CN112614293B - Electric power Internet of things safety early warning method and system based on edge calculation - Google Patents
Electric power Internet of things safety early warning method and system based on edge calculation Download PDFInfo
- Publication number
- CN112614293B CN112614293B CN202011398460.6A CN202011398460A CN112614293B CN 112614293 B CN112614293 B CN 112614293B CN 202011398460 A CN202011398460 A CN 202011398460A CN 112614293 B CN112614293 B CN 112614293B
- Authority
- CN
- China
- Prior art keywords
- early warning
- network
- unit
- risk
- data
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y30/00—IoT infrastructure
- G16Y30/10—Security thereof
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a safety early warning method and a safety early warning system for an electric power internet of things based on edge calculation, wherein the safety early warning method comprises the steps of monitoring environmental data information of equipment of the electric power internet of things; dividing risk areas according to weather early warning levels and setting thresholds of risk level sensors; the exclusive channel transmission of the data information is realized by utilizing the network slice; and performing edge processing on the data information, comparing a threshold value and judging whether to send out an early warning signal or not. Dynamic scheduling is realized by three-level progressive layering, network slice transmission is carried out as required, congestion of a transmission network and overtime of early warning are avoided, the threshold is diversified by adding an image threshold and a non-image threshold, early warning misinformation and missing report caused by a single threshold are avoided, and early warning accuracy is improved.
Description
Technical Field
The invention relates to the technical field of electric power internet of things safety early warning, in particular to an electric power internet of things safety early warning method and system based on edge calculation.
Background
Nowadays, the electric power thing networking has realized that everything links to each other, has brought many facilities for production and life, and the electric power thing networking is because self sensor is numerous, and the equipment and the circuit of monitoring are numerous, and abnormal conditions and incident can appear in sensor equipment or other electric power thing networking devices sometimes. The safety problem of conflagration is caused because of accidents such as fault short circuit to electric power thing networking equipment is considered in this patent, proposes electric power thing networking safety precaution method and system based on edge calculation, and the very first time early warning before the emergence of conflagration or when taking place can reduce the damage of conflagration to power equipment, and the loss of production and life outage illumination is avoided the conflagration to personnel to the at utmost.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and title of the application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The invention is provided in view of the problems that the prior fire early warning is easy to miss the report and delay.
Therefore, the technical problem solved by the invention is as follows: the existing fire early warning sensor is classified disorderly and lacks detailed analysis, the threshold values of the sensor are the same under various environments, so that the threshold values are too single plates, false alarm and missed alarm conditions are easy to occur, network congestion possibly occurs by adopting wireless network transmission in the traditional fire early warning, the fire early warning is delayed, and the congestion of a data transmission network is easily caused by all-weather starting of all perceptions.
In order to solve the technical problems, the invention provides the following technical scheme: monitoring environmental data information of the power Internet of things equipment; dividing risk areas according to weather early warning levels and setting thresholds of risk level sensors; the exclusive channel transmission of the data information is realized by utilizing the network slice; and performing edge processing on the data information, comparing a threshold value and judging whether to send out an early warning signal or not.
As a preferred scheme of the electric power Internet of things safety early warning method based on edge calculation, the method comprises the following steps: monitoring electric power thing networking equipment environmental data includes, carries out the monitoring of data through tertiary mode that advances one-level, and wherein the one-level monitoring utilizes one-level sensor to carry out accurate monitoring to real-time temperature and its temperature trend, and the second grade monitoring utilizes the second grade sensor to carry out accurate monitoring to particulate matter and carbon monoxide gas in the dense smoke when the conflagration is in the smoldering state, and tertiary monitoring utilizes tertiary sensor to electric arc, and open flame takes place to carry out accurate monitoring.
As a preferred scheme of the electric power Internet of things safety early warning method based on edge calculation, the method comprises the following steps: the risk area division comprises the step of dividing the area into low risk areas if the weather early warning of the weather station of the area is yellow or blue early warning or no weather early warning; if the weather early warning of the weather station in the area is an orange early warning, dividing the area into medium risk areas; and if the weather early warning of the weather station in the area is a red early warning, dividing the area into high-risk areas.
As an optimal scheme of the electric power internet of things safety early warning method based on edge calculation, the method comprises the following steps: setting the threshold values of all the areas comprises setting image threshold values and non-image threshold values, wherein the non-image data threshold values are the threshold values of historical data, the threshold values have the advantages of early warning sensitivity, low false alarm rate and low missing report rate, and the factory theoretical safety values of all the equipment form an expert threshold value library; and setting the threshold value of the image class by using a trained convolutional neural network.
As an optimal scheme of the electric power internet of things safety early warning method based on edge calculation, the method comprises the following steps: the method for realizing the exclusive channel transmission of the data information by using the network slice comprises the steps of carrying out network resource statistics according to the requirements of high, medium and low risk areas, carrying out initial configuration on the network slice by analyzing and processing comprehensive data, analyzing the requirements of the three risk areas by using a multi-attribute decision model in a configuration method, and quantifying the requirements of the risk areas to realize the resource initialization configuration of the network slice; the network resource statistics is divided into three parts, namely access resources of an access network, transmission resources of a bearer network and network element resources of a core network.
As an optimal scheme of the electric power internet of things safety early warning method based on edge calculation, the method comprises the following steps: and performing edge processing on the data information, judging whether to send out an early warning signal or not, identifying the sensor level of the data information, comparing risk areas with the threshold value of each area, and sending out an early warning and scheduling the sensor if the data exceeds the threshold value.
As a preferred scheme of the electric power Internet of things safety early warning method based on edge calculation, the method comprises the following steps: the early warning and the dispatching of the sensors comprise the steps of dividing data into a fire early warning, an emergency early warning and a danger early warning, wherein the fire early warning is that the data of one primary or secondary sensor exceeds a threshold value, the emergency early warning is that the data of two primary or secondary sensors exceeds the threshold value, and the danger early warning is that the data of one or more tertiary sensors and one or more primary or secondary sensors exceed the threshold value; if the fire early warning is judged, the first-stage sensor, the second-stage sensor and the third-stage sensor are all started at the same time from time-sharing, if the emergency early warning is judged, the first-stage sensor and the second-stage sensor are all started at the same time from time-sharing, the third-stage sensor continues to keep the time-sharing starting state, if the danger early warning is judged, the first-stage sensor is started at the time-sharing mode to simultaneously start all the sensors in the area, and the second-stage sensor and the third-stage sensor continue to keep the time-sharing starting state.
As an optimal scheme of the electric power internet of things safety early warning system based on edge computing, the system comprises: the sensing module is used for monitoring environmental data information of the power Internet of things equipment and comprises a primary sensing unit, a secondary sensing unit and a tertiary sensing unit; the 5G network transmission module is connected with the sensing module and used for deploying network slices according to different actual requirements of risk areas and ensuring the transmission of data of each risk area when the network is jammed, and comprises a requirement management unit, a network resource counting unit, a network slice configuration dynamic updating unit and a network transmission quality evaluation unit; the threshold management module is used for dividing risk areas and setting thresholds, and comprises three layers of risk area dividing units and threshold setting units, wherein the three layers of risk area dividing units divide the risk areas into three layers of risk areas according to weather early warning information of a local weather station; the threshold setting unit is connected with the three-layer risk area dividing unit, and the threshold of each level of risk area is set according to the expert threshold library and the trained convolutional neural network; the edge calculation module is connected with the network transmission module and the threshold management module and used for processing data and comprises a function unit, an early warning unit, a scheduling unit and a slice sinking unit.
As an optimal scheme of the electric power internet of things safety early warning system based on edge computing, the system comprises: the network transmission module comprises a demand management unit, a network resource statistical unit, a network slice configuration dynamic updating unit and a network slice configuration unit, wherein the demand management unit is used for analyzing and processing demands according to differences of broadband demands, the network resource statistical unit is used for counting residual resources of access network access resources, bearer network transmission resources and core network element resources, the network slice configuration unit is connected with the demand management unit and the network resource statistical unit and is used for analyzing and quantifying the demands of three risk zones to realize the initial configuration of the network resource statistical unit, the network slice configuration dynamic updating unit is connected with the network slice configuration unit and is used for dynamically updating the network slice configuration, and the configured slices are used for three types of risk zones, wherein the slices used for transmitting high risk zone data are high risk zone slices, and the slices used for transmitting medium risk zone data are medium risk zone slices, the slice for transmitting the low risk area data is a low risk area slice, and the network transmission quality evaluation unit is connected to the network slice configuration dynamic update unit and is used for evaluating the early warning state and the network transmission speed.
As an optimal scheme of the electric power internet of things safety early warning system based on edge computing, the system comprises: the edge calculation module comprises a functional unit, wherein the functional unit is used for designing high, medium and low priorities to reasonably distribute calculation resources of an emergency server, the ignition early warning corresponds to the high priority, the emergency early warning corresponds to the medium priority, the danger early warning corresponds to the low priority, the early warning unit is connected with the functional unit and used for dividing the ignition early warning, the emergency early warning and the danger early warning, a scheduling unit is connected with the early warning unit and used for scheduling a primary sensing unit, a secondary sensing unit and a tertiary sensing unit in the sensing module according to the classification of the early warning unit, and a section sinking unit is connected with the functional unit sinks data in each area to different network accessories respectively to carry out edge calculation processing.
The invention has the beneficial effects that: dynamic scheduling is realized by three-level progressive layering, network slice transmission is carried out as required, congestion of a transmission network and overtime of early warning are avoided, an image threshold and a non-image threshold are added to enable the thresholds to be diversified, early warning misinformation and missing report caused by a single threshold are avoided, and early warning accuracy is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flow chart of a safety warning method for an electric power internet of things based on edge computing according to a first embodiment of the present invention;
fig. 2 is a general framework diagram of an electric power internet of things security early warning system based on edge computing according to a second embodiment of the present invention;
fig. 3 is a sensing module sub-block diagram of an electric power internet of things security early warning system based on edge computing according to a second embodiment of the present invention;
fig. 4 is a sub-block diagram of a 5G network transmission module of an electric power internet of things safety warning system based on edge computing according to a second embodiment of the present invention;
fig. 5 is a sub-block diagram of a threshold management module of an electric power internet of things safety warning system based on edge computing according to a second embodiment of the present invention;
fig. 6 is a block diagram of an edge computing module of an electric power internet of things security early warning system based on edge computing according to a second embodiment of the present invention;
fig. 7 is a schematic system flow diagram of an electric power internet of things safety warning system based on edge computing according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, embodiments accompanying figures of the present invention are described in detail below, and it is apparent that the described embodiments are a part, not all or all of the embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, the references herein to "one embodiment" or "an embodiment" refer to a particular feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not necessarily enlarged to scale, and are merely exemplary, which should not limit the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected" and "connected" in the present invention are to be construed broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides an electric power internet of things security early warning method based on edge computing, including:
s1: monitoring environmental data information of the electric power Internet of things equipment. In which it is to be noted that,
monitoring electric power thing networking equipment environmental data information includes, carries out the monitoring of data through the mode that the tertiary advances one-level, and wherein the one-level monitoring utilizes one-level sensor to carry out accurate monitoring to real-time temperature and its temperature trend, and the second grade monitoring utilizes the second grade sensor to carry out accurate monitoring to particulate matter and carbon monoxide gas in the dense smoke when the conflagration is in the smoldering state, and tertiary monitoring utilizes tertiary sensor to electric arc, takes place to open flame and carries out accurate monitoring.
S2: and dividing risk areas according to the weather early warning levels and setting thresholds of the risk level sensors. In which it is to be noted that,
the risk area division comprises that the judgment standard of judging high, medium and low risk areas is weather early warning according to a local weather station, and if the area is yellow and blue early warning or no weather early warning, the area is a low risk area; if the area is an orange early warning area, the area is a medium risk area; if the area is a red early warning area, the area is a high risk area; setting thresholds of each area, namely setting image thresholds and non-image thresholds, wherein the non-image data thresholds are thresholds of historical data, and the thresholds are thresholds of a type which has sensitive early warning, low false alarm rate and low missing report rate, and factory theoretical safety values of each device and constitute an expert threshold library; and setting the threshold value of the image class by using a trained convolutional neural network.
Further, the dividing of the risk region may further include dividing the data information into static factor information and dynamic factor information, after normalization, the principal component analysis method is adopted to distribute the weight and calculate the risk factors of different risk areas to obtain quantitative data, and finally, the risk areas are evaluated according to the comprehensive evaluation of real-time dynamic data and static data, namely high risk areas, medium risk areas and low risk areas, wherein the normalization is to classify according to the fire firing reasons in the fire of the historical power equipment, the ambient real-time temperature, the ambient real-time landform environment, the ambient real-time weather condition, the overload condition of the power grid equipment, the existence of an external fire source and the density of the equipment, normalizing according to the proportion of the times of the fires caused by various reasons to the total times of the fires, and whether the specific gravity is adjusted by manual intervention is judged by considering the outage area and the economic loss after the fire disaster occurs.
Furthermore, the trained convolutional neural network is used for obtaining an image threshold, firstly, the convolutional neural network comprising an input layer, a convolutional layer, a pooling layer, a full-link layer and an output layer needs to be established, a large amount of two-dimensional data of the historical image is used as sample input for training the convolutional neural network to obtain the trained convolutional neural network, fire visual recognition is carried out on the trained convolutional neural network, images in a flame shape and an electric arc shape are recognized, and the threshold is set; wherein the thresholds are set as follows: setting A, B, C, D, E, F and G as the general names of thresholds of a temperature sensor, a voltage sensor, a current sensor, a smoke sensor, a carbon monoxide sensor, a video monitoring sensor and a thermal imaging sensor, and obtaining the threshold of the temperature sensor of which A1 is a high risk area, the threshold of the temperature sensor of which A2 is a medium risk area and the threshold of the temperature sensor of which A3 is a low risk area by an expert threshold library and a trained convolutional neural network; b1 is the voltage sensor threshold for the high risk zone, B2 is the voltage sensor threshold for the medium risk zone, B3 is the voltage sensor threshold for the low risk zone; c1 is the current sensor threshold for the high risk zone, C2 is the current sensor threshold for the medium risk zone, C3 is the current sensor threshold for the low risk zone; d1 is the smoke sensor threshold for the high risk zone, D2 is the smoke sensor threshold for the medium risk zone, D3 is the smoke sensor threshold for the low risk zone; e1 is the carbon monoxide sensor threshold for the high risk zone, E2 is the carbon monoxide sensor threshold for the medium risk zone, E3 is the carbon monoxide sensor threshold for the low risk zone; f1 is the video monitoring sensor threshold of the high risk area, F2 is the video monitoring sensor threshold of the medium risk area, and F3 is the video monitoring sensor threshold of the low risk area; g1 is the thermal imaging sensor threshold for the high risk zone, G2 is the thermal imaging sensor threshold for the medium risk zone, and G3 is the thermal imaging sensor threshold for the low risk zone.
S3: and the exclusive channel transmission of the data information is realized by utilizing the network slice. In which it is to be noted that,
the method for realizing the exclusive channel transmission of the data information by using the network slice comprises the steps of carrying out network resource statistics according to the requirements of high, medium and low risk areas, carrying out initial configuration on the network slice by analyzing and processing comprehensive data, analyzing the requirements of the three risk areas by using a multi-attribute decision model in the configuration method, and quantifying the requirements of the risk areas to realize the resource initialization configuration of the network slice; the network resource calculation is divided into three parts, namely an access network for accessing resources, a bearer network for transmitting resources and a core network element resource for performing resource calculation.
Furthermore, the network resources are currently available and obtained through network resource calculation, and a large amount of data information is generated when the environmental data is detected, so that network congestion is likely to be caused, and therefore, the resource calculation is performed to generate a network slicing service, the network congestion phenomenon is further reduced, and early warning delay caused by the situations of network congestion and the like of early warning signals is avoided.
S4: and performing edge processing on the data information, comparing a threshold value and judging whether to send out an early warning signal or not. In which it is to be noted that,
and performing edge processing on the data information, judging whether to send out an early warning signal, identifying the sensor level of the data information, identifying the risk area, comparing the risk area with the threshold value of each area, and if the data exceeds the threshold value, sending out an early warning and scheduling the sensor. The early warning and the dispatching of the sensors comprise the steps of dividing data into a fire early warning, an emergency early warning and a danger early warning, wherein the fire early warning is that the data of one primary or secondary sensor exceeds a threshold value, the emergency early warning is that the data of two primary or secondary sensors exceeds the threshold value, and the danger early warning is that the data of one or more tertiary sensors and one or more primary or secondary sensors exceed the threshold value; if the fire early warning is judged, a first sensor, a second sensor and a third sensor are started in a time-sharing mode and are all started simultaneously, if the fire early warning is judged to be emergency early warning, the first sensor is started in the time-sharing mode, the second sensor is started in the time-sharing mode and are all started simultaneously, the third sensor continues to be in a time-sharing starting state, if the fire early warning is judged to be danger early warning, the first sensor is started in the time-sharing mode and is all sensors in the area are started simultaneously, and the second sensor and the third sensor continue to be in the time-sharing starting state.
It should be further noted that the network propagation communication mode used in the method of the present invention is 5G network, and the 5G network has the characteristics of "high speed, high capacity, high reliability, low time delay and low energy consumption", further improving the accuracy of the early warning, reducing the early warning time,
in order to better verify and explain the technical effects adopted in the method of the present invention, in the embodiment, a mobile remote power monitoring system and a monitoring method based on a 4G network are selected for testing, and the test results are compared by means of scientific demonstration to verify the real effects of the method.
The invention relates to an electric power Internet of things safety early warning method based on edge calculation, which selects three groups of experimental groups with different equipment numbers for verification, wherein the equipment number of a group I is 0.1 ten thousand, the equipment number of a group II is 1 ten thousand, and the equipment number of a group III is 10 ten thousand, wherein a traditional mobile remote electric power monitoring system and a monitoring method based on a 4G network are used for filtering and analyzing data by acquiring data and transmitting the data by using the 4G network so as to achieve the monitoring purpose, the method acquires the data in a three-level progressive mode and uses a network slice and a 5G network to realize the data transmission and set threshold values of two aspects of images and non-images so as to achieve the effects of early warning speed and accuracy, and randomly selects 30 equipment in the experimental groups during the experiment to simulate three conditions of no open fire of a small amount of smoke, medium smoke and fire of the smoke and large amount of the smoke and the open fire, the fire warning time was measured by two methods, and the results are shown in table 1 below:
table 1: and (5) fire early warning experimental results.
As can be seen from Table 1, when the traditional 4G network method is used for early warning, the propagation rates of the early warnings of different numbers of devices are all about 15Mb/s, and the early warning time is about 30ms, but by using the method provided by the invention, the network propagation speed is nearly 96Mb/s, which is ten times that of the traditional method, and the time used by the method provided by the invention is 1-2 ms, which is 1/30 of the traditional method, so that the early warning rate can be effectively improved by using the method provided by the invention, and real-time early warning is realized to avoid loss.
Example 2
Referring to fig. 2 to 7, a second embodiment of the present invention is different from the first embodiment in that the second embodiment provides an electric power internet of things security early warning system based on edge computing, which includes a sensing module 100, a network transmission module 200, a threshold management module 300, and an edge computing module 400, where the sensing module 100 is configured to monitor environmental data information of an electric power internet of things device, and includes a primary sensing unit 101, a secondary sensing unit 102, and a tertiary sensing unit 103; the 5G network transmission module 200 is connected to the sensing module 100, and is configured to perform network slice deployment according to different actual requirements of risk areas, and ensure transmission of data in each risk area when a network is congested, and includes a requirement management unit 201, a network resource statistics unit 202, a network slice configuration unit 203, a network slice configuration dynamic update unit 204, and a network transmission quality evaluation unit 205; the threshold management module 300 is configured to divide risk areas and set thresholds, and includes a three-layer risk area dividing unit 301 and a threshold setting unit 302, where the three-layer risk area dividing unit 301 divides the risk areas into three layers according to weather warning information of a local weather station; the threshold setting unit 302 is connected to the three-layer risk area dividing unit 301, and the threshold of each level of risk area is set according to an expert threshold library and a trained convolutional neural network; the edge calculation module 400 is connected to the network transmission module 200 and the threshold management module 300, and is configured to process data, and includes a function unit 401, an early warning unit 402, a scheduling unit 403, and a slice sinking unit 404.
Further, the network transmission module 200 includes a requirement management unit 201 for analyzing and processing requirements according to differences of broadband requirements, a network resource statistics unit 202 for accessing resources of an access network, carrying network transmission resources, and calculating currently remaining resources by a core network, a network slice configuration unit 203 connected to the requirement management unit 201 and the network resource statistics unit 202 for analyzing and quantifying the requirements of three risk areas to implement initialization configuration of the network resource statistics unit 202, a network slice configuration dynamic update unit 204 connected to the network slice configuration unit 203 for dynamically updating network slice configuration and using configured slices for three types of risk areas, where a slice for transmitting high risk area data is a high risk area slice, a slice for transmitting middle risk area data is a middle risk area slice, the slice for transmitting the low risk area data is a low risk area slice, and the network transmission quality evaluation unit 205 is connected to the network slice configuration dynamic update unit 204 and is used for evaluating the early warning state and the network transmission speed.
The edge calculation module 400 includes a functional unit 401 configured to reasonably allocate high, medium, and low priorities for emergency data, wherein the fire warning corresponds to a high priority, the emergency warning corresponds to a medium priority, and the danger warning corresponds to a low priority, the warning unit 402 is connected to the functional unit 401, and is configured to divide the fire warning, the emergency warning, and the danger warning, a scheduling unit 403 is connected to the warning unit 402, and schedules the first level sensing unit 101, the second level sensing unit 102, and the third level sensing unit 103 in the sensing module 100 according to the classification of the warning unit, and a slice sinking unit 404 is connected to the functional unit 401 to sink data of each area to different network accessories respectively for edge calculation processing.
It should be recognized that embodiments of the present invention can be realized and implemented in computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable connection, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, or the like. Aspects of the invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated onto a computing platform, such as a hard disk, optically read and/or write storage media, RAM, ROM, etc., so that it is readable by a programmable computer, which when read by the computer can be used to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (4)
1. An electric power Internet of things safety early warning method based on edge calculation is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
monitoring environmental data information of the power Internet of things equipment;
the monitoring of the environmental data information of the power Internet of things equipment comprises the steps of,
monitoring data in a three-level progressive mode, wherein the first-level monitoring utilizes a first-level sensor to accurately monitor real-time temperature and temperature trend thereof, the second-level monitoring utilizes a second-level sensor to accurately monitor particles and carbon monoxide gas in the dense smoke when a fire disaster is in a smoldering state, and the third-level monitoring utilizes a third-level sensor to accurately monitor electric arcs and open fire;
dividing risk areas according to weather early warning levels and setting threshold values of all risk level sensors;
the making of the division into the risk zones comprises,
if the weather early warning of the weather station of the area is yellow or blue early warning or no weather early warning, dividing the area into low-risk areas; if the weather early warning of the weather station in the area is an orange early warning, the area is divided into a medium risk area; if the weather early warning of the regional weather station is a red early warning, dividing the region into high-risk regions;
and the threshold values of the respective regions are set including,
setting image and non-image threshold values, wherein the non-image threshold value is a threshold value of historical data, and has the advantages of early warning sensitivity, low false alarm rate and low missing report rate, and factory theoretical safety values of all equipment are combined to form an expert threshold value library; setting a threshold value by using a trained convolutional neural network for the image threshold value;
the exclusive channel transmission of the data information is realized by utilizing the network slice;
performing edge processing on the data information, comparing a threshold value and judging whether to send out an early warning signal or not;
the utilizing network slices to enable dedicated channel transmission of the data information includes,
network resource statistics is carried out according to the requirements of high, medium and low risk areas, initial configuration of network slices is carried out by analyzing and processing comprehensive data, the configuration method adopts a multi-attribute decision-making model to analyze the requirements of the three risk areas, and the requirements of the risk areas are quantized to realize the resource initialization configuration of the network slices; the network resource statistics is divided into three parts, namely access network access resources, bearer network bearer resources and residual resources of core network element resources are counted;
the data information is processed by edge processing and whether an early warning signal is sent out or not is judged,
according to the sensor level for identifying the data information, corresponding to the risk area level and comparing with a threshold corresponding to the risk level and the sensor type, if the data exceeds the threshold, sending out early warning and scheduling the sensor;
the early warning and the scheduling of the sensors comprise,
dividing data into three types of fire early warning, emergency early warning and danger early warning, wherein the fire early warning is that data of one primary or secondary sensor exceeds a threshold value, the emergency early warning is that data of two primary or secondary sensors exceeds the threshold value, and the danger early warning is that data of one or more than one tertiary sensors and one or more than one primary or secondary sensors exceed the threshold value; if the fire is judged to be early-warning, the first-stage sensor, the second-stage sensor and the third-stage sensor are enabled to be started at the same time from time-sharing, if the fire is judged to be early-warning, the first-stage sensor and the second-stage sensor are enabled to be started at the same time from time-sharing, the third-stage sensor continues to be in a time-sharing starting state, if the fire is judged to be early-warning, the first-stage sensor is enabled to be started at the same time from time-sharing, and the second-stage sensor and the third-stage sensor continue to be in a time-sharing starting state.
2. The utility model provides an electric power thing networking safety precaution system based on edge calculation which characterized in that: comprises the steps of (a) preparing a substrate,
the sensing module (100) is used for monitoring environmental data information of the power Internet of things equipment and comprises a primary sensing unit (101), a secondary sensing unit (102) and a tertiary sensing unit (103);
the 5G network transmission module (200) is connected with the perception module (100) and is used for deploying network slices according to different actual demands of risk areas and guaranteeing transmission of data of each risk area when a network is congested, and the network transmission module comprises a demand management unit (201), a network resource counting unit (202), a network slice configuration unit (203), a network slice configuration dynamic updating unit (204) and a network transmission quality evaluation unit (205);
the threshold management module (300) is used for dividing risk areas and setting thresholds, and comprises a three-layer risk area dividing unit (301) and a threshold setting unit (302), wherein the three-layer risk area dividing unit (301) divides the risk areas into three layers according to weather early warning information of a local weather station; the threshold setting unit (302) is connected with the three-layer risk area dividing unit (301), and the threshold of each level of risk area is set according to the expert threshold library and the trained convolutional neural network;
the edge calculation module (400) is connected with the network transmission module (200) and the threshold management module (300) and is used for processing data, and comprises a function unit (401), an early warning unit (402), a scheduling unit (403) and a slice sinking unit (404).
3. The electric power internet of things safety precaution system based on edge computing of claim 2, characterized in that: the network transmission module (200) comprises,
the demand management unit (201) is configured to analyze and process demands according to differences of broadband demands, the network resource statistics unit (202) is configured to perform statistics on access network access resources, bearer network transmission resources, and remaining resources of core network element resources, the network slice configuration unit (203) is connected to the demand management unit (201) and the network resource statistics unit (202) and is configured to analyze and quantify demands of three risk zones to implement initial configuration of the network resource statistics unit (202), the network slice configuration dynamic update unit (204) is connected to the network slice configuration unit (203) and is configured to dynamically update network slice configuration and use the configured slices in three types of risk zones, where a slice for transmitting high risk zone data is a high risk zone slice and a slice for transmitting medium risk zone data is a medium risk zone slice, the slice for transmitting the low risk area data is a low risk area slice, and the network transmission quality evaluation unit (205) is connected to the network slice configuration dynamic update unit (204) and used for evaluating the early warning state and the network transmission speed.
4. The electric power internet of things safety precaution system based on edge computing of claim 2 or 3, characterized by: the edge calculation module (400) comprises,
the system comprises a functional unit (401), a scheduling unit (403), a first-level sensing unit (101), a second-level sensing unit (102) and a third-level sensing unit (103) in a sensing module (100) are scheduled according to the classification of the early warning units, and a slice sinking unit (404) is connected with the functional unit (401) and sinks data of each area into different network accessories respectively for edge calculation processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011398460.6A CN112614293B (en) | 2020-12-04 | 2020-12-04 | Electric power Internet of things safety early warning method and system based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011398460.6A CN112614293B (en) | 2020-12-04 | 2020-12-04 | Electric power Internet of things safety early warning method and system based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112614293A CN112614293A (en) | 2021-04-06 |
| CN112614293B true CN112614293B (en) | 2022-07-22 |
Family
ID=75229013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011398460.6A Active CN112614293B (en) | 2020-12-04 | 2020-12-04 | Electric power Internet of things safety early warning method and system based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614293B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110179A (en) * | 2021-04-16 | 2021-07-13 | 广东电网有限责任公司清远供电局 | Electric power safety early warning method, device, equipment and storage medium based on edge calculation |
| CN113472065A (en) * | 2021-05-18 | 2021-10-01 | 广东电网有限责任公司广州供电局 | Power transmission line state monitoring method, device, equipment and storage medium |
| CN113359631B (en) * | 2021-06-07 | 2023-11-24 | 江苏海企化工仓储股份有限公司 | Major hazard source monitoring and early warning system |
| CN113554776A (en) * | 2021-06-23 | 2021-10-26 | 广东润建电力科技有限公司 | Power distribution room intelligent inspection and operation and maintenance method, system and device based on 5G message |
| CN113177873B (en) * | 2021-06-29 | 2021-09-10 | 南京紫核鑫智能科技有限公司 | Urban public safety early warning system based on progressive early warning mode |
| CN115545347B (en) * | 2022-11-15 | 2023-07-28 | 贵州电网有限责任公司 | Power system risk prediction system and method based on big data analysis |
| CN115604319B (en) * | 2022-11-21 | 2023-03-10 | 青岛大学威海创新研究院 | Intelligent community management platform based on multi-dimensional sensor |
| CN117350889A (en) * | 2023-02-14 | 2024-01-05 | 安徽健驰智能科技有限公司 | Transmission line edge calculation and thing allies oneself with proxy device |
| CN116647836B (en) * | 2023-07-27 | 2023-10-03 | 深圳市芯保迪电子科技有限公司 | Network security intelligent monitoring system and method based on 5G communication technology |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8089356B2 (en) * | 2009-04-13 | 2012-01-03 | Jason Lee Moore | Weather alerts |
| CN103136893B (en) * | 2013-01-24 | 2015-03-04 | 浙江工业大学 | Tunnel fire early-warning controlling method based on multi-sensor data fusion technology and system using the same |
| CN103971483A (en) * | 2014-05-08 | 2014-08-06 | 国家电网公司 | Method for early warning power grid transmission line mountain fire intelligently in graded mode |
| CN104183080B (en) * | 2014-08-29 | 2016-08-24 | 武汉理工大学 | A kind of cigarette sense fire detecting method and device |
| CN104766433A (en) * | 2015-04-23 | 2015-07-08 | 河南理工大学 | Electrical fire warning system based on data fusion |
| CN105513262A (en) * | 2016-01-28 | 2016-04-20 | 山东神戎电子股份有限公司 | Threshold-variable forest fire prevention thermal imaging monitoring system and method |
| CN107564232B (en) * | 2017-09-15 | 2020-02-21 | 山东建筑大学 | Electrical fire early warning system and method based on Internet of things |
| CN207234831U (en) * | 2017-09-18 | 2018-04-13 | 天元瑞信通信技术股份有限公司 | A kind of 5G network architectures based on edge calculations and microtomy |
| CN108109318A (en) * | 2017-11-29 | 2018-06-01 | 深圳市亿兆互联技术有限公司 | A kind of fire hazard monitoring system and the fire monitoring method based on LoRa |
| CN110599732A (en) * | 2019-08-07 | 2019-12-20 | 赛特威尔电子股份有限公司 | Smoke alarm management method and device and smoke alarm |
-
2020
- 2020-12-04 CN CN202011398460.6A patent/CN112614293B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112614293A (en) | 2021-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112614293B (en) | Electric power Internet of things safety early warning method and system based on edge calculation | |
| US20190108739A1 (en) | Fire detection system | |
| Li et al. | Investigation of the causality patterns of non-helmet use behavior of construction workers | |
| Goulet et al. | Data‐driven post‐earthquake rapid structural safety assessment | |
| CN105357063B (en) | A kind of cyberspace security postures real-time detection method | |
| CN106156913B (en) | Health control method for aircraft department enclosure | |
| CN105976116B (en) | Fire safety dynamic evaluation method and system based on Internet of things | |
| CN111178598A (en) | Passenger flow prediction method and system for railway passenger station, electronic device and storage medium | |
| CN104780361B (en) | A kind of quality evaluating method of city video monitoring system | |
| CN114821946B (en) | Fire disaster early warning method, monitoring terminal and system for transformer substation alternating current power supply | |
| CN114386845A (en) | Intelligent mall fire fighting monitoring processing system based on BIM | |
| US11378485B2 (en) | Structural monitoring system | |
| KR102480449B1 (en) | Disaster prediction method using multiple sensors | |
| CN115759729A (en) | Disaster risk early warning management system based on algorithm and prediction method | |
| Rehak et al. | Indication of critical infrastructure resilience failure | |
| CN114997607A (en) | Anomaly assessment early warning method and system based on engineering detection data | |
| CN108259223B (en) | Unmanned aerial vehicle network system security situation perception evaluation method for preventing GPS deception | |
| CN117114406A (en) | Emergency event intelligent early warning method and system based on equipment data aggregation | |
| CN117094852B (en) | Energy monitoring system and method for industrial and commercial energy storage | |
| CN108731731A (en) | A kind of lighning proof type safety supervision system and lighning proof type safety supervision method | |
| KR20220064575A (en) | ESS Fire Prevention System and the method thereof | |
| Lambert et al. | Cost–benefit functions for the allocation of security sensors for air contaminants | |
| CN108650124A (en) | A kind of communication system of power grids early warning system based on WebGIS | |
| MY201743A (en) | A method for predicting a disease outbreak | |
| CN113741249A (en) | Industrial control system network security analysis monitoring 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |