CN106886591A - A kind of intelligent road-lamp energy consumption analysis system based on data mining - Google Patents
A kind of intelligent road-lamp energy consumption analysis system based on data mining Download PDFInfo
- Publication number
- CN106886591A CN106886591A CN201710091740.4A CN201710091740A CN106886591A CN 106886591 A CN106886591 A CN 106886591A CN 201710091740 A CN201710091740 A CN 201710091740A CN 106886591 A CN106886591 A CN 106886591A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- data
- consumption data
- values
- street lamp
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of intelligent road-lamp energy consumption analysis system based on data mining, including:Original energy consumption data table and the energy consumption data table of amendment, the two tables are respectively used to store the original energy consumption data and energy consumption data after treatment of street lamp;Energy consumption monitoring model, for real-time monitoring street lamp energy consumption data, shows monitoring result in graphical form;Energy consumption forecast model, for predicting street lamp following a period of time in power consumption values, display in graphical form predicts the outcome;The inquiry of historical data model, for inquiring about street lamp history energy consumption data, shows Query Result in graphical form;Energy consumption data processes model, for importing and processing street lamp history energy consumption data, display processing result in graphical form;User interface, in the form of the structure and left and right pane of single window multi views, while showing the result of energy consumption analysis using diagrammatic form.Can effectively be monitored by the inventive method and manage street lamp energy consumption, realize road lamp energy-saving.
Description
Technical field
The present invention relates to data mining, intelligent road-lamp and energy consumption analysis field, refer in particular to a kind of based on data mining
Intelligent road-lamp energy consumption analysis (Smart Light Energy consumption Analysis, SLEA) system.
Background technology
In recent years, China accelerates the paces of urbanization, and the development in city promotes increasing and using model for street lamp species
The expansion enclosed, mainly there is the street lightings such as street, highway, tunnel, subway, landscape, park at present.Street lighting be unable to do without street lamp
The control and management of monitoring system, with the continuous popularization and construction of " smart city " and " wisdom street lamp ", Street Lamp Monitor System
More and more intelligent, automation, information-based, networking, the function of system are also more and more perfect.Street lamp all consumes substantial amounts of every year
Electric energy and other resources, set up and improve the energy consumption analysis platform of Intelligent streetlamp monitoring system and realize that road lamp energy-saving turns into road
The problem that lamp construction and the development of wisdom street lamp must be solved.
Current Intelligent streetlamp monitoring system is more paid attention to realize the intelligentized control of street lamp and management, integrated more work(
Can, such as using lamp stand as charging pile, the carrier of environmental monitoring, and road lamp energy-saving is realized by illumination strategies, as on demand according to
Bright lamp.The method of road lamp energy-saving mainly has:1) low energy consumption light source is selected;2) line loss is reduced;3) new energy street lamp is used;4)
Illuminate on demand;5) energy consumption analysis.Energy consumption analysis are an important components of Intelligent streetlamp monitoring system, not only can be real-time
The energy consumption of street lamp is monitored, and road lamp energy-saving can also be provided according to analysis result and supported.By analyzing street lamp energy consumption data, energy
Enough to find street lamp exception in time, such as power consumption is abnormal, street lamp device is damaged, it is to avoid the waste of electric energy, is the timely of street lamp device
Safeguard and maintenance provides safeguard.Therefore, improve and improve Intelligent streetlamp monitoring system energy consumption analysis platform it is very necessary.
The content of the invention
Shortcoming and deficiency it is an object of the invention to overcome prior art, it is proposed that a kind of availability and reliability are stronger
Based on data mining intelligent road-lamp energy consumption analysis (Smart Light Energy consumption Analysis,
SLEA data mining technology is applied to) system, the system monitoring and management of street lamp energy consumption data, by excavating street lamp energy consumption
The exception of the law discovery energy consumption data of data, the power consumption values for estimating street lamp etc., so that effectively monitor and manage street lamp energy consumption, it is real
Existing road lamp energy-saving.
To achieve the above object, technical scheme provided by the present invention is:A kind of intelligent road-lamp energy based on data mining
Consumption analysis system, including:
Tables of data, including original energy consumption data table and the energy consumption data table of amendment, the two tables are respectively used to store street lamp
Original energy consumption data and energy consumption data after treatment;
Energy consumption monitoring model, for real-time monitoring street lamp energy consumption data, shows monitoring result, to abnormal energy in graphical form
Consumption data are pointed out and alarmed, and for later energy consumption monitoring and the accuracy of energy consumption prediction, to abnormal energy consumption data
It is modified;
Energy consumption forecast model, for predicting street lamp following a period of time in power consumption values, show that prediction is tied in graphical form
Really, and csv file can be exported as by predicting the outcome;
The inquiry of historical data model, for inquiring about street lamp history energy consumption data, shows Query Result in graphical form, can
Choose whether to be contrasted original energy consumption data with the energy consumption data of amendment, so as to there is an abnormal energy consumption one to become apparent from
Understanding, and place's Query Result can be exported as csv file;
Energy consumption data processes model, for importing and processing street lamp history energy consumption data, display processing knot in graphical form
Really, the abnormal data in historical data is modified, and in the data and the data Cun Chudao databases of amendment that will be imported;
User interface, in the form of the structure and left and right pane of single window multi views, while being shown using diagrammatic form
The result of energy consumption analysis.
It, for preserving the original energy consumption data that collects, is not by any amendment that described original energy consumption data table is
Or the data of modification, including energy consumption record label, terminal number, terminal name, energy consumption acquisition time, power consumption values, database update
Time these fields, wherein:
Energy consumption records label:Which bar energy consumption record represented;
Terminal number:Intelligent streetlamp monitoring system for convenience of street lamp terminal management, be its set one numbering;
Terminal name:It is corresponding with terminal number, it is the title of terminal;
Energy consumption acquisition time:Represent the time of collection street lamp energy consumption data;
Power consumption values:The power consumption values of the street lamp that expression is collected, the i.e. power consumption of street lamp;
Data base update time:Represent the time in the record storage to tables of data;
The energy consumption data table of described amendment is for preserving by the energy consumption data after amendment, to original energy consumption data
In missing data filled up and abnormal data is corrected, including energy consumption record label, terminal number, terminal name, energy
Whether consumption acquisition time, power consumption values, the power consumption values of amendment, energy consumption are corrected, whether energy consumption is abnormal, whether energy consumption lacks, data
Storehouse updates these fields of time, wherein:
Energy consumption record label, terminal number, terminal name, energy consumption acquisition time, power consumption values:For same energy consumption record,
The value of these fields of the energy consumption data table of amendment is identical with original energy consumption data table;
The power consumption values of amendment:If energy consumption is normal, the power consumption values corrected are identical with original power consumption values, if energy consumption is lacked
Or it is abnormal, then the power consumption values corrected are by the value after amendment;
Whether energy consumption is corrected:If energy consumption is corrected, the value is 1, is also meant that the energy consumption is missing from or abnormal
, otherwise, the value is 0, also means that the energy consumption is normal;
Whether energy consumption is abnormal:If energy consumption exception, the value is 1, and otherwise, the value is 0;
Whether energy consumption lacks:If energy consumption is lacked, the value is 1, and otherwise, the value is 0;
Data base update time:The time in the record storage to tables of data is represented, the time is always than original energy consumption number
According to the data base update time evening of table, because energy consumption data always first storage is to original energy consumption data table, then by model
The energy consumption data table of amendment is then stored into after analysis and treatment.
Described energy consumption monitoring model is, based on local outlier factor algorithm and regression tree, to realize to abnormal energy consumption data
Detection and amendment, comprise the following steps that:
1) newest street lamp power consumption values are received, energy consumption monitoring event is triggered;
2) energy consumption monitoring thread is created;
3) energy consumption data that will be received is stored in original energy consumption data table;
4) call energy consumption monitoring model to be analyzed street lamp power consumption values, recognize its generic, the category point have it is normal,
Missing, exception, and be modified when it is missing or abnormal data, its implementation is as follows:
4.1) newest energy consumption data is gathered;
4.2) energy consumption data in a period of time recently is read from the energy consumption data table of amendment;
4.3) judge whether energy consumption data lacks, that is, whether the power consumption values for judging collection are 0, if 0 shows that energy consumption lacks
Lose, jump to step 4.5), otherwise, continue;
4.4) the lof values of the energy consumption data for collecting are calculated using local outlier factor algorithm, judges whether lof values are big
In threshold value, if showing less than if, energy consumption is normal, terminates, and otherwise shows energy consumption exception, continues;
4.5) regression tree is set up using recurrence tree algorithm, and uses the regression tree amendment power consumption values set up;
5) by the energy consumption data table of energy consumption monitoring result storage to amendment;
6) energy consumption monitoring result is shown in the block diagram and form at energy consumption monitoring interface;
7) energy consumption monitoring thread is destroyed.
Described energy consumption forecast model is, based on radial basis function neural network, to realize the prediction to energy consumption data, its tool
Body step is as follows:
1) user sets predicted time section, triggers energy consumption predicted events;
2) energy consumption prediction thread is created;
3) energy consumption forecast model is called, radial basis function neural network is trained, the energy of the street lamp of time period to be predicted is obtained
Consumption value, its implementation is as follows:
3.1) predicted time section or prediction number of days are set;
3.2) energy consumption data in a period of time recently is read from the energy consumption data table of amendment;
3.3) radial basis function neural network is trained using gradient descent method;
3.4) the neural network prediction street lamp power consumption values obtained using training;
4) energy consumption prediction result is shown in the block diagram and form of energy consumption prediction interface;
5) energy consumption prediction thread is destroyed;
6) user decides whether to derive energy consumption prediction result according to demand, if necessary to derive, then by energy consumption prediction result
Export as csv file.
In the middle of the inquiry of historical data model, user inquires about going through in the time period by setting query time section
History energy consumption data, Query Result will be displayed in block diagram and form, and it is comprised the following steps that:
1) user sets query time section and chooses whether contrast, trigger data query event;
2) data query thread is created;
3) the energy consumption data table of the condition query amendment set according to user;
4) the display data Query Result in the block diagram and form at data query interface;
5) data query thread is destroyed;
6) user decides whether to derive data query result according to demand, if necessary to derive, then by data query result
Export as csv file.
Described energy consumption data treatment model is, based on local outlier factor algorithm and regression tree, to realize to historical data
Importing and treatment, it is comprised the following steps that:
1) user's selection history energy consumption data source, triggering energy consumption data treatment event;
2) energy consumption data treatment thread is created;
3) the history energy consumption data for selecting user is stored in original energy consumption data table;
4) energy consumption data is called to process Modifying model problem energy consumption data, implementation is as follows:
4.1) history energy consumption data is imported from csv file or database;
4.2) missing values in detection energy consumption data, jump to step 4.4 if without missing values), otherwise, continue;
4.3) regression tree is set up using the energy consumption data for importing, and missing values is filled up using the regression tree set up;
4.4) the lof values of all energy consumption datas are calculated using local outlier factor algorithm, each energy consumption data is judged
Whether lof values are more than threshold value, if being more than threshold value in the absence of lof values, terminate, if there is lof values more than threshold value, show the number
According to exception, continue;
4.5) regression tree is re-established using the energy consumption data after filling up, and corrects abnormal using the regression tree set up
Value;
5) by the energy consumption data table of energy consumption data result storage to amendment;
6) energy consumption data result is shown in the block diagram and form at energy consumption data treatment interface;
7) energy consumption data treatment thread is destroyed.
The main interface of the user interface is in the form of the structure and left and right pane of single window multi views, wherein left side
Pane display function list, right side pane shows the corresponding contents of each function;The feature list of main interface includes:Energy consumption is supervised
Survey, energy consumption prediction, historical data, data processing, help document this five functional, it is specific as follows:
Energy consumption monitoring:Energy consumption monitoring result is displayed in block diagram and form, when finding that energy consumption occurs abnormal, in column
Can be identified by changing the color of display in figure and form;
Energy consumption is predicted:User can determine the time period of prediction by setting deadline or number of days, predict the outcome
It is displayed in block diagram and form;
Historical data:User can read the energy consumption data of this period of time, inquiry knot by the time period from database
Fruit be displayed in block diagram and form, when energy consumption data be missing data or abnormal data when, by change display color come
Mark;
Data processing:User processes corresponding history energy consumption data by selecting historical data source, and result is displayed in
In block diagram and form, when having missing data or abnormal data in the history energy consumption data for the treatment of, by the face for changing display
Color is marked;
Help document:For introducing mode of operation and display in detail by way of word is described to aforementioned four function
Explanation.
The present invention has the following advantages and effect relative to prior art:
1st, the present invention is, to the supplement of Intelligent streetlamp monitoring system and perfect, to make the function of Intelligent streetlamp monitoring system more
It is complete, realize the intellectual analysis to street lamp energy consumption and management.
2nd, the problem data that the present invention can be in Classification and Identification and amendment energy consumption data, it is to avoid problem data is supervised to energy consumption
The interference and misleading with energy consumption prediction are surveyed, the reliability and accuracy of energy consumption analysis is improve.
3rd, the present invention can in time have found the problem and failure that street lamp device is present so that the maintenance and maintenance of street lamp device
Much sooner, the safety trip of people has been ensured.
4th, the present invention can in time have found the abnormal power consumption of street lamp device, it is to avoid the waste of electric energy, realize saving electric energy, right
Energy-saving and emission-reduction and environmental protection have great significance.
5th, energy consumption analysis result of the invention can provide reference and foundation for urban electric power upgrading, help to promote
The foundation of " wisdom electric power ", realizes the overall balanced development of " smart city ".
6th, user interface of the present invention simplifies attractive in appearance, simple to operate, availability and highly reliable, can help streetlight monitoring portion
The energy consumption of door real-time monitoring street lamp, contributes to the development and construction of " wisdom street lamp ".
Brief description of the drawings
Fig. 1 a are the design drawings of original energy consumption data table.
Fig. 1 b are the design drawings of the energy consumption data table of amendment.
Fig. 2 is the energy consumption monitoring functional flow diagram of energy consumption monitoring model.
Fig. 3 is the energy consumption forecast function flow chart of energy consumption forecast model.
Fig. 4 is the inquiry of historical data functional flow diagram of the inquiry of historical data model.
Fig. 5 is the data processing function flow chart that energy consumption data processes model.
Fig. 6 is the implementation flow chart of energy consumption monitoring model.
Fig. 7 is the implementation flow chart of energy consumption forecast model.
Fig. 8 is the design drawing of radial basis function neural network model.
Fig. 9 is the implementation flow chart that energy consumption data processes model.
Figure 10 is the interface schematic diagram of energy consumption monitoring function.
Figure 11 is the interface schematic diagram of energy consumption forecast function.
Figure 12 is the interface schematic diagram of historian data record.
Figure 13 is the interface schematic diagram of data processing function.
Figure 14 is to aid in the interface schematic diagram of document function.
Specific embodiment
With reference to embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited
In this.
Intelligent road-lamp energy consumption analysis (the Smart Light Energy based on data mining described in the present embodiment
Consumption Analysis, SLEA) system, using Analysis on Data Mining street lamp energy consumption data, realize street lamp energy consumption
Real-time monitoring, abnormal energy consumption are alarmed, street lamp energy consumption is predicted, street lamp energy consumption data is processed, street lamp energy consumption is inquired about and is derived etc..Specifically
Realize that content is as follows:
First, according to the characteristics of street lamp energy consumption data, energy consumption analysis result and functional requirement, devise for storing energy consumption
The original energy consumption data table of data and the energy consumption data table of amendment.
2nd, the need for according to energy consumption analysis function, realize energy consumption monitoring, energy consumption prediction, historical data, data processing,
Five functions of help document.Wherein, predicted and data processing for energy consumption monitoring, energy consumption, separately designed energy consumption monitoring
(Energy consumption Monitoring, EM) model, energy consumption prediction (Energy consumption
Forecasting, EF) model, energy consumption data treatment (Energy consumption Data Processing, EDP) model.
3rd, the user interface of above-mentioned five functions is had devised and embodied, using the structure and left and right window of single window multi views
The form of lattice, the result of energy consumption analysis is shown using forms such as charts.
Referring to shown in Fig. 1 a and 1b, the Data Sheet Design described in the present embodiment, it includes two tables of data:
1) original energy consumption data table:The original energy consumption data that preservation is collected is not by any amendment or is changed
Data.Mainly include energy consumption record label, terminal number, terminal name, energy consumption acquisition time, power consumption values, data base update time
Etc. field.
1.1) energy consumption record label:Which bar energy consumption record represented.Such as, storage is recorded to first in tables of data, its
Marked as 1;Article 2 is recorded, and it is marked as 2;……
1.2) terminal number:Intelligent streetlamp monitoring system for convenience of street lamp terminal management, be its set one numbering.
1.3) terminal name:It is corresponding with terminal number, it is the title of terminal.
1.4) energy consumption acquisition time:Represent the time of collection street lamp energy consumption data.
1.5) power consumption values:The power consumption values of the street lamp that expression is collected, the i.e. power consumption of street lamp.
1.6) data base update time:Represent the time in the record storage to tables of data.
2) the energy consumption data table of amendment:Preserve by the energy consumption data after amendment, to the missing in original energy consumption data
Data fill up and abnormal data is corrected.Mainly include energy consumption record label, terminal number, terminal name, energy
Whether consumption acquisition time, power consumption values, the power consumption values of amendment, energy consumption are corrected, whether energy consumption is abnormal, whether energy consumption lacks, data
The fields such as storehouse renewal time.
2.1) energy consumption record label, terminal number, terminal name, energy consumption acquisition time, power consumption values:Remember for same energy consumption
Record, the value of these fields of the energy consumption data table of amendment is identical with original energy consumption data table.
2.2) power consumption values of amendment:If energy consumption is normal, the power consumption values corrected are identical with original power consumption values;If energy consumption
Missing is abnormal, then the power consumption values corrected are by the value after algorithm model amendment.
2.3) whether energy consumption is corrected:If energy consumption is corrected, the value be 1, also mean that it is that the energy consumption is missing from or
Abnormal;Otherwise, the value is 0, also means that the energy consumption is normal.
2.4) whether energy consumption is abnormal:If energy consumption exception, the value is 1;Otherwise, the value is 0.
2.5) whether energy consumption lacks:If energy consumption is lacked, the value is 1;Otherwise, the value is 0.
2.6) data base update time:Represent the time in the record storage to tables of data.The time is always than original energy
The data base update time of tables of data is consumed a little later, because energy consumption data is always first stored to original energy consumption data table, Ran Houjing
The energy consumption data table of amendment is then stored into after the analysis and treatment of crossing model.
It is shown in Figure 2, the energy consumption monitoring (Energy consumption Monitoring, EM) described in the present embodiment
Model is, based on local outlier factor algorithm and regression tree, to realize the detection and amendment to abnormal energy consumption data, its specific step
It is rapid as follows:
1) newest street lamp power consumption values (NewE) are received, energy consumption monitoring event is triggered.
2) energy consumption monitoring thread is created.
3) energy consumption data that will be received is stored in original energy consumption data table.
4) call EM models to be analyzed NewE, recognize its generic (normal, missing, exception), and when it is scarce
It is modified when mistake or abnormal data, shown in Figure 6, its implementation is as follows:
4.1) newest energy consumption data is gathered.
4.2) energy consumption data in a period of time recently is read from the energy consumption data table of amendment.
4.3) judge whether energy consumption data lacks, that is, whether the power consumption values for judging collection are 0.If 0 shows that energy consumption lacks
Lose, jump to step 4.5);Otherwise, continue.
4.4) the lof values of the energy consumption data for collecting are calculated using local outlier factor algorithm, judges whether lof values are big
In threshold value.If showing less than if, energy consumption is normal, terminates;Otherwise show energy consumption exception, continue.
Wherein, the computing formula of lof values is as follows:
In formula, k is a numerical value, and kNeighbor (A) represents the k- neighborhoods of A, and B is the sample point in the k- neighborhoods of A.
In all sample points, the k- neighborhoods of sample point A refer to the k sample nearest with sample point A, i.e., k is small before ranking with A
That k sample point.
In formula, reachDensity (A) represents the reachable density of A, i.e. sample point A and all sample points in its k- neighborhoods
Reach distance average value inverse:
In formula:
ReachDistance (A, B) represents the reach distance of the sample B in sample point A and its k- neighborhoods, i.e. sample point
Maximum in the distance of A and sample point B and the k- distances of sample point B:
ReachDistance (A, B)=max { kDistance (B), d (A, B) }, in formula:
KDistance (B) represents the k- distances of sample point A, i.e., sample point near with sample point A kth and the distance of A,
It is exactly that distance apart from ranking kth position of all sample points and A.
4.5) regression tree is set up using recurrence tree algorithm, and uses the regression tree amendment power consumption values set up.
Wherein, the optimal dividing standard of regression tree is built as CART using a square overall error (SSE).
5) by the energy consumption data table of energy consumption monitoring result storage to amendment.
6) energy consumption monitoring result is shown in the block diagram and form at energy consumption monitoring interface.
7) energy consumption monitoring thread is destroyed.
It is shown in Figure 3, energy consumption prediction (Energy consumption Forecasting, EF) described in the present embodiment
Model is, based on radial basis function neural network, to realize the prediction to energy consumption data, and it is comprised the following steps that:
1) user sets predicted time section, triggers energy consumption predicted events.
2) energy consumption prediction thread is created.
3) EF models are called, radial basis function neural network is trained, the power consumption values of the street lamp of time period to be predicted, ginseng are obtained
As shown in Figure 7, its implementation is as follows:
3.1) predicted time section or prediction number of days are set.
3.2) energy consumption data in a period of time recently is read from the energy consumption data table of amendment.
3.3) radial basis function neural network is trained using gradient descent method.
Wherein, radial basis function neural network uses Gaussian function as RBF:
As shown in figure 8, in figure, Layer L1 are input layer to the radial basis function neural network model, and Layer L2 are hidden
Containing layer, Layer L3 are output layer.Input vector is x, and input layer is ω with the connection weight of output layeri, so hidden layer L2
I-th node is output as:
Output layer L3 is output as:
3.4) the neural network prediction street lamp power consumption values obtained using training.
4) energy consumption prediction result is shown in the block diagram and form of energy consumption prediction interface.
5) energy consumption prediction thread is destroyed.
6) user decides whether to derive energy consumption prediction result according to demand.If necessary to derive, then by energy consumption prediction result
Export as csv file.
It is shown in Figure 4, the inquiry of historical data model described in the present embodiment, in the middle of the model, user is by setting
Query time section, the history energy consumption data inquired about in the time period, Query Result will be displayed in block diagram and form, its tool
Body step is as follows:
1) user sets query time section and chooses whether contrast, trigger data query event.
2) data query thread is created.
3) the energy consumption data table of the condition query amendment set according to user.
4) the display data Query Result in the block diagram and form at data query interface.
5) data query thread is destroyed.
6) user decides whether to derive data query result according to demand.If necessary to derive, then by data query result
Export as csv file.
It is shown in Figure 5, energy consumption data treatment (the Energy consumption Data described in the present embodiment
Processing, EDP) model is, based on local outlier factor algorithm and regression tree, to realize the importing to historical data and place
Reason, it is comprised the following steps that:
1) user's selection history energy consumption data source, triggering energy consumption data treatment event.
2) energy consumption data treatment thread is created.
3) the history energy consumption data for selecting user is stored in original energy consumption data table.
4) EDP Modifying model problem energy consumption datas are called, shown in Figure 9, implementation is as follows:
4.1) history energy consumption data is imported from csv file or database.
4.2) missing values in detection energy consumption data.Step 4.4 is jumped to if without missing values);Otherwise, continue.
4.3) regression tree is set up using the energy consumption data for importing, and missing values is filled up using the regression tree set up.
4.4) the lof values of all energy consumption datas are calculated using local outlier factor algorithm, each energy consumption data is judged
Whether lof values are more than threshold value.If being more than threshold value in the absence of lof values, terminate;If there is lof values more than threshold value, show the number
According to exception, continue.
4.5) regression tree is re-established using the energy consumption data after filling up, and corrects abnormal using the regression tree set up
Value.
5) by the energy consumption data table of energy consumption data result storage to amendment.
6) energy consumption data result is shown in the block diagram and form at energy consumption data treatment interface.
7) energy consumption data treatment thread is destroyed.
Referring to shown in Figure 10-14, intelligent road-lamp energy consumption analysis (the Smart Light Energy described in the present embodiment
Consumption Analysis, SLEA) main interface of user interface of system is structure and a left side using single window multi views
The form of right pane, the wherein list of left-hand pane display function, right side pane show the corresponding contents of each function, in left side window
In lattice, when some function is selected, show that the color of the word of the function is changed into black, be otherwise white;Main interface
Feature list includes:Energy consumption monitoring, energy consumption prediction, historical data, data processing, help document this five functional, it is specific as follows:
1. energy consumption monitoring
Energy consumption monitoring function will be triggered when street lamp energy consumption data is collected, energy consumption monitoring interface display energy consumption monitoring
As a result.The content of energy consumption monitoring interface display mainly has:The terminal of current selection, the date of current newest energy consumption data and energy
Consumption value, block diagram show recently a period of time in energy consumption data, form show recently for a period of time in energy consumption data.Energy consumption
Refresh button on observation interface is used for the newest energy consumption monitoring result that manual refreshing shows present terminal.
When finding that energy consumption occurs abnormal, can be marked by changing the shading or gray scale of display in block diagram and form
Know.For example, when energy consumption is normal the pillar of block diagram without shading, the pillar of block diagram is vertical line shading and in pillar when energy consumption is lacked
Top marks " energy consumption missing ", and the pillar of block diagram is oblique line shading and marks that " energy consumption is different at the top of pillar when energy consumption is abnormal
Often ".It is as shown in Figure 10 the interface schematic diagram of energy consumption monitoring function.
2. energy consumption prediction
User can determine the time period of prediction by setting deadline or number of days.Energy consumption prediction interface shows
Content mainly has:Time period, the block diagram of the terminal of current selection, the mode for determining prediction period, the number of days predicted and prediction
Show result, the result of form display prediction of prediction.Prediction button in energy consumption prediction interface is used to set predicted time
Start predicted operation after section, reset button is used to recover the default setting of prediction mode, and data derive button and predicted for deriving
Street lamp energy consumption data.It is as shown in figure 11 the interface schematic diagram of energy consumption forecast function.
3. historical data
User can read the energy consumption data of this period of time by the time period from database.Historical data interface display
Content mainly have:Between at the beginning of terminal, the energy consumption data of current selection and deadline, whether the energy consumption data with amendment
Compare, the result of block diagram display inquiry, form show the result inquired about.Inquiry button on historical data interface is used for
Operation is started a query at after query time section is set, data derive button to be used to derive the street lamp history energy consumption number in this time period
According to.
When energy consumption data is missing data or abnormal data, it is labeled similar to energy consumption monitoring function.Such as Figure 12 institutes
Show be historian data record interface schematic diagram.
4. data processing
User processes corresponding history energy consumption data by selecting historical data source.The content master of data processing interface display
Have:The energy consumption number that the terminal of current selection, the source of energy consumption data, the number of data processing, block diagram display processing are obtained
The energy consumption data obtained according to, form display processing.Data processing button on data processing interface is used in selection data source
After start data processing operation.
When having missing data or abnormal data in the history energy consumption data for the treatment of, rower is entered similar to energy consumption monitoring function
Note.It is as shown in figure 13 the interface schematic diagram of data processing function.
5. help document
To above-mentioned 4 functions (energy consumption monitoring, energy consumption prediction, historical data, data processing) by way of word is described
Its mode of operation and display explanation etc. are introduced in introduction in detail.The content of help document interface display mainly has:Energy consumption monitoring is helped
Help content, energy consumption prediction help content, historical data help content, data processing help content.It is to aid in text as shown in figure 14
The interface schematic diagram of shelves function.
In sum, the present invention is improved and perfect street lamp energy consumption analysis platform, and data mining technology is applied into street lamp
On energy consumption analysis, real-time monitoring, the prediction of street lamp energy consumption, the treatment of street lamp energy consumption data, the street lamp energy consumption number of street lamp energy consumption are realized
According to inquiry and derivation etc., the effective energy consumption of monitoring and management street lamp has impetus, is worth to the development of " wisdom street lamp "
Promote.
Above-described embodiment is the present invention preferably implementation method, but embodiments of the present invention are not by above-described embodiment
Limitation, it is other it is any without departing from Spirit Essence of the invention and the change, modification, replacement made under principle, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (7)
1. a kind of intelligent road-lamp energy consumption analysis system based on data mining, including:
Tables of data, including original energy consumption data table and the energy consumption data table of amendment, the two tables are respectively used to store the original of street lamp
Beginning energy consumption data and energy consumption data after treatment;
Energy consumption monitoring model, for real-time monitoring street lamp energy consumption data, shows monitoring result in graphical form, to abnormal energy consumption number
According to being pointed out and alarmed, and the accuracy predicted for later energy consumption monitoring and energy consumption, abnormal energy consumption data is carried out
Amendment;
Energy consumption forecast model, for predicting street lamp following a period of time in power consumption values, display in graphical form predicts the outcome, and
And csv file can be exported as by predicting the outcome;
The inquiry of historical data model, for inquiring about street lamp history energy consumption data, shows Query Result in graphical form, can select
Whether by original energy consumption data with amendment energy consumption data contrasted, so as to have to abnormal energy consumption one become apparent from recognize
Know, and place's Query Result can be exported as csv file;
Energy consumption data processes model, and for importing and processing street lamp history energy consumption data, display processing result, right in graphical form
Abnormal data in historical data is modified, and in the data and the data Cun Chudao databases of amendment that will be imported;
User interface, in the form of the structure and left and right pane of single window multi views, while showing energy consumption using diagrammatic form
The result of analysis.
2. a kind of intelligent road-lamp energy consumption analysis system based on data mining according to claim 1, it is characterised in that:Institute
It, for preserving the original energy consumption data for collecting, is the number not by any amendment or modification that the original energy consumption data table stated is
According to, including energy consumption record label, terminal number, terminal name, energy consumption acquisition time, power consumption values, data base update time these words
Section, wherein:
Energy consumption records label:Which bar energy consumption record represented;
Terminal number:Intelligent streetlamp monitoring system for convenience of street lamp terminal management, be its set one numbering;
Terminal name:It is corresponding with terminal number, it is the title of terminal;
Energy consumption acquisition time:Represent the time of collection street lamp energy consumption data;
Power consumption values:The power consumption values of the street lamp that expression is collected, the i.e. power consumption of street lamp;
Data base update time:Represent the time in the record storage to tables of data;
The energy consumption data table of described amendment is for preserving by the energy consumption data after amendment, in original energy consumption data
Missing data is filled up and abnormal data is corrected, including energy consumption record label, terminal number, terminal name, energy consumption are adopted
The collection time, power consumption values, the power consumption values of amendment, whether energy consumption is corrected, whether energy consumption abnormal, whether energy consumption lacks, database more
New these fields of time, wherein:
Energy consumption record label, terminal number, terminal name, energy consumption acquisition time, power consumption values:For same energy consumption record, amendment
Energy consumption data table these fields value it is identical with original energy consumption data table;
The power consumption values of amendment:If energy consumption is normal, the power consumption values corrected are identical with original power consumption values, if energy consumption missing or different
Often, then the power consumption values corrected are by the value after amendment;
Whether energy consumption is corrected:If energy consumption is corrected, the value be 1, also mean that it is that the energy consumption is missing from or exception, it is no
Then, the value is 0, also means that the energy consumption is normal;
Whether energy consumption is abnormal:If energy consumption exception, the value is 1, and otherwise, the value is 0;
Whether energy consumption lacks:If energy consumption is lacked, the value is 1, and otherwise, the value is 0;
Data base update time:The time in the record storage to tables of data is represented, the time is always than original energy consumption data table
Data base update time evening because energy consumption data always first storage is to original energy consumption data table, then by the analysis of model
With the energy consumption data table that amendment is then stored into after treatment.
3. a kind of intelligent road-lamp energy consumption analysis system based on data mining according to claim 1, it is characterised in that:Institute
The energy consumption monitoring model stated is, based on local outlier factor algorithm and regression tree, to realize to the detection of abnormal energy consumption data and repair
Just, comprise the following steps that:
1) newest street lamp power consumption values are received, energy consumption monitoring event is triggered;
2) energy consumption monitoring thread is created;
3) energy consumption data that will be received is stored in original energy consumption data table;
4) call energy consumption monitoring model to be analyzed street lamp power consumption values, recognize its generic, the category point has normal, scarce
Mistake, exception, and be modified when it is missing or abnormal data, its implementation is as follows:
4.1) newest energy consumption data is gathered;
4.2) energy consumption data in a period of time recently is read from the energy consumption data table of amendment;
4.3) judge whether energy consumption data lacks, that is, whether the power consumption values for judging collection are 0, if 0 shows that energy consumption is lacked, jump
To step 4.5), otherwise, continue;
4.4) the lof values of the energy consumption data for collecting are calculated using local outlier factor algorithm, judges lof values whether more than threshold
Value, if showing less than if, energy consumption is normal, terminates, and otherwise shows energy consumption exception, continues;
4.5) regression tree is set up using recurrence tree algorithm, and uses the regression tree amendment power consumption values set up;
5) by the energy consumption data table of energy consumption monitoring result storage to amendment;
6) energy consumption monitoring result is shown in the block diagram and form at energy consumption monitoring interface;
7) energy consumption monitoring thread is destroyed.
4. a kind of intelligent road-lamp energy consumption analysis system based on data mining according to claim 1, it is characterised in that:Institute
The energy consumption forecast model stated is, based on radial basis function neural network, to realize the prediction to energy consumption data, and it is comprised the following steps that:
1) user sets predicted time section, triggers energy consumption predicted events;
2) energy consumption prediction thread is created;
3) energy consumption forecast model is called, radial basis function neural network is trained, the power consumption values of the street lamp of time period to be predicted are obtained,
Its implementation is as follows:
3.1) predicted time section or prediction number of days are set;
3.2) energy consumption data in a period of time recently is read from the energy consumption data table of amendment;
3.3) radial basis function neural network is trained using gradient descent method;
3.4) the neural network prediction street lamp power consumption values obtained using training;
4) energy consumption prediction result is shown in the block diagram and form of energy consumption prediction interface;
5) energy consumption prediction thread is destroyed;
6) user decides whether to derive energy consumption prediction result according to demand, if necessary to derive, then derives energy consumption prediction result
It is csv file.
5. a kind of intelligent road-lamp energy consumption analysis system based on data mining according to claim 1, it is characterised in that:
In the middle of the inquiry of historical data model, user by setting query time section, the history energy consumption data inquired about in the time period,
Query Result will be displayed in block diagram and form, and it is comprised the following steps that:
1) user sets query time section and chooses whether contrast, trigger data query event;
2) data query thread is created;
3) the energy consumption data table of the condition query amendment set according to user;
4) the display data Query Result in the block diagram and form at data query interface;
5) data query thread is destroyed;
6) user decides whether to derive data query result according to demand, if necessary to derive, then derives data query result
It is csv file.
6. a kind of intelligent road-lamp energy consumption analysis system based on data mining according to claim 1, it is characterised in that:Institute
The energy consumption data treatment model stated is, based on local outlier factor algorithm and regression tree, to realize the importing to historical data and place
Reason, it is comprised the following steps that:
1) user's selection history energy consumption data source, triggering energy consumption data treatment event;
2) energy consumption data treatment thread is created;
3) the history energy consumption data for selecting user is stored in original energy consumption data table;
4) energy consumption data is called to process Modifying model problem energy consumption data, implementation is as follows:
4.1) history energy consumption data is imported from csv file or database;
4.2) missing values in detection energy consumption data, jump to step 4.4 if without missing values), otherwise, continue;
4.3) regression tree is set up using the energy consumption data for importing, and missing values is filled up using the regression tree set up;
4.4) the lof values of all energy consumption datas are calculated using local outlier factor algorithm, the lof values of each energy consumption data are judged
Whether it is more than threshold value, if being more than threshold value in the absence of lof values, terminates, if there is lof values more than threshold value, shows that the data are different
Often, continue;
4.5) regression tree is re-established using the energy consumption data after filling up, and exceptional value is corrected using the regression tree set up;
5) by the energy consumption data table of energy consumption data result storage to amendment;
6) energy consumption data result is shown in the block diagram and form at energy consumption data treatment interface;
7) energy consumption data treatment thread is destroyed.
7. a kind of intelligent road-lamp energy consumption analysis system based on data mining according to claim 1, it is characterised in that:Institute
The main interface for stating user interface is that wherein left-hand pane shows work(in the form of the structure and left and right pane of single window multi views
Energy list, right side pane shows the corresponding contents of each function;The feature list of main interface includes:Energy consumption monitoring, energy consumption prediction,
Historical data, data processing, help document this five functional, it is specific as follows:
Energy consumption monitoring:Energy consumption monitoring result is displayed in block diagram and form, when finding that energy consumption occurs abnormal, in block diagram and
Can be identified by changing the color of display in form;
Energy consumption is predicted:User can determine the time period of prediction by setting deadline or number of days, and predict the outcome display
In block diagram and form;
Historical data:User can read the energy consumption data of this period of time by the time period from database, and Query Result shows
Show in block diagram and form, when energy consumption data is missing data or abnormal data, marked by changing the color of display;
Data processing:User processes corresponding history energy consumption data by selecting historical data source, and result is displayed in column
Figure and form in, when treatment history energy consumption data in have missing data or abnormal data when, by change display color come
Mark;
Help document:Said for introducing aforementioned four function mode of operation in detail by way of word is described and showing
It is bright.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710091740.4A CN106886591A (en) | 2017-02-21 | 2017-02-21 | A kind of intelligent road-lamp energy consumption analysis system based on data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710091740.4A CN106886591A (en) | 2017-02-21 | 2017-02-21 | A kind of intelligent road-lamp energy consumption analysis system based on data mining |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106886591A true CN106886591A (en) | 2017-06-23 |
Family
ID=59180000
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710091740.4A Pending CN106886591A (en) | 2017-02-21 | 2017-02-21 | A kind of intelligent road-lamp energy consumption analysis system based on data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106886591A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109710702A (en) * | 2018-12-28 | 2019-05-03 | 税友软件集团股份有限公司 | A kind of tables of data processing method, device, equipment and medium |
CN112102105A (en) * | 2019-05-28 | 2020-12-18 | 中华电信股份有限公司 | Street lamp loop abnormity analysis method and device |
CN116523181A (en) * | 2023-05-22 | 2023-08-01 | 中国标准化研究院 | Intelligent green energy monitoring and analyzing method and system based on big data |
CN117077899A (en) * | 2023-10-16 | 2023-11-17 | 四川邕合科技有限公司 | Intelligent park energy consumption anomaly monitoring and analyzing method, system, terminal and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289585A (en) * | 2011-08-15 | 2011-12-21 | 重庆大学 | Real-time monitoring method for energy consumption of public building based on data mining |
CN103310088A (en) * | 2012-03-16 | 2013-09-18 | 同济大学 | Automatic detecting method of abnormal illumination power consumption |
CN103559576A (en) * | 2013-10-30 | 2014-02-05 | 广东工业大学 | Energy management system |
WO2015073996A3 (en) * | 2013-11-15 | 2015-10-29 | Bidgely Inc. | Solar energy disaggregation techniques for whole-house energy consumption data |
CN105117988A (en) * | 2015-10-14 | 2015-12-02 | 国家电网公司 | Method for interpolating missing data in electric power system |
CN105590174A (en) * | 2015-12-29 | 2016-05-18 | 南京因泰莱电器股份有限公司 | Enterprise power consumption load prediction method based on K-means clustering RBF neural network |
CN106055696A (en) * | 2016-06-15 | 2016-10-26 | 南京威联达自动化技术有限公司 | Motor protection controller for achieving energy efficiency management and energy conservation through data mining technology |
-
2017
- 2017-02-21 CN CN201710091740.4A patent/CN106886591A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102289585A (en) * | 2011-08-15 | 2011-12-21 | 重庆大学 | Real-time monitoring method for energy consumption of public building based on data mining |
CN103310088A (en) * | 2012-03-16 | 2013-09-18 | 同济大学 | Automatic detecting method of abnormal illumination power consumption |
CN103559576A (en) * | 2013-10-30 | 2014-02-05 | 广东工业大学 | Energy management system |
WO2015073996A3 (en) * | 2013-11-15 | 2015-10-29 | Bidgely Inc. | Solar energy disaggregation techniques for whole-house energy consumption data |
CN105117988A (en) * | 2015-10-14 | 2015-12-02 | 国家电网公司 | Method for interpolating missing data in electric power system |
CN105590174A (en) * | 2015-12-29 | 2016-05-18 | 南京因泰莱电器股份有限公司 | Enterprise power consumption load prediction method based on K-means clustering RBF neural network |
CN106055696A (en) * | 2016-06-15 | 2016-10-26 | 南京威联达自动化技术有限公司 | Motor protection controller for achieving energy efficiency management and energy conservation through data mining technology |
Non-Patent Citations (1)
Title |
---|
杨文人: "基于能耗预测模型的能源管理系统研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109710702A (en) * | 2018-12-28 | 2019-05-03 | 税友软件集团股份有限公司 | A kind of tables of data processing method, device, equipment and medium |
CN112102105A (en) * | 2019-05-28 | 2020-12-18 | 中华电信股份有限公司 | Street lamp loop abnormity analysis method and device |
CN116523181A (en) * | 2023-05-22 | 2023-08-01 | 中国标准化研究院 | Intelligent green energy monitoring and analyzing method and system based on big data |
CN116523181B (en) * | 2023-05-22 | 2024-01-26 | 中国标准化研究院 | Intelligent green energy monitoring and analyzing method and system based on big data |
CN117077899A (en) * | 2023-10-16 | 2023-11-17 | 四川邕合科技有限公司 | Intelligent park energy consumption anomaly monitoring and analyzing method, system, terminal and medium |
CN117077899B (en) * | 2023-10-16 | 2023-12-22 | 四川邕合科技有限公司 | Intelligent park energy consumption anomaly monitoring and analyzing method, system, terminal and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106886591A (en) | A kind of intelligent road-lamp energy consumption analysis system based on data mining | |
CN103853106B (en) | A kind of energy consumption Prediction Parameters optimization method of building energy supplied equipment | |
CN106171047A (en) | There is intelligent illuminating system and the method for operation thereof of predictive maintenance scheduling | |
CN106997669B (en) | Method for judging traffic jam cause based on feature importance | |
CN110555568B (en) | Road traffic running state real-time perception method based on social network information | |
CN114118224B (en) | Neural network-based full-system telemetry parameter anomaly detection system | |
CN107481511A (en) | A kind of method and system for calculating candidate bus station | |
CN106447584A (en) | Highway network operation-oriented decision support system and using method thereof | |
CN111861211B (en) | System with double-layer anti-electricity-stealing model | |
CN106709017A (en) | Big data-based aid decision making method | |
CN105046456A (en) | GIS-based intelligent monitoring method for land full life circle | |
CN104537052B (en) | Traffic trip transfer point recognition methods based on wavelet analysis Study of modulus maximum algorithm | |
CN109933637A (en) | A kind of flood risk Dynamic Display and analysis system | |
CN108830413A (en) | A kind of the visualization prediction technique and system of building energy consumption | |
CN104598548B (en) | A kind of method and device of anal yzing agricul products price space relevance | |
CN111985716A (en) | Passenger traffic prediction system with visualized passenger traffic information | |
CN105243841A (en) | Real-time road condition acquisition and prediction method based on site map | |
CN107506937B (en) | Hydropower station power generation capacity evaluation method based on association rule | |
CN102495856B (en) | Generating method of pedestribusiness district based on electronic map | |
Yang | Analysis of the Impacts of Open Residential Communities on Road Traffic Based on AHP and Fuzzy Theory. | |
CN113159473A (en) | Big data correlation index intelligent recommendation model, modeling method and modeling device | |
Bagheri et al. | Application of GIS and AHP technique for land-use suitability analysis on coastal area in terengganu | |
Banks et al. | Modelling changes in dimensions, health status, and arboricultural implications for urban trees | |
CN103235804A (en) | Presentation method and presentation platform of energy, economy and environment data | |
Zhu et al. | Rural road network planning based on 5g and traffic big data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170623 |