CN113705992A - Edge control algorithm and system based on 5G + artificial neural network - Google Patents
Edge control algorithm and system based on 5G + artificial neural network Download PDFInfo
- Publication number
- CN113705992A CN113705992A CN202110944907.3A CN202110944907A CN113705992A CN 113705992 A CN113705992 A CN 113705992A CN 202110944907 A CN202110944907 A CN 202110944907A CN 113705992 A CN113705992 A CN 113705992A
- Authority
- CN
- China
- Prior art keywords
- equipment
- area
- coefficient
- sub
- 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.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 36
- 230000002159 abnormal effect Effects 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims description 65
- 238000012423 maintenance Methods 0.000 claims description 52
- 238000011156 evaluation Methods 0.000 claims description 42
- 230000007613 environmental effect Effects 0.000 claims description 37
- 238000000034 method Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 11
- 230000007175 bidirectional communication Effects 0.000 claims description 7
- 230000003449 preventive effect Effects 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 6
- 238000011895 specific detection Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000003111 delayed effect Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000011321 prophylaxis Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000005856 abnormality Effects 0.000 abstract description 3
- 238000013480 data collection Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
-
- 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
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Signal Processing (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Medical Informatics (AREA)
- Circuit Arrangement For Electric Light Sources In General (AREA)
Abstract
The invention discloses an edge control algorithm and system based on a 5G + artificial neural network, relates to the technical field of edge control algorithms, and solves the problem that the prior art cannot clearly analyze the state of energy equipment in each area, so that the edge control efficiency of a park is reduced; the gateways correspond to the areas one by one, so that data of each area in the park can be separated, and meanwhile, the data influence among the gateways can be clearly seen through a plurality of areas, so that the park management is facilitated, and the management working efficiency is improved; the analysis is carried out on the public equipment, so that the stable operation efficiency of the park is improved, the abnormal operation of the park is prevented, and the use quality of users is reduced; simultaneously providing data for edge control calculation; the influence factors of the public equipment are collected, so that the management efficiency of the public equipment is improved, and the management and control of the public equipment are effective; the public equipment is processed in advance, and the influence of the abnormality of the public equipment on the park is reduced.
Description
Technical Field
The invention relates to the technical field of edge control algorithms, in particular to an edge control algorithm and system based on a 5G + artificial neural network.
Background
Along with the continuous perfection and continuous expansion of the space of each function of the park, industrial enterprises built in the edge zone of the park in the early stage are gradually integrated into the city in the urbanization process, and in recent years, along with the demand of economic development of China, the industrial park is gradually valued by governments at all levels, and becomes an important booster for regional economic development. The industrial linkage bridge is formed between regional economy and industrial economy, and bears the system combination and supplement of the regional industry and the function functions of reasonable linking and matching of the leading industry and the like;
the development of the park economy is gradually improved and matured, a special operation mode of construction and development of an industrial park is formed, the park economy becomes an indispensable component in regional economy development, and a huge effect of pulling the regional economy to rapidly grow is further exerted in future economic construction;
however, in the prior art, data of each area cannot be independent through a gateway in the park edge control, so that data are mixed, and the working intensity of workers is increased; meanwhile, the states of energy equipment in each area cannot be clearly analyzed, so that the edge control calculation lacks necessary standards; in addition, the energy equipment is important equipment in the garden, and the management efficiency of the energy equipment is reduced, so that the whole work efficiency of the garden is reduced.
Disclosure of Invention
The invention aims to provide an edge control algorithm and system based on a 5G + artificial neural network, which can be used for carrying out one-to-one correspondence between gateways and areas, separating data of each area in a park, clearly seeing the data influence among the gateways through a plurality of areas, facilitating park management and improving management work efficiency; the analysis is carried out on the public equipment, so that the stable operation efficiency of the park is improved, the abnormal operation of the park is prevented, and the use quality of users is reduced; while providing data for edge control calculations.
The purpose of the invention can be realized by the following technical scheme:
an edge control system based on a 5G + artificial neural network comprises an edge control platform, a plurality of gateways and a park data acquisition platform;
the plurality of gateways correspond to areas in the garden one by one, monitor data of each area through the gateways and send the data in the garden data acquisition platform to the edge control platform;
the garden data acquisition platform is used for acquiring data of each area in a garden, a server is arranged in the garden data acquisition platform, and the server is in bidirectional communication connection with an equipment detection unit and a street lamp detection unit; detecting public equipment in the park through an equipment detection unit, and acquiring data of the running state of the public equipment through detection; detecting street lamps in the garden through a street lamp detection unit, and binding all street lamps in the garden with a single gateway;
the edge control platform is used for analyzing data in the park data acquisition platform, a controller is arranged in the edge control platform, and the controller is in bidirectional communication connection with an influencing factor acquisition unit and a preventive processing unit; the influence factor acquisition unit is used for acquiring influence factors of the public equipment; the utility device is prophylactically treated by the prophylactic treatment unit.
Further, the specific detection process of the device detection unit is as follows:
dividing the garden into i sub-areas, wherein i is a natural number greater than 1, the sub-areas are matched with the gateways one by one, public equipment in each sub-area is collected and marked as o, and o is a natural number greater than 0; acquiring the surface temperature value and the average temperature floating value of the equipment in the running process of the public equipment in each sub-area, and obtaining an equipment running coefficient Xio of the public equipment in each sub-area through analysis; collecting the times of untimely power supply of the public equipment in each sub-area and the delay time during delayed power supply, and obtaining the efficiency coefficient Zio of the public equipment in each sub-area through analysis;
comparing the equipment operation coefficient and the efficiency coefficient of the public equipment in each subarea with an equipment operation coefficient threshold value and an efficiency coefficient threshold value respectively: if any coefficient of the equipment operation coefficient and the efficiency coefficient of the public equipment in the sub-area is larger than or equal to the corresponding threshold value, marking the public equipment in the corresponding sub-area as abnormal equipment, generating an equipment abnormal signal and sending the equipment abnormal signal and the abnormal equipment to the server; and if any coefficient of the equipment operation coefficient and the efficiency coefficient of the public equipment in the sub-area is less than the corresponding threshold value, marking the public equipment in the corresponding sub-area as normal equipment, generating an equipment normal signal and sending the equipment normal signal and the normal equipment to the server.
Further, the specific detection process of the street lamp detection unit is as follows:
marking the street lamps in each sub-region as u, wherein u is a positive integer larger than 0, acquiring the light coverage area of the street lamps in each sub-region and the light cross coverage area of the adjacent street lamps, and obtaining the efficiency coefficient Giu of the street lamps in each sub-region through analysis; the method comprises the steps of collecting the time when the ambient illumination intensity of each subregion reaches a street lamp starting illumination intensity threshold in real time, collecting the time when each subregion street lamp is started in real time, and calculating and acquiring the delay time of each subregion street lamp through a difference value; acquiring times that the delay time is greater than a time threshold, and obtaining a timely coefficient Fiu of the street lamps in each sub-area through analysis; the method comprises the steps of collecting the number of vehicles which generate braking deceleration when the vehicles in each sub-area pass through a street lamp light coverage area and the frequency of the braking deceleration in real time; collecting the average number of passing people per hour of the street lamp light coverage area in each sub-area; obtaining influence coefficients Diu of street lamps in each sub-area through analysis;
substituting the efficiency coefficient, the timeliness coefficient and the influence coefficient of each sub-area street lamp into the detection model to calculate the detection coefficient of the street lamp in each sub-area, and comparing the detection coefficient of the street lamp in each sub-area with the threshold value of the street lamp detection coefficient: if the detection coefficient of the street lamps in the sub-area is larger than or equal to the threshold value of the detection coefficient of the street lamps, judging that the street lamps in the corresponding sub-area are qualified in detection, marking the street lamps as qualified street lamps, generating qualified street lamp detection signals and sending the qualified street lamp detection signals and the qualified street lamps to a server; and if the detection coefficient of the street lamps in the sub-area is less than the threshold value of the street lamp detection coefficient, judging that the street lamp detection in the corresponding sub-area is unqualified, marking the street lamp detection as an unqualified street lamp, generating a street lamp detection unqualified signal and sending the street lamp detection unqualified signal and the unqualified street lamp to the server together.
Further, the specific collecting process of the influencing factor collecting unit is as follows:
setting a time analysis threshold, wherein the same equipment in the time analysis threshold has a qualified time and an unqualified time, acquiring a temperature difference between the qualified time and the unqualified time, and acquiring a humidity difference between the qualified time and the unqualified time; obtaining an environmental factor evaluation coefficient HJ through analysis, and comparing the environmental factor evaluation coefficient with an environmental factor evaluation coefficient threshold value: if the environmental factor evaluation coefficient is larger than or equal to the environmental factor evaluation coefficient threshold value, judging that the environmental data influences the public equipment, and marking the environmental data as an influence factor; if the environmental factor evaluation coefficient is less than the environmental factor evaluation coefficient threshold value, judging that the environmental data does not influence the public equipment, and marking the environmental data as a non-influence factor;
acquiring a difference value of public equipment maintenance times and a difference value of maintenance duration at a qualified moment and a unqualified moment, acquiring a human factor evaluation coefficient RW through analysis, and comparing the human factor evaluation coefficient with a human factor evaluation coefficient threshold value: if the human factor evaluation coefficient is larger than or equal to the human factor evaluation coefficient threshold value, judging that the human data influences the public equipment, and marking the human data as the influence factor; and if the human factor evaluation coefficient is less than the human factor evaluation coefficient threshold value, judging that the human data does not influence the public equipment, and marking the human data as non-influencing factors.
Further, the specific processing procedures of the preventive processing unit are as follows:
acquiring temperature values and humidity values corresponding to all qualified moments in a time analysis threshold, acquiring a maximum temperature value and a minimum temperature value, a maximum humidity value and a minimum humidity value through numerical analysis, and acquiring a qualified temperature interval and a qualified humidity interval through the maximum temperature value, the minimum temperature value and the maximum humidity value; if the environmental temperature or the humidity of the public equipment in the sub-area is not in the corresponding interval range, generating a temperature adjusting signal or a humidity adjusting signal, and sending the temperature adjusting signal or the humidity adjusting signal to the controller;
acquiring the maintenance times and the maintenance duration corresponding to all qualified moments in a time analysis threshold, acquiring the minimum maintenance times and the minimum maintenance duration through numerical analysis, respectively marking the minimum maintenance times and the minimum maintenance duration as a maintenance time threshold and a maintenance duration threshold, if the maintenance times and the maintenance duration of the public equipment in the sub-area are smaller than the corresponding thresholds, generating a maintenance time increasing signal or a maintenance duration increasing signal, and sending the maintenance time increasing signal or the maintenance duration increasing signal to a controller.
Further, an edge control algorithm based on a 5G + artificial neural network comprises the following specific steps:
step one, arranging a plurality of gateways, wherein the plurality of gateways correspond to areas in a garden one by one, monitoring data of each area through the gateways, and sending the data in a garden data acquisition platform to an edge control platform;
step two, performing data acquisition on each area in the park through a park data acquisition platform, and judging the running state of the public equipment through the data acquisition;
and step three, analyzing the data in the park data acquisition platform through the edge control platform, and judging the influence factors of the public equipment through data analysis.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, the gateways correspond to the areas one by one, data of each area in the garden can be separated, and meanwhile, data influence among the gateways can be clearly seen through the areas, so that the garden management is facilitated, and the management working efficiency is improved; the analysis is carried out on the public equipment, so that the stable operation efficiency of the park is improved, the abnormal operation of the park is prevented, and the use quality of users is reduced; simultaneously providing data for edge control calculation; the method has the advantages that the street lamps in the garden are detected, so that the outgoing quality of users in the garden is improved, and meanwhile, the energy in the garden is analyzed;
the influence factors of the public equipment are collected, so that the management efficiency of the public equipment is improved, and the management and control of the public equipment are effective; the public equipment is processed in advance, and the influence of the abnormality of the public equipment on the park is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is an overall schematic block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an edge control system based on a 5G + artificial neural network includes an edge control platform, a plurality of gateways, and a campus data collection platform, where the gateways are in bidirectional communication with the edge control platform and the campus data collection platform;
the plurality of gateways correspond to areas in the garden one by one, monitor data of each area through the gateways and send the data in the garden data acquisition platform to the edge control platform; the gateways correspond to the areas one by one, so that data of each area in the park can be separated, and meanwhile, the data influence among the gateways can be clearly seen through a plurality of areas, so that the park management is facilitated, and the management working efficiency is improved;
the garden data acquisition platform is used for acquiring data of each area in a garden, a server is arranged in the garden data acquisition platform, and the server is in bidirectional communication connection with an equipment detection unit and a street lamp detection unit;
the edge control platform is used for analyzing data in the park data acquisition platform, a controller is arranged in the edge control platform, and the controller is in bidirectional communication connection with an influencing factor acquisition unit and a preventive processing unit;
the equipment detection unit is used for detecting the public equipment in the park, acquiring data of the running state of the public equipment through detection, and analyzing the public equipment, so that the stable running efficiency of the park is improved, the abnormal running of the park is prevented, and the use quality of a user is reduced; meanwhile, data are provided for edge control calculation, the public equipment comprises public energy equipment for supplying power in a park, and the specific detection process is as follows:
dividing the garden into i sub-areas, wherein i is a natural number greater than 1, the sub-areas are matched with the gateways one by one, public equipment in each sub-area is collected and marked as o, and o is a natural number greater than 0;
acquiring a device surface temperature value and a temperature average floating value in the running process of the public devices in each sub-area, and respectively marking the device surface temperature value and the temperature average floating value in the running process of the public devices in each sub-area as WDio and FDio; by the formulaObtaining an equipment operation coefficient Xio of the public equipment in each subarea, wherein a1 and a2 are both preset proportionality coefficients, a1 is more than a2 is more than 0, e is a natural constant, and the equipment operation coefficient is obtained by normalizing the measurement parameters of the public equipment in the subarea to evaluate the operation of the public equipment in the subareaA numerical value of the qualification rate; the larger the surface temperature value and the average temperature floating value obtained by a formula are, the larger the equipment operation coefficient is, and the smaller the probability of representing qualified operation of public equipment in the sub-area is;
collecting the times of untimely power supply of the public equipment in each sub-area and the delay time length during delayed power supply, and respectively marking the times of untimely power supply of the public equipment in each sub-area and the delay time length during delayed power supply as CSio and SCio; obtaining an efficiency coefficient Zio of public equipment in each sub-area by a formula Zio ═ alpha (CSio × a3+ SCio × a4), wherein a3 and a4 are both preset proportionality coefficients, a3 is more than a4 is more than 0, and alpha is an error correction factor and takes the value of 1.25; the efficiency coefficient of the public equipment is a numerical value used for evaluating the qualified rate of the efficiency of the public equipment in the sub-region by carrying out normalization processing on the measurement parameters of the public equipment in the sub-region; the larger the times and delay time of power supply failure can be obtained through a formula, the larger the efficiency coefficient is, and the smaller the probability of representing the qualified efficiency of the public equipment in the sub-area is;
comparing the equipment operation coefficient and the efficiency coefficient of the public equipment in each subarea with an equipment operation coefficient threshold value and an efficiency coefficient threshold value respectively:
if any coefficient of the equipment operation coefficient and the efficiency coefficient of the public equipment in the sub-area is larger than or equal to the corresponding threshold value, marking the public equipment in the corresponding sub-area as abnormal equipment, generating an equipment abnormal signal and sending the equipment abnormal signal and the abnormal equipment to the server; if any coefficient of the equipment operation coefficient and the efficiency coefficient of the public equipment in the sub-area is less than the corresponding threshold value, marking the public equipment in the corresponding sub-area as normal equipment, generating an equipment normal signal and sending the equipment normal signal and the normal equipment to the server;
street lamp detecting element is used for detecting the street lamp in the garden to bind all street lamps in the garden with single gateway, detect the street lamp in the garden, improved the quality of the interior user trip of garden, carry out the analysis to the energy in the garden simultaneously, prevent the extravagant phenomenon of the energy, concrete testing process is as follows:
to mark the street lamp in each sub-areaRecording u as a positive integer larger than 0, collecting the light coverage area of each sub-region street lamp and the light cross coverage area of the adjacent street lamp, and respectively marking the light coverage area of each sub-region street lamp and the light cross coverage area of the adjacent street lamp as FGiu and JCiu; by the formulaObtaining an efficiency coefficient Giu of each sub-region street lamp, wherein b1 and b2 are both preset proportionality coefficients, b1 is greater than b2 and is greater than 0, and beta 1 is an error correction factor and takes a value of 2.13;
the method comprises the steps of collecting the time when the ambient illumination intensity of each sub-area reaches a street lamp starting illumination intensity threshold in real time, collecting the time when each sub-area street lamp is started in real time, calculating and obtaining the delay time of each sub-area street lamp through a difference value, and marking the delay time of each sub-area street lamp as YCiu; collecting the times that the delay time length is greater than the time length threshold value, and marking the times as RSiu; acquiring a timely coefficient Fiu of the street lamp in each sub-area by using a formula Fiu ═ beta 2(YCiu × b3+ RSiu × b4), wherein b3 and b4 are preset proportional coefficients, b3 is greater than b4 is greater than 0, and beta 2 is an error correction factor and takes a value of 2.86;
the method comprises the steps of collecting the number of vehicles generating braking deceleration and the frequency of generating braking deceleration when the vehicles in each sub-area pass through a street lamp light coverage area in real time, and respectively marking the number of the vehicles as Siu and Piu; collecting the average number of passing people per hour of the street lamp light coverage area in each sub-area, and marking the average number of passing people per hour of the street lamp light coverage area as Riu; obtaining an influence coefficient Diu of the street lamps in each sub-area through a formula Diu-beta 3(Siu × b5+ Piu × b6), wherein b5 and b6 are both preset proportional coefficients, b5 > b6 > 0, and beta 3 is an error correction factor and takes a value of 2.94;
substituting the efficiency coefficient, the timeliness coefficient and the influence coefficient of each sub-area street lamp into a detection model to calculate and obtain the detection coefficient of the street lamp in each sub-area, wherein the detection model isWherein e is fromHowever, Kiu is expressed as the detection coefficient of the street lamp in each subarea;
comparing the detection coefficient of the street lamp in each sub-area with a street lamp detection coefficient threshold value: if the detection coefficient of the street lamps in the sub-area is larger than or equal to the threshold value of the detection coefficient of the street lamps, judging that the street lamps in the corresponding sub-area are qualified in detection, marking the street lamps as qualified street lamps, generating qualified street lamp detection signals and sending the qualified street lamp detection signals and the qualified street lamps to a server; if the detection coefficient of the street lamps in the sub-area is smaller than the threshold value of the street lamp detection coefficient, judging that the street lamp detection in the corresponding sub-area is unqualified, marking the street lamp detection as an unqualified street lamp, generating a street lamp detection unqualified signal and sending the street lamp detection unqualified signal and the unqualified street lamp to the server;
the influence factor acquisition unit is used for acquiring influence factors of the public equipment, the management efficiency of the public equipment is improved by acquiring the influence factors of the public equipment, the management and control of the public equipment are effective, and the specific acquisition process is as follows:
setting a time analysis threshold, wherein the same equipment in the time analysis threshold has a qualified time and an unqualified time, acquiring a temperature difference between the qualified time and the unqualified time, and marking the temperature difference between the qualified time and the unqualified time as WDC; acquiring a humidity difference value between a qualified moment and an unqualified moment, and marking the humidity difference value between the qualified moment and the unqualified moment as SDC; by the formulaObtaining an environmental factor evaluation coefficient HJ, wherein v1 and v2 are preset proportionality coefficients, and v1 is greater than v2 is greater than 0;
comparing the environmental factor evaluation coefficient with an environmental factor evaluation coefficient threshold value: if the environmental factor evaluation coefficient is larger than or equal to the environmental factor evaluation coefficient threshold value, judging that the environmental data influences the public equipment, and marking the environmental data as an influence factor; if the environmental factor evaluation coefficient is less than the environmental factor evaluation coefficient threshold value, judging that the environmental data does not influence the public equipment, and marking the environmental data as a non-influence factor; environmental factors include humidity and temperature within the environment;
collecting a difference value of the maintenance times and the maintenance duration of the public equipment at the qualified time and the unqualified time, and respectively marking the difference value of the maintenance times and the maintenance duration of the public equipment at the qualified time and the unqualified time as WHC and WSC; by the formulaAcquiring an artificial factor evaluation coefficient RW, wherein v3 and v4 are preset proportionality coefficients, and v3 is greater than v4 is greater than 0;
comparing the human factor evaluation coefficient with a human factor evaluation coefficient threshold value: if the human factor evaluation coefficient is larger than or equal to the human factor evaluation coefficient threshold value, judging that the human data influences the public equipment, and marking the human data as the influence factor; if the human factor evaluation coefficient is less than the human factor evaluation coefficient threshold value, judging that the human data does not influence the public equipment, and marking the human data as a non-influence factor; the artificial data comprises maintenance times and maintenance duration of the public equipment;
the preventive processing unit is used for carrying out preventive processing on the public equipment, processing the public equipment in advance and reducing the influence of the abnormality of the public equipment on the park, and the specific processing process is as follows:
acquiring temperature values and humidity values corresponding to all qualified moments in a time analysis threshold, acquiring a maximum temperature value and a minimum temperature value, a maximum humidity value and a minimum humidity value through numerical analysis, and acquiring a qualified temperature interval and a qualified humidity interval through the maximum temperature value, the minimum temperature value and the maximum humidity value; if the environmental temperature or the humidity of the public equipment in the sub-area is not in the corresponding interval range, generating a temperature adjusting signal or a humidity adjusting signal, and sending the temperature adjusting signal or the humidity adjusting signal to the controller;
acquiring the maintenance times and the maintenance duration corresponding to all qualified moments in a time analysis threshold, acquiring the minimum maintenance times and the minimum maintenance duration through numerical analysis, respectively marking the minimum maintenance times and the minimum maintenance duration as a maintenance time threshold and a maintenance duration threshold, if the maintenance times and the maintenance duration of the public equipment in the sub-area are smaller than the corresponding thresholds, generating a maintenance time increasing signal or a maintenance duration increasing signal, and sending the maintenance time increasing signal or the maintenance duration increasing signal to a controller.
The edge control algorithm based on the 5G + artificial neural network comprises the following specific steps:
step one, arranging a plurality of gateways, wherein the plurality of gateways correspond to areas in a garden one by one, monitoring data of each area through the gateways, and sending the data in a garden data acquisition platform to an edge control platform;
step two, performing data acquisition on each area in the park through a park data acquisition platform, and judging the running state of the public equipment through the data acquisition;
and step three, analyzing the data in the park data acquisition platform through the edge control platform, and judging the influence factors of the public equipment through data analysis.
A5G + artificial neural network-based edge control algorithm and a system thereof are provided, wherein during operation, a plurality of gateways are arranged, correspond to areas in a garden one by one, monitor data of each area through the gateways, and send data in a garden data acquisition platform to an edge control platform; the method comprises the steps that data collection is carried out on each area in a park through a park data collection platform, and the running state of public equipment is judged through the data collection; and analyzing the data in the park data acquisition platform through the edge control platform, and judging the influence factors of the public equipment through data analysis.
The above formulas are all calculated by taking the numerical value of the dimension, the formula is a formula which obtains the latest real situation by acquiring a large amount of data and performing software simulation, and the preset parameters in the formula are set by the technical personnel in the field according to the actual situation.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (6)
1. An edge control system based on a 5G + artificial neural network is characterized by comprising an edge control platform, a plurality of gateways and a park data acquisition platform;
the plurality of gateways correspond to areas in the garden one by one, monitor data of each area through the gateways and send the data in the garden data acquisition platform to the edge control platform;
the garden data acquisition platform is used for acquiring data of each area in a garden, a server is arranged in the garden data acquisition platform, and the server is in bidirectional communication connection with an equipment detection unit and a street lamp detection unit; detecting public equipment in the park through an equipment detection unit, and acquiring data of the running state of the public equipment through detection; detecting street lamps in the garden through a street lamp detection unit, and binding all street lamps in the garden with a single gateway;
the edge control platform is used for analyzing data in the park data acquisition platform, a controller is arranged in the edge control platform, and the controller is in bidirectional communication connection with an influencing factor acquisition unit and a preventive processing unit; the influence factor acquisition unit is used for acquiring influence factors of the public equipment; the utility device is prophylactically treated by the prophylactic treatment unit.
2. The edge control system based on the 5G + artificial neural network of claim 1, wherein the specific detection process of the equipment detection unit is as follows:
dividing the garden into i sub-areas, wherein i is a natural number greater than 1, the sub-areas are matched with the gateways one by one, public equipment in each sub-area is collected and marked as o, and o is a natural number greater than 0; acquiring the surface temperature value and the average temperature floating value of the equipment in the running process of the public equipment in each sub-area, and obtaining an equipment running coefficient Xio of the public equipment in each sub-area through analysis; collecting the times of untimely power supply of the public equipment in each sub-area and the delay time during delayed power supply, and obtaining the efficiency coefficient Zio of the public equipment in each sub-area through analysis;
comparing the equipment operation coefficient and the efficiency coefficient of the public equipment in each subarea with an equipment operation coefficient threshold value and an efficiency coefficient threshold value respectively: if any coefficient of the equipment operation coefficient and the efficiency coefficient of the public equipment in the sub-area is larger than or equal to the corresponding threshold value, marking the public equipment in the corresponding sub-area as abnormal equipment, generating an equipment abnormal signal and sending the equipment abnormal signal and the abnormal equipment to the server; and if any coefficient of the equipment operation coefficient and the efficiency coefficient of the public equipment in the sub-area is less than the corresponding threshold value, marking the public equipment in the corresponding sub-area as normal equipment, generating an equipment normal signal and sending the equipment normal signal and the normal equipment to the server.
3. The edge control system based on the 5G + artificial neural network of claim 1, wherein the specific detection process of the street lamp detection unit is as follows:
marking the street lamps in each sub-region as u, wherein u is a positive integer larger than 0, acquiring the light coverage area of the street lamps in each sub-region and the light cross coverage area of the adjacent street lamps, and obtaining the efficiency coefficient Giu of the street lamps in each sub-region through analysis; the method comprises the steps of collecting the time when the ambient illumination intensity of each subregion reaches a street lamp starting illumination intensity threshold in real time, collecting the time when each subregion street lamp is started in real time, and calculating and acquiring the delay time of each subregion street lamp through a difference value; acquiring times that the delay time is greater than a time threshold, and obtaining a timely coefficient Fiu of the street lamps in each sub-area through analysis; the method comprises the steps of collecting the number of vehicles which generate braking deceleration when the vehicles in each sub-area pass through a street lamp light coverage area and the frequency of the braking deceleration in real time; collecting the average number of passing people per hour of the street lamp light coverage area in each sub-area; obtaining influence coefficients Diu of street lamps in each sub-area through analysis;
substituting the efficiency coefficient, the timeliness coefficient and the influence coefficient of each sub-area street lamp into the detection model to calculate the detection coefficient of the street lamp in each sub-area, and comparing the detection coefficient of the street lamp in each sub-area with the threshold value of the street lamp detection coefficient: if the detection coefficient of the street lamps in the sub-area is larger than or equal to the threshold value of the detection coefficient of the street lamps, judging that the street lamps in the corresponding sub-area are qualified in detection, marking the street lamps as qualified street lamps, generating qualified street lamp detection signals and sending the qualified street lamp detection signals and the qualified street lamps to a server; and if the detection coefficient of the street lamps in the sub-area is less than the threshold value of the street lamp detection coefficient, judging that the street lamp detection in the corresponding sub-area is unqualified, marking the street lamp detection as an unqualified street lamp, generating a street lamp detection unqualified signal and sending the street lamp detection unqualified signal and the unqualified street lamp to the server together.
4. The edge control system based on the 5G + artificial neural network as claimed in claim 1, wherein the specific acquisition process of the influencing factor acquisition unit is as follows:
setting a time analysis threshold, wherein the same equipment in the time analysis threshold has a qualified time and an unqualified time, acquiring a temperature difference between the qualified time and the unqualified time, and acquiring a humidity difference between the qualified time and the unqualified time; obtaining an environmental factor evaluation coefficient HJ through analysis, and comparing the environmental factor evaluation coefficient with an environmental factor evaluation coefficient threshold value: if the environmental factor evaluation coefficient is larger than or equal to the environmental factor evaluation coefficient threshold value, judging that the environmental data influences the public equipment, and marking the environmental data as an influence factor; if the environmental factor evaluation coefficient is less than the environmental factor evaluation coefficient threshold value, judging that the environmental data does not influence the public equipment, and marking the environmental data as a non-influence factor;
acquiring a difference value of public equipment maintenance times and a difference value of maintenance duration at a qualified moment and a unqualified moment, acquiring a human factor evaluation coefficient RW through analysis, and comparing the human factor evaluation coefficient with a human factor evaluation coefficient threshold value: if the human factor evaluation coefficient is larger than or equal to the human factor evaluation coefficient threshold value, judging that the human data influences the public equipment, and marking the human data as the influence factor; and if the human factor evaluation coefficient is less than the human factor evaluation coefficient threshold value, judging that the human data does not influence the public equipment, and marking the human data as non-influencing factors.
5. The edge control system based on the 5G + artificial neural network of claim 1, wherein the preventive processing unit specifically processes as follows:
acquiring temperature values and humidity values corresponding to all qualified moments in a time analysis threshold, acquiring a maximum temperature value and a minimum temperature value, a maximum humidity value and a minimum humidity value through numerical analysis, and acquiring a qualified temperature interval and a qualified humidity interval through the maximum temperature value, the minimum temperature value and the maximum humidity value; if the environmental temperature or the humidity of the public equipment in the sub-area is not in the corresponding interval range, generating a temperature adjusting signal or a humidity adjusting signal, and sending the temperature adjusting signal or the humidity adjusting signal to the controller;
acquiring the maintenance times and the maintenance duration corresponding to all qualified moments in a time analysis threshold, acquiring the minimum maintenance times and the minimum maintenance duration through numerical analysis, respectively marking the minimum maintenance times and the minimum maintenance duration as a maintenance time threshold and a maintenance duration threshold, if the maintenance times and the maintenance duration of the public equipment in the sub-area are smaller than the corresponding thresholds, generating a maintenance time increasing signal or a maintenance duration increasing signal, and sending the maintenance time increasing signal or the maintenance duration increasing signal to a controller.
6. An edge control algorithm based on a 5G + artificial neural network is characterized by comprising the following specific steps:
step one, arranging a plurality of gateways, wherein the plurality of gateways correspond to areas in a garden one by one, monitoring data of each area through the gateways, and sending the data in a garden data acquisition platform to an edge control platform;
step two, performing data acquisition on each area in the park through a park data acquisition platform, and judging the running state of the public equipment through the data acquisition;
and step three, analyzing the data in the park data acquisition platform through the edge control platform, and judging the influence factors of the public equipment through data analysis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110944907.3A CN113705992A (en) | 2021-08-17 | 2021-08-17 | Edge control algorithm and system based on 5G + artificial neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110944907.3A CN113705992A (en) | 2021-08-17 | 2021-08-17 | Edge control algorithm and system based on 5G + artificial neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113705992A true CN113705992A (en) | 2021-11-26 |
Family
ID=78653254
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110944907.3A Pending CN113705992A (en) | 2021-08-17 | 2021-08-17 | Edge control algorithm and system based on 5G + artificial neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113705992A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117318796A (en) * | 2023-11-10 | 2023-12-29 | 速度科技股份有限公司 | Edge data computing and evaluating system based on satellite communication |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109213057A (en) * | 2017-06-29 | 2019-01-15 | 上海微电子装备(集团)股份有限公司 | Intelligent diagnostics device and method |
CN112351558A (en) * | 2020-11-07 | 2021-02-09 | 杭州集联科技有限公司 | Intelligent street lamp and fault remote control system thereof |
CN112595972A (en) * | 2020-11-17 | 2021-04-02 | 马鞍山安慧智电子科技有限公司 | Motor running state real-time monitoring system based on computer |
CN112631157A (en) * | 2020-11-17 | 2021-04-09 | 马鞍山安慧智电子科技有限公司 | Explosion-proof electrical apparatus monitoring system based on computer cloud platform |
CN112686649A (en) * | 2021-02-03 | 2021-04-20 | 浙江金卡实业有限公司 | Construction equipment management system based on artificial intelligence |
CN112688820A (en) * | 2021-01-13 | 2021-04-20 | 铜陵市金鑫人防工程防护设备有限公司 | Civil air defense engineering equipment maintenance method based on big data |
CN112767217A (en) * | 2021-01-27 | 2021-05-07 | 森罗云科技(广州)有限公司 | Intelligent community management system based on Internet of things |
CN112862118A (en) * | 2021-01-21 | 2021-05-28 | 安徽德诺科技股份公司 | Intelligent park safety operation and maintenance system |
CN113077128A (en) * | 2021-03-19 | 2021-07-06 | 贵州航天云网科技有限公司 | Heterogeneous industrial data intelligent analysis system based on user drive |
CN113095985A (en) * | 2021-05-08 | 2021-07-09 | 王美珍 | Smart city management method and system based on Internet of things |
-
2021
- 2021-08-17 CN CN202110944907.3A patent/CN113705992A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109213057A (en) * | 2017-06-29 | 2019-01-15 | 上海微电子装备(集团)股份有限公司 | Intelligent diagnostics device and method |
CN112351558A (en) * | 2020-11-07 | 2021-02-09 | 杭州集联科技有限公司 | Intelligent street lamp and fault remote control system thereof |
CN112595972A (en) * | 2020-11-17 | 2021-04-02 | 马鞍山安慧智电子科技有限公司 | Motor running state real-time monitoring system based on computer |
CN112631157A (en) * | 2020-11-17 | 2021-04-09 | 马鞍山安慧智电子科技有限公司 | Explosion-proof electrical apparatus monitoring system based on computer cloud platform |
CN112688820A (en) * | 2021-01-13 | 2021-04-20 | 铜陵市金鑫人防工程防护设备有限公司 | Civil air defense engineering equipment maintenance method based on big data |
CN112862118A (en) * | 2021-01-21 | 2021-05-28 | 安徽德诺科技股份公司 | Intelligent park safety operation and maintenance system |
CN112767217A (en) * | 2021-01-27 | 2021-05-07 | 森罗云科技(广州)有限公司 | Intelligent community management system based on Internet of things |
CN112686649A (en) * | 2021-02-03 | 2021-04-20 | 浙江金卡实业有限公司 | Construction equipment management system based on artificial intelligence |
CN113077128A (en) * | 2021-03-19 | 2021-07-06 | 贵州航天云网科技有限公司 | Heterogeneous industrial data intelligent analysis system based on user drive |
CN113095985A (en) * | 2021-05-08 | 2021-07-09 | 王美珍 | Smart city management method and system based on Internet of things |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117318796A (en) * | 2023-11-10 | 2023-12-29 | 速度科技股份有限公司 | Edge data computing and evaluating system based on satellite communication |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114966467A (en) | Power transmission line state evaluation method based on digital twinning | |
CN114819415B (en) | Power equipment fault prediction system based on data analysis | |
CN107886171B (en) | PMU data-based breaker state online diagnosis method and system | |
CN115375154A (en) | Building construction quality safety online risk management system | |
CN114979584A (en) | Data acquisition monitoring device for road construction equipment | |
CN115514318B (en) | Photovoltaic power station monitoring system | |
CN116800517A (en) | Data acquisition intelligent management system based on data analysis | |
CN115528810A (en) | Temperature measurement data operation, inspection, analysis and management system based on power equipment | |
CN115167273A (en) | Construction power consumption energy-saving management control system on construction site | |
CN116990626B (en) | Alternating current power grid voltage transmission state monitoring method and system | |
CN114936652A (en) | Electrical equipment remote monitoring control system | |
CN113705992A (en) | Edge control algorithm and system based on 5G + artificial neural network | |
CN117078017A (en) | Intelligent decision analysis system for monitoring power grid equipment | |
CN106325258B (en) | Relay protection device state evaluation method based on online monitoring information | |
CN116827264B (en) | Early warning system for photovoltaic power generation | |
CN115755752B (en) | PLC-based automation equipment energy-saving control method and system | |
CN117614487A (en) | Beidou system-based transmission line communication method and system | |
CN116886043A (en) | Monitoring system for automatically identifying problems of photovoltaic string system | |
CN110836835A (en) | Intelligent SF6 density on-line monitoring data analysis and information feedback system | |
CN115639423A (en) | Internet-based intelligent distribution box monitoring control method and system | |
CN2570789Y (en) | Device for monitoring moisture in transformer oil | |
CN115528686A (en) | Distributed power distribution fault processing system and method based on edge calculation | |
CN114638485A (en) | Full-service ubiquitous power Internet of things danger coefficient induction and fault repair system | |
CN112001561A (en) | Electric power industry risk prediction method and system | |
CN111245097A (en) | Intelligent power grid management and control system and method |
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 |