CN114826933B - Non-cooperative topology inference method based on unknown node positions - Google Patents
Non-cooperative topology inference method based on unknown node positions Download PDFInfo
- Publication number
- CN114826933B CN114826933B CN202210748002.3A CN202210748002A CN114826933B CN 114826933 B CN114826933 B CN 114826933B CN 202210748002 A CN202210748002 A CN 202210748002A CN 114826933 B CN114826933 B CN 114826933B
- Authority
- CN
- China
- Prior art keywords
- node
- cooperative
- nodes
- training
- sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 230000000694 effects Effects 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 62
- 238000003062 neural network model Methods 0.000 claims description 24
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 4
- 239000000654 additive Substances 0.000 claims description 3
- 230000000996 additive effect Effects 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000001364 causal effect Effects 0.000 abstract description 7
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 238000013488 ordinary least square regression Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000669618 Nothes Species 0.000 description 1
- 238000012952 Resampling Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Optimization (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention relates to a non-cooperative topology inference method based on unknown node positions, which comprises the following steps: using random distribution within a given area LMonitoring the power of a non-cooperative network in a given area L by each sensor node; dividing a given area L intoThe grids with the same size are obtained according to the power detected by the sensor nodes; inputting the power of each grid into a neural network to obtain the coordinate position of a non-cooperative node; monitoring a time sequence of non-cooperative nodes by using a sensor network; constructing non-cooperative nodes according to time sequence of non-cooperative nodesAndan autoregressive model of the composed node pairs; constructing statistics using sum of squares of residuals from autoregressive models(ii) a According toObtaining non-cooperative nodesAndthe cause and effect relationship of (1). The invention discloses a non-cooperative topology inference method based on unknown node positions, which combines node positioning and causal inference into a system to realize topology inference when the node positions are unknown.
Description
Technical Field
The invention belongs to the technical field of positioning and topology inference, and relates to a non-cooperative topology inference method based on unknown node positions.
Background
The internet is becoming ubiquitous in today's world. From climate research to cancer research, from computational neuroscience to metrological economics, a scenario can be modeled as a network with multiple interaction variables. In the study of these networks, one of the main goals is to determine how certain variables affect other variables.
In network research, inferring causal relationships between network nodes will help to better understand how the different components of a network interact. In wireless network management, topology reasoning can provide information support for administrators, help them to remove faults and enhance the safety and the robustness of a network. For monitoring wireless networks, especially in the field of electronic warfare, topological reasoning can help identify and combat key nodes and key links in enemy networks. In addition, information can be mined from the topological information, the fighting intention of enemies can be inferred, and the information advantage on a battlefield can be realized.
However, in the conventional research, only one aspect is considered from topology inference alone, and the situation that the node position is unknown is not considered.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a non-collaborative topology inference method based on unknown node positions. The technical problem to be solved by the invention is realized by the following technical scheme:
the embodiment of the invention provides a non-cooperative topology inference method based on unknown node positions, which comprises the following steps:
step 1, using random distribution in a given area LA sensor network consisting of sensor nodes monitors the power of an uncooperative network in the given area L, the uncooperative network comprisingA plurality of non-cooperative nodes;
step 2, dividing the given area L intoThe grids with the same size are obtained, and the power of each grid is obtained according to the power detected by the sensor nodes;
step 3, inputting the power of each grid into a trained neural network model to obtain the coordinate position of the uncooperative node;
step 4, after the coordinate position of the non-cooperative node is obtained, monitoring the time sequence of the non-cooperative node in the non-cooperative network by using the sensor network;
step 5, constructing the non-cooperative nodes according to the time sequence of the non-cooperative nodesAnd non-cooperative nodesAn autoregressive model of the composed node pairs;
Step 7, according to the statistic quantityObtaining the non-cooperative nodeAnd the non-cooperative nodeThe cause and effect relationship of (1).
In one embodiment of the present invention, the step 1 comprises:
step 1.1, randomly setting the given area LA plurality of sensor nodes, wherein the locations of the sensor nodes are known;
step 1.2, utilizing theEach sensor node monitors the power of the uncooperative network in the given area L, whereinThe monitored power of each sensor node is as follows:
wherein,denotes the firstA sensor node monitorsThe power of the individual non-cooperating nodes,,is shown asTransmit power of a plurality of non-cooperating nodes, wherein,,,representing the total number of uncooperative nodes in the uncooperative network,the antenna gain of the transmitting antenna is indicated,which represents the antenna gain of the receiving antenna,which is indicative of the wavelength of the light,denotes the firstA sensor node monitorsDistance between the non-cooperating nodes.
wherein,denotes the firstThe power of the individual grids is,is shown asThe number of sensors contained in each grid, wherein,。
in one embodiment of the present invention, the training method of the neural network model includes:
s1, obtaining a training set, wherein the training set comprises a plurality of non-cooperative training nodes;
s2, dividing the area where the non-cooperative training nodes are located intoTraining grids of the same size, wherein,;
S4, according to the distanceTo obtain the firstIndividual sensor training node toTraining power of each non-cooperative training node;
s5, connecting a plurality of input-output pairsInputting the data into the neural network model to train the neural network model to obtain a trained neural network model, wherein,is the training power of the uncooperative training node,and the mesh is the real position of the non-cooperative training node.
In one embodiment of the present invention, the step 3 comprises:
step 3.1, inputting the power of each grid into a trained neural network model to obtain a positioning result of the non-cooperative node so as to determine the grid where the non-cooperative node is located;
and 3.2, taking the central position of the network of the non-cooperative node as the coordinate position of the non-cooperative node.
In an embodiment of the present invention, the time sequence of the non-cooperative node is:
wherein,a time series representing the non-cooperative node,the function of the index is expressed,which indicates the amount of time information that is to be transmitted,which represents the period of the sampling,indicating sensorSlave nodeThe start time and the end time of an observed set of transmission events.
In one embodiment of the invention, the non-cooperative nodesAnd the non-cooperative nodeThe autoregressive model of (a) is:
wherein,a constrained regression model is represented that has a constraint on the regression model,an unconstrained regression model is represented that is,representing the non-cooperative nodeThe time series of (a) and (b),representing the non-cooperative nodeThe time series of (a) and (b),、、is a constant number of times, and is,representing the non-cooperative nodeThe number of the lag terms of (a) is,representing the non-cooperative nodeThe number of the lag terms of (a) is,andindicating uncorrelated additive white noise.
wherein,representing the sum of squared residuals of the constrained regression model,representing the sum of squared residuals of the unconstrained regression model,the volume of the sample is represented by,representing the non-cooperative nodeThe number of the lag terms of (a) is,representing the non-cooperative nodeThe number of the lag terms of (a) is,representing complianceThe distribution of the water content is controlled by the control system,representing a degree of freedom ofAndf distribution of (3).
In one embodiment of the present invention, the step 7 includes:
step 7.1, set original hypothesisComprises the following steps: the non-cooperative nodeNot to cause said non-cooperative nodeThe cause of the change glange;
step 7.2, judgmentAndin relation to the threshold value of (1), ifIs present from the non-cooperative nodeTo the non-cooperative nodeOtherwise there is no link from the non-cooperative nodeTo the non-cooperative nodeThe link of (2).
Compared with the prior art, the invention has the following beneficial effects:
the invention discloses a non-cooperative topology inference method based on unknown node positions, which combines node positioning and causal inference into a system to realize topology inference work when the node positions are unknown.
The positioning method of the invention adopts a machine learning method to realize the positioning of the non-cooperative nodes.
Other aspects and features of the present invention will become apparent from the following detailed description, which proceeds with reference to the accompanying drawings. It is to be understood, however, that the drawings are designed solely for purposes of illustration and not as a definition of the limits of the invention, for which reference should be made to the appended claims. It should be further understood that the drawings are not necessarily drawn to scale and that, unless otherwise indicated, they are merely intended to conceptually illustrate the structures and procedures described herein.
Drawings
Fig. 1 is a schematic flowchart of a non-collaborative topology inference method based on unknown node positions according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a non-cooperative network including sensor nodes according to an embodiment of the present invention;
fig. 3 is a schematic diagram of inference accuracy of a non-cooperative network topology according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific examples, but the embodiments of the present invention are not limited thereto.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart of a non-collaborative topology inference method based on unknown node positions according to an embodiment of the present invention, and the present invention provides a non-collaborative topology inference method based on unknown node positions, where the non-collaborative topology inference method includes steps 1 to 7, where:
step 1, using random distribution in a given area LA sensor network composed of sensor nodes monitors the power of a non-cooperative network in a given area L, wherein the non-cooperative network comprisesA non-cooperative node.
In a particular embodiment, step 1 may particularly comprise steps 1.1-1.2, wherein:
step 1.1, randomly setting in a given area LA sensor node, wherein the location of the sensor node is known.
Specifically, referring to fig. 2, an embodiment of the present invention provides a schematic diagram of an uncooperative network including sensor nodes, where the uncooperative network includesA sensor network consisting ofEach sensor node and a sink node (the sink node is used for collecting data sent by all other nodes and carrying out related processing and the like),the sensor nodes are scattered in a given area randomly, and the coordinates of the sensor nodes are,Which represents the transpose of the matrix,a set of real numbers is represented as,to representReal matrix of row 2 column, noThe coordinates of each sensor are。
Step 1.2, useEach sensor node monitors the power of the uncooperative network within a given area L.
In particular, according toThe sensor nodes detect the energy distribution in a given area, and each sensor node obtains the receiving power at the position of the sensor node.
In this embodiment, the sensor monitors the power of the uncooperative node to obtainFirst, ofThe monitored power of each sensor node is as follows:
wherein,denotes the firstA sensor node monitorsThe power of the individual non-cooperating nodes,,is shown asTransmit power of a plurality of non-cooperating nodes, wherein,,,representing the total number of non-cooperating nodes in the non-cooperating network,the antenna gain of the transmitting antenna is indicated,which represents the antenna gain of the receiving antenna,which is indicative of the wavelength of the light,is shown asIndividual sensor node monitorMeasured to the firstDistance between the non-cooperating nodes.
Step 2, dividing the given area L intoAnd obtaining the power of each grid according to the power detected by the sensor nodes.
Specifically, a given area L is divided by the number of sensorsThe power data for each grid is then obtained based on the power data obtained for each sensor and the known sensor location information.
In this embodiment, the power data monitored by each sensor is obtained by the above-mentioned methodThe power distribution of the grid, i.e.Wherein the firstThe power of each grid is represented as:,denotes the firstThe number of sensors contained in each grid, wherein,。
and 3, inputting the power of each grid into the trained neural network model to obtain the coordinate position of the non-cooperative node.
In this embodiment, the training method of the neural network model includes:
s1, obtaining a training set, wherein the training set comprises a plurality of non-cooperative training nodes, and the non-cooperative training nodes are non-cooperative nodes for training.
In particular, the training set consists of data that can monitor some of the non-cooperating nodes and can derive their location.
S2, dividing the area where the non-cooperative training nodes are located intoTraining grids of the same size, wherein,。
Specifically, the training set consists of data that can monitor and derive the location of some of the non-cooperative nodes, sayThe coordinates of each non-cooperative training node are(ii) a The distance between each uncooperative training node and each sensor training node (i.e., the sensor node used for training) is then calculatedFrom, toIndividual sensor training node anddistance between non-cooperative training nodesComprises the following steps:
S4, according to distanceTo obtain the firstThe sensor trains the node to the firstTraining power of each non-cooperative training node.
In particular, the distance is measuredSubstituting the power formula of step 1.2 to obtain the secondIndividual sensor training node toReceived power of each uncooperative training node.
S5, connecting a plurality of input-output pairsInputting the data into a neural network model to train the neural network model to obtain a trained neural network model, wherein,is the training power of the non-cooperative training nodes,and training grids in which the real positions of the non-cooperative training nodes are located.
Specifically, a combination of uncooperative training nodes is created, and assuming that there are n uncooperative training nodes, the total number of combinations of uncooperative training nodes that may appear in each grid is:
will train the setInput into a neural network model, whereinTo be an input-output pair, the input-output pair,in order to acquire the power data of the power,and training the weight parameters of the neural network model for the training grid where the real position of the non-cooperative node is located to obtain the trained neural network model.
In a particular embodiment, step 3 may particularly comprise steps 3.1-3.2, wherein:
and 3.1, inputting the power of each grid into the trained neural network model to obtain a positioning result of the non-cooperative node so as to determine the grid where the non-cooperative node is located.
And 3.2, taking the central position of the network of the non-cooperative node as the coordinate position of the non-cooperative node.
Specifically, when the sensor network monitors a given area, power data of a scene to be measured is obtainedThe data is used as the input of a trained neural network model, the neural network model outputs the positioning result of the non-cooperative node, namely, the non-cooperative node is positioned in a certain grid, and then the central position of the grid is positionedAs coordinates of non-cooperative nodes, whereinIs shown asCoordinates of the individual nodes.
And 4, after the coordinate position of the non-cooperative node is obtained, monitoring the time sequence of the non-cooperative node in the non-cooperative network by using the sensor network.
Specifically, after coordinate position information of the non-cooperative node is obtained, the sensor node records the time when the non-cooperative node sends information.
In this embodiment, the sensor monitors the network by observing information transmissions by uncooperative nodes in an RF (radio frequency) environment. The topology of the entire network is inferred from the observation of the sensors. Since the sensors cannot access the uncooperative network, i.e. cannot obtain the internal state of the network, externally observable features must be used. Radio station fingerprint identification technology by combining information such as frequency, interception time and the like of signalsDifferentiation of communication signals between nodes in the network may be achieved, i.e. the sensor node determines by which node the detected signal is emitted. The sensors collect the IDs of the uncooperative nodes they observe and the time series of transmitted information. Each node in the network requires a time series representation, e.g. sensor node monitoring for uncooperative nodesTime series ofThe feature obtained from each sensor node is a set of non-uniformly sampled eventsWhereinIs the time of a set of transmission events. To obtain a time series representation, events must be representedResampling to form a time series:
whereinA time series representing the non-cooperative node,the function of the index is expressed,which indicates the amount of time information that is to be transmitted,which represents the period of the sampling,indicating sensorSlave nodeThe start time and end time of an observed set of transmission events, ifAt intervals ofAn event (whether the transmission is started or completed) is included, the value is 1, otherwise, the value is 0.
Step 5, constructing the non-cooperative nodes according to the time sequence of the non-cooperative nodesAnd non-cooperative nodesAn autoregressive model of the constituent node pairs.
wherein,a constrained regression model is represented that has a constraint on the regression model,an unconstrained regression model is represented that is,representing non-cooperative nodesThe time series of (a) and (b),representing non-cooperative nodesThe time series of (a) and (b),、、is constant, is calculated by using Ordinary Least Squares (OLS),representing the non-cooperative nodeThe number of the lag terms of (a) is,representing the non-cooperative nodeNumber of lag terms of, i.e.Andthe maximum number of lag-behind periods is indicated,andindicating uncorrelated additive white noise. If, in the above-described model,constant of the foregoingAll zeros, or values negligible, are apparent nodesWill not affect the node. I.e. nodesIs not a nodeThe reason for (1) and vice versa. Of course, if the coefficient、Are not zero, then the nodeIs a nodeBecause of the presence of a slave nodePointing nodeThe link of (2).
Step 6, utilizing the residual sum of squares of the autoregressive model to construct statisticsWherein the statisticComprises the following steps:
wherein,representing the sum of the squared residuals of the constrained regression model,represents the sum of the squared residuals of the unconstrained regression model,the volume of the sample is represented by,representing non-cooperative nodesThe number of the lag terms of (a) is,representing non-cooperative nodesThe number of the lag terms of (a) is,representing complianceThe distribution of the water content is carried out,representing a degree of freedom ofAndthe F distribution is a sampling distribution of the ratio of two independent random variables subjected to chi-square distribution after the independent random variables are divided by the degree of freedom of the independent random variables, is an asymmetric distribution, and is not interchangeable in position. Unconstrained residual sum of squaresIs to the current non-cooperative nodeFor all the lagged termsMaking a regression, but not including a lag term in this regression. Similarly, there is a constrained sum of squares of residualsIs to the current non-cooperative nodeFor all the lag termsAnd a lag termAnd (6) making regression.
Step 7, according to the statisticObtaining non-cooperative nodesAnd non-cooperative nodesThe cause and effect relationship of (1).
In a particular embodiment, step 7 may particularly comprise steps 7.1-7.2, wherein:
step 7.1, setting original hypothesisComprises the following steps: non-cooperative nodeNot to cause non-cooperative nodesThe cause of the change granger.
Step 7.2, judgmentAndin relation to the threshold value of (1), ifIf there is a secondary non-cooperative nodeTo non-cooperative nodesOtherwise there is no slave non-cooperative nodeTo non-cooperative nodesThe link(s) of (a) is (are),is a distribution case, which is selected to correspond to a critical confidence levelThe value of (d) is a threshold value, the threshold value is a constant.
In particular, the original hypothesisIs expressed as,Representing a constant, by calculation using Ordinary Least Squares (OLS), ifA threshold value ofSignificantly different from 0, so the original hypothesis is rejectedIs ready to storeAt a slave non-cooperative nodeTo non-cooperative nodesOtherwise, the original hypothesis cannot be rejectedI.e. there is no slave non-cooperative nodeTo non-cooperative nodesThe link of (2). Repeating the steps 4 to 7, and checking whether all node pairs meet the original hypothesisTo determine the links between the various uncooperative nodes.
That is, it is assumed that there is a networkRepeating the steps 4 to 7, traversing all node pairs, constructing an autoregressive model of the nodes, and constructing the uncooperative nodesStatistics, judging whether the node pair satisfies the original hypothesisI.e. whether a causal relationship exists between pairs of nodes. Thereby obtaining topology inference results of the entire network.
It is worth noting that the granger causal relationship test is sometimes sensitive to the choice of lag phase length, and different lag phases may yield completely different test results. Therefore, it is first necessary to perform checks for different lag period lengths.
The effectiveness of the non-collaborative topology inference method based on unknown node positions in the embodiment is verified through experiments.
Specifically, energy distribution conditions in the non-cooperative area are detected through a sensor, and coarse positioning is carried out on the non-cooperative nodes. Specifically, the power monitored by each sensor is put into a trained neural network for training, and the positioning result of the uncooperative node is obtained. Then, through effective monitoring of non-cooperative nodes, after an autoregressive model of the nodes is constructed, statistics are constructedJudging whether the node pair satisfies the original assumptionI.e. whether there is a causal relationship between pairs of nodes, thereby obtaining a topology inference of the entire network.
In the simulation, the antenna type of the non-cooperative node is set to be an omnidirectional antenna, a given area is divided into grids equal to the number of sensors, and fig. 3 shows the topology inference accuracy of the non-cooperative network topology.
The invention provides a non-cooperative topology inference method based on unknown node positions, wherein under the condition of unknown node positions, a sensor node collects the power distribution condition of a given area L, feeds the power distribution condition into a trained neural network model to obtain the positioning result of a non-cooperative node, uses the distance and frame interval information between nodes as the characteristics for judging whether a communication relation exists between the nodes, and feeds the trained classification model to obtain an inferred topology.
The positioning method of the invention adopts a machine learning method to realize the positioning of the non-cooperative nodes.
The invention combines node positioning and causal inference into a system to realize topology inference work when the node position is unknown based on a non-collaborative topology inference method with unknown node position.
Example two
Yet another aspect of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor, when calling the computer program in the memory, implements the steps of the non-collaborative topology inference method based on node location unknown according to any of the above embodiments.
In the description of the invention, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to imply that the number of indicated technical features is significant. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic data point described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristic data points described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples described in this specification can be combined and combined by those skilled in the art.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (9)
1. A non-cooperative topology inference method based on unknown node positions is characterized by comprising the following steps:
step 1, using random distribution in a given area LA sensor network consisting of sensor nodes monitors the power of an uncooperative network in the given area L, the uncooperative network comprisingA plurality of non-cooperative nodes;
step 2, dividing the given area L intoThe grids with the same size are obtained, and the power of each grid is obtained according to the power detected by the sensor nodes;
step 3, inputting the power of each grid into a trained neural network model to obtain the coordinate position of the uncooperative node;
step 4, after the coordinate position of the non-cooperative node is obtained, monitoring the time sequence of the non-cooperative node in the non-cooperative network by using the sensor network;
step 5, constructing the non-cooperative nodes according to the time sequence of the non-cooperative nodesAnd non-cooperative nodesAn autoregressive model of the composed node pairs;
2. The method for non-cooperative topology inference based on unknown node locations according to claim 1, wherein the step 1 comprises:
step 1.1, randomly setting the given area LA plurality of sensor nodes, wherein the locations of the sensor nodes are known;
step 1.2, utilizing theEach sensor node monitors the power of the uncooperative network in the given area L, whereinThe monitored power of each sensor node is as follows:
wherein,is shown asA sensor node monitorsThe power of the individual non-cooperating nodes,,is shown asTransmit power of a plurality of non-cooperating nodes, wherein,,,representing the total number of non-cooperating nodes in the non-cooperating network,the antenna gain of the transmitting antenna is indicated,which represents the antenna gain of the receiving antenna,which is indicative of the wavelength of the light,is shown asA sensor node monitorsDistance between the non-cooperating nodes.
3. The method of claim 2, wherein the first step is to determine the topology of the non-cooperative topology based on the unknown node locationThe power of each grid is:
4. the method of claim 1, wherein the training of the neural network model comprises:
s1, obtaining a training set, wherein the training set comprises a plurality of non-cooperative training nodes;
s2, dividing the area where the non-cooperative training nodes are located intoTraining grids of the same size, wherein,;
S4, according to the distanceTo obtain the firstIndividual sensor training node toTraining power of each non-cooperative training node;
s5, connecting a plurality of input-output pairsInputting the data into the neural network model to train the neural network model to obtain a trained neural network model, wherein,is the training power of the uncooperative training node,and training grids in which the real positions of the non-cooperative training nodes are located.
5. The method of claim 1, wherein step 3 comprises:
step 3.1, inputting the power of each grid into a trained neural network model to obtain a positioning result of the non-cooperative node so as to determine the grid where the non-cooperative node is located;
and 3.2, taking the central position of the grid with the non-cooperative node as the coordinate position of the non-cooperative node.
6. The method of claim 1, wherein the time series of the uncooperative nodes is:
wherein,a time series representing the non-cooperative node,the function of the index is expressed,which indicates the amount of time information that is to be transmitted,which represents the period of the sampling,indicating sensorSlave nodeThe start time and the end time of an observed set of transmission events.
7. The method of claim 1, wherein the uncooperative nodes are unknown based on location of the nodesAnd the non-cooperative nodeThe autoregressive model of (a) is:
wherein,a constrained regression model is represented that has a constraint on the regression model,an unconstrained regression model is represented that is,representing the non-cooperative nodeThe time series of (a) and (b),representing the non-cooperative nodeThe time series of (a) and (b),、、is a constant number of times, and is,representing the non-cooperative nodeThe number of the lag terms of (a) is,representing the non-cooperative nodeThe number of the lag terms of (a) is,andindicating uncorrelated additive white noise.
8. The method of claim 7, wherein the statistics are based on an unknown location of the nodeComprises the following steps:
wherein,representing the sum of the squared residuals of the constrained regression model,representing the sum of the squared residuals of the unconstrained regression model,the volume of the sample is represented by,representing the non-cooperative nodeThe number of the lag terms of (a) is,representing the non-cooperative nodeThe number of the lag terms of (a) is,representing complianceThe distribution of the water content is controlled by the control system,representing a degree of freedom ofAndf distribution of (3).
9. The method of claim 8, wherein the step 7 comprises:
step 7.1, set original hypothesisComprises the following steps: the non-cooperative nodeNot to cause the non-cooperative nodeThe cause of the change glange;
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210748002.3A CN114826933B (en) | 2022-06-29 | 2022-06-29 | Non-cooperative topology inference method based on unknown node positions |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210748002.3A CN114826933B (en) | 2022-06-29 | 2022-06-29 | Non-cooperative topology inference method based on unknown node positions |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114826933A CN114826933A (en) | 2022-07-29 |
CN114826933B true CN114826933B (en) | 2022-09-09 |
Family
ID=82522523
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210748002.3A Active CN114826933B (en) | 2022-06-29 | 2022-06-29 | Non-cooperative topology inference method based on unknown node positions |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114826933B (en) |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7567523B2 (en) * | 2004-01-29 | 2009-07-28 | Microsoft Corporation | System and method for network topology discovery |
CN109560972B (en) * | 2018-12-27 | 2021-07-27 | 中国人民解放军国防科技大学 | Non-cooperative inference method for Ad Hoc network physical topology |
CN109688540B (en) * | 2018-12-27 | 2021-01-01 | 中国人民解放军国防科技大学 | Ad Hoc network physical topology non-cooperative inference system |
CN110135482B (en) * | 2019-04-30 | 2021-07-13 | 中国地质大学(武汉) | Network topology inference method and system based on convolutional neural network |
CN110888134B (en) * | 2019-11-04 | 2023-07-18 | 电子科技大学 | Non-cooperative and cooperative integrated airport scene monitoring system |
CN112272364B (en) * | 2020-10-19 | 2023-02-24 | 广州大学 | Non-cooperative game power control method based on rechargeable wireless sensor network |
CN112558471B (en) * | 2020-11-24 | 2022-05-24 | 西北工业大学 | Spacecraft formation discrete distributed non-cooperative game method based on dynamic event triggering |
CN113238185B (en) * | 2021-07-12 | 2021-09-24 | 中国人民解放军国防科技大学 | Fibonacci scatter search-based non-cooperative target positioning method and system |
CN113489619B (en) * | 2021-09-06 | 2021-11-19 | 中国人民解放军国防科技大学 | Network topology inference method and device based on time series analysis |
CN114520799B (en) * | 2021-12-27 | 2023-05-05 | 中国人民解放军战略支援部队信息工程大学 | Urban IP positioning and error estimation method and system based on minimum circle coverage |
CN114666227B (en) * | 2022-03-18 | 2024-02-06 | 中国人民解放军战略支援部队信息工程大学 | Network topology detection method under non-cooperative condition |
-
2022
- 2022-06-29 CN CN202210748002.3A patent/CN114826933B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN114826933A (en) | 2022-07-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Acar et al. | Peek-a-boo: I see your smart home activities, even encrypted! | |
Raghavan et al. | Quickest change detection of a Markov process across a sensor array | |
CN102333307B (en) | Wireless sensor network (WSN) trust evaluation method based on subjective belief | |
DE60314514T2 (en) | SYSTEM AND METHOD FOR INFERRING AN ELECTRONIC PLAYBACK OF AN ENVIRONMENT | |
CN101835158B (en) | Sensor network trust evaluation method based on node behaviors and D-S evidence theory | |
Tsitsiroudi et al. | EyeSim: A mobile application for visual-assisted wormhole attack detection in IoT-enabled WSNs | |
CN109040302A (en) | Vacant lot information on soil moisture acquisition system | |
CN106899442B (en) | Method for measuring survivability of command control network based on operational link efficiency | |
CN105553442B (en) | The H of network-based Lipschitz nonlinear system∞Filter information processing method | |
TW201301209A (en) | Environment monitoring method and device with cloud computing as framework using data fusion computation design | |
CN112052149A (en) | Big data information acquisition system and use method | |
CN103702282B (en) | A kind of multiple types multiple target passive type localization method based on migration compressed sensing | |
CN109861825A (en) | Detection method is internaled attack based on Weighted Rule and consistent degree in CPS system | |
CN106953754A (en) | Charge network survivability Measurement Method based on operation link entropy | |
CN105933932A (en) | Real-time fault diagnosis method and method for wireless sensor network in complex environment | |
CN114826933B (en) | Non-cooperative topology inference method based on unknown node positions | |
US11002826B2 (en) | Distributed-cooperative-information processing device, distributed-cooperative-information processing method, and recording medium | |
Muravyov et al. | Multisensor accuracy enhancement on the base of interval voting in form of preference aggregation in WSN for ecological monitoring | |
Feng et al. | Securing cooperative spectrum sensing against rational SSDF attack in cognitive radio networks | |
Deelip et al. | ExpSFROA-based DRN: exponential sunflower rider optimization algorithm-driven deep residual network for the intrusion detection in IOT-based plant disease monitoring | |
Kumar et al. | Intrusion detection in MANET using self organizing map (SOM) | |
Zhao et al. | Reliability analysis of body sensor networks subject to random isolation time | |
Fei et al. | Irregular sensing range detection model for coverage based protocols in wireless sensor networks | |
Suganya et al. | Evaluation of a Wireless Sensor Network for the Detection of Forest Fires | |
Chander et al. | Introduction to wireless sensor networks |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |