Optimization method and device based on intelligent distributed network topology and electronic equipment

Abstract

The invention relates to an optimization method and device based on intelligent distributed network topology and electronic equipment, and the method comprises the steps: obtaining network state information monitored in real time on network nodes, the network state information comprising a bandwidth utilization rate, communication delay between the nodes and a loss rate of a data packet in a transmission process; calling a dynamic topology adjustment strategy in response to abnormity of the network state information; a decision algorithm is added for each network node, each node shares a decision result and network state information, all nodes coordinate decisions according to a consensus mechanism, and the decision algorithm is used for analyzing the network state information of the nodes. According to the optimization method, the data transmission path is optimized by dynamically adjusting the network topology, the overall performance of the network is improved, continuously changing communication requirements and states in the network can be conveniently adapted, and meanwhile, the reliability of key data transmission is improved and the network maintenance cost is reduced through node autonomous decision-making, inter-node cooperation and a consensus mechanism.

Description

Technical Field

[0001] The present invention relates to the field of network topology optimization, and in particular to an optimization method, device and electronic equipment based on intelligent distributed network topology. Background Art

[0002] In traditional distributed networks, the optimization of network topology is a long-standing challenge. Traditional distributed networks usually adopt static topology structures, which cannot adapt to the ever-changing communication needs and states in the network. Although some networks can perform adaptive adjustments to a certain extent, they often have problems such as simple adjustment strategies, low efficiency, and inability to cope with large-scale network dynamic changes. In addition, traditional network topology adjustment methods often require centralized control units, which not only increases the complexity and cost of the network, but also easily becomes a single point of failure in the system. Therefore, they need to be improved. Summary of the invention

[0003] Based on this, it is necessary to provide an optimization method, device and electronic device based on intelligent distributed network topology, as traditional distributed networks usually adopt static topology structures, which cannot adapt to the ever-changing communication needs and status in the network. At the same time, traditional network topology adjustment methods often require a centralized control unit, which not only increases the complexity and cost of the network, but also easily becomes a single point of failure in the system.

[0004] The present invention provides an optimization method based on intelligent distributed network topology, the method comprising:

[0005] Acquire network status information monitored in real time on network nodes, the network status information including bandwidth usage, communication delay between nodes, and loss rate of data packets during transmission;

[0006] In response to abnormal network status information, a dynamic topology adjustment strategy is invoked;

[0007] A decision-making algorithm is added to each network node, and each node shares its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision-making algorithm is used to analyze the network status information of the node.

[0008] In one embodiment, obtaining network status information monitored in real time on a network node includes:

[0009] Receiving data flow information monitored on a network node and calculating bandwidth usage, wherein the data flow information includes data transmission speed and flow size;

[0010] Record the round-trip time of sending test packets and calculate the communication delay between nodes;

[0011] Count the number of packets sent and received within a specific period of time and calculate the packet loss rate.

[0012] In one of the embodiments, in response to abnormal network status information, calling a dynamic topology adjustment strategy includes:

[0013] Based on the anomaly of network status information, determine all nodes and links in the network;

[0014] Set the distance of the source node to zero, and the initial distance of each other node to infinity;

[0015] Starting from the source node, select a node with the shortest distance and has not been visited as the current node;

[0016] For each neighbor node of the current node, calculate the total cost to reach the neighbor through the current node;

[0017] In response to the path cost through the current node being less than the original path cost, updating the distance of the neighbor node;

[0018] In response to all nodes being visited, the predecessor node of each node is recorded, and the shortest path from the source node to the target node is constructed;

[0019] Redistribute the network onto the shortest path.

[0020] In one of the embodiments, in response to abnormal network status information, calling a dynamic topology adjustment strategy further includes:

[0021] Evaluate the congestion level of each link based on the network status information of each link;

[0022] Based on the congestion assessment result, a non-congested path or a low-congested path is selected;

[0023] For each possible path between the source node and the destination node, calculate the total congestion value of the path and select the path with the least congestion;

[0024] Redistribute the network onto the least congested paths.

[0025] In one of the embodiments, in response to abnormal network status information, calling a dynamic topology adjustment strategy further includes:

[0026] Get real-time information to mark failed nodes or links and determine which parts need to be bypassed;

[0027] Identify all paths that pass through the failed node or link;

[0028] Generate available alternative paths based on algorithms in graph theory;

[0029] Reconfigure the routing table and direct traffic to go through alternative paths based on bypassing failed nodes or critical links.

[0030] In one of the embodiments, in response to abnormal network status information, calling a dynamic topology adjustment strategy further includes:

[0031] In response to a link load being greater than a preset threshold, allocating part of the traffic of the link to an alternative path according to a load balancing algorithm;

[0032] In response to the overall load on the path being less than a preset threshold value, the newly initiated link is allocated to the path according to a priority steering strategy.

[0033] In one embodiment, the optimization method based on intelligent distributed network topology further includes:

[0034] Classify the data in the network and assign a unique identifier to each type of data;

[0035] Define different priority levels based on the importance and urgency of the data;

[0036] In response to data with a high priority level, more bandwidth resources are allocated to the data, and a priority queue is set at each node in the network so that data packets in the high priority queue are transmitted before data packets in the low priority queue.

[0037] The present invention also provides an optimization device based on intelligent distributed network topology, comprising:

[0038] An acquisition module is used to acquire network status information monitored in real time on network nodes, wherein the network status information includes bandwidth utilization, communication delay between nodes, and loss rate of data packets during transmission;

[0039] A calling module, used for calling a dynamic topology adjustment strategy in response to abnormal network status information;

[0040] The coordination module is used to add a decision-making algorithm to each network node, and enable each node to share its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision-making algorithm is used to analyze the network status information of the node.

[0041] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the optimization method based on intelligent distributed network topology as described in any one of the above is implemented.

[0042] The present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the optimization method based on intelligent distributed network topology as described above is implemented.

[0043] The above-mentioned optimization method, device and electronic device based on intelligent distributed network topology monitor the network status in real time and dynamically adjust the network topology to optimize the data transmission path, thereby improving the overall performance of the network and facilitating adaptation to the ever-changing communication needs and status in the network. At the same time, by adding a decision-making algorithm to each network node, each node shares its decision results and network status information, and coordinates its decisions according to the consensus mechanism, thereby improving the adaptability and robustness of the network and the reliability of key data transmission, while reducing the network maintenance cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A schematic diagram of a flow chart of an optimization method based on intelligent distributed network topology in one embodiment;

[0046] Figure 2 A schematic diagram of a process for obtaining network status information in an embodiment;

[0047] Figure 3 A schematic diagram of a first dynamic topology adjustment strategy process in an embodiment;

[0048] Figure 4 A schematic diagram of a second dynamic topology adjustment strategy process in an embodiment;

[0049] Figure 5 A schematic diagram of a third dynamic topology adjustment strategy process in one embodiment;

[0050] Figure 6 A schematic diagram of a fourth dynamic topology adjustment strategy process in an embodiment;

[0051] Figure 7 is a schematic diagram of a priority management process in an embodiment;

[0052] Figure 8 is a schematic diagram of the structure of an optimization device based on intelligent distributed network topology in one embodiment;

[0053] Fig. 9FIG. 4 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0055] Combine the following Figure 1-Figure 9 The invention describes an optimization method, device and electronic device based on intelligent distributed network topology.

[0056] like Figure 1 As shown, in one embodiment, an optimization method based on intelligent distributed network topology includes the following steps:

[0057] Step S100, obtaining network status information monitored in real time on network nodes, the network status information including bandwidth usage, communication delay between nodes and loss rate of data packets during transmission.

[0058] By installing monitoring software on each network node, it is equipped with the ability to collect and process data, thereby facilitating real-time monitoring of network status information on the network node.

[0059] Step S200: In response to abnormal network status information, a dynamic topology adjustment strategy is called.

[0060] By dynamically adjusting the network topology based on real-time monitored network data such as traffic, latency, node load, etc., it is convenient to improve network performance and reliability.

[0061] Step S300, add a decision algorithm to each network node, and make each node share its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision algorithm is used to analyze the network status information of the node.

[0062] Initialize nodes: Deploy decision-making algorithms on each node and ensure that the nodes can collect and exchange network status information.

[0063] Autonomous decision execution: Each node runs a decision algorithm based on the information it collects to determine whether the topology needs to be adjusted.

[0064] The node autonomous decision algorithm is an algorithm for network optimization, which allows each node to decide whether to adjust its connection based on the network status information.

[0065] Here is a simplified example of how such a decision algorithm might be implemented:

[0066] The node autonomous decision-making algorithm can be based on the following steps:

[0067] 1. Collect network status information: The node collects information such as bandwidth, latency, and packet loss rate of other nodes directly connected to it.

[0068] 2. Calculate network status indicators: Use the collected information to calculate one or more network status indicators, which are used to represent the current performance of the network.

[0069] 3. Decision-making: Based on pre-set thresholds and calculated network status indicators, the node decides whether to adjust its connection.

[0070] The specific examples are as follows:

[0071] Assume a simple network status metric (S) based on bandwidth (B), latency (L), and packet loss rate (P):

[0072] S=W 1 ·B 1 +W 2 ·L+w 3 ·P,

[0073] Among them, w 1 , w 2 , w 3 is the weight coefficient, which is used to adjust the importance of different network status information.

[0074] Assume that a node sets a threshold (T). If the calculated status indicator (S) exceeds this threshold, the node considers that the network performance is poor and the connection needs to be adjusted.

[0075] If (S>T), the node executes the connection adjustment strategy, and each node decides whether to adjust its connection based on the network status information;

[0076] If (S<T), the node maintains the current connection state.

[0077] In this example, the node may choose to disconnect from the worst performing node and try to connect to a better performing node in order to optimize the overall network topology.

[0078] It should be noted that the above example is a very simplified description of the decision algorithm. In actual applications, the decision algorithm may be more complex and need to consider multiple factors and optimization strategies.

[0079] Information exchange: The node broadcasts its decision results and current status information to other nodes in the network.

[0080] Consensus and global optimization: All nodes coordinate their decisions through a consensus mechanism to achieve global optimization of the network.

[0081] In order to achieve global optimization of the network, all nodes coordinate their decisions through a consensus mechanism as follows:

[0082] Consensus mechanism: In the network, each node independently evaluates the network state according to the consensus algorithm and makes decisions based on local information. These decisions are then coordinated across the entire network to ensure consistency.

[0083] Consensus and global optimization: All nodes coordinate their decisions through a consensus mechanism to achieve global optimization of the network. In this process, each node's decision is not only based on its local network view, but also takes into account the goals of the global network, such as minimizing overall latency, maximizing throughput, or balancing resource allocation. Through this distributed collaboration, the network is able to adaptively adjust its topology and traffic distribution to maintain optimal performance in a dynamically changing network environment.

[0084]

[0085] Where: Global Optimization represents the global optimization goal; V is the set of all nodes in the network, cost(i) represents the cost function of node i under the current network configuration, which can be based on multiple indicators such as latency, bandwidth usage, node load, etc.

[0086] Initializing nodes: For example, if a node detects that the bandwidth utilization of its connections is consistently above 80%, it may decide to add new connections or adjust the paths of existing connections.

[0087] Information exchange: The node sends its decision and current bandwidth utilization information to other nodes.

[0088] Consensus and global optimization: After receiving the information, other nodes will adjust their decisions according to the consensus mechanism. Eventually, all nodes reach a consensus and the network topology is optimized.

[0089] In this way, the network can quickly adapt to changes, improving overall performance and stability.

[0090] This optimization method based on intelligent distributed network topology monitors the network status in real time and dynamically adjusts the network topology to optimize the data transmission path, thereby improving the overall performance of the network and facilitating adaptation to the ever-changing communication needs and status in the network. At the same time, by adding a decision-making algorithm to each network node, each node shares its decision results and network status information and coordinates its decisions according to a consensus mechanism, thereby improving the adaptability and robustness of the network and the reliability of key data transmission, while reducing network maintenance costs.

[0091] In this embodiment, see Figure 2 , obtain the network status information monitored in real time on the network node, including the following steps:

[0092] Step S110, receiving data flow information monitored on the network node and calculating bandwidth usage, the data flow information includes data transmission speed and flow size.

[0093] The specific bandwidth usage calculation formula is as follows:

[0094]

[0095] Step S120, record the round trip time of sending the test data packet and calculate the communication delay between nodes. The specific communication delay calculation formula is as follows:

[0096] RTT = response time - sending time,

[0097]

[0098] Among them, RTT (Round-Trip Time) represents the round-trip time.

[0099] By recording the RTT of each data packet, you can get the fluctuation of delay and find possible network congestion.

[0100] Step S130, counting the number of data packets sent and received within a specific time, and calculating the packet loss rate.

[0101] The loss rate is calculated by comparing the number of packets sent and the number of packets received. The specific calculation formula is as follows:

[0102]

[0103] Specific application examples are as follows:

[0104] Install and configure the monitoring software on a network node. After the software is started, it starts to capture data packets passing through the node in real time. Assuming that within 5 minutes, the software captures 1,000 data packets with a total data volume of 500MB and a total bandwidth of 1Gbps, the software will calculate as follows:

[0105] Bandwidth usage:

[0106]

[0107] Assume that the communication delay is 20ms on average.

[0108] Assume a packet loss rate of 1%.

[0109] By obtaining real-time network status data, a basis is provided for further network optimization.

[0110] In this embodiment, see Figure 3 In response to abnormal network status information, a dynamic topology adjustment strategy is called, including the following steps:

[0111] Step S211, based on the abnormality of the network status information, determine all nodes and links in the network.

[0112] Suppose there is a network graph G = (V, E), where V is the vertex set (representing the nodes in the network), E is the edge set (representing the links between nodes), and each edge (u, v) ∈ E has a weight w uv , weight w uv Represents the delay or traffic between nodes u and v.

[0113] Step S212, setting the distance of the source node to zero, and setting the initial distance of each other node to infinity.

[0114] Set d(s)=0 and d(v)=∞, where for all v≠s.

[0115] By initializing the shortest path estimation of all nodes, it is convenient to select the shortest path later.

[0116] Step S213, starting from the source node, select a node with the shortest distance and not visited as the current node.

[0117] In each selection, by giving priority to the node with the shortest current distance, unnecessary path expansion is avoided, the optimal solution is quickly converged, and the calculation time is reduced.

[0118] Step S214: for each neighbor node of the current node, calculate the total cost of reaching the neighbor node through the current node.

[0119] When traversing the neighbor nodes of the current node, all possible paths are considered to ensure that the cost of the neighbor nodes is always kept at the optimal value, ensuring the dynamic adjustment of the path. When a better path is found, the cost of the neighbor nodes can be updated in time. At the same time, it is convenient to build a gradually converging global shortest path.

[0120] Step S215 , in response to the path cost through the current node being less than the original path cost, updating the distance of the neighboring node.

[0121] By updating the distances of neighbor nodes, the network can dynamically adjust path selection to avoid links with high traffic and ensure efficient data transmission.

[0122] Step S216, in response to all nodes being visited, the predecessor node of each node is recorded, and the shortest path from the source node to the target node is constructed.

[0123] The specific expression is as follows:

[0124]

[0125] Among them, Pred(v) is the set of all predecessor nodes of node v.

[0126] Step S217, reallocate the network to the shortest path.

[0127] The following are some examples:

[0128] Assume that the flow f on the edge (u,v) is monitored uv Exceeds the preset threshold T, that is, f uv >T, the path selection algorithm is triggered to recalculate the path from the source node to the destination node.

[0129] Use the SPF (Shortest Path First) algorithm to update the weight w of the edge (u,v) uv , perhaps setting it to a higher value to represent the increased “cost” caused by high traffic.

[0130] w uv ′=w uv +Δw

[0131] Where Δw is a positive value representing the additional “cost” due to the increase in flow.

[0132] Then, the SPF algorithm will be based on the updated weight w uv 'Recalculate the shortest path.

[0133] In this way, the network can dynamically adjust path selection to avoid links with high traffic and ensure efficient transmission of data.

[0134] For example:

[0135] Suppose a network consists of nodes A, B, C, and D, where the link between nodes B and C is the bottleneck in the network.

[0136] Initially, all traffic from A to D goes through link BC.

[0137] When the monitoring system finds that the traffic of the BC link is close to the upper limit, the path selection algorithm is triggered to find an alternative path AD (bypassing BC).

[0138] In this embodiment, see Figure 4 In response to abnormal network status information, a dynamic topology adjustment strategy is called, and the following steps are also included:

[0139] Step S221 , evaluating the congestion degree of each link according to the network status information of each link.

[0140] The congestion level of a link can be evaluated by calculating the load of the link. Links with high load or high latency are considered "congested" links.

[0141] Step S222: Select a non-congested path or a low-congested path based on the congestion evaluation result.

[0142] This facilitates the subsequent dynamic adjustment of the path.

[0143] Step S223: For each possible path between the source node and the target node, calculate the total congestion value of the path, and select the path with the least congestion.

[0144] When network traffic changes, routing will be adjusted according to the new congestion situation. For example, a path may be the optimal path at a certain moment, but as network traffic changes, it may be necessary to switch to another path.

[0145] Step S224, reallocate the network to the path with the least congestion.

[0146] Reduce network congestion by reallocating the network to the path with the least congestion based on real-time data on network status.

[0147] In this embodiment, see Figure 5 In response to abnormal network status information, a dynamic topology adjustment strategy is called, and the following steps are also included:

[0148] Step S231, obtaining real-time information to mark the nodes or links with faults, and determining the parts that need to be bypassed.

[0149] For example, a network consists of nodes A, B, C, and D. If node B fails, a new link ACD is created to ensure that communication from A to D is not affected.

[0150] Step S232, identifying all paths passing through the faulty node or link.

[0151] This facilitates the subsequent generation of available alternative paths.

[0152] Step S233: Generate available alternative paths based on graph theory algorithms.

[0153] Through algorithms in graph theory, such as the minimum cut set algorithm or the maximum flow minimum cut theorem, it is convenient to find key nodes and links in the network, thereby generating available alternative paths.

[0154] Suppose there is a network graph G = (V, E), where V is the set of nodes and E is the set of edges.

[0155] Suppose a network consists of nodes A, B, C, and D, where the link between nodes B and C is the bottleneck in the network. When node B fails, an alternative path needs to be found.

[0156] The following is a simplified formula to express this reconstruction process:

[0157]

[0158] Among them: new path(A,D) is the new path from node A to node D; P is the set of all possible paths from A to D; cost(e) is the cost of edge e, which can be bandwidth, delay, link utilization, etc.

[0159] Step S234, reconfigure the routing table based on bypassing the faulty node or critical link, and instruct the traffic to pass through an alternative path.

[0160] The specific examples are as follows:

[0161] 1. Network initialization:

[0162] Node set V = {A, B, C, D};

[0163] Edge set E = {{A,B},{B,C},{C,D}};

[0164] Assume that the cost of each edge, cost(e), is the same.

[0165] 2. Failure occurs: Node B fails.

[0166] 3. Topology reconstruction:

[0167] The new path needs to bypass the failed node B.

[0168] Using the above formula, find a new path.

[0169] Assuming the new path is ACD, the formula can be specified as:

[0170] new path(A,D)=(A,C,D),

[0171] This means that when node B fails, the algorithm will select path ACD as the new communication path.

[0172] Here is a graphic representation of this process:

[0173] Original path: A--B--C–D;

[0174] After failure: AC–D;

[0175] New path: A--C–D.

[0176] In this way, it is convenient to automatically find alternative paths to maintain communication between nodes in the network.

[0177] In this embodiment, see Figure 6 In response to abnormal network status information, a dynamic topology adjustment strategy is called, and the following steps are also included:

[0178] Step S241 , in response to a link load being greater than a preset threshold, a portion of the traffic on the link is allocated to an alternative path according to a load balancing algorithm.

[0179] When it is detected that the load of the BC link is too high, the traffic transfer mechanism will be activated to transfer part of the traffic from the BC path to the new ACD path.

[0180] Step S242: In response to the overall load on the path being less than a preset threshold value, the newly initiated link is allocated to the path according to a priority steering strategy.

[0181] When the overall load on the ACD path is low, the load balancing algorithm will prioritize newly initiated connections to this path. The following is a simplified description of this process:

[0182] 1. Load monitoring: Continuously monitor the load of each link in the network.

[0183] 2. Determine congestion: If it is detected that the BC link load is too high, the congestion condition is met.

[0184] 3. Traffic distribution: Traffic distribution is carried out according to the following principles:

[0185] If load(ACD) <load(B-C),then redirect traffic to A-C-D,

[0186] Wherein, load(ACD) and load(BC) represent the loads of paths ACD and BC respectively.

[0187] The specific examples are as follows:

[0188] Original traffic path: A--B--C–D;

[0189] Congestion detection: B--C (high load);

[0190] New path: A--C--D (low load);

[0191] Traffic redirection: New connections prioritize A--C--D.

[0192] Through load balancing, you can ensure that traffic in the network is evenly distributed and avoid overloading a single path, thereby improving the performance and stability of the entire network.

[0193] In this embodiment, see Figure 7 , the optimization method based on intelligent distributed network topology also includes the following steps:

[0194] Step S400: classify the data in the network and assign a unique identifier to each type of data.

[0195] Data can be classified based on a variety of criteria, such as the type of data, its source, its destination, and predetermined quality of service requirements.

[0196] By assigning a unique identifier to each type of data, it is easy to identify during transmission.

[0197] Step S500, defining different priority levels according to the importance and urgency of the data.

[0198] Dynamically allocate transmission resources according to the importance and urgency of the data to ensure priority transmission of critical data.

[0199] Step S600, in response to data with a high priority level, more bandwidth resources are allocated to the data, and a priority queue is set at each node in the network so that data packets in the high priority queue are transmitted before data packets in the low priority queue.

[0200] Data classification and identification: Add a priority field to the header of the data packet to identify the priority of the data packet. For example, medical emergency data can be marked as the highest priority, and regular file transfer data can be marked as low priority.

[0201] Bandwidth allocation: Bandwidth allocation = priority coefficient × basic bandwidth share.

[0202] Based on the priority, more bandwidth is allocated to medical emergency data, such as 100Mbps, while file transfer data may only be allocated 10Mbps. The specific calculation process is as follows:

[0203] Bandwidth allocation医疗紧急数据 =1.0×100Mbps=100Mbps;

[0204] Bandwidth allocation 文件传输数据 =0.1×100Mbps=10Mbps.

[0205] Queue management: In the output queue of the network node, the data packets are placed into the corresponding priority queue according to the priority field of the data packet. The data packets in the high priority queue will be transmitted before the data packets in the low priority queue. At the network node, the priority queue is set to ensure that the medical emergency data is always at the front of the queue.

[0206] This priority management mechanism ensures that critical data can still be processed first when the network is congested, thereby improving the response speed and reliability of key services. This is especially important for scenarios that are time-sensitive or have strict requirements on business continuity.

[0207] The optimization device based on intelligent distributed network topology provided by the present invention is described below. The optimization device based on intelligent distributed network topology described below and the optimization method based on intelligent distributed network topology described above can refer to each other.

[0208] like Figure 8 As shown, in one embodiment, an optimization device based on intelligent distributed network topology includes an acquisition module 810, a calling module 820 and a coordination module 830.

[0209] The acquisition module 810 is used to acquire network status information monitored in real time on network nodes. The network status information includes bandwidth usage, communication delay between nodes, and loss rate of data packets during transmission.

[0210] The calling module 820 is used to call a dynamic topology adjustment strategy in response to abnormal network status information.

[0211] The coordination module 830 is used to add a decision algorithm to each network node, and enable each node to share its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision algorithm is used to analyze the network status information of the node.

[0212] In this embodiment, the network status information monitored in real time on the network node is obtained, specifically for:

[0213] Receive data flow information monitored on the network node and calculate bandwidth usage, the data flow information includes data transmission speed and flow size;

[0214] Record the round-trip time of sending test packets and calculate the communication delay between nodes;

[0215] Count the number of packets sent and received within a specific period of time and calculate the packet loss rate.

[0216] In this embodiment, the calling module 820 is specifically used to:

[0217] Based on the anomaly of network status information, determine all nodes and links in the network;

[0218] Set the distance of the source node to zero, and the initial distance of each other node to infinity;

[0219] Starting from the source node, select a node with the shortest distance and has not been visited as the current node;

[0220] For each neighbor node of the current node, calculate the total cost to reach the neighbor through the current node;

[0221] In response to the path cost through the current node being less than the original path cost, updating the distance of the neighbor node;

[0222] In response to all nodes being visited, the predecessor node of each node is recorded, and the shortest path from the source node to the target node is constructed;

[0223] Redistribute the network onto the shortest path.

[0224] In this embodiment, the calling module 820 is further specifically used for:

[0225] Evaluate the congestion level of each link based on the network status information of each link;

[0226] Based on the congestion assessment result, a non-congested path or a low-congested path is selected;

[0227] For each possible path between the source node and the destination node, calculate the total congestion value of the path and select the path with the least congestion;

[0228] Redistribute the network onto the least congested paths.

[0229] In this embodiment, the calling module 820 is further specifically used for:

[0230] Get real-time information to mark failed nodes or links and determine which parts need to be bypassed;

[0231] Identify all paths that pass through the failed node or link;

[0232] Analyze the volume of traffic affected and calculate the bandwidth or capacity required for rerouting to ensure that the bypassed path can meet traffic demand;

[0233] Generate available alternative paths based on algorithms in graph theory;

[0234] Reconfigure routing tables to bypass failed nodes or critical links and direct traffic to go through alternative paths;

[0235] Allocate sufficient bandwidth to critical traffic on alternative paths and set priorities based on congestion conditions.

[0236] In this embodiment, the calling module 820 is further specifically used for:

[0237] In response to a link load being greater than a preset threshold, allocating part of the traffic of the link to an alternative path according to a load balancing algorithm;

[0238] In response to the overall load on the path being less than a preset threshold value, the newly initiated link is allocated to the path according to a priority steering strategy.

[0239] In this embodiment, the optimization device based on intelligent distributed network topology further includes a classification module 840 , a grading module 850 and a response module 860 .

[0240] The classification module 840 is used to classify the data in the network and assign a unique identifier to each type of data.

[0241] The classification module 850 is used to define different priority levels according to the importance and urgency of the data.

[0242] The response module 860 is used to respond to data with a high priority level by allocating more bandwidth resources to the data and setting a priority queue at each node in the network so that data packets in the high priority queue are transmitted before data packets in the low priority queue.

[0243] This optimization device based on intelligent distributed network topology monitors the network status in real time and dynamically adjusts the network topology to optimize the data transmission path, thereby improving the overall performance of the network and facilitating adaptation to the ever-changing communication needs and status in the network. At the same time, by adding a decision-making algorithm to each network node, each node shares its decision results and network status information and coordinates its decisions according to a consensus mechanism, thereby improving the adaptability and robustness of the network and the reliability of key data transmission, while reducing network maintenance costs.

[0244] Fig. 9 An example of a physical structure diagram of an electronic device is shown. The electronic device may be a smart terminal, and its internal structure diagram may be as follows: Fig. 9As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an optimization method based on an intelligent distributed network topology is implemented, and the method includes:

[0245] Obtaining real-time network status information monitored on network nodes, including bandwidth usage, communication delay between nodes, and packet loss rate during transmission;

[0246] In response to abnormal network status information, a dynamic topology adjustment strategy is invoked;

[0247] Add a decision-making algorithm to each network node, and make each node share its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision-making algorithm is used to analyze the network status information of the node.

[0248] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the electronic device to which the scheme of the present invention is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0249] On the other hand, the present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, implements an optimization method based on intelligent distributed network topology, the method comprising:

[0250] Obtaining real-time network status information monitored on network nodes, including bandwidth usage, communication delay between nodes, and packet loss rate during transmission;

[0251] In response to abnormal network status information, a dynamic topology adjustment strategy is invoked;

[0252] Add a decision-making algorithm to each network node, and make each node share its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision-making algorithm is used to analyze the network status information of the node.

[0253] In another aspect, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and when the processor executes the computer instructions, an optimization method based on an intelligent distributed network topology is implemented, the method comprising:

[0254] Obtaining real-time network status information monitored on network nodes, including bandwidth usage, communication delay between nodes, and packet loss rate during transmission;

[0255] In response to abnormal network status information, a dynamic topology adjustment strategy is invoked;

[0256] Add a decision-making algorithm to each network node, and make each node share its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision-making algorithm is used to analyze the network status information of the node.

[0257] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory.

[0258] By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0259] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0260] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. An optimization method based on intelligent distributed network topology, characterized in that: The method comprises: Acquire network status information monitored in real time on network nodes, the network status information including bandwidth usage, communication delay between nodes, and loss rate of data packets during transmission; In response to abnormal network status information, a dynamic topology adjustment strategy is invoked; A decision-making algorithm is added to each network node, and each node shares its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision-making algorithm is used to analyze the network status information of the node.

2. The optimization method based on intelligent distributed network topology according to claim 1, characterized in that: The obtaining of network status information monitored in real time on the network node includes: Receiving data flow information monitored on a network node and calculating bandwidth usage, wherein the data flow information includes data transmission speed and flow size; Record the round-trip time of sending test packets and calculate the communication delay between nodes; Count the number of packets sent and received within a specific period of time and calculate the packet loss rate.

3. The optimization method based on intelligent distributed network topology according to claim 2, characterized in that: The invoking of a dynamic topology adjustment strategy in response to abnormal network status information includes: Based on the anomaly of network status information, determine all nodes and links in the network; Set the distance of the source node to zero, and the initial distance of each other node to infinity; Starting from the source node, select a node with the shortest distance and has not been visited as the current node; For each neighbor node of the current node, calculate the total cost to reach the neighbor through the current node; In response to the path cost through the current node being less than the original path cost, updating the distance of the neighbor node; In response to all nodes being visited, the predecessor node of each node is recorded, and the shortest path from the source node to the target node is constructed; Redistribute the network onto the shortest path.

4. The optimization method based on intelligent distributed network topology according to claim 3 is characterized in that: The invoking of a dynamic topology adjustment strategy in response to abnormal network status information also includes: Evaluate the congestion level of each link based on the network status information of each link; Based on the congestion assessment result, a non-congested path or a low-congested path is selected; For each possible path between the source node and the destination node, calculate the total congestion value of the path and select the path with the least congestion; Redistribute the network onto the least congested paths.

5. The optimization method based on intelligent distributed network topology according to claim 4 is characterized in that: The invoking of a dynamic topology adjustment strategy in response to abnormal network status information also includes: Get real-time information to mark failed nodes or links and determine which parts need to be bypassed; Identify all paths that pass through the failed node or link; Generate available alternative paths based on algorithms in graph theory; Reconfigure the routing table and direct traffic to go through alternative paths based on bypassing failed nodes or critical links.

6. The optimization method based on intelligent distributed network topology according to claim 5, characterized in that: The invoking of a dynamic topology adjustment strategy in response to abnormal network status information also includes: In response to a link load being greater than a preset threshold, allocating part of the traffic of the link to an alternative path according to a load balancing algorithm; In response to the overall load on the path being less than a preset threshold value, the newly initiated link is allocated to the path according to a priority steering strategy.

7. The optimization method based on intelligent distributed network topology according to any one of claims 1 to 6, characterized in that: The method further includes: Classify the data in the network and assign a unique identifier to each type of data; Define different priority levels based on the importance and urgency of the data; In response to data with a high priority level, more bandwidth resources are allocated to the data, and a priority queue is set at each node in the network so that data packets in the high priority queue are transmitted before data packets in the low priority queue.

8. An optimization device based on intelligent distributed network topology, characterized in that: include: An acquisition module is used to acquire network status information monitored in real time on network nodes, wherein the network status information includes bandwidth utilization, communication delay between nodes, and loss rate of data packets during transmission; A calling module, used for calling a dynamic topology adjustment strategy in response to abnormal network status information; The coordination module is used to add a decision-making algorithm to each network node, and enable each node to share its decision results and network status information, and all nodes coordinate their decisions according to the consensus mechanism. The decision-making algorithm is used to analyze the network status information of the node.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the optimization method based on intelligent distributed network topology described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the optimization method based on intelligent distributed network topology described in any one of claims 1 to 7 are implemented.

Images