Method and device for generating data transmission path of distributed wireless sensor

Abstract

The invention provides a data transmission path generation method and device for a distributed wireless sensor, and belongs to the technical field of data transmission, and the method comprises the steps: constructing a state space based on the state of a sensor network, and constructing an action space based on a selectable transmission strategy of the sensor network in each state in the state space; determining an optimal data transmission strategy set based on the state space and the action space, and adjusting transmission parameters of the plurality of sensors based on the optimal data transmission strategy set; updating the sensor network based on the transmission path set, the optimal data transmission strategy and the adjusted sensor parameters to obtain a distributed sensor network; and determining a target transmission path based on the pheromone concentration of each transmission path in the distributed sensor network. According to the data transmission path generation method of the distributed wireless sensor, the technical problem that the efficiency of the data transmission process is relatively low in the data transmission path generation method of the distributed wireless sensor in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data transmission, and in particular to a method and device for generating a data transmission path of a distributed wireless sensor. Background Art

[0002] With the rapid development of rail transit, especially high-speed rail technology, the speed of trains and the complexity of lines are constantly increasing, and the demand for real-time monitoring and intelligent management of the operating status of high-speed rail systems is also growing. The safe, stable and efficient operation of high-speed rail systems depends on the real-time data collection and transmission of a large number of sensor nodes. These sensors are distributed in different parts of the train and along the track to monitor key parameters such as train speed, wheel status, car temperature, vibration, track conditions, etc. In traditional high-speed rail monitoring systems, data transmission relies on wired or centralized wireless network architectures, which have problems such as complex wiring, high maintenance costs, and signal delays. The emergence of distributed wireless sensor networks provides an efficient and flexible solution for the monitoring of high-speed rail systems. By deploying distributed wireless sensor networks, seamless data collection and transmission can be achieved in the entire high-speed rail system, thereby improving data transmission efficiency, system reliability, and response time.

[0003] In the related technology, by providing a data transmission management system for wireless sensors, the effects of information encryption during the collection and transmission process, improved storage efficiency and data access speed are achieved. However, there is a lot of unnecessary redundant data transmission, and the overall data transmission energy consumption is high, resulting in low stability and reliability of the sensor network.

[0004] It can be seen that the data transmission path generation method of the distributed wireless sensor in the related art has the technical problem of low efficiency of the data transmission process. Summary of the invention

[0005] The present invention provides a data transmission path generation method and device for a distributed wireless sensor, which are used to solve the technical problem that the data transmission path generation method for a distributed wireless sensor in the related art has low efficiency in the data transmission process.

[0006] The present invention provides a method for generating a data transmission path of a distributed wireless sensor, comprising the following steps: constructing an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of a plurality of sensors, the edges of the undirected weighted graph are communication links between the plurality of sensors, and the weights of the undirected weighted graph are data transmission costs between the plurality of sensors; constructing a minimum spanning tree based on the undirected weighted graph, and determining a transmission path set according to the minimum spanning tree; constructing a state space based on the state of a sensor network, and constructing an action space based on transmission strategies selectable by the sensor network in each state in the state space, wherein the sensor network is constructed based on the plurality of sensors and the communication links between the plurality of sensors; determining an optimal data transmission strategy set based on the state space and the action space, and adjusting the transmission parameters of the plurality of sensors based on the optimal data transmission strategy set to obtain adjusted multiple sensor parameters; updating the sensor network based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network; determining a target transmission path based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is a transmission path with the highest pheromone concentration in the distributed sensor network.

[0007] According to a method for generating a data transmission path of a distributed wireless sensor provided by the present invention, the state space includes the energy level of the sensor network, the load condition of the communication link, the transmission quality of the communication link and various states of external environmental factors, and the action space includes various groups of actions of the sensor network changing the transmission path, adjusting the transmission power, switching to a backup node and adjusting the transmission rate.

[0008] According to a data transmission path generation method for a distributed wireless sensor provided by the present invention, the optimal data transmission strategy set is determined based on the state space and the action space, including: taking each state in the state space as the target state and executing the following steps to obtain the optimal data transmission strategy set consisting of multiple optimal data transmission strategies: calculating the transition probability of the sensor network transferring to other states after selecting the target action in the target state; obtaining the instantaneous benefit of the sensor network after selecting the target action in the target state, and performing multiple recursive calculations using the Bellman equation based on the transition probability and the instantaneous benefit to obtain the optimal data transmission strategy.

[0009] According to a data transmission path generation method for a distributed wireless sensor provided by the present invention, the target transmission path is determined based on the pheromone concentration of each transmission path in the distributed sensor network, including: obtaining a source node and a destination node in the distributed sensor network, wherein the source node is a sensor node for collecting data, and the destination node is a node for receiving and processing data sent by the source node; initializing a plurality of exploration bodies at different source nodes, and determining a plurality of transmission paths to be confirmed through the plurality of exploration bodies based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the end point of the transmission path to be confirmed is the destination node; and determining the path with the highest pheromone concentration among the plurality of transmission paths to be confirmed as the target transmission path.

[0010] According to a method for generating a data transmission path of a distributed wireless sensor provided by the present invention, after determining the target transmission path based on the pheromone concentration of each transmission path in the distributed sensor network, the method further includes: acquiring an original data set, wherein the original data set includes data collected by the multiple sensors; preprocessing the original data set to obtain a preprocessed data set; transmitting the preprocessed data set to a parsing and storage module along the target transmission path, wherein the parsing and storage module is used to parse the received data and store it in a database.

[0011] According to a method for generating a data transmission path of a distributed wireless sensor provided by the present invention, the original data set is preprocessed to obtain a preprocessed data set, including: when there are missing values ​​in the sensor data in the original data set, the missing values ​​are filled to obtain a filled data set; the first quartile and the third quartile of the filled data set are calculated, the interquartile range is calculated based on the first quartile and the third quartile, the target data range is determined based on the first quartile, the third quartile and the interquartile range, and the data outside the target data range in the filled data set is deleted to obtain an optimized data set; the optimized data set is smoothed and denoised using a sliding average method and a low-pass filter respectively, and normalized by a minimum and maximum normalization method to obtain the preprocessed data set.

[0012] The present invention also provides a data transmission path generation device for distributed wireless sensors, comprising the following modules: a first construction module, used to construct an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are the data transmission costs between the multiple sensors; a first execution module, used to construct a minimum spanning tree based on the undirected weighted graph, and determine a transmission path set based on the minimum spanning tree; a second construction module, used to construct a state space based on the state of the sensor network, and construct an action space based on the transmission strategies that can be selected by the sensor network in each state in the state space, wherein the sensor network is based on A communication link is constructed based on the multiple sensors and between the multiple sensors; a second execution module is used to determine an optimal data transmission strategy set based on the state space and the action space, and adjust the transmission parameters of the multiple sensors based on the optimal data transmission strategy set to obtain multiple sensor parameters after adjustment; an update module is used to update the sensor network based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network; a determination module is used to determine a target transmission path based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for generating a data transmission path for a distributed wireless sensor as described in any one of the above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for generating a data transmission path for a distributed wireless sensor as described in any one of the above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for generating a data transmission path of a distributed wireless sensor as described in any one of the above is implemented.

[0016] The data transmission path generation method and device of the distributed wireless sensor provided by the present invention construct an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are the data transmission costs between the multiple sensors; a minimum spanning tree is constructed based on the undirected weighted graph, and a transmission path set is determined based on the minimum spanning tree; a state space is constructed based on the state of the sensor network, and an action space is constructed based on the transmission strategies that can be selected by the sensor network in each state in the state space, wherein the sensor network is constructed based on multiple sensors and the communication links between the multiple sensors; an optimal data transmission strategy set is determined based on the state space and the action space, and the transmission parameters of the multiple sensors are adjusted based on the optimal data transmission strategy set to obtain the adjusted multiple sensor parameters; based on the transmission path The invention discloses a method for updating a sensor network based on a set of transmission paths, an optimal data transmission strategy and adjusted parameters of multiple sensors to obtain a distributed sensor network; a target transmission path is determined based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network; a minimum spanning tree is constructed based on an undirected weighted graph to determine a set of transmission paths with the lowest transmission cost; an optimal data transmission strategy set is determined based on a state space and an action space to obtain an optimal data transmission strategy; a distributed sensor network is constructed based on the transmission path set and the optimal data transmission strategy; and a target transmission path with the highest transmission efficiency can be determined according to the pheromone concentration of each transmission path, thereby solving the technical problem of low efficiency of the data transmission process in the data transmission path generation method of distributed wireless sensors in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced one by one below. 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 creative work.

[0018] Figure 1 It is a flow chart of the data transmission path generation method of the distributed wireless sensor provided by the present invention.

[0019] Figure 2 It is a schematic diagram of the data transmission management system of the distributed wireless sensor provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of a data transmission path generating device for a distributed wireless sensor provided by the present invention.

[0021] Figure 4It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0023] It should be noted that in the description of the present invention, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. The orientation or position relationship indicated by the terms "upper", "lower" and the like is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] The terms "first", "second", etc. in the present invention are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" means at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0025] With the rapid development of rail transit, especially high-speed rail technology, the speed of trains and the complexity of lines are constantly increasing, and the demand for real-time monitoring and intelligent management of the operating status of high-speed rail systems is also growing. The safe, stable and efficient operation of high-speed rail systems depends on the real-time data collection and transmission of a large number of sensor nodes. These sensors are distributed in different parts of the train and along the track to monitor key parameters such as train speed, wheel status, car temperature, vibration, track conditions, etc. In traditional high-speed rail monitoring systems, data transmission relies on wired or centralized wireless network architectures, which have problems such as complex wiring, high maintenance costs, and signal delays. The emergence of distributed wireless sensor networks provides an efficient and flexible solution for the monitoring of high-speed rail systems. By deploying distributed wireless sensor networks, seamless data collection and transmission can be achieved in the entire high-speed rail system, thereby improving data transmission efficiency, system reliability, and response time.

[0026] In the related art, by providing a data transmission management system for wireless sensors, the effects of encrypting information during the collection and transmission process, improving storage efficiency and data access speed, etc. are achieved. However, there is a lot of unnecessary redundant data transmission, and the overall data transmission energy consumption is high, resulting in low stability and reliability of the sensor network. In addition, the data transmission management system of the distributed wireless sensors in the related art cannot achieve effective local and global coordination, has low flexibility in path selection, and cannot respond to dynamic changes of nodes in high-speed rail scenarios in real time. It can be seen that the data transmission path generation method of the distributed wireless sensors in the related art has the technical problem of low efficiency in the data transmission process.

[0027] In order to at least solve some of the above problems, the following Figure 1-Figure 4 The invention describes a method and device for generating a data transmission path for a distributed wireless sensor.

[0028] The data transmission path generation method for distributed wireless sensors provided in this embodiment can be applied to the scenario of confirming the most efficient data transmission path in the data transmission management system of distributed wireless sensors; the data transmission path generation method for distributed wireless sensors in this embodiment can be executed by a server.

[0029] Figure 1 FIG. 1 is a flow chart of a method for generating a data transmission path of a distributed wireless sensor provided by the present invention. Figure 1 As shown, including but not limited to the following steps: Step 101, constructing an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are data transmission costs between the multiple sensors.

[0030] The multiple sensors in this embodiment are distributed wireless sensors, which may specifically include but are not limited to: temperature sensors, humidity sensors, pressure sensors, acceleration sensors, displacement sensors, vibration sensors, light sensors, gas sensors, sound sensors, positioning sensors and flow sensors.

[0031] An undirected weighted graph is constructed, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are the data transmission costs between the multiple sensors.

[0032] Specifically, each sensor is taken as a node, the communication link between each sensor is taken as an edge, and the transmission cost between sensors is taken as the weight of the corresponding edge. Based on the sensor node distribution and the communication link, a corresponding undirected weighted graph is constructed.

[0033] Step 102: construct a minimum spanning tree based on the undirected weighted graph, and determine a transmission path set according to the minimum spanning tree.

[0034] A minimum spanning tree is constructed based on an undirected weighted graph, and a set of transmission paths is determined based on the minimum spanning tree. Specifically, an initial node is randomly selected from the undirected weighted graph as the starting point of the minimum spanning tree, and then all edges are sorted in ascending order from small to large according to the weights. After the sorting is completed, the minimum edge is selected from the edge with the minimum weight to be added to the minimum spanning tree. If the selected edge will cause a loop, the edge is skipped and the next edge is selected. Edges are selected step by step. When the number of added edges reaches n-1, the selection is stopped and the construction of the minimum spanning tree is terminated, where n represents the number of sensor nodes. After the spanning tree is constructed, the set of transmission paths with the lowest transmission cost is obtained based on the construction of the spanning tree.

[0035] It should be noted that the minimum spanning tree (MST) refers to a subgraph in a weighted undirected graph that contains all the vertices in the graph. The subgraph is a tree, and the sum of the weights of all its edges is the smallest. The minimum spanning tree has the following characteristics: it is a tree, so it contains all the vertices in the graph and has n−1 edges (where n is the number of vertices); it has no cycles, it connects all the vertices in the graph, and the sum of the weights is the smallest; in the process of constructing the minimum spanning tree, it is actually constructing a loop-free path network that connects all sensor nodes. This network is not a single path, but is composed of multiple paths (a set of transmission paths). These paths connect all sensor nodes and ensure that the overall transmission cost is the lowest. The set of transmission paths can make all sensor nodes interconnected and have the lowest transmission cost.

[0036] Optionally, the constructed transmission paths are checked regularly, and when a new sensor is added or any sensor node in the original transmission path fails, the minimum spanning tree is recalculated and constructed to generate the latest transmission path set for replacement.

[0037] Understandably, this set of transmission paths is regularly checked and maintained to ensure efficient operation and reliability of the network. If the network structure changes (for example, new sensors are added or existing sensors fail), the minimum spanning tree needs to be recalculated to ensure that the transmission path is still the one with the lowest cost.

[0038] Step 103, constructing a state space based on the state of the sensor network, and constructing an action space based on the selectable transmission strategies of the sensor network in each state in the state space, wherein the sensor network is constructed based on multiple sensors and communication links between the multiple sensors.

[0039] In this embodiment, the state space represents all possible states of the sensor network, and each state reflects a configuration of the network, such as the energy level of the node, the quality of the link, etc.; the action space represents the set of transmission strategies that the sensor network can choose in each state, such as which path to choose for data transmission.

[0040] Step 104 : determining an optimal data transmission strategy set based on the state space and the action space, and adjusting transmission parameters of the multiple sensors based on the optimal data transmission strategy set to obtain adjusted multiple sensor parameters.

[0041] In this embodiment, reinforcement learning or other optimization algorithms can be applied to learn which actions in a given state space can bring the greatest long-term rewards using methods such as Q learning, deep Q networks, and policy gradients; explore different actions through simulation or actual operations, and adjust strategies based on the results (rewards); after sufficient exploration and learning, determine a set of optimal strategies that can guide the behavior of sensors in the network to optimize overall performance.

[0042] Based on the optimal data transmission strategy set, the transmission parameters of multiple sensors are adjusted to obtain the adjusted parameters of multiple sensors; according to the learned optimal strategy, the transmission parameters of the sensors are adjusted, such as increasing or decreasing the transmission power, changing the data packet size, etc.

[0043] Step 105 , updating the sensor network based on the transmission path set, the optimal data transmission strategy, and the adjusted multiple sensor parameters to obtain a distributed sensor network.

[0044] In this embodiment, the transmission path set represented by the minimum spanning tree is applied to the sensor network; the optimal data transmission strategy is applied to each sensor; each sensor in the network is reconfigured according to the adjusted sensor parameters; the sensor network starts to operate according to the new transmission path, strategy and parameters to transmit data.

[0045] Step 106 , determining a target transmission path based on the pheromone concentrations of each transmission path in the distributed sensor network, wherein the target transmission path is a transmission path with the highest pheromone concentration in the distributed sensor network.

[0046] In this embodiment, in the initial stage of the network, an initial pheromone concentration is assigned to each edge. As data is transmitted, the pheromone concentration on each transmission path is monitored and updated. The update of pheromones can be based on factors such as actual usage of the path and transmission efficiency.

[0047] Specifically, the ant colony optimization algorithm can be used to simulate the behavior of ants, in which ants tend to choose paths with high pheromone concentrations, and based on the pheromone concentrations, the path with the highest concentration is selected as the target transmission path; it can be understood that through the above steps, the distributed sensor network can adaptively adjust to optimize data transmission and improve the efficiency and reliability of the network.

[0048] Through the embodiments provided by the present application, an undirected weighted graph is constructed, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are the data transmission costs between the multiple sensors; a minimum spanning tree is constructed based on the undirected weighted graph, and a set of transmission paths is determined based on the minimum spanning tree; a state space is constructed based on the state of the sensor network, and an action space is constructed based on the transmission strategies that can be selected by the sensor network in each state in the state space, wherein the sensor network is constructed based on multiple sensors and communication links between the multiple sensors; an optimal data transmission strategy set is determined based on the state space and the action space, and the transmission parameters of the multiple sensors are adjusted based on the optimal data transmission strategy set to obtain multiple adjusted sensor parameters; the sensor network is updated based on the transmission path set, the optimal data transmission strategy, and the adjusted multiple sensor parameters to obtain a distributed sensor network; a target transmission path is determined based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network; the data transmission path generation method of the distributed wireless sensor in the related art has a technical problem of low efficiency in the data transmission process, and the efficiency of data transmission is improved.

[0049] As an optional solution, the state space includes the energy level of the sensor network, the load condition of the communication link, the transmission quality of the communication link and various states of external environmental factors, and the action space includes various groups of actions such as the sensor network changing the transmission path, adjusting the transmission power, switching to the backup node and adjusting the transmission rate.

[0050] Optionally, an optimal data transmission strategy set is determined based on the state space and the action space, including: Take each state in the state space as the target state and perform the following steps to obtain an optimal data transmission strategy set consisting of multiple optimal data transmission strategies: S11, calculate the transition probability of the sensor network transferring to other states after selecting the target action in the target state; S12, obtaining the instantaneous benefit of the sensor network after selecting the target action in the target state, and performing multiple recursive calculations using the Bellman equation based on the transition probability and the instantaneous benefit to obtain the optimal data transmission strategy.

[0051] Exemplarily, different states of the sensor network are collected to construct a state space S, and selectable transmission strategies or decisions in each state of the state space are collected to construct an action space A. Then, based on the constructed state space and action space, the transition probability P of transferring to another state after selecting any action a in each state s is calculated; based on various indicators such as energy consumption, transmission delay, and network reliability, the immediate benefit or cost obtained by taking action a in state s is evaluated, and then multiple recursive calculations are performed through the Bellman equation to obtain the long-term reward obtained by taking action a in state s; in each round of recursion, the optimal data transmission strategy selected in state s is selected to maximize the long-term reward value in the current recursive process, until the change in the long-term reward value reaches a preset threshold, the recursion is stopped, and the optimal data transmission strategy is output, and then the transmission parameters of each sensor are adjusted according to the data transmission strategy.

[0052] Through this embodiment, the accuracy of the obtained optimal data transmission strategy set can be improved by performing multiple recursive calculations based on the state space and the action space according to the Bellman equation to determine the optimal data transmission strategy set.

[0053] As an optional solution, the target transmission path is determined based on the pheromone concentration of each transmission path in the distributed sensor network, including: S21, acquiring a source node and a destination node in a distributed sensor network, wherein the source node is a sensor node that collects data, and the destination node is a node that receives and processes data sent by the source node; S22, initializing a plurality of exploration bodies at different source nodes respectively, and determining a plurality of transmission paths to be confirmed through the plurality of exploration bodies based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the end point of the transmission path to be confirmed is the destination node; S23, determining the path with the highest pheromone concentration among the multiple transmission paths to be confirmed as the target transmission path.

[0054] Optionally, the sensor network is updated based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network, including: obtaining source nodes and destination nodes in the distributed sensor network, and at the same time, obtaining all sensor nodes in the sensor network, including source nodes and destination nodes, paths between sensor nodes, pheromone concentrations on each path, and expected transmission quality between two groups of nodes, and constructing the infrastructure of the distributed sensor network based on the above information.

[0055] Exemplarily, multiple groups of exploration bodies are randomly generated, and the positions of each exploration body are initialized on different source nodes. Each exploration body starts from the source node, calculates the selection probability of each relay node through the pheromone concentration and the expected transmission quality, and selects the next node according to the calculated probability, and continuously calculates the relay node probability for node selection until it reaches the destination node; when each exploration body finds a complete path, it calculates the transmission cost of each path according to the energy consumption and delay, and then updates the pheromone concentration on the path according to the quality of the found path, it iterates multiple times in the distributed sensor network, and continuously optimizes the path until it stops after reaching the preset iteration time; detects the pheromone concentration of each path, and determines the final transmission path (target transmission path) using the path or path combination with the highest pheromone concentration, and applies it to the actual transmission plan, while detecting the sensor network information in real time. When the network status changes, a new optimal path is searched again.

[0056] Through this embodiment, the target transmission path is determined in combination with ant colony optimization, which improves the accuracy of the obtained target transmission path, thereby improving the reliability of the data transmission path generation method of the distributed wireless sensor in this embodiment.

[0057] As an optional solution, after determining the target transmission path based on the pheromone concentrations of each transmission path in the distributed sensor network, the method further includes: S31, obtaining an original data set, wherein the original data set includes data collected by multiple sensors; S32, preprocessing the original data set to obtain a preprocessed data set; S33, transmitting the preprocessed data set to the parsing and storage module along the target transmission path, wherein the parsing and storage module is used to parse the received data and store it in a database.

[0058] Obtain a raw data set, where the raw data set includes data collected by multiple sensors; collect data from each sensor in a distributed sensor network, which may include environmental parameters such as temperature, humidity, pressure, light intensity, and other variables monitored by sensors; integrate the data collected by multiple sensors into a raw data set, which is usually time series data, and each data point has a timestamp indicating the time when the data was collected.

[0059] Preprocess the original data set to obtain a preprocessed data set; optionally, the preprocessing steps may include: data cleaning, checking the errors, outliers, missing values, etc. in the original data set, and performing necessary cleaning, which may include deleting outliers and filling missing values ​​(for example, using the mean, median or interpolation method); data conversion, converting the data to make it more suitable for subsequent analysis, which may include normalization, standardization, conversion of data types, etc.; feature extraction, extracting useful features from the original data, which will be used for subsequent data transmission and analysis; data set construction, after preprocessing, constructing a clean, uniformly formatted and representative data set to facilitate further processing and analysis.

[0060] Through this embodiment, the process of performing data transmission based on the target transmission path after the target transmission path is determined is improved, and the reliability of the data transmission path generation method of the distributed wireless sensor in this embodiment is improved.

[0061] As an optional solution, the original data set is preprocessed to obtain a preprocessed data set, including: S41, when there are missing values ​​in the sensor data in the original data set, fill the missing values ​​to obtain a filled data set; S42, calculating the first quartile and the third quartile of the padded data set, calculating the interquartile range based on the first quartile and the third quartile, determining the target data range based on the first quartile, the third quartile and the interquartile range, deleting the data outside the target data range in the padded data set, and obtaining an optimized data set; S43, using a sliding average method and a low-pass filter to smooth and denoise the optimized data set respectively, and normalizing it through a minimum and maximum standardization method to obtain a preprocessed data set.

[0062] Specifically, detect whether there are missing values ​​in the sensor data of the original data set. If so, fill the detected missing values ​​through the mean filling method; integrate the processed sensor data to construct the filled data set, and calculate the first quartile and the third quartile of the data set, then calculate the interquartile range based on the two sets of quartiles, use the quartiles and the interquartile range to draw the upper and lower bounds of the corresponding range, then mark the data points exceeding the upper bound or below the lower bound as outliers and delete them to obtain the optimized data set; smooth the data in the optimized data set through the sliding average method and the low-pass filter, and deal with the high-frequency noise in the data, and then scale the data to the range of [0, 1] through the minimum and maximum normalization method (Min-Max normalization method), and classify and mark the preprocessed sensor data according to the collection time period.

[0063] Through this embodiment, by preprocessing the sensor data in the original data set, the data quality can be effectively improved, thereby improving the efficiency of the subsequent data transmission process.

[0064] The data transmission path generation method of the distributed wireless sensor in the embodiment of the present application is described below with reference to optional examples. Figure 2 is a schematic diagram of a data transmission management system for distributed wireless sensors provided by the present invention, see Figure 2 , provides a data transmission management system based on distributed wireless sensors, the data transmission management system based on distributed wireless sensors is used to execute the data transmission path generation method of the distributed wireless sensors in the embodiment of the present application, the data transmission management system based on distributed wireless sensors includes: a data acquisition module, a data preprocessing module, an aggregation compression module, a transmission optimization module, a dynamic selection module, a relay routing module, a detection and correction module, a cache retransmission module and a parsing and storage module.

[0065] The data acquisition module is used to obtain the original data in the rail transit environment from the distributed wireless sensors; the data preprocessing module is used to preprocess the collected original data; the aggregation compression module is used to compress the preprocessed data and encrypt it; the transmission optimization module is used to optimize the transmission path of the distributed sensor network; the dynamic selection module is used to make dynamic decisions according to different network states and external environments; the relay routing module is used to select the best relay nodes and routing paths in the distributed sensor network; the detection and error correction module is used to detect and correct errors in the transmission data packets in real time; the cache retransmission module is used to temporarily cache data and perform retransmission control when packet loss or network congestion occurs during the transmission process; the parsing and storage module is used to parse the final received data and store it in the database.

[0066] In this embodiment, each sensor is taken as a node, the communication link between each sensor is taken as an edge, and the transmission cost between sensors is taken as the weight of the corresponding edge. Based on the distribution of sensor nodes and the communication link, a corresponding undirected weighted graph is constructed, and an initial node is randomly selected from the undirected weighted graph as the starting point of the minimum spanning tree. Then, all the edges are sorted in ascending order from small to large according to the weight. After the sorting is completed, the minimum edge is selected from the edge with the minimum weight to be added to the minimum spanning tree. If the selected edge will cause a loop, the edge is skipped and the next edge is selected. The edges are selected step by step. When the number of added edges reaches n-1, the selection is stopped. Select and end the minimum spanning tree construction, where n represents the number of sensor nodes. After the spanning tree is constructed, the transmission path set with the lowest transmission cost is obtained according to the construction of the spanning tree, and the constructed transmission path is regularly detected. When a new sensor is added or any sensor node in the original transmission path fails, the minimum spanning tree is recalculated and constructed to generate the latest transmission path set for replacement, reducing unnecessary redundant data transmission, significantly reducing the overall transmission energy consumption, shortening the transmission time, improving the stability and reliability of the network, simplifying the network structure, reducing the workload of maintenance personnel, and reducing the long-term operation cost of the system.

[0067] According to the output of the transmission optimization module and the dynamic selection module, all sensor nodes in the sensor network are obtained, including the source node and the destination node, the path between the sensor nodes, the pheromone concentration on each path, and the expected transmission quality between the two groups of nodes. The basic structure of the distributed sensor network is constructed based on the above information, and multiple groups of exploration bodies are randomly generated. The positions of each exploration body are initialized on different source nodes. Each exploration body starts from the source node, calculates the selection probability of each relay node according to the pheromone concentration and the expected transmission quality, and selects the next node according to the calculated probability. The relay node probability is continuously calculated for node selection until the destination node is reached. When each exploration body finds a complete path Finally, the transmission cost of each path is calculated according to the energy consumption and delay, and then the pheromone concentration on the path is updated according to the quality of the found path. It is iterated multiple times in the distributed sensor network, and the path is continuously optimized until the preset iteration time is reached and stopped. The pheromone concentration of each path is detected, and the path or path combination with the highest pheromone concentration is used to determine the final transmission path, and apply it to the actual transmission plan. At the same time, the sensor network information is detected in real time. When the network status changes, a new optimal path is searched again to achieve effective coordination between the local and the global, enhance the flexibility of path selection, and be able to respond to the dynamic changes of nodes in the high-speed rail scenario in real time, maintain efficient network operation, and reduce the cost and complexity of system reconfiguration.

[0068] Figure 3 : is a schematic diagram of the structure of the data transmission path generating device of the distributed wireless sensor provided by the present invention, such as Figure 3 As shown, including but not limited to the following modules: A first construction module 301 is used to construct an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are data transmission costs between the multiple sensors; A first execution module 302 is used to construct a minimum spanning tree based on the undirected weighted graph, and determine a transmission path set according to the minimum spanning tree; A second construction module 303 is used to construct a state space based on the state of the sensor network, and to construct an action space based on the transmission strategies selectable in each state of the sensor network in the state space, wherein the sensor network is constructed based on a plurality of sensors and communication links between the plurality of sensors; A second execution module 304 is used to determine an optimal data transmission strategy set based on the state space and the action space, and adjust the transmission parameters of the multiple sensors based on the optimal data transmission strategy set to obtain adjusted multiple sensor parameters; An updating module 305, configured to update the sensor network based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network; The determination module 306 is used to determine a target transmission path based on the pheromone concentrations of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network.

[0069] Through the embodiments of the present application, an undirected weighted graph is constructed, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are the data transmission costs between the multiple sensors; a minimum spanning tree is constructed based on the undirected weighted graph, and a transmission path set is determined based on the minimum spanning tree; a state space is constructed based on the state of the sensor network, and an action space is constructed based on the transmission strategies that can be selected by the sensor network in each state in the state space, wherein the sensor network is constructed based on multiple sensors and communication links between the multiple sensors; an optimal data transmission strategy set is determined based on the state space and the action space, and the transmission parameters of the multiple sensors are adjusted based on the optimal data transmission strategy set to obtain multiple adjusted sensor parameters; the sensor network is updated based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network; a target transmission path is determined based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network; the data transmission path generation method of the distributed wireless sensor in the related art is solved, and the technical problem of low efficiency of the data transmission process exists, thereby improving the efficiency of data transmission.

[0070] It should be noted that the data transmission path generation device for distributed wireless sensors provided by the present invention can execute the data transmission path generation method for distributed wireless sensors of any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0071] Figure 4 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4As shown, the electronic device may include: a processor (processor) 410 , a communication interface (Communications Interface) 420 , a memory (memory) 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other through the communication bus 440 . The processor 410 can call the logic instructions in the memory 430 to execute the data transmission path generation method of the distributed wireless sensor, which includes: constructing an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are data transmission costs between the multiple sensors; constructing a minimum spanning tree based on the undirected weighted graph, and determining a set of transmission paths based on the minimum spanning tree; constructing a state space based on the state of the sensor network, and constructing an action space based on the transmission strategies that can be selected by the sensor network in each state in the state space, wherein the sensor network is constructed based on multiple sensors and communication links between multiple sensors; determining an optimal data transmission strategy set based on the state space and the action space, and adjusting the transmission parameters of the multiple sensors based on the optimal data transmission strategy set to obtain multiple adjusted sensor parameters; updating the sensor network based on the transmission path set, the optimal data transmission strategy, and the adjusted multiple sensor parameters to obtain a distributed sensor network; determining a target transmission path based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network.

[0072] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0073] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the data transmission path generation method of the distributed wireless sensor provided by the above-mentioned embodiments, and the method includes: constructing an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are the data transmission costs between the multiple sensors; constructing a minimum spanning tree based on the undirected weighted graph, and determining a transmission path set based on the minimum spanning tree; constructing a state space based on the state of the sensor network, and An action space is constructed based on the transmission strategies that can be selected by the sensor network in each state in the state space, wherein the sensor network is constructed based on multiple sensors and communication links between the multiple sensors; an optimal data transmission strategy set is determined based on the state space and the action space, and the transmission parameters of the multiple sensors are adjusted based on the optimal data transmission strategy set to obtain multiple adjusted sensor parameters; the sensor network is updated based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network; a target transmission path is determined based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network.

[0074] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the data transmission path generation method of the distributed wireless sensor provided in the above-mentioned embodiments, the method comprising: constructing an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are the data transmission costs between the multiple sensors; constructing a minimum spanning tree based on the undirected weighted graph, and determining a transmission path set based on the minimum spanning tree; constructing a state space based on the state of the sensor network, and determining a transmission path set based on each state of the sensor network in the state space; The invention relates to an embodiment of the present invention, wherein the sensor network is constructed based on multiple sensors and communication links between multiple sensors; an optimal data transmission strategy set is determined based on the state space and the action space, and the transmission parameters of multiple sensors are adjusted based on the optimal data transmission strategy set to obtain multiple adjusted sensor parameters; the sensor network is updated based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network; a target transmission path is determined based on the pheromone concentration of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network.

[0075] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0076] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating a data transmission path of a distributed wireless sensor, characterized in that: include: Constructing an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of a plurality of sensors, the edges of the undirected weighted graph are communication links between the plurality of sensors, and the weights of the undirected weighted graph are data transmission costs between the plurality of sensors; Constructing a minimum spanning tree based on the undirected weighted graph, and determining a set of transmission paths according to the minimum spanning tree; Constructing a state space based on the state of a sensor network, and constructing an action space based on transmission strategies selectable by the sensor network in each state in the state space, wherein the sensor network is constructed based on the plurality of sensors and communication links between the plurality of sensors; Determine an optimal data transmission strategy set based on the state space and the action space, and adjust the transmission parameters of the multiple sensors based on the optimal data transmission strategy set to obtain adjusted multiple sensor parameters; Based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters, the sensor network is updated to obtain a distributed sensor network; A target transmission path is determined based on the pheromone concentrations of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network.

2. The method for generating a data transmission path of a distributed wireless sensor according to claim 1, characterized in that: The state space includes the energy level of the sensor network, the load condition of the communication link, the transmission quality of the communication link and various states of external environmental factors, and the action space includes various groups of actions of the sensor network changing the transmission path, adjusting the transmission power, switching to the backup node and adjusting the transmission rate.

3. The method for generating a data transmission path of a distributed wireless sensor according to claim 2, characterized in that: The determining of an optimal data transmission strategy set based on the state space and the action space includes: Each state in the state space is used as a target state to perform the following steps to obtain the optimal data transmission strategy set consisting of multiple optimal data transmission strategies: Calculate the transition probability of the sensor network transferring to other states after selecting the target action in the target state; The instantaneous benefit of the sensor network after selecting the target action in the target state is obtained, and multiple recursive calculations are performed using the Bellman equation based on the transition probability and the instantaneous benefit to obtain an optimal data transmission strategy.

4. The method for generating a data transmission path of a distributed wireless sensor according to claim 1, characterized in that: The determining of the target transmission path based on the pheromone concentration of each transmission path in the distributed sensor network includes: Acquire a source node and a destination node in the distributed sensor network, wherein the source node is a sensor node that collects data, and the destination node is a node that receives and processes data sent by the source node; Initializing a plurality of exploration bodies at different source nodes respectively, and determining a plurality of transmission paths to be confirmed through the plurality of exploration bodies based on the pheromone concentrations of each transmission path in the distributed sensor network, wherein the end point of the transmission path to be confirmed is the destination node; The path with the highest pheromone concentration among the multiple transmission paths to be confirmed is determined as the target transmission path.

5. The method for generating a data transmission path of a distributed wireless sensor according to any one of claims 1 to 4, characterized in that: After determining the target transmission path based on the pheromone concentrations of each transmission path in the distributed sensor network, the method further includes: Acquire an original data set, wherein the original data set includes data collected by the multiple sensors; Preprocessing the original data set to obtain a preprocessed data set; The preprocessed data set is transmitted to the parsing and storage module along the target transmission path, wherein the parsing and storage module is used to parse the received data and store it in a database.

6. The method for generating a data transmission path of a distributed wireless sensor according to claim 5, characterized in that: The preprocessing of the original data set to obtain a preprocessed data set includes: In the case where there are missing values ​​in the sensor data in the original data set, the missing values ​​are filled to obtain a filled data set; Calculating the first quartile and the third quartile of the padded data set, calculating the interquartile range based on the first quartile and the third quartile, determining a target data range based on the first quartile, the third quartile and the interquartile range, and deleting data outside the target data range in the padded data set to obtain an optimized data set; The optimized data set is smoothed and denoised using a sliding average method and a low-pass filter, respectively, and normalized using a minimum-maximum standardization method to obtain the preprocessed data set.

7. A data transmission path generation device for a distributed wireless sensor, characterized in that: include: A first construction module is used to construct an undirected weighted graph, wherein the nodes of the undirected weighted graph are composed of multiple sensors, the edges of the undirected weighted graph are communication links between the multiple sensors, and the weights of the undirected weighted graph are data transmission costs between the multiple sensors; A first execution module, configured to construct a minimum spanning tree based on the undirected weighted graph, and determine a transmission path set according to the minimum spanning tree; A second construction module is used to construct a state space based on the state of the sensor network, and to construct an action space based on the transmission strategies selectable by the sensor network in each state in the state space, wherein the sensor network is constructed based on the multiple sensors and the communication links between the multiple sensors; a second execution module, configured to determine an optimal data transmission strategy set based on the state space and the action space, and adjust transmission parameters of the plurality of sensors based on the optimal data transmission strategy set to obtain adjusted plurality of sensor parameters; An updating module, configured to update the sensor network based on the transmission path set, the optimal data transmission strategy and the adjusted multiple sensor parameters to obtain a distributed sensor network; The determination module is used to determine a target transmission path based on the pheromone concentrations of each transmission path in the distributed sensor network, wherein the target transmission path is the transmission path with the highest pheromone concentration in the distributed sensor network.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for generating a data transmission path of a distributed wireless sensor according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating a data transmission path of a distributed wireless sensor according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for generating a data transmission path of a distributed wireless sensor according to any one of claims 1 to 6 is implemented.

Images