministic upper and lower bounds of the end-to-end transmission delay, but also does not require complex configuration for each switch compared with the other two models, and the complexity of the control algorithm is lower. The CQF algorithm is implemented through the combination of the per-stream filtering and policing (PSFP) defined by IEEE Std802.1Qci and the traffic scheduling mechanism defined by IEEE Std 802.1Qbv 8.6.8.4 and 8.6.9. PSFP is used to direct the received frames to one of a pair of outbound queues on a timed basis, which is determined by the period time of the per-stream filter (PSF), and traffic scheduling is used to ensure the transmission of data frames from the appropriate queue using the same period time. Its basic principle is that traffic is transmitted and queued along the network path in a cyclic manner.

[0102] The CQF algorithm occupies a total of two queues, one for caching data packets and the other for sending data packets. Therefore, in each time slot, the total length of the data streams in the cache queue should not exceed the length of the cache queue, and the data streams transmitted by the transmission queue should not exceed the queue bandwidth size. Q i,t is a binary variable. If the data stream F iThe m-th data stream passes through switch S at time slot t k , then Q i,t = 1, otherwise Q i,t is 0. C4 is a constraint on the m-th data stream, and C5 is a constraint on time slot t. The switch queue resource constraint C6 is expressed as follows:

[0103]

[0104]

[0105]

[0106] Among them, let L que represent the length of the buffer queue, is the number of data stream frames that data stream F i will pass through in the scheduling period T.

[0107] For the receive window constraint, according to the transmission rules described in the CQF algorithm, the time slot when the upstream switch sends a data stream should be the same as the time slot when the adjacent downstream switch receives the data stream. The smallest time slot that satisfies the CQF transmission rules can ensure this constraint.

[0108] The working process of a 5G converged network traffic scheduling method is illustrated below through a specific embodiment. Among them, the 5G converged network is obtained by the convergence of a 5G network and a TSN network. The TSN network topology is abstracted as an undirected graph G = (V, E), where V represents the set of all nodes in the 5G converged network. E is the edge set of two adjacent nodes, that is, the link set in the network. Time-sensitive data streams are modeled as periodic data streams, and each data stream is only transmitted within its period. In this converged network, the queue scheduling algorithm adopts the CQF algorithm. An enabled CQF switch contains 8 pairs of queues for each output port, and the two queues with the highest default priority are used as the CQF queues for transmitting and buffering time-sensitive flows. Let the set of traffic flows with time-sensitive characteristics be

[0109] F = {F1, F2,..., Fi,...}

[0110] F i = [f i source , f i destination , f i lenth , f i period , f i τ , t i inject , f i pathT

[0111] Among them, F i The parameters represent the source end station system, the terminal end station system, the data frame length, the data transmission period, the upper bound of the end-to-end delay, the optimal value of the injection time, and the transmission switch path in sequence.

[0112] Figure 2 It is a flowchart of the 5G converged network traffic scheduling method. In Figure 2 QRAND and QBUF respectively represent the storage spaces provided for the bandwidth and cache occupancy. fspace represents the frame transmission offset set. tmp-able represents the current frame transmission offset. Foffset(i) represents the end-to-end allowed delay of traffic i. Foffset(i)-1 represents mapping the data stream from the maximum offset. Q-SLOTCHECK(temp-able) represents whether the current transmission offset time slot meets the conditions. f-cspace and MY-TIME{} respectively represent the current frame transmission offset time slot and the set of appropriate frame transmission offset time slots. Each switch in the path checks the status of its bandwidth and cache resources. f-cspace→MY-TIME{} is to find sufficient bandwidth and cache time slots for each switch in the path and store and record them. fi.flag is the total length of the data stream transmitted within the time slot, and sw_queue_constraint(fi,G,T) is the length of the cache queue.

[0113] For the working process of the 5G converged network traffic scheduling method, it can be summarized into the following five steps.

[0114] Step 1: First, find the shortest path of the flow transmission according to the minimum path algorithm based on the source address and terminal address of the data stream. The minimum path algorithm can perform V-1 relaxation operations on the topology G=(V, E) to obtain all possible shortest paths. Sort according to the allowed end-to-end delay set by F i set.

[0115] Step 2: Initialize each switch with bandwidth and cache resources. Each switch in the flow path checks the status of its bandwidth and cache resources, so as to find sufficient time slots for bandwidth and cache for each switch in the path.

[0116] Step 3: Due to the transmission mechanism of CQF, it is necessary to find coherent time slots in the available time slots of the switches on each path.

[0117] Step 4: Add the available time slots to the set time slots. In order to balance the load and make full use of network resources, the network flow will preferentially select the time slots with lower resource utilization for injection.

[0118] ​Step 5: Determine the selected time slot according to the latency constraint. If the allowed end-to-end delay is satisfied, the scheduling is successful.

[0119] Figure 3 A 5G converged network traffic scheduling system proposed according to an exemplary embodiment. As Figure 3 shown, the system includes: a network topology analysis module 1 and a global routing and scheduling module 2;

[0120] The network topology analysis module 1 is used to obtain the network data of the 5G converged network and the service flow data of at least one data flow; and send the network data and each service flow data to the global routing and scheduling module 2.

[0121] The global routing and scheduling module 2 is used to determine the paths of each data flow according to the network data and each service flow data; determine the first time slot of each data flow in each switch according to each path; and determine the routing and scheduling result of each data flow according to each first time slot and the pre-constructed constraint conditions.

[0122] Through the above system, the global routing and scheduling module 2 uses the obtained network data of the 5G converged network and the service flow data of the data flow to determine the transmission paths of each data flow in the 5G converged network, determines the first time slot of each data flow in each switch according to the paths, and further determines the routing and scheduling result of the data flow according to the first time slot and the constraint conditions, meeting the requirements of the 5G converged network, realizing the traffic scheduling of the 5G converged network and the end-to-end deterministic transmission, and ensuring the heterogeneous network adaptation and seamless cross-network highly reliable bearer.

[0123] In an example, the system further includes: a network resource analysis module, a network connection management module, and an application program interface.

[0124] The network resource analysis module is connected to the network topology analysis module 1 and is used to manage virtual network resources and provide resource scheduling information through the application program interface.

[0125] In an alternative embodiment, the resource scheduling information includes, but is not limited to, resource utilization rate, task scheduling information, virtual machine and container information, network topology information, load balancing information, etc. Among them, the resource utilization rate refers to the current utilization information of computing, storage, and network resources, including CPU usage rate, memory utilization rate, disk space utilization rate, etc. The task scheduling information includes information such as tasks being executed, task queues, and task priorities, facilitating application developers to understand the status and priorities of task execution. The virtual machine and container information includes the status, configuration, and performance statistics information of virtual machines or containers during operation in the cloud environment, i.e., the number of virtual machines, running status, IP addresses, etc. The network topology information includes network topology, device connections, traffic conditions, etc., enabling application developers to understand the network structure and performance. The load balancing information includes information about the status, rules, and current load distribution of the load balancer, facilitating application developers to optimize the performance of their applications.

[0126] The network connection management module is connected to the global routing and scheduling module 2 and is used to implement end-to-end service connections.

[0127] In the embodiment of the present invention, the network resource analysis module manages virtual network resources and provides resource scheduling information through an application programming interface, enabling the system to more precisely manage network resources and perform dynamic scheduling according to business requirements, improving the resource utilization efficiency and network performance; the network connection management module is connected to the global routing and scheduling module 2 to implement end-to-end service connections. This enables the system to better support various business requirements, provide stable and reliable connection services, and improve the network availability and service quality; by adding the network resource analysis module and the application programming interface, the system can more flexibly expand and manage network resources. This enables the system to adapt to the constantly changing network environment and business requirements, improving the system scalability and adaptability.

[0128] In an example, the system further includes: a protocol management module.

[0129] The protocol management module is used to parse the protocols in the 5G converged network and implement the interaction between the 5G converged network and the network topology analysis module 1, the global routing and scheduling module 2, and the network connection management module.

[0130] In the embodiment of the present invention, the protocol management module can parse the protocols in the 5G converged network to ensure the communication and interaction between the system and various network devices and application programs, enabling the system to be seamlessly integrated with the existing network infrastructure and achieving protocol compatibility and interoperability; at the same time, the protocol management module can provide standardized interfaces and protocols, simplifying the work of developers and network administrators, enabling the system to be more conveniently integrated with other network devices and application programs, and reducing the cost and complexity of development and maintenance.

[0131] In one example, the global routing and scheduling module 2 includes a data flow information analysis sub-module. The data flow information analysis sub-module is used to determine packets with the same source MAC address, destination MAC address, source IP address, destination IP address, and port number as the same data flow.

[0132] Figure 4 It is a schematic diagram of the specific structure of a 5G converged network traffic scheduling system. The 5G converged network is obtained by integrating the 5G network and the TSN network. This system includes functional modules such as protocol management, network topology analysis, global routing and scheduling, network connection management, network resource analysis, and application program interfaces. Among them, the global routing and scheduling is also used for data flow information analysis.

[0133] In Figure 4 the control plane of the 5G TSN converged architecture, the domain controllers (5G system controller and TSN system configurator) communicate with each other to complete the exchange of local network data, and then forward the network information to the coordination controller, so that the system (5G TSN coordination controller) has a complete network view. The 5G TSN coordination controller grasps the global network status. The northbound interface provides abstract network information to the network application APP to obtain service requirements, and the southbound interface interacts with the domain controllers (5G system controller and TSN system configurator) to support the coordinated configuration of the entire 5G TSN network. Its specific configuration process includes:

[0134] First, the domain controllers exchange parameter information such as the TSN flow transfer direction, transmission delay budget, priority, etc., as well as network management and configuration information to achieve the effective transfer of traffic data.

[0135] Then, the domain controllers transfer all the network information to the coordination controller through the interface, and the coordination controller calculates the global route according to the topology information and resource information of the entire network it grasps.

[0136] Finally, the coordination controller transfers the calculated routing and scheduling information to the domain controller, so that the network configuration command is issued to the network device, and the TSN data flows with different Quality of Service (QoS) requirements are mapped to appropriate Protocol Data Unit (PDU) sessions and QoS flows to achieve differentiated QoS scheduling to ensure the deterministic end-to-end transmission of the TSN service flow. In the control plane of the 5G TSN converged architecture, the domain controllers communicate with each other to complete the exchange of local network data, and then forward the network information to the coordination controller, so that the coordination controller has a complete network view.

[0137] Network resource analysis is responsible for managing virtual network resources and opening northbound interfaces to provide resource scheduling information for application developers. Connection management is responsible for end-to-end service connections. Global routing scheduling grasps the topology of the entire network, calculates the optimal inter-domain route, and forwards the calculated route information to each domain controller. The network topology analysis process is responsible for collecting, organizing and updating data about network topology and network resources in each domain controller. The protocol management process mainly conducts interaction between the collaborative controller and the domain controller, and can parse related protocols.

[0138] Figure 5 FIG. 1 is a schematic diagram of a hardware structure of a computer device according to an exemplary embodiment. Figure 5 As shown, the device includes one or more processors 510 and a memory 520, and the memory 520 includes a persistent memory, a volatile memory, and a hard disk. Figure 5 A processor 510 is taken as an example. The device may also include: an input device 530 and an output device 540.

[0139] The processor 510, the memory 520, the input device 530 and the output device 540 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0140] The processor 510 may be a central processing unit (CPU). The processor 510 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips. A general-purpose processor may be a microprocessor or the processor may be any conventional processor.

[0141] The memory 520 is a non-transient computer-readable storage medium, including persistent memory, volatile memory and hard disk, which can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the 5G converged network traffic scheduling method in the embodiment of the present application. The processor 510 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 520, that is, implementing any of the above-mentioned 5G converged network traffic scheduling methods.

[0142] The memory 520 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data used as needed, etc. In addition, the memory 520 may include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 520 may optionally include a memory remotely disposed relative to the processor 510, and these remote memories may be connected to the data processing device through a network. Examples of the above networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0143] The input device 530 may receive input digital or character information and generate signal inputs related to user settings and function controls. The output device 540 may include a display device such as a display screen.

[0144] One or more modules are stored in the memory 520 and, when executed by one or more processors 510, perform the method as Figure 1 shown.

[0145] The above product may execute the method provided in the embodiments of the present invention and has functional modules and beneficial effects corresponding to the execution of the method. For technical details not described in detail in this embodiment, reference may specifically be made to the relevant descriptions in the embodiments as Figure 1 shown.

[0146] The embodiments of the present invention also provide a non-transitory computer storage medium storing computer-executable instructions that can execute the methods in any of the above method embodiments. The storage medium may be a magnetic disk, an optical disc, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above types of memories.

[0147] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0148] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features claimed herein.

Claims

1. A 5G converged network traffic scheduling method, characterized in that, The method includes: Obtaining network data of a 5G converged network and traffic flow data of at least one data stream; Determining paths of the data streams according to the network data and the traffic flow data of each; Determining first time slots of the data streams in each switch according to the paths of each; Determining routing and scheduling results of the data streams according to the first time slots of each and pre-constructed constraint conditions.

2. The method according to claim 1, wherein The traffic flow data includes a source address and a terminal address. Determining the path of the data stream according to the network data and the traffic flow data includes: Determining the path of the data stream according to the network data, the source address, the terminal address, and a minimum path algorithm.

3. The method according to claim 1, characterized in that The traffic flow data includes a deadline. Determining the first time slots of the data streams in each switch according to the paths of each includes: Sorting the data streams according to the deadlines of each to obtain a first sorting result; Determining the first time slots of the data streams in each switch according to the paths of each and the first sorting result.

4. The method according to claim 3, characterized in that Determining the first time slot of the data stream in the switch according to the path and the first sorting result includes: Determining multiple second time slots of the data stream in the switch according to the path and the first sorting result; Calculating the resource utilization rate of each second time slot; Selecting the second time slot with the minimum resource utilization rate as the first time slot of the data stream in the switch.

5. The method according to claim 1, wherein The routing and scheduling result includes a scheduling order. Determining the routing and scheduling results of the data streams according to the first time slots of each and pre-constructed constraint conditions includes: Regarding the first time slots that meet the constraint conditions as third time slots; Determining the data streams corresponding to the third time slots of each; Sorting the data streams corresponding to the third time slots of each according to the offsets of the third time slots of each to obtain the scheduling order of the data streams of each.

6. A 5G converged network traffic scheduling system, characterized in that, The system includes: a network topology analysis module and a global routing and scheduling module; The network topology analysis module is configured to obtain network data of a 5G converged network and traffic flow data of at least one data stream; and send the network data and the traffic flow data of each to the global routing and scheduling module; The global routing and scheduling module is configured to determine paths of the data streams according to the network data and the traffic flow data of each; determine first time slots of the data streams in each switch according to the paths of each; and determine routing and scheduling results of the data streams according to the first time slots of each and pre-constructed constraint conditions.

7. The system according to claim 6, wherein The system further includes: a network resource analysis module, a network connection management module, and an application programming interface; The network resource analysis module is connected to the network topology analysis module and is configured to manage virtual network resources and provide resource scheduling information through the application programming interface; The network connection management module is connected to the global routing and scheduling module and is configured to implement end-to-end service connections.

8. The system according to claim 7, wherein The system further includes: a protocol management module; The protocol management module is used to parse the protocols in the 5G converged network and implement the interaction between the 5G converged network and the network topology analysis module, the global routing and scheduling module, and the network connection management module.

9. A computer device, characterized in that, It includes a memory and a processor, which are communicatively connected to each other. Computer instructions are stored in the memory, and the processor executes the computer instructions to perform the steps of the 5G converged network traffic scheduling method according to any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the 5G converged network traffic scheduling method according to any one of claims 1-5.

Images