Wireless sensor network energy-saving routing method and system based on intelligent algorithm

Abstract

The invention discloses a wireless sensor network energy-saving routing method and system based on an intelligent algorithm. Residual energy values of all wireless sensors in a wireless sensor network are collected, and a data processing and analysis algorithm is introduced at the rear end to carry out time sequence analysis on the residual energy values of all the wireless sensors. And residual energy time sequence characteristic mapping correction of each wireless sensor is carried out by combining network space topology of the wireless sensor network and distance information between the nodes and the base station, so that the probability that the nodes become cluster heads is predicted, and the optimal cluster head node is selected. Therefore, the energy utilization efficiency can be improved, and the life cycle of the network is prolonged.

Description

Technical Field

[0001] The present application relates to the field of wireless sensor networks, and more specifically, to an energy-saving routing method and system for wireless sensor networks based on intelligent algorithms. Background Art

[0002] Wireless sensor network (WSN) is a self-organizing network composed of a large number of sensor nodes distributed in the sensing area, which can monitor, collect, process and transmit data on the target or environment in the sensing area. Wireless sensor networks have broad application prospects, such as military reconnaissance, environmental monitoring, intelligent transportation, smart home, etc. However, since the nodes in wireless sensor networks are usually powered by batteries or micro-energy harvesting technology, the energy is limited and difficult to replace or charge, how to effectively use limited energy resources to achieve energy saving and extend the life cycle of the network is an important issue in the research of wireless sensor networks.

[0003] Clustering routing protocol is a commonly used energy-saving routing method. Clustering-based routing protocol divides the network into several clusters, and each cluster selects a cluster head node to collect and forward data, thereby reducing the communication overhead between nodes.

[0004] The low-energy adaptive clustering hierarchy (LEACH) protocol is one of the most representative clustering routing protocols. Each node randomly generates a random number and compares it with a threshold. If it is less than the value, it becomes the cluster head. Other nodes join each cluster according to the principle of proximity. The cluster head fuses the collected data and sends it directly to the base station. In this scheme, each node has the same probability of becoming a cluster head. The number of clusters is determined by experiments, and the residual energy of the node is not considered when selecting the cluster head.

[0005] The LEACH-C (LEACH-centralized) protocol is an improved version of the LEACH protocol. Unlike the distributed cluster head election adopted by the LEACH protocol, the LEACH-C uses a centralized cluster head election method. Each node sends its location and remaining energy information to the base station (BS). The base station uses the simulated annealing method to select the cluster head from the nodes with remaining energy higher than the average value, based on the optimization principle of the shortest total transmission distance. However, this method requires the estimation of the optimal number of clusters through experiments or formulas before the algorithm runs. The formulas have some assumptions and are only applicable to specific networks. Some formulas can only calculate the range of the optimal number of clusters, and the accurate value still needs to be determined through experiments.

[0006] Therefore, an energy-saving routing scheme for wireless sensor networks based on intelligent algorithms is desired. Summary of the invention

[0007] In view of this, the present application proposes an energy-saving routing method and system for wireless sensor networks based on an intelligent algorithm, which can take into account the remaining energy of the node, the network space topology relationship, and the distance information between the node and the base station when selecting the cluster head node, and there is no need to estimate the optimal number of clusters before the algorithm runs. It can adaptively perform cluster routing according to different data fusion rates, thereby improving energy utilization efficiency and extending the life cycle of the network.

[0008] According to one aspect of the present application, a wireless sensor network energy-saving routing method based on an intelligent algorithm is provided, which includes: Model the wireless sensor network to obtain the network space topology matrix; Constructing a degree matrix of the wireless sensor network relative to a base station; Obtaining residual energy values ​​of each wireless sensor in the wireless sensor network at multiple predetermined time points within a predetermined time period; Arranging the residual energy values ​​of the wireless sensors at a plurality of predetermined time points within a predetermined time period into input vectors according to the time dimension to obtain a plurality of wireless sensor residual energy time series input vectors; By using a time series feature extractor based on a deep neural network model, feature extraction is performed on the plurality of wireless sensor residual energy time series input vectors respectively to obtain a plurality of wireless sensor residual energy time series feature vectors; Respectively mapping each of the plurality of wireless sensor residual energy time series feature vectors to the feature space where the network space topology matrix is ​​located and then to the feature space where the degree matrix is ​​located to obtain a plurality of corrected wireless sensor residual energy time series feature vectors as a plurality of wireless sensor residual energy time series features; and A cluster head is determined based on the residual energy time series characteristics of the multiple wireless sensors.

[0009] According to another aspect of the present application, there is provided a wireless sensor network energy-saving routing system based on an intelligent algorithm, comprising: A modeling module, used for modeling the wireless sensor network to obtain a network space topology matrix; A degree matrix construction module, used to construct a degree matrix of the wireless sensor network relative to the base station; A residual energy value acquisition module, used to acquire the residual energy value of each wireless sensor in the wireless sensor network at a plurality of predetermined time points within a predetermined time period; A vectorization module, used for arranging the residual energy values ​​of each wireless sensor at a plurality of predetermined time points within a predetermined time period into input vectors according to a time dimension to obtain a plurality of wireless sensor residual energy time series input vectors; A time series feature extraction module, used to extract features from the plurality of wireless sensor residual energy time series input vectors respectively through a time series feature extractor based on a deep neural network model to obtain a plurality of wireless sensor residual energy time series feature vectors; A mapping module, used to map each of the plurality of wireless sensor residual energy time series feature vectors to the feature space where the network space topology matrix is ​​located and then to the feature space where the degree matrix is ​​located to obtain a plurality of corrected wireless sensor residual energy time series feature vectors as a plurality of wireless sensor residual energy time series features; and The cluster head determination module is used to determine the cluster head based on the residual energy time series characteristics of the multiple wireless sensors.

[0010] According to the embodiment of the present application, the residual energy value of each wireless sensor in the wireless sensor network is collected, and the data processing and analysis algorithm is introduced in the back end to perform the time series analysis of the residual energy value of each wireless sensor, and the residual energy time series feature mapping correction of each wireless sensor is performed in combination with the network space topology of the wireless sensor network and the distance information between the node and the base station, so as to predict the probability of the node becoming the cluster head and select the optimal cluster head node. In this way, the energy utilization efficiency can be improved and the life cycle of the network can be extended.

[0011] Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the present application and, together with the description, serve to explain the principles of the present application.

[0013] Figure 1 A flow chart of an energy-saving routing method for a wireless sensor network based on an intelligent algorithm according to an embodiment of the present application is shown.

[0014] Figure 2 A flowchart of sub-step S170 of the wireless sensor network energy-saving routing method based on an intelligent algorithm according to an embodiment of the present application is shown.

[0015] Figure 3 A flowchart of sub-step S171 of the wireless sensor network energy-saving routing method based on an intelligent algorithm according to an embodiment of the present application is shown.

[0016] Figure 4 A block diagram of an energy-saving routing system for a wireless sensor network based on an intelligent algorithm according to an embodiment of the present application is shown.

[0017] Figure 5 An application scenario diagram of an energy-saving routing method for a wireless sensor network based on an intelligent algorithm according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0019] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0020] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0021] In addition, in order to better illustrate the present application, numerous specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0022] In response to the above technical problems, the technical concept of the present application is to collect the residual energy value of each wireless sensor in the wireless sensor network, and introduce data processing and analysis algorithms at the back end to perform time series analysis of the residual energy value of each wireless sensor, and at the same time, combine the network space topology of the wireless sensor network and the distance information between the node and the base station to perform residual energy time series feature mapping correction of each wireless sensor, so as to predict the probability of the node becoming the cluster head and select the optimal cluster head node. In this way, when selecting the cluster head node, the residual energy of the node, the network space topology relationship and the distance information between the node and the base station can be considered, and there is no need to estimate the optimal number of clusters before the algorithm runs. Different data fusion rates can be adaptively adjusted for cluster routing, thereby improving energy efficiency and extending the life cycle of the network.

[0023] Figure 1 FIG. 1 is a flow chart showing a wireless sensor network energy-saving routing method based on an intelligent algorithm according to an embodiment of the present application. Figure 1 As shown, according to the energy-saving routing method for wireless sensor networks based on intelligent algorithms in the embodiments of the present application, the method comprises the following steps: S110, modeling the wireless sensor network to obtain a network space topology matrix; S120, constructing a degree matrix of the wireless sensor network relative to a base station; S130, obtaining the residual energy values ​​of each wireless sensor in the wireless sensor network at multiple predetermined time points within a predetermined time period; S140, arranging the residual energy values ​​of each wireless sensor at multiple predetermined time points within a predetermined time period as input vectors according to the time dimension to obtain a plurality of residual energy time series input vectors of wireless sensors; S150, by using a deep learning-based The timing feature extractor of the degree neural network model respectively extracts features from the plurality of wireless sensor residual energy timing input vectors to obtain a plurality of wireless sensor residual energy timing feature vectors; S160, respectively maps each of the plurality of wireless sensor residual energy timing feature vectors to the feature space where the network space topology matrix is ​​located and then to the feature space where the degree matrix is ​​located to obtain a plurality of corrected wireless sensor residual energy timing feature vectors as a plurality of wireless sensor residual energy timing features; and, S170, determines a cluster head based on the plurality of wireless sensor residual energy timing features.

[0024] Specifically, in the technical solution of the present application, first, the residual energy values ​​of each wireless sensor in the wireless sensor network at multiple predetermined time points within a predetermined time period are obtained. Next, considering that the residual energy values ​​of each wireless sensor have a time-series dynamic change law in the time dimension, that is, the residual energy values ​​of each wireless sensor at multiple predetermined time points within the predetermined time period have a time-series correlation relationship in the time dimension. Therefore, in the technical solution of the present application, it is necessary to arrange the residual energy values ​​of each wireless sensor at multiple predetermined time points within the predetermined time period as input vectors according to the time dimension to obtain multiple wireless sensor residual energy time series input vectors, so as to respectively integrate the distribution information of the residual energy values ​​of each wireless sensor in the wireless sensor network in time series.

[0025] Then, the residual energy time series input vectors of the multiple wireless sensors are respectively subjected to feature mining in a time series feature extractor based on a one-dimensional convolutional layer to respectively extract the time series dynamic feature information of the residual energy value of each wireless sensor in the time dimension, thereby obtaining the residual energy time series feature vectors of the multiple wireless sensors.

[0026] Correspondingly, in step S150, the time series feature extractor based on the deep neural network model is a time series feature extractor based on a one-dimensional convolution layer. It is worth mentioning that the one-dimensional convolution layer is a common layer type in a deep neural network, which is used to extract features from time series data. It is mainly used to process data with a time series structure. In the present application, a one-dimensional convolution layer is used as a time series feature extractor to extract features from a time series input vector of residual energy of multiple wireless sensors. The one-dimensional convolution layer performs a convolution operation on the input sequence by sliding a fixed-size window (convolution kernel) to obtain local features. The weight parameters of the convolution kernel are automatically learned according to the training data to capture important patterns and features in the input sequence. The main function of the one-dimensional convolution layer is to extract local features of the input sequence through a convolution operation, thereby capturing the time series pattern and related features in the input sequence. These features can be further used for subsequent classification, regression or other tasks. The one-dimensional convolution layer has good feature extraction capability and parameter efficiency in deep learning, and can help the model learn more meaningful representations from time series data. In summary, the one-dimensional convolutional layer is a deep neural network layer used to extract features from time series data. It is used in the energy-saving routing method of wireless sensor networks to extract the time series characteristics of the residual energy of multiple wireless sensors to help determine the cluster head node.

[0027] Furthermore, it is also considered that the residual energy values ​​of the various wireless sensors in the wireless sensor network also have a time-series coordinated correlation relationship, and this correlation relationship exists in the spatial topology between the various wireless sensors. Therefore, in the technical solution of the present application, the wireless sensor network is further modeled to obtain a network space topology matrix, wherein the value of each position on the non-diagonal position in the network space topology matrix is ​​the spatial distance value between the corresponding two wireless sensors.

[0028] Moreover, when actually selecting the cluster head node, it is necessary to consider not only the spatial topology information of the wireless sensor network, but also the distance information between each node in the wireless sensor network and the base station, so as to improve the energy utilization efficiency. Therefore, in the technical solution of the present application, a degree matrix of the wireless sensor network relative to the base station is further constructed, wherein the values ​​of each position on the diagonal position in the degree matrix are the spatial distance values ​​between the corresponding wireless sensor and the base station.

[0029] Next, each of the wireless sensor remaining energy time series feature vectors in the plurality of wireless sensor remaining energy time series feature vectors is first mapped to the feature space where the network space topology matrix is ​​located and then mapped to the feature space where the degree matrix is ​​located to obtain a plurality of corrected wireless sensor remaining energy time series feature vectors. It should be understood that by mapping the respective wireless sensor remaining energy time series feature vectors to the feature space where the network space topology matrix is ​​located, the spatial relationship between the nodes can be considered. That is, since the network space topology matrix describes the spatial distance between the nodes, by mapping the wireless sensor remaining energy time series feature vector to the feature space, the spatial information between the nodes can be captured. In this way, the respective wireless sensor remaining energy time series feature vectors can better reflect the spatial relationship between the nodes, thereby better guiding the selection of the cluster head. Furthermore, after mapping the wireless sensor remaining energy time series feature vector to the network space topology matrix feature space, it is further mapped to the feature space where the degree matrix is ​​located, wherein the degree matrix describes the spatial distance between the node and the base station, and by mapping the feature vector to the feature space, the spatial relationship between the node and the base station can be considered. In this way, the spatial relationship between the node and the base station and the spatial relationship between the nodes can be comprehensively considered to obtain a more comprehensive and accurate feature representation.

[0030] Then, the multiple corrected wireless sensor residual energy time series feature vectors are passed through a classifier to obtain multiple probability values. That is to say, the residual energy time series features of each wireless sensor are mapped to the high-dimensional feature space of the spatial topology of the wireless sensor network and the spatial distance between the node and the base station to obtain the mapping feature information for classification processing, so as to calculate the probability of each wireless sensor, and then the wireless sensor corresponding to the largest of the multiple probability values ​​is used as the cluster head. In this way, when selecting the cluster head node, the residual energy of the node, the network space topology relationship and the distance information between the node and the base station can be taken into account, and there is no need to estimate the optimal number of clusters before the algorithm runs. Different data fusion rates can be adaptively adjusted for cluster routing, thereby improving energy efficiency.

[0031] Accordingly, in step S170, if Figure 2 As shown, based on the residual energy timing characteristics of the multiple wireless sensors, the cluster head is determined, including: S171, passing the multiple corrected wireless sensor residual energy timing characteristic vectors through a classifier to obtain multiple probability values; and, S172, taking the wireless sensor corresponding to the largest one of the multiple probability values ​​as the cluster head.

[0032] It should be understood that in step S171, the classifier determines the possibility of each wireless sensor becoming a cluster head based on the input feature vector and outputs the corresponding probability value. In step S172, the wireless sensor with the maximum value is selected as the cluster head from multiple probability values, which means that after the classifier evaluation, the wireless sensor with the highest probability value is selected as the cluster head. Selecting the wireless sensor with the highest probability as the cluster head can ensure that the sensor has the highest energy level and lower energy consumption, thereby improving the energy efficiency of the entire wireless sensor network. In summary, step S171 calculates the probability value of each wireless sensor becoming a cluster head through the classifier, and step S172 selects the wireless sensor with the highest probability value as the cluster head to achieve energy-saving routing of the wireless sensor network.

[0033] Among them, in step S171, if Figure 3 As shown, the multiple corrected wireless sensor remaining energy timing series feature vectors are passed through a classifier to obtain multiple probability values, including: S1711, optimizing the corresponding corrected wireless sensor remaining energy timing series feature vectors based on the respective wireless sensor remaining energy timing series feature vectors to obtain multiple optimized wireless sensor remaining energy timing series feature vectors; and, S1712, passing the multiple optimized wireless sensor remaining energy timing series feature vectors through the classifier to obtain the multiple probability values.

[0034] It should be understood that in step S171, the process of passing multiple corrected wireless sensor residual energy time series feature vectors through the classifier to obtain multiple probability values ​​includes two sub-steps: S1711 and S1712. Among them, the purpose of step S1711 is to further process the feature vectors to extract more informative features to improve the performance and accuracy of the classifier.

[0035] In particular, in the technical solution of the present application, each of the multiple wireless sensor residual energy time series feature vectors respectively expresses the local time series correlation characteristics of the residual energy value of the corresponding wireless sensor. Thus, after the wireless sensor residual energy time series feature vector is first mapped to the feature space where the network space topology matrix is ​​located and then mapped to the feature space where the degree matrix is ​​located, the time series correlation characteristics of the residual energy value of the corresponding wireless sensor can be further topologically mapped under the wireless sensor space topology structure. That is, each group of corresponding corrected wireless sensor residual energy time series feature vectors is equivalent to an interpolated space topology correlation mapping mixture of the corresponding wireless sensor residual energy time series feature vectors.

[0036] In this way, in order to improve the spatial topological association mapping enhanced expression effect of the corrected wireless sensor residual energy time series feature vector based on the expression consistency of the local time series association feature of the corresponding wireless sensor residual energy time series feature vector, based on the wireless sensor residual energy time series feature vector, for example, The residual energy time series feature vector of the wireless sensor after correction is recorded as Optimize, the specific optimization includes the following steps: The residual energy time series feature vectors of the wireless sensor are respectively and the corrected wireless sensor residual energy time series feature vector By jointly mapping the weight matrix Perform a public multi-dimensional mapping to obtain the time series mapping feature vector of the remaining energy of the wireless sensor and the corrected wireless sensor residual energy time series mapping feature vector : ; ; in, Represents matrix multiplication; The residual energy time series of the wireless sensor is mapped to the feature vector and the corrected wireless sensor residual energy time series mapping feature vector by After the function is activated, the unit eigenvector is subtracted and the absolute value of each eigenvalue is calculated to obtain the wireless sensor residual energy time series prior decoupling eigenvector and the corrected wireless sensor residual energy time series prior decoupling feature vector : ; ; in is the unit eigenvector, represents vector subtraction; The wireless sensor residual energy time series prior decoupling feature vector The square of the second norm and the prior decoupling eigenvector of the residual energy time series of the corrected wireless sensor The bit-by-bit eigenvalue reciprocal of is multiplied to obtain the eigenvector term of the optimized corrected wireless sensor residual energy timing prior decoupling eigenvector: ; in, represents positional multiplication, The eigenvector term representing the optimized corrected wireless sensor residual energy time series prior decoupling eigenvector; The eigenvector term of the optimized corrected wireless sensor residual energy time series prior decoupling eigenvector is combined with the eigenvector term of the corrected wireless sensor residual energy time series prior decoupling eigenvector The bias term obtained by the square of the second norm is point-added to obtain the optimized corrected wireless sensor residual energy time series prior decoupling eigenvector , Represents vector addition.

[0037] That is, for the residual energy time series feature vector of the wireless sensor and the corrected wireless sensor residual energy time series feature vector In the process of feature information extraction, the fitting time series correlation feature fusion of the prediction index is based on the idea of ​​calibration regularization. By and the corrected wireless sensor residual energy time series feature vector The outlier representation decoupling realizes the residual energy time series feature vector of the wireless sensor and the corrected wireless sensor residual energy time series feature vector Specifically, the suboptimal enhancement mechanism is used to reconstruct the residual energy time series feature vector of the wireless sensor. and the corrected wireless sensor residual energy time series feature vector The manifold topology structure achieves the residual energy time series characteristic vector of the wireless sensor and the corrected wireless sensor residual energy time series feature vector The synergistic feature enhancement mapping of the fitting sample and the prediction result is performed to maintain the residual energy time series feature vector of the wireless sensor and the corrected wireless sensor residual energy time series feature vector While maintaining the consistency of the local time series correlation expression, the enhanced feature representation effect is obtained through spatial distribution correlation mapping, thereby effectively improving the overall expression effect of the optimized corrected wireless sensor residual energy time series feature vector, so as to improve the accuracy of the classification results obtained by the classifier. In this way, when selecting the cluster head node, the node's residual energy, the network space topology relationship, and the distance information between the node and the base station can be considered, and there is no need to estimate the optimal number of clusters before the algorithm runs. It can adaptively perform cluster routing based on different data fusion rates, thereby improving energy efficiency and extending the life cycle of the network.

[0038] Further, in step S1712, the multiple optimized wireless sensor residual energy time series feature vectors are passed through the classifier to obtain the multiple probability values, including: using multiple fully connected layers of the classifier to fully connect the multiple optimized wireless sensor residual energy time series feature vectors to obtain multiple encoded classification feature vectors; and, passing the multiple encoded classification feature vectors through the Softmax classification function of the classifier to obtain the multiple probability values.

[0039] It should be understood that the role of the classifier is to use the given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression, SVM, etc. are often used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-classification, but this is prone to errors and inefficient. Commonly used multi-classification methods include the Softmax classification function.

[0040] It is worth mentioning that fully connected encoding is a technique for mapping input data to a fixed-length encoding vector. In the step, the optimized wireless sensor residual energy time series feature vector is fully connected using multiple fully connected layers of the classifier to obtain multiple encoded classification feature vectors. The fully connected layer is a common layer type in deep neural networks, in which each neuron is connected to all neurons in the previous layer. In this case, the fully connected layer maps the input data to a new feature space by multiplying the input feature vector with the weight matrix and applying an activation function. Multiple fully connected layers can gradually extract higher-level feature representations. The purpose of fully connected encoding is to convert the optimized feature vector into a more representative encoding vector. Through the combination of multiple fully connected layers, the network can learn more abstract and discriminative feature representations. These encoded classification feature vectors can better describe the residual energy time series characteristics of the wireless sensor and provide the classifier with richer information to more accurately predict the probability of each wireless sensor becoming a cluster head. In the subsequent stage of the step, these encoded classification feature vectors are converted into corresponding probability values ​​by passing through the Softmax classification function of the classifier. The Softmax function maps the value of each encoded classification feature vector to a probability value between 0 and 1, indicating the possibility of the wireless sensor becoming a cluster head. These probability values ​​can be used to select the wireless sensor with the highest probability as the cluster head to achieve energy-saving routing in wireless sensor networks.

[0041] In summary, the energy-saving routing method for wireless sensor networks based on intelligent algorithms according to the embodiments of the present application can improve energy utilization efficiency and extend the life cycle of the network.

[0042] Figure 4 FIG. 1 is a block diagram of a wireless sensor network energy-saving routing system 100 based on an intelligent algorithm according to an embodiment of the present application. Figure 4As shown, according to the embodiment of the present application, the wireless sensor network energy-saving routing system 100 based on the intelligent algorithm includes: a modeling module 110, which is used to model the wireless sensor network to obtain a network space topology matrix; a degree matrix construction module 120, which is used to construct the degree matrix of the wireless sensor network relative to the base station; a residual energy value acquisition module 130, which is used to obtain the residual energy value of each wireless sensor in the wireless sensor network at multiple predetermined time points within a predetermined time period; a vectorization module 140, which is used to arrange the residual energy values ​​of each wireless sensor at multiple predetermined time points within a predetermined time period as input vectors according to the time dimension to obtain a plurality of wireless sensor residual energy time series input vectors; and a time series feature extraction module 130. Module 150 is used to extract features from the multiple wireless sensor residual energy timing input vectors respectively through a timing feature extractor based on a deep neural network model to obtain multiple wireless sensor residual energy timing feature vectors; mapping module 160 is used to map each of the multiple wireless sensor residual energy timing feature vectors to the feature space where the network space topology matrix is ​​located and then to the feature space where the degree matrix is ​​located to obtain multiple corrected wireless sensor residual energy timing feature vectors as multiple wireless sensor residual energy timing features; and cluster head determination module 170 is used to determine the cluster head based on the multiple wireless sensor residual energy timing features.

[0043] In a possible implementation manner, the value of each non-diagonal position in the network space topology matrix is ​​a spatial distance value between corresponding two wireless sensors.

[0044] In a possible implementation manner, the value of each position on the diagonal position in the degree matrix is ​​a spatial distance value between the corresponding wireless sensor and the base station.

[0045] Here, those skilled in the art can understand that the specific functions and operations of the various units and modules in the above-mentioned wireless sensor network energy-saving routing system 100 based on the intelligent algorithm have been referred to above. Figures 1 to 3 The description of the energy-saving routing method for wireless sensor networks based on intelligent algorithm has been introduced in detail, and therefore, its repeated description will be omitted.

[0046] As described above, the energy-saving routing system 100 for wireless sensor networks based on intelligent algorithms according to the embodiments of the present application can be implemented in various wireless terminals, such as a server with an energy-saving routing algorithm for wireless sensor networks based on intelligent algorithms. In a possible implementation, the energy-saving routing system 100 for wireless sensor networks based on intelligent algorithms according to the embodiments of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the energy-saving routing system 100 for wireless sensor networks based on intelligent algorithms can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the energy-saving routing system 100 for wireless sensor networks based on intelligent algorithms can also be one of the many hardware modules of the wireless terminal.

[0047] Alternatively, in another example, the intelligent algorithm-based wireless sensor network energy-saving routing system 100 and the wireless terminal may also be separate devices, and the intelligent algorithm-based wireless sensor network energy-saving routing system 100 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0048] Figure 5 FIG. 1 shows an application scenario diagram of a wireless sensor network energy-saving routing method based on an intelligent algorithm according to an embodiment of the present application. Figure 5 As shown, in this application scenario, first, each wireless sensor in the wireless sensor network is obtained (for example, Figure 5 The remaining energy values ​​(eg, N1) at multiple predetermined time points within a predetermined time period. Figure 5 D1 shown in FIG), corresponding to two wireless sensors (for example, Figure 5 The spatial distance value between N1) shown in the figure (for example, Figure 5 D2 as shown in FIG. 1 ), and corresponding wireless sensors (e.g., Figure 5 N1 as shown in the figure) and a base station (e.g. Figure 5 N2) shown in the figure (e.g., Figure 5 Then, the residual energy values ​​of each wireless sensor at multiple predetermined time points within a predetermined time period, the spatial distance values ​​between the corresponding two wireless sensors, and the spatial distance values ​​between the corresponding wireless sensor and the base station are input to a server (for example, Figure 5In S), the server can use the wireless sensor network energy-saving routing algorithm based on the intelligent algorithm to process the residual energy values ​​of each wireless sensor at multiple predetermined time points within a predetermined time period, the spatial distance values ​​between the corresponding two wireless sensors, and the spatial distance values ​​between the corresponding wireless sensor and the base station to obtain multiple probability values, and then use the wireless sensor corresponding to the largest one among the multiple probability values ​​as the cluster head.

[0049] Furthermore, the present application also provides a wireless sensor network cluster routing method based on the genetic algorithm, which includes the following steps: (1) Modeling the wireless sensor network, initializing the network topology and wireless communication energy consumption model; sorting all sensor nodes in order from near to far from the base station, and the sorting is to allow the sensor nodes far from the base station to preferentially select the cluster head. (2) For all surviving nodes, call the genetic algorithm to select the cluster head and free nodes from the nodes with residual energy higher than the median value, based on the optimization principle of reducing the total energy consumption of this round and balancing the energy consumption of each node, and the remaining nodes become cluster member nodes. (3) The cluster member nodes select the cluster head to form a cluster, and communicate with the base station in a round through the cluster head forwarding method, and the free nodes directly communicate with the base station in a round, and calculate the energy consumption of each node in this round. (4) Update the residual energy of all nodes, determine whether the sensor node has died, and jump to step (2) if there are still surviving nodes, otherwise the program ends.

[0050] Specifically, the specific process of step (1) is as follows: initialize the length and width of the monitoring area, base station coordinates, number of sensor nodes, coordinates and initial energy, data fusion rate, information packet size, and initialize wireless communication energy consumption parameters; calculate the distance between each sensor node and the base station, and store the position coordinates of all sensor nodes in the order from near to far from the base station into array S. Specifically, in the specific process of step (2), the MPCESSALS algorithm can be used.

[0051] Furthermore, a method for calculating the energy consumption of the corresponding sensor nodes in one round of transmission is also provided. Specifically, it includes: (1) Cluster establishment: using Boolean vector represents the type of sensor node in the network, where n represents the number of surviving nodes, each component of x corresponds to a sensor node, 1 represents the node is a candidate cluster head node, and 0 represents the node is a cluster member node. There are two conditions for a candidate cluster head to be selected as a cluster head. One is that the residual energy is equal to or greater than the median of the residual energy of all nodes, and the other is that there is a member node that selects this candidate cluster head as the cluster head. The member nodes select their own cluster heads according to the order of the previous sorting and the principle of proximity. If the number of cluster members connected to the nearest cluster head exceeds the limit, the next nearest cluster head is selected, and so on. Candidate nodes that are not selected as cluster heads and other nodes that do not belong to any cluster become free nodes. (2) Calculation of transmission energy consumption: Member nodes send data to the cluster head. After the cluster head collects the data of all member nodes, it fuses the data and then forwards it to the base station. The free node communicates directly with the base station. The energy consumption of each node in this process can be calculated based on the wireless communication energy consumption model.

[0052] It should be understood that the present application uses the genetic algorithm to select cluster heads. It is not necessary to specify the number of cluster heads before the algorithm runs. The number of cluster heads is automatically determined by the genetic algorithm. The objective function of the genetic algorithm is the weighted sum of the total energy consumption of the network in this round and the standard deviation of the remaining energy of the nodes. While taking into account the balance of energy consumption, a greedy strategy is adopted to minimize the total energy consumption of the entire network in each round, thereby extending the survival time of the network. The present application can also consider the energy consumption of data fusion in the objective function, and the number of cluster heads that the data fusion rate will affect is also determined by the algorithm, so the algorithm can adapt to changes in the data fusion rate.

[0053] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the function involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a dedicated hardware-based system that performs the function or action of the specification, or can be realized by a combination of special-purpose hardware and computer instructions.

[0054] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A wireless sensor network energy-saving routing method based on intelligent algorithm, characterized in that: include: Model the wireless sensor network to obtain the network space topology matrix; Constructing a degree matrix of the wireless sensor network relative to a base station; Obtaining residual energy values ​​of each wireless sensor in the wireless sensor network at multiple predetermined time points within a predetermined time period; Arranging the residual energy values ​​of the wireless sensors at a plurality of predetermined time points within a predetermined time period into input vectors according to the time dimension to obtain a plurality of wireless sensor residual energy time series input vectors; By using a time series feature extractor based on a deep neural network model, feature extraction is performed on the plurality of wireless sensor residual energy time series input vectors respectively to obtain a plurality of wireless sensor residual energy time series feature vectors; Respectively mapping each of the plurality of wireless sensor residual energy time series feature vectors to the feature space where the network space topology matrix is ​​located and then mapping to the feature space where the degree matrix is ​​located to obtain a plurality of corrected wireless sensor residual energy time series feature vectors as a plurality of wireless sensor residual energy time series features; as well as A cluster head is determined based on the residual energy time series characteristics of the multiple wireless sensors.

2. The energy-saving routing method for wireless sensor networks based on intelligent algorithms according to claim 1 is characterized in that: The value of each non-diagonal position in the network space topology matrix is ​​the spatial distance value between the corresponding two wireless sensors.

3. The energy-saving routing method for wireless sensor networks based on intelligent algorithms according to claim 2 is characterized in that: The value of each position on the diagonal position in the degree matrix is ​​the spatial distance value between the corresponding wireless sensor and the base station.

4. The energy-saving routing method for wireless sensor networks based on intelligent algorithms according to claim 3 is characterized in that: The temporal feature extractor based on the deep neural network model is a temporal feature extractor based on a one-dimensional convolutional layer.

5. The energy-saving routing method for wireless sensor networks based on intelligent algorithms according to claim 4 is characterized in that: Determining a cluster head based on the residual energy time series characteristics of the plurality of wireless sensors includes: Passing the multiple corrected wireless sensor residual energy time series feature vectors through a classifier to obtain multiple probability values; and The wireless sensor corresponding to the largest one among the multiple probability values ​​is used as the cluster head.

6. The energy-saving routing method for wireless sensor networks based on intelligent algorithms according to claim 5 is characterized in that: The multiple corrected wireless sensor residual energy time series feature vectors are passed through a classifier to obtain multiple probability values, including: Optimizing the corresponding corrected wireless sensor residual energy time series feature vector based on the respective wireless sensor residual energy time series feature vectors to obtain a plurality of optimized wireless sensor residual energy time series feature vectors; and The multiple optimized wireless sensor residual energy time series feature vectors are passed through the classifier to obtain the multiple probability values.

7. The energy-saving routing method for wireless sensor networks based on intelligent algorithms according to claim 6 is characterized in that: Passing the plurality of optimized wireless sensor residual energy time series feature vectors through the classifier to obtain the plurality of probability values ​​includes: Using multiple fully connected layers of the classifier to perform fully connected encoding on the multiple optimized wireless sensor residual energy time series feature vectors to obtain multiple encoded classification feature vectors; and The multiple encoded classification feature vectors are passed through the Softmax classification function of the classifier to obtain the multiple probability values.

8. A wireless sensor network energy-saving routing system based on intelligent algorithm, characterized in that: include: A modeling module, used for modeling the wireless sensor network to obtain a network space topology matrix; A degree matrix construction module, used to construct a degree matrix of the wireless sensor network relative to the base station; A residual energy value acquisition module, used to acquire the residual energy value of each wireless sensor in the wireless sensor network at a plurality of predetermined time points within a predetermined time period; A vectorization module, used for arranging the residual energy values ​​of each wireless sensor at a plurality of predetermined time points within a predetermined time period into input vectors according to a time dimension to obtain a plurality of wireless sensor residual energy time series input vectors; A time series feature extraction module, used to extract features from the plurality of wireless sensor residual energy time series input vectors respectively through a time series feature extractor based on a deep neural network model to obtain a plurality of wireless sensor residual energy time series feature vectors; A mapping module, used to map each of the plurality of wireless sensor residual energy time series feature vectors to the feature space where the network space topology matrix is ​​located and then to the feature space where the degree matrix is ​​located to obtain a plurality of corrected wireless sensor residual energy time series feature vectors as a plurality of wireless sensor residual energy time series features; as well as The cluster head determination module is used to determine the cluster head based on the residual energy time series characteristics of the multiple wireless sensors.

9. The energy-saving routing system for wireless sensor networks based on intelligent algorithms according to claim 8 is characterized in that: The value of each non-diagonal position in the network space topology matrix is ​​the spatial distance value between the corresponding two wireless sensors.

10. The energy-saving routing system for wireless sensor networks based on intelligent algorithms according to claim 9, characterized in that: The value of each position on the diagonal position in the degree matrix is ​​the spatial distance value between the corresponding wireless sensor and the base station.

Images