Intra-network cache driven active network telemetering method

Abstract

The invention discloses an in-network cache-driven active network telemetering scheme. The scheme comprises the following steps of: storing and multiplexing network information collected by a telemetering probe by using a designed cache strategy; the data transmission quantity from the data plane to the controller is reduced by using an incremental transmission technology; and finishing planning oriented to the path of the cache probe in the network by using deep reinforcement learning based on an attention mechanism. According to the method provided by the invention, the data transmission quantity from the data plane to the controller can be greatly reduced, and the control overhead is also remarkably reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of network flow remote sensing, and in particular relates to an active network telemetry method driven by an in-network cache. Background Art

[0002] With the rapid development of network technology, modern networks are becoming increasingly large and complex, and network management has become particularly important. Network management systems need to monitor network status in real time in order to promptly discover and solve potential problems and ensure the stability and efficient operation of the network. As a key technology, network telemetry provides network managers with the ability to gain in-depth understanding of network behavior by embedding detectors in the network to collect network status information. However, with the expansion of network scale and the surge in traffic, traditional network telemetry methods face huge challenges, especially the sharp increase in the amount of telemetry data transmitted from the data plane to the control plane, which not only increases the consumption of network bandwidth, but also may increase the processing burden of the control plane, thereby affecting the performance and response speed of the entire network.

[0003] In particular, in network telemetry systems, technologies based on in-band network telemetry (INT) have attracted much attention due to their ability to embed telemetry information directly in data packets. INT technology allows nodes along the way (such as routers) to add state information (such as delay, packet loss rate, etc.) when processing data packets to the packet header during data packet transmission, thereby achieving comprehensive monitoring of network status without the need for additional network resources. However, this approach also faces the problem of data redundancy and unnecessary information transmission, because multiple data packets may contain repeated or similar telemetry information, which may be redundant for the controller's decision-making.

[0004] In addition, how to effectively plan the detection path to maximize the efficiency of telemetry data collection and minimize the impact on normal network traffic is also one of the key issues that the network telemetry system needs to solve. Traditional path planning methods are often based on static network topology and preset rules, which are difficult to adapt to dynamically changing network environments.

[0005] In view of the above challenges, how to design a network telemetry system that can effectively reduce the amount of redundant and unnecessary telemetry data and improve the efficiency of detection path planning has become a research hotspot in the current network management field. This invention is an innovative attempt to address this problem. By introducing a cache mechanism and incremental transmission technology, as well as a detection path planning algorithm based on deep reinforcement learning (DRL), the invention aims to significantly improve the efficiency and performance of the network telemetry system. Summary of the invention

[0006] The purpose of the present invention is to reduce the amount of redundant and unnecessary telemetry data from the data plane to the controller, while improving the detection efficiency and adapting to the dynamic network environment, and to provide an active network telemetry method driven by an in-network cache;

[0007] In order to achieve the above object, the present invention adopts the following technical solution: an active network telemetry method driven by in-network cache, comprising:

[0008] Step S1: The controller generates a planned telemetry path according to a detection path planning algorithm based on deep reinforcement learning and attention mechanism, and then the controller sends probes to the detection network according to the planned telemetry path;

[0009] Step S2: In step S1, the probe records the relevant information to be detected at each node, and then the probe caches the collected information in the cache node, and the cache node stores, updates and retrieves the cached information through a preset cache strategy;

[0010] Step S3: The cache node uses incremental transmission technology to transmit the information stored in the cache node back to the controller.

[0011] Furthermore, the detection path planning algorithm based on deep reinforcement learning and attention mechanism in step S1 specifically includes:

[0012] Step S11: Set a specific detection path planning target, which is expressed as a constrained optimization problem, and its mathematical expression is:

[0013] min C

[0014]

[0015]

[0016] L=E,

[0017] T≤T max ,

[0018] |p k |≤l th ,k=1,…,K.

[0019] The optimization goal is to minimize the control cost C of the telemetry system, and the constraints are After collecting all network information, the probe must store the information on the cache node. is the Nth k nodes; is the cache capacity limit of the i-th router, S k is the cache space required by the kth probe, is an indicator function, when The value is 1 when L=E, otherwise it is 0; L=E means that the probe needs to detect all physical paths in the network, L is the set of physical links of all detection paths, and E is the set of direct physical links of network nodes; T≤T max is the telemetry delay constraint, T is the actual maximum telemetry delay of the telemetry system, and T max The maximum telemetry latency allowed for the control plane; |p k |<l th Indicates that the length of the port information has an upper limit, |p k | is the length of the kth telemetry path, l th represents the length threshold of the auxiliary probe path;

[0020] Step S12: Map the high-load network graph to the vector space, input in It is a tuple containing the connection status and delay information of the i-th node and other nodes at time slot t, and uses one-dimensional convolution to Embed it and get

[0021] Step S13: Use content-based attention mechanism to obtain h from the decoder t , combined with step S12 to obtain Compute variable-length alignment vectors Variable length alignment vector The calculation formula is: in h t ∈R D represents the memory state of the RNN unit at time t during decoding. The symbol “;” represents the connection of two vectors. The variable and is a trainable variable;

[0022] Step S14: Using step S12 to obtain Combined with step S13, the variable length alignment vector is obtained Calculate the context vector c t , context vector c t The calculation formula is: Where M is the input length, and the input The lengths are equal, and the conditional probability is obtained by normalizing with the softmax function. Conditional Probability for: in Variable v c and W c is a trainable variable;

[0023] Step S15: Use the greedy decoder to get the conditional probability according to step S14 To select an action, and update the telemetry path planning scheme according to the selected action, and at the same time Update and get the updated input and telemetry path until the specific detection path planning target in step S11 is met, where Where f is the state transition function.

[0024] Furthermore, the training steps of the deep reinforcement learning neural network in the detection path planning algorithm based on deep reinforcement learning and attention mechanism specifically include:

[0025] Step S101: Input In each It is a tuple containing the connection status and delay information of the i-th node and other nodes at time slot t, which is embedded using one-dimensional convolution. After embedding, it is expressed as Get the data set;

[0026] Step S102: Initialize the action network and the evaluation network with random weights θ and δ, and then set the number of iteration cycles. In each iteration cycle, first reset the gradients dθ←0, dδ←0, and then select a sample set M for training from the data set obtained in step S101. The number of samples is recorded as batch. Then, for each sample in M, start from time slot t=0 and calculate the conditional probability Get new status Then update t to t+1, repeat the calculation of conditional probability and get the new state until the specific detection path planning goal is met. After the calculation is completed, the reward R is calculated according to the generated strategy m , and when each sample in M ​​completes the strategy generation and reward calculation, the gradients dθ and dδ are calculated according to the reward:

[0027]

[0028]

[0029] Then, θ and δ are updated according to the calculated gradient to complete one iteration cycle of training. When the set number of iteration cycles is completed, the deep reinforcement learning neural network training is completed.

[0030] Furthermore, the cache strategy preset in step S2 specifically includes:

[0031] Step S21: Cache object classification: classify cached information into time-varying data and static data;

[0032] Step S22: cache key design: each cache item corresponds to the same cached information bound to a specific timestamp, and the cache key of each cache item is formulated according to the data type and its associated timestamp;

[0033] Step S23: cache update strategy design: for time-varying data, cache contents and keys are updated when new probes are received to ensure that the cache always reflects the latest network status. When the capacity limit is reached, the smallest fresh items of the same type will be cleared first. For static data, only the latest cached information is cached and they are directly updated when new probes are received, thereby minimizing unnecessary cache operations.

[0034] Step S24: cache expiration mechanism design: set the global cache expiration time, and the global cache expiration time is dynamically adjusted according to the network environment. For time-varying data, cache items that exceed the global cache expiration time will be automatically deleted to ensure the timeliness and accuracy of the cached data. For static data, it is set to never fail to reduce unnecessary cache operations;

[0035] Step S25: Cache access mechanism design: Based on the cache key search method, when querying the cache, the system quickly searches for the corresponding cache item according to the cache key. If a matching cache item is found, the cached network information is returned. Otherwise, the "cache lost" status is returned.

[0036] Furthermore, the incremental transmission technology in step S3 specifically includes:

[0037] Step S31: Divide the information stored in the cache node into multiple data blocks according to the probe;

[0038] Step S32: Calculate unique hash values ​​for all data blocks using a hash function and systematically store them in a dedicated hash library for subsequent comparison and analysis. Whenever the system receives a new probe, the network telemetry system calculates a new hash value based on the new data block and compares it with the existing hash value in the hash library.

[0039] Step S33: Update the hash library accordingly. For static data, as long as its hash value changes, the network telemetry system will immediately generate an incremental file. For time-varying data, after checking whether the hash value has changed, it is necessary to evaluate whether the data change amplitude exceeds the preset threshold. When the data change exceeds this threshold, the network telemetry system will generate an incremental file.

[0040] Step S34: After the incremental file is generated, it is immediately sent to the controller. After receiving the file, the controller calculates and compares the hash value. If the comparison result is a correct hash, it indicates that the data has not been tampered with. The information stored in the cache node received by the controller is used for the local database and network management application. Finally, the controller updates the local hash database to facilitate subsequent data synchronization and verification.

[0041] Beneficial effects: The present invention successfully solves the problems of data redundancy and excessive transmission volume in modern network management by integrating efficient caching strategies, incremental transmission technology, and intelligent detection path planning algorithms based on deep reinforcement learning. The system can intelligently store and reuse key network information and only transmit necessary change data, thereby significantly reducing network bandwidth consumption and the processing burden of the control plane. At the same time, its flexible cache router upgrade solution and intelligent path planning capabilities ensure the comprehensiveness and efficiency of network telemetry, bringing unprecedented convenience and performance improvement to modern network management. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A framework diagram of an active network telemetry solution driven by an in-network cache provided in an embodiment.

[0043] Figure 2 This is the incremental transmission technology flow chart.

[0044] Figure 3 Schematic diagram of deep reinforcement learning. DETAILED DESCRIPTION

[0045] The present invention will be further explained below in conjunction with the accompanying drawings.

[0046] like Figure 1 As shown, the present invention provides an active network telemetry method driven by in-network cache, comprising:

[0047] Step S1: The controller generates a planned telemetry path according to a detection path planning algorithm based on deep reinforcement learning and attention mechanism, and then the controller sends probes to the detection network according to the planned telemetry path.

[0048] Step S2: In step S1, the probe records the relevant information to be detected at each node, and then the probe caches the collected information in the cache node, and the cache node stores, updates and retrieves the cached information through a preset cache strategy.

[0049] Step S3: The cache node uses incremental transmission technology to transmit the information stored in the cache node back to the controller.

[0050] In step S1, the network topology is initialized according to the original data, which specifically includes: defining the detection network as an undirected physical graph, represented by G = (V, E); where V = {v i |i=1,…,N} is the set of physical nodes, v i ∈V is the physical node with serial number i in the monitoring network; E={e ij =(v i ,v j )|v i ,v j ∈V} is the set of direct physical links between nodes, where e ij ∈E is the physical link status between node i and node j. If there is a connected physical link between node i and node j, then e ij exists; otherwise e ij does not exist. The set of cache nodes is represented as U = {j∈V|x j =1}, x i is a binary variable indicating whether node i is upgraded. i =1, then node i has been upgraded; if x i = 0, node i has not been upgraded. The total number of cache nodes is Q, that is

[0051] Assume there are K telemetry paths, where the kth path is represented as: where v k,i is the i-th node passed by the k-th telemetry path. N k is the total number of nodes passed by the kth path. Since the Fwd stack is a fixed-length stack, the length of the port information cannot exceed the length of the SR stack, which can be expressed as |p k |≤l th Among them, |p k | represents the length of the kth path, l th Indicates the length threshold of the auxiliary probe path.

[0052] The kth physical link in the kth probe is represented by (v k,i ,v k,i+1 ) is represented by the set of physical links that the kth probe passes through is represented by L k ={(v k,i ,v k,i+1 )|i=1,…,N i -1}, After obtaining the set of links covered by each probe, we can express the set of physical links L of all probe paths as Since the probe needs to detect all physical paths in the network, the set L should satisfy L=E.

[0053] Telemetry delay is very important for real-time network services. The delay of each link can be obtained through the network telemetry of the previous cycle. Define the delay function t:E→T. Denote the delay of forwarding a packet from node i to node j as t(i,j). If there is no physical link between the nodes, then t(i,j) is infinite. The telemetry delay of the Kth detection path can be expressed as Where t(v k,i ,v k,i+1 ) is the delay of the ith physical link on the kth detection path. Considering the frequency consistency, the telemetry delay T of the network telemetry system is the maximum detection delay, expressed as T = max{T k}, k = 1, 2, ..., K. Assume that the maximum telemetry delay allowed by the control plane is Tmax. To ensure that the control plane obtains network information in a timely manner, the telemetry delay constraint can be expressed as T≤T max .

[0054] Control overhead is an indicator that network telemetry systems need to focus on. In active network telemetry, control overhead is mainly caused by the generation and collection of probes. Therefore, control overhead is related to the number of probes in the network and can be expressed as a linear function related to the number of probe paths. It can be expressed as follows:

[0055] C = h·K, where h is a scaling factor used to quantify the overhead of each detection path.

[0056] In order to efficiently utilize the in-network cache, we need to store all the network information collected by the probe in the cache router. This not only maximizes the use of differential transmission technology to reduce the amount of transmitted data, but also uses the same set of cache data to respond to the control plane's requests due to the integrity of the network information. In order to ensure that all network information can be stored in the cache router, the probe must store the information on the cache node after collecting all network information, which can be expressed as

[0057] In addition, the total amount of network information stored in each cache router cannot exceed the maximum cache limit. The number of bytes that each probe needs to store in the cache switch is determined by the number of INT tags in the INT stack. We can define the cache space required by the kth probe as s k , can be calculated as s k =a·|p k |, a is a scaling factor determined by the number of bytes per label. Therefore, the cache capacity limit of the i-th router can be expressed as in is an indicator function, when (i.e., node i is the last hop of the kth telemetry path), and 0 otherwise.

[0058] Since the number of probes and the detection frequency will increase the network load for network telemetry, the number of probes should be minimized when the detection frequency is fixed, and all switches should be within the telemetry range. In addition, in order to ensure that all network information can be stored by cache-enabled routers, all probes should be forwarded to cache-enabled switches. Therefore, based on the above analysis, the detection path planning problem can be summarized as a constrained optimization problem, and its mathematical expression is:

[0059] minC

[0060]

[0061]

[0062] L=E,

[0063] T≤T max ,

[0064] |p k |≤l th ,k=1,…,K.

[0065] The optimization goal is to minimize the telemetry system control overhead C, and the constraints are After collecting all network information, the probe must store the information on the cache node. is the Nth k nodes; is the cache capacity limit of the i-th router, S k is the cache space required by the kth probe, is an indicator function, when The value is 1 when L=E, otherwise it is 0; L=E means that the probe needs to detect all physical paths in the network, L is the set of physical links of all detection paths, and E is the set of direct physical links of network nodes; T≤T max is the telemetry delay constraint, T is the maximum detection delay, T max The maximum telemetry delay allowed for the control plane; |p k |<l th Indicates that the length of the port information has an upper limit, |p k | represents the length of the kth telemetry path, l th Indicates the length threshold of the auxiliary probe path.

[0066] Then we use a network model based on deep reinforcement learning to solve the above optimization problem. The main implementation idea is: first map the high-load network graph to the vector space, input In each It is a tuple containing the connection status and delay information of the i-th node and other nodes at time slot t;

[0067] We first arbitrarily choose At time slot t,t∈[0,T], we select the available input Select y t Until the constraints in constraint formula (1) are met, the node sequence generated by this process can be expressed as T″ is the length of the sequence, and the sequence is decomposed using the probability chain rule Probability of occurrence It is expressed as:

[0068]

[0069] in Calculated by the attention layer of the deep reinforcement learning network. If an affine function g is used to represent the transformation from input to output vector, the state of the recurrent neural network (RNN) decoder is represented by h t , which summarizes the previous steps y0,…,y t information, probability It can be expressed as:

[0070]

[0071] This allows the input Recursively update to:

[0072]

[0073] The state transition function f is used to recursively update the input

[0074] like Figure 3 As shown in the figure, during the actual algorithm operation, the input of the model is a set of node information, and their input order does not affect the output probability information, so input embedding is used directly.

[0075] So through deep reinforcement learning network computing The specific steps are as follows: First, the input is mapped into a vector space, which may have multiple embeddings corresponding to different input elements. The embedding operation is performed using a one-dimensional convolutional layer.

[0076] A content-based attention mechanism is used to extract relevant information h from the decoder input t Variable length alignment vector To calculate this mechanism, input After embedding, it is expressed as Among them, h t ∈R D Represents the memory state of the RNN unit at decoding realization t. Variable length alignment vector It can be calculated as:

[0077]

[0078] and:

[0079]

[0080] The relevance of each input data point to the upcoming decoding step t is determined, and the symbol ";" indicates the concatenation of two vectors. and is a trainable variable. To calculate the conditional probability, we first calculate the context vector c using the embedded input t , defined as:

[0081]

[0082] These values ​​are then normalized using the softmax function to obtain the conditional probabilities as follows:

[0083]

[0084] and:

[0085]

[0086] Among them, the variable v c and W c It is also a trainable variable.

[0087] Finally, a greedy decoder is used to decode the conditional probability To select an action, and update the telemetry path planning scheme according to the selected action, and Update to get new input and the planned telemetry path until the telemetry path planning target is met.

[0088] This example also trains the deep reinforcement learning neural network in the detection path planning algorithm based on deep reinforcement learning and attention mechanism, thereby realizing the detection path planning algorithm based on deep reinforcement learning and attention mechanism. The training steps specifically include:

[0089] Step S101: Input In each It is a tuple containing the connection status and delay information of the i-th node and other nodes at time slot t, which is embedded using one-dimensional convolution. After embedding, it is expressed as Get the dataset.

[0090] Step S102: Initialize the action network and the evaluation network with random weights θ and δ, and then set the number of iteration cycles. In each iteration cycle, first reset the gradients dθ←0, dδ←0, and then select a sample set M for training from the data set obtained in step S101. The number of samples is recorded as batch. Then, for each sample in M, start from time slot t=0 and calculate the conditional probability Get new status Then update the time slot t to t+1, repeat the conditional probability calculation and get the new state until the specific detection path planning goal is met. After the calculation is completed, calculate the reward R according to the generated strategy m , and when each sample in M ​​completes the strategy generation and reward calculation, the gradients dθ and dδ are calculated according to the reward:

[0091]

[0092]

[0093] Then, θ and δ are updated according to the calculated gradient to complete one iteration cycle of training. When the set number of iteration cycles is completed, the training of the detection path planning algorithm based on deep reinforcement learning and attention mechanism is completed.

[0094] In step S2, the preset cache strategy specifically includes: cache object selection, cache key design, cache update strategy, cache invalidation mechanism and cache access strategy.

[0095] Cache object classification: Network information can be divided into two types: time-varying data and static data. Time-varying data refers to dynamic network information that needs to be updated in real time to reflect the latest network status, such as router load, latency, etc. Static data is network information that hardly changes but is equally important to the overall understanding of the network, such as port connection status.

[0096] Cache key design: Each cache item corresponds to the same network information tied to a specific timestamp. The cache key for each item is based on the data type and its associated timestamp. This approach ensures that the cache maintains a high level of accuracy and timeliness while simplifying retrieval and subsequent updates.

[0097] Cache update strategy, as follows:

[0098] We adopt different cache update strategies to handle time-varying data and static data. For time-varying data, we use a freshness-based update strategy to update cache content and keys when new probes are received, ensuring that the cache always reflects the latest network status. When the capacity limit is reached, the smallest fresh items of the same type will be cleared first.

[0099] For static data, only the latest network information is cached and new probes are directly updated when they are received, thus minimizing unnecessary cache operations.

[0100] Cache expiration mechanism, in order to maintain the timeliness and accuracy of time-varying data, we set a global cache expiration time, which is dynamically adjusted according to the network environment. Cache items that exceed this time will be automatically deleted to ensure the timeliness and accuracy of cached data. For static data, since the change frequency is low, we can set it to never fail to reduce unnecessary cache operations.

[0101] For cache access mechanism, we use a cache key-based lookup method. When querying the cache, the system quickly looks up the corresponding cache item based on the cache key. If a matching cache item is found, the cached network information is returned. Otherwise, a "cache miss" status is returned.

[0102] like Figure 2 As shown, the details of the incremental transmission technology in step S3 include: first, the network information is divided into multiple data blocks according to the probe. Then, the unique hash values ​​of all data blocks are calculated using a hash function and systematically stored in a dedicated hash library for subsequent comparison and analysis. Whenever the system receives a new probe, the network telemetry system calculates a new hash value based on the new data block and compares it with the existing hash value in the hash library. Then, the hash library is updated accordingly. For static data, as long as its hash value changes, the network telemetry system will immediately generate an incremental file. For time-varying data, after checking whether the hash value has changed, it is also necessary to evaluate whether the data change amplitude exceeds the preset threshold, which can be flexibly adjusted according to the network environment and the specific requirements of the user. Only when the data change exceeds this threshold, the network telemetry system generates an incremental file. After the incremental file is generated, it is immediately sent to the controller. After the controller receives the file, it calculates and compares the hash value to ensure the integrity and security of the data. The correct hash indicates that the data has not been tampered with. The control plane of the controller uses the received new network information for the local database and network management application. Finally, to ensure the consistency of information between the data plane and the controller’s control plane, the controller updates the local hash database to facilitate subsequent data synchronization and verification.

[0103] In summary, the present invention proposes an active network telemetry solution driven by in-network cache. This method can effectively reduce the overall number of probes and data transmission volume based on cache strategy, incremental transmission and deep reinforcement learning, and improve detection efficiency.

[0104] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An active network telemetry method driven by in-network cache, characterized in that: include: Step S1: The controller generates a planned telemetry path according to a detection path planning algorithm based on deep reinforcement learning and attention mechanism, and then the controller sends probes to the detection network according to the planned telemetry path; Step S2: In step S1, the probe records the relevant information to be detected at each node, and then the probe caches the collected information in the cache node, and the cache node stores, updates and retrieves the cached information through a preset cache strategy; Step S3: The cache node uses incremental transmission technology to transmit the information stored in the cache node back to the controller.

2. The active network telemetry method driven by in-network cache according to claim 1, characterized in that: The detection path planning algorithm based on deep reinforcement learning and attention mechanism in step S1 specifically includes: Step S11: Set a specific detection path planning target, which is expressed as a constrained optimization problem, and its mathematical expression is: The optimization goal is to minimize the control cost C of the telemetry system, and the constraints are After collecting all network information, the probe must store the information on the cache node. is the Nth k nodes; is the cache capacity limit of the i-th router, S k is the cache space required by the kth probe, is an indicator function, when The value is 1 when L=E, otherwise it is 0; L=E means that the probe needs to detect all physical paths in the network, L is the set of physical links of all detection paths, and E is the set of direct physical links of network nodes; T≤T max is the telemetry delay constraint, T is the actual maximum telemetry delay of the telemetry system, and T max The maximum telemetry latency allowed for the control plane; |p k |<l th Indicates that the length of the port information has an upper limit, |p k | is the length of the kth telemetry path, l th represents the length threshold of the auxiliary probe path; Step S12: Map the high-load network graph to the vector space, input where x t i It is a tuple containing the connection status and delay information of the i-th node and other nodes at time slot t, and uses one-dimensional convolution to transform x t i Embed it and get Step S13: Use content-based attention mechanism to obtain h from the decoder t , combined with step S12 to obtain Compute variable-length alignment vectors Variable length alignment vector The calculation formula is: in represents the memory state of the RNN unit at time t during decoding. The symbol ";" represents the connection of two vectors. The variable and is a trainable variable; Step S14: Using step S12 to obtain Combined with step S13, the variable length alignment vector is obtained Calculate the context vector c t , context vector c t The calculation formula is: Where M is the input length, and the input The lengths are equal, and the conditional probability is obtained by normalizing with the softmax function. Conditional Probability for: in Variable v c and W c is a trainable variable; Step S15: Use the greedy decoder to get the conditional probability according to step S14 To select an action, and update the telemetry path planning scheme according to the selected action, and at the same time Update and get the updated input and telemetry path until the specific detection path planning target in step S11 is met, where Where f is the state transition function.

3. The active network telemetry method driven by in-network cache according to claim 2, characterized in that: The training steps of the deep reinforcement learning neural network in the detection path planning algorithm based on deep reinforcement learning and attention mechanism specifically include: Step S101: Input In t i It is a tuple containing the connection status and delay information of the i-th node and other nodes at time slot t, which is embedded using one-dimensional convolution. After embedding, it is expressed as Get the data set; Step S102: Initialize the action network and the evaluation network with random weights θ and δ, and then set the number of iteration cycles. In each iteration cycle, first reset the gradients dθ←0, dδ←0, and then select a sample set M for training from the data set obtained in step S101. The number of samples is recorded as batch. Then, for each sample in M, start from time slot t=0 and calculate the conditional probability Get new status Then update t to t+1, repeat the calculation of conditional probability and get the new state until the specific detection path planning goal is met. After the calculation is completed, calculate the reward R according to the generated strategy m , and when each sample in M ​​completes the strategy generation and reward calculation, the gradients dθ and dδ are calculated according to the reward: Then, θ and δ are updated according to the calculated gradient to complete one iteration cycle of training. When the set number of iteration cycles is completed, the deep reinforcement learning neural network training is completed.

4. The active network telemetry method driven by in-network cache according to claim 1, characterized in that: The cache strategy preset in step S2 specifically includes: Step S21: Cache object classification: classify cached information into time-varying data and static data; Step S22: Cache key design: Each cache item corresponds to the same cached information bound to a specific timestamp. And the cache key of each cache item is formulated based on the data type and its associated timestamp; Step S23: cache update strategy design: for time-varying data, cache contents and keys are updated when new probes are received to ensure that the cache always reflects the latest network status. When the capacity limit is reached, the smallest fresh items of the same type will be cleared first. For static data, only the latest cached information is cached and they are directly updated when new probes are received, thereby minimizing unnecessary cache operations. Step S24: cache expiration mechanism design: set the global cache expiration time, and the global cache expiration time is dynamically adjusted according to the network environment. For time-varying data, cache items that exceed the global cache expiration time will be automatically deleted to ensure the timeliness and accuracy of the cached data. For static data, it is set to never fail to reduce unnecessary cache operations; Step S25: Cache access mechanism design: Based on the cache key search method, when querying the cache, the system quickly searches for the corresponding cache item according to the cache key. If a matching cache item is found, the cached network information is returned. Otherwise, Returns a "cache miss" status.

5. The active network telemetry method driven by in-network cache according to claim 1, characterized in that: The incremental transmission technology in step S3 specifically includes: Step S31: Divide the information stored in the cache node into multiple data blocks according to the probe; Step S32: Calculate unique hash values ​​for all data blocks using a hash function and systematically store them in a dedicated hash library for subsequent comparison and analysis. Whenever the system receives a new probe, the network telemetry system calculates a new hash value based on the new data block and compares it with the existing hash value in the hash library. Step S33: Update the hash library accordingly. For static data, as long as its hash value changes, the network telemetry system will immediately generate an incremental file. For time-varying data, after checking whether the hash value has changed, it is necessary to evaluate whether the data change amplitude exceeds the preset threshold. When the data change exceeds this threshold, the network telemetry system will generate an incremental file. Step S34: After the incremental file is generated, it is immediately sent to the controller. After receiving the file, the controller calculates and compares the hash value. If the comparison result is a correct hash, it indicates that the data has not been tampered with. The information stored in the cache node received by the controller is used for the local database and network management application. Finally, the controller updates the local hash database to facilitate subsequent data synchronization and verification.

Images