CN113411366A - Internet of things data linkage method, device, equipment and medium based on edge calculation - Google Patents

Internet of things data linkage method, device, equipment and medium based on edge calculation Download PDF

Info

Publication number
CN113411366A
CN113411366A CN202010184966.0A CN202010184966A CN113411366A CN 113411366 A CN113411366 A CN 113411366A CN 202010184966 A CN202010184966 A CN 202010184966A CN 113411366 A CN113411366 A CN 113411366A
Authority
CN
China
Prior art keywords
data
edge computing
monitoring data
internet
things
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.)
Pending
Application number
CN202010184966.0A
Other languages
Chinese (zh)
Inventor
廖冬阳
衡亚亚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Shanghai ICT Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Shanghai ICT Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd, China Mobile Shanghai ICT Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN202010184966.0A priority Critical patent/CN113411366A/en
Publication of CN113411366A publication Critical patent/CN113411366A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G06N3/08—Learning 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
    • 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
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/02—Capturing of monitoring data
    • H04L43/028—Capturing of monitoring data by filtering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/16—Threshold monitoring
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Computer And Data Communications (AREA)

Abstract

The embodiment of the invention provides an Internet of things data linkage method, device, equipment and medium based on edge calculation, wherein the method comprises the following steps: sending IP information of the edge computing node equipment to the Internet of things equipment; receiving monitoring data of a monitoring object sent by the Internet of things equipment according to the IP information; filtering the monitoring data according to the user demand information to obtain effective monitoring data; sending effective monitoring data to a cloud platform, wherein the effective monitoring data is used for the cloud platform to generate prediction data; receiving prediction data sent by a cloud platform; and updating the monitoring data according to the prediction data. The invention can effectively utilize the received real-time monitoring data, reduces the data processing pressure of the cloud platform and simultaneously ensures the validity of the data.

Description

Internet of things data linkage method, device, equipment and medium based on edge calculation
Technical Field
The invention relates to the technical field of Internet of things control, in particular to an Internet of things data linkage method, device, equipment and medium based on edge calculation.
Background
The information interaction mode of the application of the Internet of things is mainly characterized in that a real-time shared and real-time updated real object network system is constructed through technologies such as a radio frequency identification technology, a sensor technology, a camera technology and a wireless communication technology, real-time data are collected by using sensor nodes, then the real-time data are transmitted to a cloud platform, and the cloud platform processes the data. However, with the rapid development of the internet of things, the number of devices in the internet of things is increased sharply, the existing cloud computing center becomes more and more complex, and the cloud platform is connected to a large number of devices, so that the difficulties of insufficient bandwidth, excessive power consumption and the like are faced.
In order to solve the problems of insufficient bandwidth and overhigh power consumption, the prior art discloses a technical scheme for applying edge calculation to the internet of things. However, the current technical scheme cannot effectively apply the data collected by the internet of things device, and all logics are arranged on the cloud platform, so that the cloud platform is not subjected to effective data linkage while huge pressure is brought to the cloud platform.
Disclosure of Invention
The embodiment of the invention provides an Internet of things data linkage method, an Internet of things data linkage device, Internet of things data linkage equipment and a computer readable storage medium, through data filtering and data updating of edge computing node equipment, received real-time monitoring data can be effectively used, data processing pressure of a cloud platform is reduced, and meanwhile data effectiveness is guaranteed.
In a first aspect, an internet of things data linkage method based on edge computing is provided, and is used for edge computing node equipment, and the method includes: sending IP information of the edge computing node equipment to the Internet of things equipment; receiving monitoring data of a monitoring object sent by the Internet of things equipment according to the IP information; filtering the monitoring data according to the user demand information to obtain effective monitoring data; sending effective monitoring data to a cloud platform, wherein the effective monitoring data is used for the cloud platform to generate prediction data; receiving prediction data sent by a cloud platform; and updating the monitoring data according to the prediction data.
In some implementation manners of the first aspect, when the monitoring data exceeds a preset threshold, an alarm message is sent to the user, where the alarm message is used to prompt that an abnormality occurs in the monitoring object within a preset monitoring range.
In some implementations of the first aspect, before filtering the monitoring data according to the user requirement to obtain valid monitoring data, the method includes: the edge computing node equipment comprises a plurality of edge computing nodes, and the edge computing node equipment determines a plurality of edge computing nodes capable of communicating according to the performance information; the edge computing node equipment carries out self-adaptive data distribution on the monitoring data and distributes the distributed monitoring data to a plurality of edge computing nodes capable of communicating.
In a second aspect, an internet of things data linkage method based on edge computing is provided, and is used for internet of things equipment, and the method includes: collecting real-time data of a monitored object in a preset monitoring range to obtain monitoring data; receiving IP information sent by edge computing node equipment; and sending monitoring data to the edge computing node equipment according to the IP information.
In a third aspect, an internet of things data linkage method based on edge computing is provided, and is used for a cloud platform, and the method comprises the following steps: receiving effective monitoring data sent by edge computing node equipment; determining a wavelet function according to the data characteristics of the effective monitoring data; determining prediction data of effective monitoring data according to a wavelet function and an error back propagation algorithm BP neural network; and sending the prediction data to the edge computing node device.
In some implementations of the third aspect, determining the prediction data of the valid monitoring data from the wavelet function and the BP neural network comprises: determining the optimal decomposition scale of the wavelet function according to the Mean Square Error (MSE); decomposing a preset sample set and a prediction set respectively according to a Marait algorithm and an optimal decomposition scale to obtain a low-frequency sequence and a high-frequency sequence of the preset sample set and a low-frequency sequence and a high-frequency sequence of the prediction set, wherein the prediction set is used for storing effective monitoring data; reconstructing each low-frequency sequence and each high-frequency sequence according to a Malat algorithm to obtain a plurality of subsequences with the sequence length equal to that of the original sequence; normalizing the subsequence to obtain zero-one interval data; and taking the zero-one interval data as an input layer of the BP neural network, training the neural network, and outputting prediction data when the training error is smaller than a preset error.
In some implementations of the third aspect, before taking the zero-one interval data as an input layer of the BP neural network and performing neural network training, when a training error is smaller than a preset error, outputting the prediction data, the method includes: and initializing the BP neural network, and determining a preset error according to the learning parameters.
In some implementations of the third aspect, the weights and thresholds of the BP network are adjusted.
In a fourth aspect, an internet of things data linkage device based on edge computing is provided, which is used for an edge computing node device, and comprises: the sending module is used for sending the IP information of the edge computing node equipment to the Internet of things equipment; the receiving module is used for receiving monitoring data of the monitoring object sent by the Internet of things equipment according to the IP information; the filtering module is used for filtering the monitoring data according to the user demand information to obtain effective monitoring data; the sending module is further used for sending effective monitoring data to the cloud platform, and the effective monitoring data is used for the cloud platform to generate prediction data; the receiving module is also used for receiving the prediction data sent by the cloud platform; and the updating module is used for updating the monitoring data according to the prediction data.
In some implementation manners of the fourth aspect, the monitoring device further includes an alarm module, configured to send alarm information to a user when the monitoring data exceeds a preset threshold, where the alarm information is used to prompt that an abnormality occurs in a monitoring object within a preset monitoring range.
In some realizations of the fourth aspect, the apparatus further comprises a shunting module configured to: the edge computing node equipment comprises a plurality of edge computing nodes, and the edge computing node equipment determines a plurality of edge computing nodes capable of communicating according to the performance information; the edge computing node equipment carries out self-adaptive data distribution on the monitoring data and distributes the distributed monitoring data to a plurality of edge computing nodes capable of communicating.
In a fifth aspect, an internet of things data linkage device based on edge computing is provided, and is used for internet of things equipment, and the device includes: the collection module is used for collecting real-time data of a monitored object in a preset monitoring range to obtain monitoring data; the receiving module is used for receiving the IP information sent by the edge computing node equipment; and the sending module is used for sending the monitoring data to the edge computing node equipment according to the IP information.
In a sixth aspect, an internet of things data linkage device based on edge computing is provided for a cloud platform, the device includes: the receiving module is used for receiving effective monitoring data sent by the edge computing node equipment; the determining module is used for determining a wavelet function according to the data characteristics of the effective monitoring data; the determining module is also used for determining the prediction data of the effective monitoring data according to the wavelet function and the error back propagation algorithm BP neural network; and the sending module is used for sending the prediction data to the edge computing node equipment.
In some implementations of the sixth aspect, the determining module is specifically configured to: determining the optimal decomposition scale of the wavelet function according to the Mean Square Error (MSE); decomposing a preset sample set and a prediction set respectively according to a Marait algorithm and an optimal decomposition scale to obtain a low-frequency sequence and a high-frequency sequence of the preset sample set and a low-frequency sequence and a high-frequency sequence of the prediction set, wherein the prediction set is used for storing effective monitoring data; reconstructing each low-frequency sequence and each high-frequency sequence according to a Malat algorithm to obtain a plurality of subsequences with the sequence length equal to that of the original sequence; normalizing the subsequence to obtain zero-one interval data; and taking the zero-one interval data as an input layer of the BP neural network, training the neural network, and outputting prediction data when the training error is smaller than a preset error.
In some implementations of the sixth aspect, the apparatus further includes an initializing module configured to initialize the BP neural network, and determine the preset error according to the learning parameter.
In some implementations of the sixth aspect, the method further includes adjusting the weight and the threshold of the BP network.
In a seventh aspect, an internet of things data linkage device based on edge computing is provided, which includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the methods for data linkage of the internet of things based on edge computing in the first to third aspects, or in some implementations of the first to third aspects.
In an eighth aspect, a computer-readable storage medium is provided, on which computer program instructions are stored, and the computer program instructions, when executed by a processor, implement the method for linking data of the internet of things based on edge computing in the first aspect to the third aspect, or in some realizations of the first aspect to the third aspect.
The invention relates to the technical field of Internet of things control, in particular to an Internet of things data linkage method, device, equipment and computer readable storage medium based on edge computing.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a data linkage method of the internet of things based on edge calculation according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of another method for linking data of the internet of things based on edge calculation according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an internet of things data linkage device based on edge calculation according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of another data linkage of the Internet of things based on edge calculation according to an embodiment of the invention;
FIG. 5 is a schematic structural diagram of a further Internet of things data linkage device based on edge calculation according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an internet of things data linkage device based on edge computing according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
At present, the application range of the internet of things technology is wide, for example, in the field of smart homes adopting the internet of things technology, control over various devices in a smart home system can be achieved through traditional manual control, intelligent wireless remote control, one-key scene control, IPAD management, telephone remote control, internet remote control, event timing management, device linkage control and the like, and smart bulbs manufactured by using the concept of the internet of things and released on the market can be turned on or off through a smart phone, the light color can be changed according to given commands, and the constant-lighting time can be set according to a specified time schedule without manual intervention.
The edge computing is originated from the technical field of media, and means that an open platform integrating network, computing, storage and application core capabilities is adopted on one side close to a data source to provide nearest-end service nearby.
With the rapid development of the internet of things, the number of devices of the internet of things is increased rapidly, the existing cloud computing center becomes more and more complex, a cloud computing center platform is connected to a large number of devices, and then the cloud computing center platform faces the difficult challenges of insufficient bandwidth, excessive power consumption and the like, so that in order to solve the problem, the prior art discloses a technical scheme for applying edge computing to the internet of things.
However, in the prior art, large-scale complex data collected by the internet of things device and the edge computing node device cannot be effectively applied and processed, and all logics are arranged on the cloud platform, so that huge pressure is brought to the cloud platform, and effective linkage cannot be performed when an accident occurs.
In order to solve the problem that the collected real-time monitoring data cannot be effectively utilized in the technical scheme of applying edge calculation to the internet of things in the prior art, the embodiment of the invention provides an internet of things data linkage method, device, equipment and medium based on edge calculation. The technical solutions of the embodiments of the present invention are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of an internet of things data linkage method based on edge computing according to an embodiment of the present invention, and as shown in fig. 1, the internet of things data linkage method based on edge computing may include the following steps:
s101, the edge computing node equipment sends IP information of the edge computing node equipment to the Internet of things equipment.
Specifically, the edge computing node device monitors peripheral internet of things devices capable of collecting data, and sends the IP information of the edge computing node device to the monitored internet of things devices.
And S102, the Internet of things equipment sends monitoring data to the edge computing node equipment according to the IP information.
The internet of things equipment can comprise a series of sensor modules such as a temperature monitoring module, a camera module, an infrared monitoring module and a gyroscope module, a monitoring object in a preset range is monitored in real time through the series of sensor modules, real-time data of the monitoring object is collected, and monitoring data are obtained.
Specifically, the internet of things device monitors the edge computing node device capable of communicating, preferentially receives the IP information sent by the edge computing node device capable of communicating nearby, establishes communication connection with the edge computing node device according to the IP information, and sends monitoring data of a monitoring object to the edge computing node device through the communication connection.
And S103, filtering the monitoring data by the edge computing node equipment according to the user demand information to obtain effective monitoring data.
For a user, monitoring data received by the edge computing node device does not completely meet the user requirements, and especially when a plurality of internet of things devices send monitoring data to the edge computing node device, a large amount of monitoring data brings great computing pressure to the edge computing node device.
The edge computing node device may include a plurality of edge computing nodes, and after receiving the monitoring data, the edge computing node device may further perform adaptive data offloading on the monitoring data, which specifically includes: the edge computing node equipment determines a plurality of edge computing nodes capable of communicating according to the performance information of the edge computing node equipment, then shunts the received monitoring data to obtain a plurality of data streams, and distributes the plurality of data streams to the plurality of edge computing nodes capable of communicating, so that the condition that a large amount of data are accumulated in a single edge computing node is avoided, and the pressure of the node is effectively reduced.
The edge computing node equipment can also judge the received monitoring data and send alarm information to the user when the monitoring data exceeds a preset threshold value.
As a specific embodiment, when receiving temperature data of a monitoring object collected by a temperature monitoring module of the internet of things device in real time, the edge computing node device determines whether the temperature data exceeds a preset temperature threshold, and when the temperature data exceeds the preset threshold, notifies a user in a short message, a mail, an internal message notification, and the like, so as to prompt the user that the temperature of the monitoring object within a preset monitoring range is abnormal.
According to the data linkage method of the Internet of things based on the edge computing, the computing pressure of the edge computing node equipment is reduced through self-adaptive data distribution, the effectiveness of the monitoring data is guaranteed to a certain extent through filtering the monitoring data, and the effective processing of the monitoring data by the edge computing node equipment is realized.
Fig. 2 is a schematic flow chart of another internet of things data linkage method based on edge computing according to an embodiment of the present invention, and as shown in fig. 2, the internet of things data linkage method based on edge computing may include S201-S208. S201 to S203 are the same as S101 to S103, and for brevity, are not described herein again.
After S203 is executed, that is, the edge computing node device filters the monitoring data according to the user requirement information to obtain effective monitoring data, the internet of things data linkage method 200 based on edge computing may further include S204-S208.
And S204, the edge computing node equipment sends effective monitoring data to the cloud platform.
S205, the cloud platform determines a wavelet function according to the data characteristics of the effective monitoring data.
Because the effective monitoring data received by the cloud platform is influenced by various interference factors such as equipment and environment and inevitably contains noise, if the effective monitoring data is not processed, the accuracy of the prediction result of the effective monitoring data is influenced, therefore, before the effective monitoring data is predicted, the noise of the data needs to be processed by utilizing wavelet analysis, and the wavelet function used in the wavelet analysis has non-uniqueness, namely the wavelet function has diversity, so that the optimal wavelet function needs to be determined before the noise is processed.
Specifically, the cloud platform determines a suitable wavelet function according to the data characteristics of the received effective monitoring data in consideration of the data characteristics.
And S206, the cloud platform determines the prediction data of the effective monitoring data according to the wavelet function and the error back propagation algorithm BP neural network.
The cloud platform predicts effective monitoring data by adopting a combined model combining a wavelet function and a BP neural network to obtain a prediction result.
The wavelet analysis is a time-frequency localization analysis method which has fixed window size, but can adjust the shape, time window and frequency of the window according to different frequency components of signals and the density of time sampling, and can decompose original signals with nonlinear characteristics on different scales to obtain high-frequency and low-frequency approximate signals and grasp the trend and local characteristics of data; the error Back Propagation (BP) neural network is a multi-layer feedforward neural network trained according to an error Back Propagation algorithm, has extremely strong learning capability and generalization capability, strong nonlinear approximation capability and high systematicness, and is suitable for complex data of the Internet of things.
Determining prediction data of valid monitoring data according to the wavelet function and the BP neural network may comprise the steps of:
step 1, determining the optimal decomposition scale of the wavelet function according to the mean square error MSE.
Mean Square Error (MSE), i.e. the deviation variance of the predicted value to the actual value, a suitable decomposition scale of the wavelet function can be found by using MSE, and the minimum decomposition level of MSE between the decomposed predicted values of the subsequences and the actual value after synthesis is the optimal decomposition scale.
And 2, decomposing the preset sample set and the prediction set respectively according to the Marait algorithm and the optimal decomposition scale to obtain a low-frequency sequence and a high-frequency sequence of the preset sample set and a low-frequency sequence and a high-frequency sequence of the prediction set.
The Mallat algorithm is a rapid algorithm for tower-type multi-resolution analysis and reconstruction of signals, and decomposes a preset sample set and a prediction set storing effective monitoring data respectively by using the Mallat algorithm and an optimal decomposition scale to obtain a low-frequency sequence and a plurality of high-frequency sequences of the preset sample set and a low-frequency sequence and a plurality of high-frequency sequences of the prediction set.
And 3, reconstructing each low-frequency sequence and each high-frequency sequence according to a Marait algorithm to obtain a plurality of subsequences with the sequence length equal to that of the original sequence.
And (3) reconstructing each decomposed time sequence by adopting a Mallat algorithm to obtain a plurality of subsequences with the sequence length equal to that of the original sequence.
And decomposing and reconstructing effective monitoring data by using a Mallat algorithm, removing the noise of the data, which is essentially equivalent to a band-pass filter with a plurality of channels, obtaining a plurality of subsequences, wherein each subsequence after decomposition and reconstruction is smoother than the original sequence.
And 4, carrying out normalization processing on the subsequence to obtain zero-one interval data.
In order to avoid the sensitivity of the neural network to the scale of the variable in the prediction problem and the influence of the performance of the neural network model on the scale of the variable, and simultaneously to improve the training efficiency of the neural network, a plurality of subsequences obtained after reconstruction are respectively normalized, and each subsequence is converted into zero-one interval data.
And 5, taking the zero-one interval data as an input layer of the BP neural network, training the neural network, and outputting prediction data when the training error is smaller than a preset error.
Firstly, initializing a BP neural network, selecting proper learning parameters, and setting a reasonable target error as a preset error.
And then, taking the zero-one interval data obtained after normalization as an input layer of the BP neural network, taking the prediction result of the effective monitoring data as an output layer, carrying out neural network training, and stopping training when the training error is smaller than a preset error to obtain the prediction result of the effective monitoring data, namely the prediction data.
Optionally, the BP neural network may be continuously optimized by adjusting the weight and the threshold of the BP network.
And S207, the cloud platform sends the prediction data to the edge computing node equipment.
And S208, the edge computing node equipment updates the monitoring data according to the prediction data.
The prediction data received by the edge computing node equipment is accurate data after noise removal and neural network training, and the monitoring data collected at the beginning is updated and stored by using the accurate data.
Optionally, the edge computing node device may determine the obtained prediction data, and send an alarm message to the user when the prediction data exceeds a preset threshold.
As a specific embodiment, the internet of things device in the smart city field can collect monitoring videos through city fine monitoring, the monitoring videos are sent to the edge computing device, the edge computing device performs adaptive data distribution and filtering on the monitoring videos, sends obtained effective monitoring video data to the cloud platform for noise removal and neural network training, receives returned prediction results, performs behavior trajectory analysis on people in the video data according to the prediction results, monitors caring people, performs labeling processing on people appearing in the videos through face recognition, and pushes warning information when people have abnormal behaviors according to the data analysis results, so that waste of human resources is reduced.
According to the data linkage method of the Internet of things based on the edge calculation, effective monitoring data are predicted by adopting the combined model of the wavelet function and the BP neural network, the accuracy of data prediction is improved, and the accuracy of a prediction result is ensured.
Fig. 3 is a schematic structural diagram of an internet of things data linkage device based on edge computing according to an embodiment of the present invention, which is used for an edge computing node device, and as shown in fig. 3, the multi-keyword ranking searchable encryption apparatus 300 may include: a sending module 310, a receiving module 320, a filtering module 330, and an updating module 340.
The sending module 310 is configured to send IP information of the edge computing node device to the internet of things device; the receiving module 320 is configured to receive monitoring data of the monitoring object sent by the internet of things device according to the IP information; the filtering module 330 is configured to filter the monitoring data according to the user requirement information to obtain effective monitoring data; the sending module 310 is further configured to send effective monitoring data to a cloud platform, where the effective monitoring data is used for the cloud platform to generate prediction data; the receiving module 320 is further configured to receive prediction data sent by the cloud platform; and an updating module 340 for updating the monitoring data according to the prediction data.
In some embodiments, the monitoring system further includes an alarm module, configured to send alarm information to a user when the monitoring data exceeds a preset threshold, where the alarm information is used to prompt that an abnormality occurs in the monitoring object within a preset monitoring range.
In some embodiments, the system further comprises a shunting module configured to: the edge computing node equipment comprises a plurality of edge computing nodes, and the edge computing node equipment determines a plurality of edge computing nodes capable of communicating according to the performance information; the edge computing node equipment carries out self-adaptive data distribution on the monitoring data and distributes the distributed monitoring data to a plurality of edge computing nodes capable of communicating.
The internet of things data linkage device based on the edge computing sends IP information of edge computing node equipment to the internet of things equipment; receiving monitoring data of a monitoring object sent by the Internet of things equipment according to the IP information; filtering the monitoring data according to the user demand information to obtain effective monitoring data; sending effective monitoring data to a cloud platform, wherein the effective monitoring data is used for the cloud platform to generate prediction data; receiving prediction data sent by a cloud platform; the monitoring data are updated according to the predicted data, the collected monitoring data can be effectively processed, the computing pressure of the edge computing node is reduced, and meanwhile the accuracy of the data is guaranteed.
Fig. 4 is a schematic structural diagram of another internet of things data linkage based on edge computing according to an embodiment of the present invention, which is used for an internet of things device, and as shown in fig. 4, the internet of things data linkage based on edge computing 400 may include: a collection module 410, a receiving module 420, and a sending module 430.
The collecting module 410 is configured to collect real-time data of a monitored object within a preset monitoring range to obtain monitoring data; a receiving module 420, configured to receive IP information sent by an edge computing node device; and a sending module 430, configured to send the monitoring data to the edge computing node device according to the IP information.
The internet of things data linkage device based on edge calculation obtains monitoring data by collecting real-time data of a monitoring object in a preset monitoring range; receiving IP information sent by edge computing node equipment; and monitoring data is sent to the edge computing node equipment according to the IP information, so that the monitoring data can be successfully sent to the edge computing node equipment, and the subsequent processing of the monitoring data by the edge computing node equipment is facilitated.
Fig. 5 is a schematic structural diagram of another edge-computing-based internet of things data linkage provided in an embodiment of the present invention, which is used for a cloud platform, and as shown in fig. 5, the edge-computing-based internet of things data linkage 500 may include: a receiving module 510, a determining module 520, and a transmitting module 530.
The receiving module 510 is configured to receive valid monitoring data sent by an edge computing node device; a determining module 520, configured to determine a wavelet function according to data characteristics of the effective monitoring data; the determining module 520 is further configured to determine prediction data of the effective monitoring data according to the wavelet function and the error back propagation algorithm BP neural network; a sending module 530 configured to send the prediction data to the edge computing node device.
In some embodiments, the determining module 520 is specifically configured to: determining the optimal decomposition scale of the wavelet function according to the Mean Square Error (MSE); decomposing a preset sample set and a prediction set respectively according to a Marait algorithm and an optimal decomposition scale to obtain a low-frequency sequence and a high-frequency sequence of the preset sample set and a low-frequency sequence and a high-frequency sequence of the prediction set, wherein the prediction set is used for storing effective monitoring data; reconstructing each low-frequency sequence and each high-frequency sequence according to a Malat algorithm to obtain a plurality of subsequences with the sequence length equal to that of the original sequence; normalizing the subsequence to obtain zero-one interval data; and taking the zero-one interval data as an input layer of the BP neural network, training the neural network, and outputting prediction data when the training error is smaller than a preset error.
In some embodiments, the apparatus further comprises an initialization module configured to initialize the BP neural network, and determine the preset error according to the learning parameter.
In some embodiments, the method further comprises adjusting the weight and the threshold of the BP network.
According to the internet of things data linkage device based on the edge computing, the effective monitoring data sent by the edge computing node equipment are received; determining a wavelet function according to the data characteristics of the effective monitoring data; determining prediction data of effective monitoring data according to a wavelet function and an error back propagation algorithm BP neural network; the prediction data are sent to the edge computing node equipment, so that the accuracy of data prediction can be improved, and the accuracy of a prediction result is ensured.
Fig. 6 is a schematic hardware structure diagram of an internet of things data linkage device based on edge computing according to an embodiment of the present invention.
As shown in fig. 6, the data linkage device 600 of the internet of things based on edge calculation in the embodiment includes an input device 601, an input interface 602, a central processor 603, a memory 604, an output interface 605, and an output device 606. The input interface 602, the central processing unit 603, the memory 604, and the output interface 605 are connected to each other via a bus 610, and the input device 601 and the output device 606 are connected to the bus 610 via the input interface 602 and the output interface 605, respectively, and further connected to other components of the information acquisition device 600.
Specifically, the input device 601 receives input information from the outside, and transmits the input information to the central processor 603 through the input interface 602; the central processor 603 processes input information based on computer-executable instructions stored in the memory 604 to generate output information, stores the output information temporarily or permanently in the memory 604, and then transmits the output information to the output device 606 through the output interface 605; the output device 606 outputs the output information to the outside of the information acquisition device 600 for use by the user.
In one embodiment, the internet of things data linkage device 600 based on edge calculation shown in fig. 6 includes: a memory 604 for storing programs; the processor 603 is configured to execute the program stored in the memory to perform the method according to the embodiment of the present invention shown in fig. 1 or fig. 2.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium has computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement the method of the embodiment of fig. 1 or fig. 2 provided by the embodiments of the present invention.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuits, semiconductor Memory devices, Read-Only memories (ROMs), flash memories, erasable ROMs (eroms), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.

Claims (13)

1. An Internet of things data linkage method based on edge computing is used for edge computing node equipment, and comprises the following steps:
sending the IP information of the edge computing node equipment to the Internet of things equipment;
receiving monitoring data of a monitoring object sent by the Internet of things equipment according to the IP information;
filtering the monitoring data according to the user demand information to obtain effective monitoring data;
sending the effective monitoring data to a cloud platform, wherein the effective monitoring data is used for the cloud platform to generate prediction data;
receiving the prediction data sent by the cloud platform;
updating the monitoring data according to the prediction data.
2. The method of claim 1, further comprising:
and when the monitoring data exceeds a preset threshold value, sending alarm information to the user, wherein the alarm information is used for prompting that the monitored object is abnormal in a preset monitoring range.
3. The method of claim 1, wherein before filtering the monitoring data according to the user's requirement to obtain valid monitoring data, the method further comprises:
the edge computing node equipment comprises a plurality of edge computing nodes, and the edge computing node equipment determines a plurality of edge computing nodes capable of communicating according to the performance information;
the edge computing node equipment performs adaptive data distribution on the monitoring data, and distributes the distributed monitoring data to the plurality of communicable edge computing nodes.
4. An Internet of things data linkage method based on edge computing is used for Internet of things equipment, and comprises the following steps:
collecting real-time data of a monitored object in a preset monitoring range to obtain monitoring data;
receiving IP information sent by edge computing node equipment;
and sending the monitoring data to the edge computing node equipment according to the IP information.
5. An Internet of things data linkage method based on edge computing is used for a cloud platform, and comprises the following steps:
receiving effective monitoring data sent by edge computing node equipment;
determining a wavelet function according to the data characteristics of the effective monitoring data;
determining prediction data of the effective monitoring data according to the wavelet function and an error back propagation algorithm BP neural network;
sending the prediction data to the edge computing node device.
6. The method of claim 5, wherein determining the prediction data of the valid monitoring data from the wavelet function and a BP neural network comprises:
determining the optimal decomposition scale of the wavelet function according to the Mean Square Error (MSE);
decomposing a preset sample set and a prediction set respectively according to a Marait algorithm and the optimal decomposition scale to obtain a low-frequency sequence and a high-frequency sequence of the preset sample set and a low-frequency sequence and a high-frequency sequence of the prediction set, wherein the prediction set is used for storing the effective monitoring data;
reconstructing each low-frequency sequence and each high-frequency sequence according to the Marait algorithm to obtain a plurality of subsequences with the sequence length equal to that of the original sequence;
normalizing the subsequence to obtain zero-one interval data;
and taking the zero-one interval data as an input layer of the BP neural network, training the neural network, and outputting prediction data when a training error is smaller than a preset error.
7. The method of claim 6, wherein before performing neural network training by using the zero-one interval data as an input layer of the BP neural network, and outputting prediction data when a training error is smaller than a preset error, the method further comprises:
and initializing the BP neural network, and determining the preset error according to the learning parameters.
8. The method of claim 6, further comprising:
and adjusting the weight value and the threshold value of the BP network.
9. An internet of things data linkage device based on edge computing, wherein the device is used for edge computing node equipment, and the device comprises:
the sending module is used for sending the IP information of the edge computing node equipment to the Internet of things equipment;
the receiving module is used for receiving monitoring data of the monitoring object sent by the Internet of things equipment according to the IP information;
the filtering module is used for filtering the monitoring data according to the user demand information to obtain effective monitoring data;
the sending module is further configured to send the valid monitoring data to a cloud platform, where the valid monitoring data is used for the cloud platform to generate prediction data;
the receiving module is further configured to receive the prediction data sent by the cloud platform;
and the updating module is used for updating the monitoring data according to the prediction data.
10. An internet of things data linkage device based on edge computing, the device being used for internet of things equipment, the device comprising:
the collection module is used for collecting real-time data of a monitored object in a preset monitoring range to obtain monitoring data;
the receiving module is used for receiving the IP information sent by the edge computing node equipment;
and the sending module is used for sending the monitoring data to the edge computing node equipment according to the IP information.
11. An internet of things data linkage device based on edge computing, the device being used for a cloud platform, the device comprising:
the receiving module is used for receiving effective monitoring data sent by the edge computing node equipment;
the determining module is used for determining a wavelet function according to the data characteristics of the effective monitoring data;
the determining module is further used for determining the prediction data of the effective monitoring data according to the wavelet function and an error back propagation algorithm BP neural network;
a sending module, configured to send the prediction data to the edge computing node device.
12. An internet of things data linkage device based on edge computing, the device comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer instructions, implements the method for linking data of internet of things based on edge computing according to any one of claims 1 to 8.
13. A computer-readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method for linking data of internet of things based on edge computing according to any one of claims 1 to 8.
CN202010184966.0A 2020-03-17 2020-03-17 Internet of things data linkage method, device, equipment and medium based on edge calculation Pending CN113411366A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010184966.0A CN113411366A (en) 2020-03-17 2020-03-17 Internet of things data linkage method, device, equipment and medium based on edge calculation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010184966.0A CN113411366A (en) 2020-03-17 2020-03-17 Internet of things data linkage method, device, equipment and medium based on edge calculation

Publications (1)

Publication Number Publication Date
CN113411366A true CN113411366A (en) 2021-09-17

Family

ID=77677002

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010184966.0A Pending CN113411366A (en) 2020-03-17 2020-03-17 Internet of things data linkage method, device, equipment and medium based on edge calculation

Country Status (1)

Country Link
CN (1) CN113411366A (en)

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542133A (en) * 2010-12-10 2012-07-04 中国科学院深圳先进技术研究院 Short-time wind speed forecasting method and system for wind power plant
CN102609766A (en) * 2012-02-17 2012-07-25 中南大学 Method for intelligently forecasting wind speed in wind power station
CN108171259A (en) * 2017-12-13 2018-06-15 南京理工大学 A kind of wisdom tip water quality monitoring system and method based on NB-IoT
CN108198447A (en) * 2018-01-17 2018-06-22 佛山杰致信息科技有限公司 Driver information alarm set and system based on vehicle flowrate prediction
CN108881475A (en) * 2018-07-12 2018-11-23 重庆市特种设备检测研究院 A kind of Industrial Boiler intelligent Data Acquisition System and acquisition method
CN109714431A (en) * 2019-01-16 2019-05-03 西安中星测控有限公司 A kind of edge calculations method and apparatus of Internet of Things intelligence sensor
CN109765863A (en) * 2019-01-21 2019-05-17 苏州首拓信息科技有限公司 A kind of device parameter edge calculations method based on cloud platform
CN109951574A (en) * 2019-04-23 2019-06-28 广州市技安电子科技有限公司 Internet of things equipment interlock method and system based on edge calculations
CN110336703A (en) * 2019-07-12 2019-10-15 河海大学常州校区 Industrial big data based on edge calculations monitors system
CN110440396A (en) * 2019-07-11 2019-11-12 雄安达实智慧科技有限公司 The central air-conditioning global optimization energy-saving control method and system of cloud side end collaboration
CN110602723A (en) * 2019-08-27 2019-12-20 华侨大学 Two-stage bidirectional prediction data acquisition method based on underwater edge equipment
CN110609512A (en) * 2019-09-25 2019-12-24 新奥（中国）燃气投资有限公司 Internet of things platform and Internet of things equipment monitoring method
US20200027009A1 (en) * 2018-07-23 2020-01-23 Kabushiki Kaisha Toshiba Device and method for optimising model performance
CN110730245A (en) * 2019-10-22 2020-01-24 青岛农业大学 Neural network based edge computing system and method
CN110807905A (en) * 2019-10-23 2020-02-18 北方工业大学 Community fire monitoring system based on end-edge-cloud architecture

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542133A (en) * 2010-12-10 2012-07-04 中国科学院深圳先进技术研究院 Short-time wind speed forecasting method and system for wind power plant
CN102609766A (en) * 2012-02-17 2012-07-25 中南大学 Method for intelligently forecasting wind speed in wind power station
CN108171259A (en) * 2017-12-13 2018-06-15 南京理工大学 A kind of wisdom tip water quality monitoring system and method based on NB-IoT
CN108198447A (en) * 2018-01-17 2018-06-22 佛山杰致信息科技有限公司 Driver information alarm set and system based on vehicle flowrate prediction
CN108881475A (en) * 2018-07-12 2018-11-23 重庆市特种设备检测研究院 A kind of Industrial Boiler intelligent Data Acquisition System and acquisition method
US20200027009A1 (en) * 2018-07-23 2020-01-23 Kabushiki Kaisha Toshiba Device and method for optimising model performance
CN109714431A (en) * 2019-01-16 2019-05-03 西安中星测控有限公司 A kind of edge calculations method and apparatus of Internet of Things intelligence sensor
CN109765863A (en) * 2019-01-21 2019-05-17 苏州首拓信息科技有限公司 A kind of device parameter edge calculations method based on cloud platform
CN109951574A (en) * 2019-04-23 2019-06-28 广州市技安电子科技有限公司 Internet of things equipment interlock method and system based on edge calculations
CN110440396A (en) * 2019-07-11 2019-11-12 雄安达实智慧科技有限公司 The central air-conditioning global optimization energy-saving control method and system of cloud side end collaboration
CN110336703A (en) * 2019-07-12 2019-10-15 河海大学常州校区 Industrial big data based on edge calculations monitors system
CN110602723A (en) * 2019-08-27 2019-12-20 华侨大学 Two-stage bidirectional prediction data acquisition method based on underwater edge equipment
CN110609512A (en) * 2019-09-25 2019-12-24 新奥（中国）燃气投资有限公司 Internet of things platform and Internet of things equipment monitoring method
CN110730245A (en) * 2019-10-22 2020-01-24 青岛农业大学 Neural network based edge computing system and method
CN110807905A (en) * 2019-10-23 2020-02-18 北方工业大学 Community fire monitoring system based on end-edge-cloud architecture

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
王小川等: "小波神经网络的时间序列预测", 《MATLAB神经网络43个案例分析》, pages 279 - 280 *
赵海涛等: "基于深度学习的车联边缘网络交通事故风险预测算法研究", 《电子与信息学报》 *
赵海涛等: "基于深度学习的车联边缘网络交通事故风险预测算法研究", 《电子与信息学报》, no. 01, 15 January 2020 (2020-01-15) *

Similar Documents

Publication Publication Date Title
CN111928888B (en) Intelligent monitoring and analyzing method and system for water pollution
CN110874550A (en) Data processing method, device, equipment and system
CN105553442B (en) The H of network-based Lipschitz nonlinear system∞Filter information processing method
CN117579101B (en) Control method and system for carrier communication module
CN116684878B (en) 5G information transmission data safety monitoring system
CN113111115A (en) Data information management system and method thereof
CN114140710A (en) Monitoring data transmission method and system based on data processing
CN116248674A (en) Data transmission method, device and system
Balaji et al. NeuroCAN: Contextual anomaly detection in controller area networks
CN111901134B (en) Method and device for predicting network quality based on recurrent neural network model (RNN)
CN117729540A (en) Perception equipment cloud edge safety control method based on unified edge computing framework
CN113589729A (en) Intelligent building automatic control method and device
CN113411366A (en) Internet of things data linkage method, device, equipment and medium based on edge calculation
Pianegiani et al. Energy-efficient signal classification in ad hoc wireless sensor networks
CN116720062A (en) Intelligent satellite signal monitoring and identifying method and device
Wu et al. VHF radio signal modulation classification based on convolution neural networks
CN116318856A (en) Model parameter optimization method and system based on differential privacy and federal learning
CN114170560A (en) Multi-device edge video analysis system based on deep reinforcement learning
CN115731616A (en) Human body posture identification method based on Wi-Fi correlation imaging
CN111783804B (en) Abnormal ticket determining method, device, equipment and storage medium
CN114979214A (en) Intelligent cooperative alarm system, method and device for power transmission line
CN109003254B (en) Method, device, equipment, system and medium for detecting icing based on logistic regression
CN105792281A (en) Intelligent fire hydrant terminal data transmission method and system
CN111988252A (en) Signal modulation mode identification method based on deep learning
Rusu et al. On the design of an acoustic based wildlife intruder detection system

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210917

RJ01 Rejection of invention patent application after publication