Multi-interface intelligent path selection network router, system and data transmission method

Abstract

The invention provides a multi-interface intelligent path selection network router, a system and a data transmission method. The method comprises the following steps: acquiring various attributes of an nth data packet transmitted by the multi-interface intelligent path selection network router; calculating a priority score Pntotal of the nth data packet transmitted by the router; the data packets are classified, and then FE interface transmission or GE interface transmission is selected for each data packet; performing path selection on the nth data packet when the nth data packet is transmitted at the GE interface or the FE interface by adopting an EMCP method; performing dynamic queue shaping, and adjusting a data packet transmission rate and a packet loss rate of each interface; and calculating and judging a data transmission quality index Uq of each interface, and judging whether queue overflow occurs or not so as to select another bandwidth interface to transmit a data packet. Through intelligent queue adjustment, the queue length is adjusted in real time according to the priority of the data packet and the interface processing capacity, and the flexibility and efficiency of data transmission are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of router data transmission, and in particular relates to a multi-interface intelligent path selection network router, a system and a data transmission method. Background Art

[0002] With the development of network equipment, Ethernet technologies of different rates are widely used in different scenarios. Among them, FastEthernet (100Mbps) and Gigabit Ethernet (1000Mbps) are the two most common interface rates. In modern communication networks, with the rapid growth of data traffic and the increase in diversified demands, traditional fixed interface configuration routers have gradually shown performance bottlenecks and insufficient flexibility. Especially in routers with both Fast Ethernet (FE) and GigabitEthernet (GE) interfaces, the transmission capabilities of different interfaces vary significantly, and the randomness and volatility of data traffic lead to uneven resource utilization, affecting the overall network performance. Therefore, how to reasonably allocate data traffic, dynamically adjust the packet transmission queue, and efficiently select the transmission path based on the packet index has become a technical problem that needs to be solved urgently.

[0003] In the prior art, transmission routers disclosed in Chinese patents with application numbers 201410494438.X and 202022847550.0 usually adopt static queue allocation and path selection strategies, which cannot be dynamically adjusted according to real-time changes in traffic. Their load balancing capabilities are limited, and high-speed GE interfaces may be idle, while low-speed FE interfaces are easily overloaded, resulting in resource waste or performance bottlenecks; in addition, Chinese patent application number 201010548431.3 is a control method for a router queue control system based on congestion identification, which performs congestion identification according to 4 different states composed of flag bit combinations, and provides the identification results to the queue control module, so as to adopt corresponding queue control methods and calculate the probability of data discard or marking. However, it only calculates the queue ratio Rq(k) and the flow rate ratio Rx(k), compares the queue ratio and the flow rate ratio with 1, and marks the corresponding flag bit. Its path selection rules for queues and data transmission are inefficient and cannot perform intelligent scheduling for traffic of different priorities. At the same time, when the queue in the FE interface overflows, it is impossible to increase the rate and transfer it to the GE interface for transmission when coordinating among multiple FE interfaces, or when the queue in the GE interface overflows, it is impossible to reduce the rate and transfer it to the GE interface for transmission when coordinating among multiple GE interfaces. It is difficult to meet the needs of high real-time or low latency, low packet loss rate services. Summary of the invention

[0004] The present invention aims at the above-mentioned defects and provides a multi-interface intelligent path selection network router, system and data transmission method. The present invention provides a multi-interface intelligent path selection network router, which can simultaneously support Fast Ethernet and Gigabit Ethernet interfaces, optimize data transmission between different rates, and improve network transmission efficiency and resource rate.

[0005] The present invention provides the following technical solution: a data transmission method of a multi-interface intelligent path selection network router, the method adopts the EMCP method to select the transmission path of each data packet and dynamically adjusts the queue of the transmission data packet of each interface in real time, comprising the following steps:

[0006] S1: Obtain the type, source address, destination address, protocol type, port number and queue length of the nth data packet transmitted by the multi-interface intelligent path selection network router;

[0007] S2: Assign a packet type score P to each packet based on the DSCP field. n_type , calculate the priority score P of the nth data packet transmitted by the router n_total ;

[0008] S3: Classify a total of N data packets according to the priority scores. When the priority score of the nth data packet is P n_total Greater than the priority threshold P thr When the nth priority score is selected, the data packet with the nth priority score is transmitted to the GE interface for transmission; otherwise, the data packet with the nth priority score is transmitted to the FE interface for transmission;

[0009] S4: using the EMCP method to select a path for the nth data packet when it is transmitted on the GE interface or the FE interface;

[0010] S5: Dynamically monitor the packet transmission congestion of each interface, perform dynamic queue shaping, and adjust the packet transmission rate and packet loss rate of each interface;

[0011] S6: Calculate and determine the data transmission quality index U of each FE interface and GE interface q When it is greater than the maximum threshold of low-quality transmission, it indicates that a queue overflow occurs. In this case, the overflowed queue of the GE interface is transferred to the FE interface for transmission at a reduced rate, or the overflowed queue of the GE interface is transferred to the GE interface for transmission at a increased rate, thereby reducing the packet loss rate.

[0012] As a preferred embodiment of the present invention, the data packet types obtained in step S1 include: one or more of VoIP real-time stream, video stream, file transfer packet, ordinary data packet or background synchronization task data packet, and the corresponding data packet type score P n_typeare 10, 8, 5, 2 and 1 respectively; the source address includes: one or more of a local network address, a trusted external address or a public external address, and the corresponding source address priority score P n_s 8, 5 and 2 respectively; the target address includes: one or more of the intranet core services, other intranet devices, external trusted servers or public Internet targets, and the corresponding target address priority score P n_d They are 10, 7, 5 and 3 respectively; the protocol type includes one or more of UDP protocol, TCP protocol or ICMP protocol, and the corresponding protocol type score P n_a 8, 5 and 3 respectively; the port number includes: one or more of HTTP / HTTPS port, SIP port, RTP port, FTP port or SSH port, and the corresponding port number score P n_p They are 6, 9, 10, 4, and 7 respectively.

[0013] As a preferred embodiment of the present invention, the step S2 calculates the priority score P of the nth data packet transmitted by the router. n_total The formula is as follows:

[0014] P n_total =ω1P n_type +ω2P n_s +ω3P n_d +ω4P n_a +ω5P n_p ; Wherein, ω1 = 0.3, ω2 = 0.2, ω3 = 0.2, ω4 = 0.2, ω5 = 0.1; the priority threshold P thr is 6.

[0015] As a preferred embodiment of the present invention, the S4 step comprises:

[0016] S41: First, according to the calculation result of the priority score, determine that the number of data packets transmitted through the FE interface is αN, and the number of data packets transmitted through the GE interface is (1-α)N;

[0017] S42: Calculate the traffic load dynamic coefficient σ of the i-th FE interface i and the traffic load dynamic coefficient δ of the jth GE interface j :

[0018] in, is the current traffic demand of the i-th FE interface, max(R FE ) is the maximum flow requirement in one FE interface; f i is the dynamic adjustment factor of the i-th FE interface; f i =0.1~0.5;

[0019] in, is the current traffic demand of the j-th GE interface, max(R GE ) is the maximum flow demand among J GE interfaces; f j =0.1~0.5; where i=1,2,…,I; j=1,2…,J;

[0020] S43: performing path selection for αN data packets of i FE interfaces and (1-α)N data packets of j GE interfaces;

[0021] When the nth data packet is selected for transmission through the FE interface, the path selection coefficient σ i is the path weight of the i-th FE interface, Hash(P n_type ,P n_s ,P n_d ,P n_a ,P n_p ) is a hash value calculation function for calculating the header field of the nth data packet related information; mod is the remainder calculation; Is the exclusive OR operator symbol;

[0022] When the nth data packet is selected for transmission through the GE interface, the path selection coefficient δ j is the path weight of the j-th GE interface;

[0023] S44: Calculate the i-th data transmission coefficient selection threshold range: For a total of I FE interfaces consisting of I data transmission paths, according to the calculated Index n Determine whether it belongs to the transmission threshold range of the i-th path. If so, transmit the n-th data packet through the i-th FE interface; if not, traverse the 1 to i-1 and i+1 to I paths to determine the FE interface for transmitting the n-th data packet;

[0024] S45: Calculate the j-th data transmission coefficient selection threshold range: For J data transmission paths consisting of J GE interfaces, according to the calculated Index n Determine whether it belongs to the transmission threshold range of the jth path. If so, transmit the nth data packet through the jth FE interface; if not, traverse the 1st to j-1th data transmission paths and the j+1th to Jth data transmission paths to determine the GE interface for transmitting the nth data packet.

[0025] As a preferred embodiment of the present invention, the step S5 comprises the following steps:

[0026] S51: Calculate the nth data packet of the qth interface in the kth time slot t k Transfer rate

[0027] When q=i,

[0028] When q=j, Where, k = 1, 2, ... K;

[0029] S52: Further calculate the qth interface in the kth time slot t k Interface transmission rate V for multiple packets q :

[0030] When q=i,

[0031] When q=j,

[0032] S53: Judgment With V q The size of and the occupancy rate of the queue capacity of the qth interface can be used to obtain the congestion degree of the qth interface. The judgment criteria are as follows:

[0033]

[0034] Among them, QO q is the queue capacity occupancy rate of the qth interface, Min th and Max th They are the minimum and maximum queue capacity occupancy thresholds of the interface respectively; Min th,q =0.45QS q , Max th =0.75QS q , QS q is the length of the packet transmission queue of the qth interface;

[0035] S54: According to the congestion level of the qth interface, update the nth data packet of the qth interface in the kth time slot t k Transfer rate and packet loss rate

[0036] As a preferred embodiment of the present invention, in step S54, when C q When there is no congestion,

[0037] When C q For low congestion, is the floor rounding function;

[0038] When C q When the congestion is moderate, is the ceiling rounding function;

[0039] When C q When the congestion is high, Furthermore, when q is i,

[0040] When q is j,

[0041] As a preferred embodiment of the present invention, the step S6 includes the following steps:

[0042] S61: Calculate the data transmission quality index U of the qth interface q :

[0043] When q=i,

[0044] When q=j,

[0045] S62: Determine the data transmission quality indicator U of the qth interface q Is it greater than or equal to the maximum threshold of low-quality transmission? If so, further determine whether the qth interface is a FE interface or a GE interface. If it is a GE interface, select to transfer the overflowed queue of the GE interface to the FE interface for transmission at a reduced rate; if it is a FE interface, select to transfer the overflowed queue of the FE interface to the GE interface for transmission at a increased rate.

[0046] If the data transmission quality index U of the qth interface q If the value is less than the maximum threshold of low-quality transmission, it is only necessary to repeat steps S1 to S5 to perform data transmission.

[0047] The present invention also provides a multi-interface intelligent path selection network router control system that uses the above method to perform data transmission, the system includes a data packet information acquisition module, a routing and forwarding module, an interface type allocation module, a path selection module and a congestion control module;

[0048] The data packet information acquisition module is used to obtain the type, source address, destination address, protocol type, port number and queue length of the nth data packet transmitted by the multi-interface intelligent path selection network router;

[0049] The routing and forwarding module is used to assign a data packet type score P to each data packet according to the DSCP field. n_type, calculate the priority score P of the nth data packet transmitted by the router n_total ;

[0050] The interface type allocation module is used to classify a total of N data packets according to priority scores, and when the priority score of the nth data packet is P n_total Greater than the priority threshold P thr When the nth priority score is selected, the data packet with the nth priority score is transmitted to the GE interface for transmission; otherwise, the data packet with the nth priority score is transmitted to the FE interface for transmission;

[0051] The path selection module is used to select a path for the nth data packet when it is transmitted on the GE interface or the FE interface by using the EMCP method;

[0052] The congestion control module is used to dynamically monitor the data packet transmission congestion of each interface, perform dynamic queue shaping, and adjust the data packet transmission rate and packet loss rate of each interface; the data transmission quality management module is used to calculate and determine the data transmission quality index U of each FE interface and GE interface. q When it is greater than the maximum threshold of low-quality transmission, it indicates that a queue overflow occurs. In this case, the overflowed queue of the GE interface is transferred to the FE interface for transmission at a reduced rate, or the overflowed queue of the GE interface is transferred to the GE interface for transmission at a increased rate, thereby reducing the packet loss rate.

[0053] The present invention also provides a multi-interface intelligent path selection network router that uses the above method for data transmission, the multi-interface intelligent path selection network router includes a memory, a processor, a liquid crystal display screen arranged on the upper part of the multi-interface intelligent path selection network router, a 12V DC power input interface arranged on the rear side of the router, a CONSOLE management interface and two antennas, as well as a USB interface, an SFP optical fiber interface, a first indicator light area arranged between the USB interface and the SFP optical fiber interface, a POE Ethernet power supply interface, a Fast Ethernet interface module, a second indicator light area and a Gigabit Ethernet interface module arranged on the front side of the multi-interface intelligent path selection network router; the Fast Ethernet interface module includes a plurality of FE interfaces, and the Gigabit Ethernet interface module includes a plurality of GE interfaces; the memory stores a computer-readable medium that can execute the above method on the processor.

[0054] As a preferred embodiment of the present invention, the several FE interfaces of the Fast Ethernet interface module support the standard IEEE802.3u protocol, and the several GE interfaces of the Gigabit Ethernet interface module support the standard IEEE802.3ab protocol.

[0055] The beneficial effects of the present invention are:

[0056] 1. The router provided by the present invention calculates the path selection coefficient Index by introducing the calculation of the hash value n The invention adopts a dynamic queue adjustment mechanism, which can calculate the index in real time based on the characteristics of the data packet (such as source address, destination address, data type, etc.), and map it to different interface paths for forwarding. Combined with the weight adjustment mechanism, the transmission load of the FE and GE interfaces is dynamically balanced to maximize bandwidth utilization. At the same time, through intelligent queue adjustment, the queue length is adjusted in real time according to the priority of the data packet and the interface processing capability, thereby improving the flexibility and efficiency of data transmission. The invention not only improves the overall performance of the router, but also reduces network delay and congestion.

[0057] 2. The router provided by the present invention has high compatibility and can support both FE interface and GE interface to meet the requirements of different network environments. By optimizing queue management and traffic shaping, the overall data transmission efficiency is improved and data is transmitted efficiently. Through traffic control and congestion management, the loss of data packets when the queue overflows is reduced.

[0058] 3. The present invention can provide efficient data transmission between the main router and branch office equipment, while ensuring smooth transition of data flows between interfaces with different rates, supporting flexible data packet transmission methods for multiple interfaces (such as FE and GE interfaces), and dynamically allocating data flow configurations between multiple FE interfaces and / or multiple GE interfaces to meet the needs of different users.

[0059] 4. When the network router provided by the present invention is transmitting a certain data packet, if the path cannot meet the transmission requirements, the system can automatically traverse other paths (such as the i±1 path of the FE or the j±1 path of the GE interface) to reallocate the data packet transmission path. This mechanism enhances the fault tolerance of the network and can maintain the normal operation of data transmission even if some interfaces fail. The present invention not only optimizes the allocation of network resources through dynamic load balancing and intelligent path selection, but also enhances the stability, flexibility and fault tolerance of the system. This mechanism is suitable for network environments with high concurrency and complex dynamic requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The present invention will be described in more detail below based on embodiments and with reference to the accompanying drawings, wherein:

[0061] Figure 1 A schematic flow chart of a data transmission method for a multi-interface intelligent path selection network router provided by the present invention;

[0062] Figure 2The method provided by the present invention selects the FE interface path coefficient Index of different data packets n Dynamic change diagram of

[0063] Figure 3 The method provided by the present invention is to select the path coefficient Index of the GE interface of different data packets n Dynamic change diagram of

[0064] Figure 4 It is a schematic diagram of monitoring values ​​of real-time throughput and packet loss rate of data packets with different transmission rates on the FE interface and queue shaping under high congestion conditions in an embodiment of the present invention;

[0065] Figure 5 It is a schematic diagram of monitoring values ​​of real-time throughput and packet loss rate of data packets with different transmission rates on a GE interface and queue shaping under high congestion conditions in an embodiment of the present invention;

[0066] Figure 6 This is a delay comparison diagram of the FE interface in an embodiment of the present invention before and after the FE interface is regulated by the method of the present invention;

[0067] Figure 7 This is a delay comparison diagram of the GE interface in the embodiment of the present invention before and after the method of the present invention is used for regulation;

[0068] Figure 8 A schematic diagram of the module structure of a multi-interface intelligent path selection network router control system provided by the present invention;

[0069] Fig. 9 A schematic diagram of data connection for the network router provided by the present invention;

[0070] Fig.10 An overall side view of the network router provided by the present invention;

[0071] Fig.11 A schematic diagram of the front view of the structure of the network router provided by the present invention;

[0072] Fig.12 This is a schematic diagram of the rear view structure of the network router provided by the present invention. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] The present invention provides a data transmission method for a multi-interface intelligent path selection network router, the method adopts the EMCP method to select the transmission path of each data packet and dynamically adjust the queue of the transmission data packet of each interface in real time, such as Figure 1 As shown, the method of the present invention comprises the following steps:

[0075] S1: Obtain the type, source address, destination address, protocol type, port number and queue length of the nth data packet transmitted by the multi-interface intelligent path selection network router;

[0076] S2: Assign a packet type score P to each packet based on the DSCP field. n_type , calculate the priority score P of the nth data packet transmitted by the router n_total ;

[0077] S3: Classify a total of N data packets according to the priority scores. When the priority score of the nth data packet is P n_total Greater than the priority threshold P thr When the nth priority score is selected, the data packet with the nth priority score is transmitted to the GE interface for transmission; otherwise, the data packet with the nth priority score is transmitted to the FE interface for transmission;

[0078] S4: using the EMCP method to select a path for the nth data packet when it is transmitted on the GE interface or the FE interface;

[0079] S5: Dynamically monitor the packet transmission congestion of each interface, perform dynamic queue shaping, and adjust the packet transmission rate and packet loss rate of each interface;

[0080] S6: Calculate and determine the data transmission quality index U of each FE interface and GE interface q When it is greater than the maximum threshold of low-quality transmission, it indicates that a queue overflow occurs. In this case, the overflowed queue of the GE interface is transferred to the FE interface for transmission at a reduced rate, or the overflowed queue of the GE interface is transferred to the GE interface for transmission at a increased rate, thereby reducing the packet loss rate.

[0081] The data packet types obtained in step S1 include: one or more of VoIP real-time stream, video stream, file transfer packet, common data packet or background synchronization task data packet, and the corresponding data packet type score P n_type They are 10, 8, 5, 2 and 1 respectively; the source address includes one or more of a local network address, a trusted external address or a public external address, and the corresponding source address priority score P n_s The target addresses include one or more of the following: Intranet core services, other Intranet devices, external trusted servers, or public Internet targets. The corresponding target address priority score P n_dThey are 10, 7, 5 and 3 respectively; the protocol type includes one or more of UDP protocol, TCP protocol or ICMP protocol, and the corresponding protocol type score P n_a 8, 5 and 3 respectively; the port number includes: one or more of HTTP / HTTPS port, SIP port, RTP port, FTP port or SSH port, and the corresponding port number score P n_p They are 6, 9, 10, 4, and 7 respectively. As shown in Tables 1 to 5, they are P n_type , P n_s , P n_d , P n_a and P n_p Scoring scores for different packet types and descriptions of the packet's priority requirements.

[0082] Table 1. Packet type priority score P n_type

[0083] Packet Type <![CDATA[P n_type Score]]> describe Implementing streaming (such as VoIP, etc.) 10 Low latency requirements Video streaming (such as conferencing) 8 High bandwidth requirements File transfer package (such as FTP protocol file transfer) 5 Medium bandwidth, low real-time requirements Ordinary data packets (such as HTTP web browsing data) 2 Normal traffic Background synchronization task package 1 Lowest priority

[0084] Table 2 Source address priority score P n_s

[0085] Source address range <![CDATA[P n_s Score]]> describe Local network address (intranet) 8 Internal traffic, higher priority Trusted external address (fixed IP) 5 Known Trusted Sources Public external address 2 Usually a lower priority

[0086] Table III Target address priority score P n_d

[0087]

[0088]

[0089] Table 4 Target address priority score P n_a

[0090]

[0091] Table 5 Port number priority score P n_p

[0092] Target address range <![CDATA[P n_p Score]]> describe HTTP / HTTPS(80 / 443) 6 Normal web access SIP(5060) 9 VoIP signal control RTP(5004) 10 Live Streaming FTP(21) 4 File Transfer SSH(22) 7 Remote Management

[0093] In order to dynamically prioritize packets based on their attributes, such as packet type, source address, destination address, protocol type, and port number, a priority scoring formula can be constructed to assign a weight to each attribute and calculate the total priority score based on the specific attribute value. In step S2, the priority score P of the nth packet transmitted by the router is calculated. n_total The formula is as follows:

[0094] P n_total =ω1P n_type +ω2P n_s +v3Pn_d +ω4P n_a +ω5P n_p ; Among them, ω1=0.3, ω2=0.2, ω3=0.2, ω4=0.2, ω5=0.1; priority threshold P thr is 6.

[0095] In order to generate more detailed and clear information on how to use P n_type , P n_s , P n_d , P n_a and P n_p Scoring different types of data packets to obtain priority scores P n_total , and then select the FE interface or the GE interface for data transmission according to the priority score, which is illustrated below with examples 1 to 3.

[0096] Example 1

[0097] When the data to be transmitted by the source address is VoIP traffic, and the data transmitted through the UDP protocol is real-time voice, the data type is VoIP, so P n_type =10; the source address is an intranet device, so P n_s =8; the target address is the core service of the intranet, so P n_d =10; the protocol type is UDP protocol, so P n_a =8; the port number is 6060 (SIP, signal control), so P n_p =9.

[0098] Therefore, P n_total =0.3×10+0.2×8+0.2×10+0.2×8+0.1×9=9. Since it is greater than P thr , the data packet has a high priority, and the GE interface is selected to transmit the data packet.

[0099] Example 2

[0100] When the data to be transmitted by the source address is a normal web traffic data packet, the data packet type score is P n_type =3; the source address is a public external address, so P n_s =2; the target address is an external trusted server, so P n_d =5; the protocol type is TCP protocol, so P n_a =5; the port number is 80, so P n_p =6.

[0101] Therefore, P n_total =0.3×3+0.2×2+0.2×5+0.2×5+0.1×6=4.1. thrThe priority of this data packet is medium to low, so the FE interface is chosen to transmit the data packet.

[0102] Example 3

[0103] When the data to be transmitted by the source address is a background file, the packet type score is P n_type =5; the source address is a trusted external address, so P n_s =5; the target address is an intranet device, so P n_d =7; the protocol type is TCP, so P n_a =5; the port number is 21, so P n_p =4.

[0104] Therefore, P n_total =0.3×5+0.2×5+0.2×7+0.2×5+0.1×4=5.4. thr , the data packet has a medium priority, so the FE interface is selected to transmit the data packet. It can be seen that the priority scoring formula quantifies the importance of the data packet by comprehensively analyzing multiple attributes of the data packet (type, source address, destination address, protocol, port number). By flexibly adjusting the weight, it can adapt to different network environments and business needs, thereby achieving efficient traffic management.

[0105] The data packet must maintain integrity during transmission. Each data packet has a clear structure, including a header, a payload, etc., and decentralized transmission will destroy this integrity. When a router receives and forwards a data packet, it is based on the header information of the data packet (such as an IP address, a port number, etc.), and this information needs to be processed completely and centrally on one interface. The router provided by the present invention uses a routing table established from high to low based on the priority score calculated as above, and determines the forwarding path of each data packet based on the routing table. Based on the matching result of the destination address, a data packet will be forwarded to a specific interface. Therefore, as another preferred embodiment of the present invention, step S4 includes:

[0106] S41: First, according to the calculation result of the priority score, determine that the number of data packets transmitted through the FE interface is αN, and the number of data packets transmitted through the GE interface is (1-α)N;

[0107] S42: Calculate the traffic load dynamic coefficient σ of the i-th FE interface i and the traffic load dynamic coefficient δ of the jth GE interface j :

[0108] in, is the current traffic demand of the i-th FE interface, max(R FE) is the maximum flow requirement in one FE interface; f i is the dynamic adjustment factor of the i-th FE interface; f i =0.1~0.5; Preferably, f i =0.4;

[0109] in, is the current traffic demand of the j-th GE interface, max(R GE ) is the maximum flow demand among J GE interfaces; f j =0.1~0.5; wherein, i=1,2,…,I; j=1,2…,J; preferably, f j =0.5;

[0110] S43: performing path selection for αN data packets of i FE interfaces and (1-α)N data packets of j GE interfaces;

[0111] When the nth data packet is selected for transmission through the FE interface, the path selection coefficient

[0112] σ i is the path weight of the i-th FE interface, Hash(P n_type ,P n_s ,P n_d ,P n_a ,P n_p ) is a hash value calculation function for calculating the header field of the nth data packet related information; mod is the remainder calculation, that is, calculation is the XOR operator, that is, the two binary numbers before and after the symbol are compared bit by bit.

[0113] When the nth data packet is selected for transmission through the GE interface, the path selection coefficient δ j is the path weight of the j-th GE interface;

[0114] S44: Calculate the i-th data transmission coefficient selection threshold range for transmitting data through the i-th FE interface: For a total of I FE interfaces consisting of I data transmission paths, according to the calculated Index n Determine whether it belongs to the transmission threshold range of the i-th path. If so, transmit the n-th data packet through the i-th FE interface; if not, traverse the 1 to i-1 and i+1 to I paths to determine the FE interface for transmitting the n-th data packet; Figure 2 As shown, the method provided by the present invention selects the FE interface path coefficient Index of different data packets. n Dynamic change diagram; the horizontal axis is the amount and location of data packets transmitted by the FE interface. When the horizontal axis is 1500, the vertical axis point value at the horizontal axis corresponding to the red curve is the data transmission coefficient of the FE interface selected by the 1500th data packet, the vertical axis point value at the horizontal axis corresponding to the green dotted line is the data transmission coefficient of the FE interface selected by the 1500th data packet, and the vertical axis point value at the horizontal axis corresponding to the blue dotted line is the path selection coefficient Index of the 1500th data packet. 1500 ;Depend on Figure 2 It can be seen that the ordinate value of the blue dashed line is always within the range of the red curve with the highest threshold and the green dashed line with the lowest threshold selected for the data transmission coefficient of the FE interface;

[0115] S45: Calculate the j-th data transmission coefficient selection threshold range for transmitting data through the j-th GE interface: For J data transmission paths consisting of J GE interfaces, according to the calculated Index n Determine whether it belongs to the transmission threshold range of the jth path. If so, transmit the nth data packet through the jth FE interface; if not, traverse the data transmission paths from 1 to j-1 and the data transmission paths from j+1 to J to determine the GE interface for transmitting the nth data packet; Figure 3 As shown in Figure 1, the GE interface path selection coefficient Index for different data packets n The definition of the red curve, green dashed line and blue dashed line is similar to that of the FE interface. Figure 3 It can be seen that the vertical coordinate value of the blue dotted line is always within the range of the red curve of the highest threshold and the green dotted line of the lowest threshold of the data transmission coefficient selection of the GE interface.

[0116] By dynamically allocating data packets to FE and GE interfaces and allocating the number of data packets (αN and (1-α)N) according to priority and traffic demand, resource allocation can be optimized when the load is heavy and interface utilization can be maximized. The dynamic adjustment mechanism effectively reduces the bottleneck problem caused by improper resource allocation and improves the overall system throughput. In addition, by calculating the traffic load dynamic coefficient σ of each FE interface and each GE interface i and δ i, it can monitor the usage of each interface in real time, and perform load balancing based on the dynamic adjustment factor (such as 0.1~0.5), which is used as the dividend of the remainder calculation of the hash value, and then re-determine the data packet capacity that the interface can accommodate in the next time slot according to the real-time dynamic traffic load of each interface, reducing the delay and resource waste caused by excessive or light interface load, and improving the stability and reliability of the system. Then, according to each priority evaluation attribute, a weighted XOR operation is performed and the hash value after the remainder of 1024 is taken, and the path selection coefficient of the data packet is calculated using the path weight and hash function to ensure that the data packet is transmitted along the optimal path. Especially in the case of multi-path, the dynamic adjustment mechanism of the path selection threshold effectively avoids congestion and data packet loss.

[0117] The data packet queue is a buffer structure in the router for temporarily storing data packets to be sent or received. The dynamic shaping of the data packet queue helps to coordinate the transmission order and flow of data packets and prevent network congestion or packet loss. Therefore, as another preferred embodiment of the present invention, step S5 includes the following steps:

[0118] S51: Calculate the nth data packet of the qth interface in the kth time slot t k Transfer rate

[0119] When q=i,

[0120] When q=j, Where, k = 1, 2, ... K;

[0121] S52: Further calculate the qth interface in the kth time slot t k Interface transmission rate V for multiple packets q :

[0122] When q=i,

[0123] When q=j,

[0124] S53: Judgment With V q The size of and the occupancy rate of the queue capacity of the qth interface can be used to obtain the congestion degree of the qth interface. The judgment criteria are as follows:

[0125]

[0126] Among them, QO q is the queue capacity occupancy rate of the qth interface, Min th and Max thThey are the minimum and maximum queue capacity occupancy thresholds of the interface respectively; Min th,q =0.45QS q , Max th =0.75QS q , QS q The length of the packet transmission queue of the qth interface obtained in step S1;

[0127] S54: According to the congestion level of the qth interface, update the nth data packet of the qth interface in the kth time slot t k Transfer rate and packet loss rate

[0128] When C q When there is no congestion,

[0129] When C q For low congestion, is the floor rounding function; For The result of the calculation of is rounded down to the result of the function;

[0130] When C q When the congestion is moderate, is the ceiling rounding function; For The result of the calculation of the function is rounded up; The result of the function of rounding down the calculated result of 0.15q;

[0131] When C q When the congestion is high, Furthermore, when q is i,

[0132] When q is j,

[0133] like Figure 4 As shown, Figure 4(A) is the real-time throughput monitoring result of the FE interface using the method of the present invention within 200s. In the figure, the blue dotted line represents the throughput of the monitored FE interface with a data packet transmission rate of 5000pkts / s and a low congestion situation, the pink dotted line represents the throughput of the monitored FE interface with a data packet transmission rate of 10000pkts / s and a medium congestion situation, the red dotted line represents the throughput of the monitored FE interface with a data packet transmission rate of 15000pkts / s and a high congestion situation, and the black dotted line represents the throughput of the monitored FE interface with a high congestion situation. The real-time throughput after the transmission queue is shown in Figure 1. The comparison of the blue, pink and red dotted lines shows that the faster the data packet transmission rate, the higher the throughput. The comparison of the black dotted line and the red dotted line shows that after the data packet transmission queue is regulated and shaped by the present invention, its throughput will not fluctuate greatly at different time points, thereby ensuring the stability of the throughput. By calculating the transmission rate of the qth interface in each time slot, the interface transmission capacity is dynamically adjusted to ensure that the data packet is transmitted at the optimal rate. At the same time, through the dynamic transmission rate adjustment strategy of the present invention, the transmission strategy can be flexibly optimized according to the real-time network status, thereby improving the system's adaptability to network fluctuations. Figure 4 (B) is the packet loss rate of the FE interface using the method of the present invention at different data packet transmission rates within 200s. The comparison of the blue, pink and red dotted lines shows that the faster the data packet transmission rate, the greater the packet loss rate. The comparison of the black dotted line and the red dotted line shows that the present invention dynamically adjusts and shapes the data packet transmission queue, calculates the priority according to the queue length and interface parameters, and high-priority data packets enjoy an advantage in the transmission rate allocation. At the same time, a higher priority transmission is provided for critical tasks or delay-sensitive data, thereby reducing the packet loss rate of the FE interface.

[0134] Figure 5 (A) and Figure 5 (B) are the monitoring and comparison results of the real-time throughput and packet loss rate of the GE interface within 200s, respectively, which have the same trend as the throughput and packet loss rate of the FE interface. It can be seen that by adopting the method provided by the present invention to shape the data packet transmission queues in multiple FE interfaces and the data packet transmission queues in multiple GE interfaces, it can be ensured that different dynamic mechanisms for data packet queue transmission are adopted under different congestion conditions, thereby effectively reducing the packet loss rate and reducing the possibility of data loss during transmission. In particular, under high congestion conditions, the method of adjusting the priority and transmission rate of the data packet transmission queue can effectively avoid packet loss. In addition, by reducing queue congestion and optimizing time slot allocation, the technology reduces data transmission delay to a certain extent. In particular, under low congestion and non-congested conditions, data packets can be transmitted at a rate close to the maximum rate.

[0135] Queue overflow is a phenomenon caused by the inability of network equipment to process more data packets when the traffic is too high, which directly causes data packet loss. Data packet loss will reduce the reliability of transmission, increase the overhead of retransmission, and have a significant impact on applications with high real-time requirements (such as video streaming, VoIP). In addition, there are differences in the transmission capabilities of different interfaces. If the load is not reasonably distributed, it may cause overflow of high-performance GE interfaces, while low-speed FE interfaces are not fully utilized, resulting in waste of resources. Therefore, as another preferred embodiment of the present invention, step S6 includes the following steps:

[0136] S61: Calculate the data transmission quality index U of the qth interface q :

[0137] When q=i,

[0138] When q=j,

[0139] S62: Determine the data transmission quality indicator U of the qth interface q Is it greater than or equal to the maximum threshold of low-quality transmission? If so, further determine whether the qth interface is a FE interface or a GE interface. If it is a GE interface, choose to transfer the overflowed queue of the GE interface to the FE interface for transmission at a reduced rate; if it is a FE interface, transfer the overflowed queue of the FE interface to the GE interface for transmission at a increased rate, thereby reducing the packet loss rate and generally improving the data transmission rate of the entire router;

[0140] If the data transmission quality index U of the qth interface q If the value is less than the maximum threshold of low-quality transmission, then only steps S1 to S5 need to be repeated for data transmission.

[0141] like Figure 6 (A) is the delay of the FE interface within 30 minutes when the method provided by the present invention is not adopted, Figure 6 (B) is the delay of the FE interface within 30 minutes when the method provided by the present invention is adopted; the column corresponding to each horizontal axis is the delay situation, and its vertical axis value is negative, which means that there is no delay within the time slot of the monitoring point for 1 minute, but the time represented by the length is ahead of the clock point; the column length represented by each horizontal axis point is the total delay length within the monitoring time slot of 1 minute, so the longer the column length, the longer the delay; Figure 7 (a) and Figure 7 (b) is the delay of the GE interface within 30 minutes when the method provided by the present invention is not adopted and when the method provided by the present invention is adopted.

[0142] pass Figure 6 (A) and Figure 6 (B) comparison, and Figure 7(A) and Figure 7 The comparison of (B) shows that the method provided by the present invention can effectively and dynamically adjust the overflow of different types of interface data packet queues. According to different interface types (such as q=i or q=j), the strategy is adjusted to adapt to the transmission requirements of the data packets in the overflow queue when the queues of different types of interfaces overflow. The elastic management method provided by the present invention enables the network to have a stronger adaptability to burst traffic, thereby improving the service quality (QoS) of the network. By monitoring and adjusting the data transmission quality index (Uq), it can be ensured that the transmission quality is maintained within an acceptable range. By dynamically adjusting the interface allocation, the packet loss rate and delay are reduced, and it is applied to a multi-interface transmission environment to meet the user's demand for high-quality services.

[0143] The present invention also provides a multi-interface intelligent path selection network router control system that uses the above method to perform data transmission, such as Figure 8 As shown, the system includes a data packet information acquisition module, a routing and forwarding module, an interface type allocation module, a path selection module, a congestion control module and a data transmission quality management module;

[0144] The data packet information acquisition module is used to obtain the type, source address, destination address, protocol type, port number and queue length of the nth data packet transmitted by the multi-interface intelligent path selection network router;

[0145] The routing and forwarding module is used to assign a packet type score P to each packet based on the DSCP field in the routing table. n_type , calculate the priority score P of the nth data packet transmitted by the router n_total ;

[0146] The interface type allocation module is used to classify a total of N data packets according to priority scores. When the priority score of the nth data packet is P n_total Greater than the priority threshold P thr When the nth priority score is selected, the data packet with the nth priority score is transmitted to the GE interface for transmission; otherwise, the data packet with the nth priority score is transmitted to the FE interface for transmission;

[0147] A path selection module, used for selecting a path for the nth data packet when it is transmitted on a GE interface or a FE interface by using an EMCP method;

[0148] The congestion control module is used to dynamically monitor the packet transmission congestion of each interface, perform dynamic queue shaping, and adjust the packet transmission rate and packet loss rate of each interface. It is responsible for controlling the data flow by packet loss or delay when the network is under high load;

[0149] The data transmission quality management module is used to calculate and determine the data transmission quality index U of each FE interface and GE interface.q When it is greater than the maximum threshold of low-quality transmission, it indicates that a queue overflow occurs. In this case, the overflowed queue of the GE interface is transferred to the FE interface for transmission at a reduced rate, or the overflowed queue of the GE interface is transferred to the GE interface for transmission at a increased rate, thereby reducing the packet loss rate.

[0150] The present invention also provides a multi-interface intelligent path selection network router that uses the above method to perform data transmission, such as Figure 10-12 As shown, the multi-interface intelligent path selection network router includes a memory, a processor, a liquid crystal display screen 1 arranged on the upper part of the multi-interface intelligent path selection network router, a 12V DC power input interface 2 arranged on the rear side of the router, a CONSOLE management interface 3 and two antennas 4, as well as a USB interface 5, an SFP optical fiber interface 6, a first indicator light area 7 arranged between the USB interface 5 and the SFP optical fiber interface 6, a POE Ethernet power supply interface 8, a Fast Ethernet interface module 9, a second indicator light area 10 and a Gigabit Ethernet interface module 11 arranged on the front side of the multi-interface intelligent path selection network router; the Fast Ethernet interface module 9 includes a plurality of FE interfaces 91, and the Gigabit Ethernet interface module 11 includes a plurality of GE interfaces 111; the memory stores a computer-readable medium that can execute the above method on the processor. Examples of machine-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk-read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0151] Preferably, the number of FE interfaces 91 included in the Fast Ethernet interface module 9 is four, and the number of GE interfaces 111 included in the Gigabit Ethernet interface module 11 is five. The present invention can display the device status such as network connection (such as the connection status of WAN and LAN, IP address, subnet mask, gateway information, etc.), interface traffic, system performance, etc. by arranging an LED display screen on the upper part of the network router. The basic network and device information provided can provide assistance for quick inspection and simple configuration and display device fault information when a device appears in the router. The four FE interfaces 91 of the Fast Ethernet interface module 9 support the standard IEEE 802.3u protocol, and the five GE interfaces 111 of the Gigabit Ethernet interface module 11 support the standard IEEE802.3ab protocol.

[0152] like Fig. 9 As shown, it is a schematic diagram of data connection between the network router provided by the present invention and mobile terminals and PC mobile terminals in different rooms or different areas that can be covered.

[0153] like Fig.12 As shown, the 12V DC power input interface 2 is the DC power input interface of the router. After receiving an external power adapter with a 12V output, it is the main power supply mode of the router, and the PoE Ethernet power supply interface 8 is an auxiliary power supply mode. The CONSOLE management interface 3 is used to directly manage and configure the router at a low level through a serial cable (usually an RJ-45 or DB9 cable). It is an external interface of the router as a backup management method. When the device cannot be accessed through a network connection such as Winbox or a Web interface, the router can be managed and set; it can also be used for initialization settings, debugging, restoring factory settings or firmware upgrade operations of the device.

[0154] like Fig.11 As shown, the first indicator area 7 includes a USB interface LED indicator 71 and an SFP optical fiber interface LED indicator 72 arranged vertically, which are used to indicate whether the corresponding interface is connected and its activity status respectively;

[0155] The second indicator area 10 includes ten LED indicators marked with numbers "1" to "10", and the ten LED indicators are arranged in two rows. The indicators "1" to "5" in the first row correspond to the POE Ethernet power supply interface 8 and the four FE interfaces 91 of the Fast Ethernet interface module 9 on the left side of the second indicator area 10. The indicator numbered "1" corresponds to the POE Ethernet power supply interface 8, and the indicators numbered "2" to "5" correspond to the four FE interfaces 91. If the indicators in the first indicator area 7 and the indicators in the second indicator area 10 are always on, it means that the corresponding interface has been connected to an external device. If they flash, it means that the corresponding interface is transmitting data. If they are off, it means that the data transmission link is not connected.

[0156] The indicators “6” to “10” in the second row of the second indicator area 10 correspond one by one to the five GE ports 111 located on the right side of the second indicator area 10 .

[0157] Fig.10 and Fig.11 The ETH1 to ETH10 marked at the bottom of the POE Ethernet power supply interface 8, the four FE interfaces 91 and the five GE interfaces 111 indicate that the interface is an Ethernet interface, that is, it is the first to tenth physical Ethernet port for connecting wired network devices. The POE Ethernet power supply interface 8 can support Ethernet power supply, which is used to provide power for other network devices (such as wireless access points or cameras). ETH2 to ETH5 of the four FE interfaces 91 support a data transmission rate of up to 100Mbps, and ETH6 to ETH10 of the five GR interfaces 111 support a data transmission rate of up to 1Gbps (i.e., 1000Mbps).

[0158] Although the present invention has been described with reference to preferred embodiments, various modifications may be made thereto and parts thereof may be replaced by equivalents without departing from the scope of the present invention. In particular, the various technical features mentioned in the various embodiments may be combined in any manner as long as there are no structural conflicts. The present invention is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

[0159] It should be noted that the serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. In this article, 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.

[0160] The above are only specific embodiments of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent 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 disclosure. Therefore, the present disclosure will not be limited to these embodiments herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data transmission method for a multi-interface intelligent path selection network router, wherein the method adopts an EMCP method to select a transmission path for each data packet and dynamically adjusts the queue of each interface's transmission data packet in real time, characterized in that: The following steps are involved: S1: Obtain the type, source address, destination address, protocol type, port number, and queue length of the nth data packet transmitted by the multi-interface intelligent path selection network router; S2: Assign a packet type score P to each packet based on the DSCP field priority n_type , calculate the priority score P of the nth data packet transmitted by the router n_total ; S3: Classify a total of N data packets according to the priority score. When the priority score of the nth data packet is P n_total Greater than the priority threshold P thr When the nth priority score is selected, the data packet with the nth priority score is transmitted to the GE interface for transmission; otherwise, the data packet with the nth priority score is transmitted to the FE interface for transmission; S4: Use the EMCP method to select a path for the nth data packet when it is transmitted on the GE interface or FE interface; S5: Dynamically monitors the packet transmission congestion of each interface, performs dynamic queue shaping, and adjusts the packet transmission rate and packet loss rate of each interface; S6: Calculate and determine the data transmission quality index U of each FE interface and GE interface q When it is greater than the maximum threshold for low-quality transmission, it indicates that a queue overflow has occurred. In this case, the overflowed queue on the GE interface is transferred to the FE interface for transmission at a reduced rate, or the overflowed queue on the GE interface is transferred to the GE interface for transmission at a increased rate, thereby reducing the packet loss rate.

2. The data transmission method of a multi-interface intelligent path selection network router according to claim 1, characterized in that: The data packet types obtained in step S1 include one or more of: VoIP real-time stream, video stream, file transfer packet, common data packet or background synchronization task data packet, and the corresponding data packet type score P n_type 10, 8, 5, 2 and 1 respectively; the source address includes one or more of a local network address, a trusted external address or a public external address, and the corresponding source address priority score P n_s 8, 5 and 2 respectively; the target address includes one or more of: intranet core services, other intranet devices, external trusted servers or public Internet targets, and the corresponding target address priority score P n_d They are 10, 7, 5 and 3 respectively; the protocol type includes one or more of UDP protocol, TCP protocol or ICMP protocol, and the corresponding protocol type score P n_a 8, 5 and 3 respectively; the port number includes: one or more of HTTP / HTTPS port, SIP port, RTP port, FTP port or SSH port, and the corresponding port number score P n_p They are 6, 9, 10, 4, and 7 respectively.

3. The data transmission method of a multi-interface intelligent path selection network router according to claim 2, characterized in that: The S2 step calculates the priority score P of the nth data packet transmitted by the router n_total The formula is as follows: P n_total =ω1P n_type +ω2P n_s +ω3P n_d +ω4P n_a +ω5P n_p ; Among them, ω1 = 0.3, ω2 = 0.2, ω3 = 0.2, ω4 = 0.2, ω5 = 0.1; the priority threshold P thr is 6.

4. The data transmission method of a multi-interface intelligent path selection network router according to claim 3, characterized in that: The S4 step includes: S41: First, according to the calculation result of the priority score, determine the number of data packets transmitted through the FE interface as αN and the number of data packets transmitted through the GE interface as (1-α)N; S42: Calculate the traffic load dynamic coefficient σ of the i-th FE interface i and the traffic load dynamic coefficient δ of the j-th GE interface j : in, is the current traffic demand of the i-th FE interface, max(R FE ) is the maximum flow demand in 1 FE interface; f i is the dynamic adjustment factor of the i-th FE interface; f i =0.1~0.5; in, is the current traffic demand of the j-th GE interface, max(R GE ) is the maximum flow demand among J GE interfaces; f j =0.1~0.5; where i=1,2,…,I; j=1,2…,J; S43: Path selection is performed for a total of αN data packets of i FE interfaces, and for a total of (1-α)N data packets of j GE interfaces; When the nth data packet is selected for transmission through the FE interface, the path selection coefficient σ i is the path weight of the i-th FE interface, Hash(Pn _type ,Pn _s ,Pn _d ,Pn _a ,Pn _p ) is a function for calculating the hash value of the header field of the relevant information of the nth data packet; mod is the remainder calculation; Is the exclusive OR operator symbol; When the nth data packet is selected for transmission through the GE interface, the path selection coefficient δ j is the path weight of the j-th GE interface; S44: Calculate the threshold range of the i-th data transmission coefficient selection: For a total of I FE interfaces consisting of I data transmission paths, according to the calculated Index n Determine whether it falls within the transmission threshold range of the i-th path. If so, transmit the n-th data packet through the i-th FE interface. If not, traverse the 1 to i-1 and i+1 to I paths to determine the FE interface for transmitting the n-th data packet. S45: Calculate the j-th data transmission coefficient and select the threshold range: For J data transmission paths consisting of J GE interfaces, according to the calculated Index n Determine whether it falls within the transmission threshold range of the j-th path. If so, transmit the n-th data packet through the j-th FE interface; if not, traverse the data transmission paths from 1 to j-1 and the data transmission paths from j+1 to J to determine the GE interface for transmitting the n-th data packet.

5. The data transmission method of a multi-interface intelligent path selection network router according to claim 4, characterized in that: The S5 step includes the following steps: S51: Calculate the nth data packet of the qth interface in the kth time slot t k Transfer rate When q=i, When q=j, Where k = 1, 2, ... K; S52: Further calculate the qth interface in the kth time slot t k Interface transmission rate V for multiple data packets q : When q=i, When q=j, S53: Judgment With V q The size of and the queue capacity occupancy rate of the qth interface are used to determine the congestion level of the qth interface. The judgment criteria are as follows: Among them, QO q is the queue capacity occupancy rate of the qth interface, Min th and Max th They are the minimum and maximum capacity occupancy thresholds of the queue on the interface; Min th,q =0.45QS q , Max th =0.75QS q , QS q is the length of the packet transmission queue of the qth interface; S54: Update the nth data packet of the qth interface in the kth time slot t according to the congestion level of the qth interface. k Transfer rate and packet loss rate 6. The data transmission method of a multi-interface intelligent path selection network router according to claim 5, characterized in that: In step S54, when C q When there is no congestion, When C q When the congestion is low, is the floor function; When C q When the congestion is moderate, is the ceiling function; When C q When congestion is high, Furthermore, when q is i, When q is j, 7. The data transmission method of a multi-interface intelligent path selection network router according to claim 6, characterized in that: The S6 step includes the following steps: S61: Calculate the data transmission quality index U of the qth interface q : When q=i, When q=j, S62: Determine the data transmission quality indicator U of the qth interface q Is the value greater than or equal to the maximum low-quality transmission threshold? If so, the system further determines whether the qth interface is an FE interface or a GE interface. If it is a GE interface, the system reduces the rate of overflowed queues on the GE interface and transfers them to the FE interface for transmission. If it is an FE interface, the system increases the rate of overflowed queues on the FE interface and transfers them to the GE interface for transmission. If the data transmission quality index U of the qth interface q If the value is less than the maximum threshold of low-quality transmission, it is only necessary to repeat steps S1 to S5 to perform data transmission.

8. A multi-interface intelligent path selection network router control system for data transmission using the method according to any one of claims 1 to 7, characterized in that: The system includes a data packet information acquisition module, a routing and forwarding module, an interface type allocation module, a path selection module and a congestion control module; The data packet information acquisition module is used to obtain the type, source address, destination address, protocol type, port number and queue length of the nth data packet transmitted by the multi-interface intelligent path selection network router; The routing and forwarding module is used to assign a data packet type score P to each data packet according to the DSCP field. n_type , calculate the priority score P of the nth data packet transmitted by the router n_total ; The interface type allocation module is used to classify a total of N data packets according to the priority score. When the priority score of the nth data packet is P n_total Greater than the priority threshold P thr When the nth priority score is selected, the data packet with the nth priority score is transmitted to the GE interface for transmission; otherwise, the data packet with the nth priority score is transmitted to the FE interface for transmission; The path selection module is used to select a path for the nth data packet when it is transmitted on the GE interface or the FE interface using the EMCP method; The congestion control module is used to dynamically monitor the data packet transmission congestion of each interface, perform dynamic queue shaping, and adjust the data packet transmission rate and packet loss rate of each interface; the data transmission quality management module is used to calculate and determine the data transmission quality index U of each FE interface and GE interface. q When it is greater than the maximum threshold for low-quality transmission, it indicates that a queue overflow has occurred. In this case, the overflowed queue on the GE interface is transferred to the FE interface for transmission at a reduced rate, or the overflowed queue on the GE interface is transferred to the GE interface for transmission at a increased rate, thereby reducing the packet loss rate.

9. A multi-interface intelligent path selection network router for data transmission using the method according to any one of claims 1 to 7, characterized in that: The multi-interface intelligent path selection network router comprises a memory, a processor, a liquid crystal display (1) arranged on the top of the multi-interface intelligent path selection network router, a 12V DC power input interface (2) arranged on the rear side of the router, a console management interface (3) and two antennas (4), and a USB interface (5), an SFP optical fiber interface (6), a first indicator light area (7) arranged between the USB interface (5) and the SFP optical fiber interface (6), a POE Ethernet power supply interface (8), a Fast Ethernet interface module (9), a second indicator light area (10) and a Gigabit Ethernet interface module (11) arranged on the front side of the multi-interface intelligent path selection network router; the Fast Ethernet interface module (9) includes a plurality of FE interfaces (91), and the Gigabit Ethernet interface module (11) includes a plurality of GE interfaces (111); the memory stores a computer-readable medium capable of executing the method according to any one of claims 1 to 7 on the processor.

10. The multi-interface intelligent path selection network router according to claim 9, characterized in that: The plurality of FE interfaces (91) of the FastEthernet interface module (9) support the standard IEEE 802.3u protocol, and the plurality of GE interfaces (111) of the GigabitEthernet interface module (11) support the standard IEEE 802.3ab protocol.

Images