CN109685258A - A kind of method and system of the intelligent irrigation model optimization based on big data - Google Patents
A kind of method and system of the intelligent irrigation model optimization based on big data Download PDFInfo
- Publication number
- CN109685258A CN109685258A CN201811532193.XA CN201811532193A CN109685258A CN 109685258 A CN109685258 A CN 109685258A CN 201811532193 A CN201811532193 A CN 201811532193A CN 109685258 A CN109685258 A CN 109685258A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- big data
- irrigation
- intelligent irrigation
- 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
- 230000002262 irrigation Effects 0.000 title claims abstract description 65
- 238000003973 irrigation Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000005457 optimization Methods 0.000 title claims abstract description 28
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 72
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 241001269238 Data Species 0.000 claims abstract description 12
- 239000000284 extract Substances 0.000 claims abstract description 6
- 238000009826 distribution Methods 0.000 claims description 25
- 238000003860 storage Methods 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 17
- 239000003621 irrigation water Substances 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 13
- 238000004088 simulation Methods 0.000 claims description 12
- 239000002689 soil Substances 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000005192 partition Methods 0.000 claims description 6
- 238000001556 precipitation Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013523 data management Methods 0.000 claims description 3
- 230000003698 anagen phase Effects 0.000 claims 1
- 238000012163 sequencing technique Methods 0.000 claims 1
- 230000006399 behavior Effects 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 4
- 238000007792 addition Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000008235 industrial water Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000037039 plant physiology Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 239000008400 supply water Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06Q10/04—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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q50/06—Energy or water supply
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method and system of the invention discloses a kind of intelligent irrigation model optimization based on big data belongs to wisdom hydrotechnics field, and this method is based on big data and handles and store, and a large amount of all kinds of irrigation related datas of upload are pre-processed by distributed memory system;Intelligent irrigation model uses Distributed Parallel Computing, calculating task is decomposed, each submodel is assigned to an independent computing unit and extracts corresponding data from corresponding partitioned file as a Map operation and is calculated, the calculated result of model is then merged into calculating analysis in Reduce operation.A kind of system of the intelligent irrigation model optimization based on big data, including data memory module and data computation analysis module.The present invention solves the problems, such as that regional water lacks and the determination of water resources rational allocation plan provides theoretical foundation using big data, and the quality for irrigating model, the precision of computational efficiency and calculated result can be greatly improved by model optimization.
Description
Technical field
The present invention relates to intelligent water conservancy technical fields, and in particular to a kind of intelligent irrigation model optimization based on big data
Method and system.
Background technique
China's water resource of per capita is about 2350m3, it is only equivalent to the 1/4 of world's per capita share, and water resource spatial and temporal distributions
Unevenly, especially northern area, cultivated area accounts for the 59.2% of the whole nation, and water resources quantity only accounts for the 14.7% of the whole nation.Currently,
China's agricultural water accounts for 70% of total water consumption or more, wherein 90% is used to irrigate, but ageing equipment of being poured water, irrigation technique are fallen
Afterwards with the influence of Irrigation Water mismanagement, the water efficiency of irrigation in China is caused there was only 0.5 or so, Jin Zhan developed country
70%.Meanwhile with the rapid development of social economy, the competition day of industrial water, cities and towns water, water-use for environment and agricultural water
It is beneficial fierce, it results in irrigation water imbalance between supply and demand and is on the rise.Therefore, scientific management irrigation water process, establishes irrigation water
Optimal Allocation Model promotes irrigated area ecological environment and economic sustainable development for efficiently utilizing the limited water resource in irrigated area
It is of great significance.
Current widely used irrigation model has:
Regional water balance model: its theoretical basis is the law of indestructibility of matter, input water and output within the given period
The difference of water is equal to the variable quantity of same period soil storage: duty+balance period rainfall+soil is aqueous early period
Amount-the water demand of crop-Surface Runoff amount=same period soil moisture content+precipitation recharge of phreatic water amount and anastatic water amount it
Difference+error.Since demand data type and data volume are too many, the theory that model is often used in the monocrop of single area is real
Test in research, therefore, such model usually has region and crop specific aim, it is complicated and changeable for irrigated area area situation in
State, the water plan formulated by this model and irrigation program can not almost implement use.
BP neural network model: the principal element of influence area crop structure has areal precipitation, ragional evaporation, region
The irrigated area in temperature on average and region.In a model, irrigation volume is explained variable, plant physiology index and temperature,
For the weather environments such as humidity, intensity of illumination factor as explanatory variable, the foundation of model includes that the network number of plies and neural network are each
The selection of neuron number in layer.If the number of neural net layer neuron is very few, network is difficult to identify sample, it is difficult to complete
Training, and the fault-tolerance of network can also reduce;If number is excessive, the number of iterations of network will increase, to extend net
The training time of network can also reduce the generalization ability of network, predictive ability is caused to decline.This just largely relies on computer
Calculated performance, in addition, BP neural network structure directly affects the approximation capability of network and promotes property, however network structure
Selection there is no a kind of unification and complete theoretical direction so far, can only generally be selected by experience.
Grey Theory Forecast model: the Water Consumption in Agriculture data that the time has occurred are utilized in model, establish agricultural water
The time series of no evident regularity is become regular time series by processing, thus in advance by the function of amount and time relationship
Survey unknown time agricultural water consumption.This method only in accordance with historical water usage to predict the following water consumption means gray theory
Prediction model is not particularly suited in the research of high efficient utilization of water resources and reasonable distribution management, because historical water usage is not intended to
Optimal water consumption, only in accordance with historical water usage data, the distribution of water resource can not reasonably be optimized.
In conclusion being limited to can be used to the accuracy and extensive use property of the simulation of reasonable irrigation water capacity in the prior art
Data class and data volume, and irrigate modeling authenticity and its calculated performance.
Summary of the invention
Technical assignment of the invention is to provide a kind of method and system of intelligent irrigation model optimization based on big data, benefit
With big data to solve the problems, such as that regional water lacks and the determination of water resources rational allocation plan provides theoretical foundation, and energy
Greatly improve the quality for irrigating model, the precision of computational efficiency and calculated result.
The technical solution adopted by the present invention to solve the technical problems is:
A method of the intelligent irrigation model optimization based on big data, this method are based on big data and handle and store, on
The a large amount of all kinds of irrigation related datas passed are pre-processed by distributed memory system;
Intelligent irrigation model uses Distributed Parallel Computing, decomposes to calculating task, using each submodel as one
Map operation, which is assigned to an independent computing unit and extracts corresponding data from corresponding partitioned file, to be calculated, so
The calculated result of model is merged into calculating analysis in Reduce operation afterwards.
Further, for the calling and service of intelligent irrigation model, one can all be started newly every time in systems by calling
Calculating task, and use asynchronous call mode, avoid long-time numerical behavior block model client end.The operation is after starting task
It returns, and exports the unique identifying number of task, and model client end can be according to the identification number query task state or execution
Other operations.
Preferably, the big data processing and storage are big data processing and storage based on GIS, a large amount of all kinds of fillings
Irrigating related data includes climatic data, environmental data and supply and demand water number evidence.Various types of data will be classified based on GIS geography information and be drawn
The otherness in region is embodied in area, thus expands the regional scope of model application, improves the popularity of model application.
Specifically, a large amount of all kinds of irrigation related datas are pre-processed by distributed storage system, by data according to it
Corresponding geography information and attribute carry out classification partition and carry out deleting to change looking into exceptional value;
By being grouped, the data in same region arrange sequentially in time to be stored the irrigation related data of different regions
It is managed in identical region, the exceptional values of some apparent errors is subjected to deleting to change and look under rule;
These data are stored in the database after pretreatment, and by functions such as query search, related data can
It is accurately extracted rapidly and carries out calculating analysis.
In addition, multidimensional analysis instrument and instrument can be passed through based on the distributed big data processing and storage system, user
Disk is directly realized by and shows to the flexible analysis of data and Visual Chart.
Preferably, the intelligent irrigation model is mainly made of three submodels: climate model, crop modeling and for moisture
With model, wherein
Climate model mainly calculates the effective precipitation that soil can store;Crop modeling simulates various crops under varying environment
In the optimal water requirement of different stages of growth;The natural supply situation in the regional underground water of water supply distribution model combination and river,
Always water supply situation and other regional work need regimen condition to optimize distribution simulation to Agricultural Irrigation Water amount to Qu;
By Distributed Parallel Computing by the climate model and crop modeling separate computations to improve computational efficiency, then will
The result data obtained carries out the Optimized Simulated of Agricultural Irrigation Water amount as the part input data of water supply distribution model.?
In the calculating process of MapReduce, calculating task is decomposed first, is assigned to each submodel as a Map operation
One independent computing unit simultaneously extracts corresponding data from corresponding partitioned file and is calculated, then by the calculating of model
As a result calculating analysis is merged in Reduce operation.
The system of the invention also discloses a kind of intelligent irrigation model optimization based on big data, including data memory module
With data computation analysis module.
Data memory module is used to irrigate the storage of related big data and a large amount of simulation output data, using distributed number
According to processing and storage;
Using distributed file system, a large amount of related data of irrigating rapidly can be provided convenient for raising for each submodel
Irrigate the popularity of model application region and its accuracy of simulation;In addition, by distributed file system, user can pass through
Multidimensional analysis instrument and instrument board are directly realized by and show to the flexible analysis of data and Visual Chart.
Rapid computations and interpretation of result of the data computation analysis module for intelligent irrigation model, using distributed parallel meter
It calculates;
Using MapReduce parallel computation engine, it is able to solve the problem that super large file process is difficult and efficiency is lower, is mentioned
High model computational efficiency.
Further, the data memory module specifically includes:
The data management function of Hadoop database is provided, including data source connection, builds library and builds table, subregion, column family, data
Additions and deletions change and look into and upload downloading data online management function;
Distributed file system is provided, is deposited for the magnanimity to structural data, semi-structured data, unstructured data
Storage.
Further, the data computation analysis module specifically includes:
With to mass data distributed computation ability, using Hadoop MapReduce distributed computing engine and
The function of definition and the scheduling of calculating task;
Have the function of quoting measured data calculation optimization model parameter in large database concept automatically.
For the calling and service of intelligent irrigation model, a new calculating can all be started every time in systems by, which calling, appoints
Business, and use asynchronous call mode.
Preferably, the data memory module is pretreatment and storage based on GIS big data, a large amount of all kinds of fillings of upload
Irrigating related data includes climatic data, environmental data and supply and demand water number evidence, and the irrigation related data of different regions is by grouping, together
Data in one region, which arrange to be stored in identical region sequentially in time, to be managed, to the different of some apparent errors
Constant value carries out deleting to change and look under rule.
Preferably, the intelligent irrigation model is mainly made of three submodels: climate model, crop modeling and for moisture
With model, Distributed Parallel Computing by climate model and crop modeling separate computations, then using the result data obtained as supply water
The part input data of distribution model carries out the Optimized Simulated of Agricultural Irrigation Water amount.It is first in the calculating process of MapReduce
First calculating task is decomposed, is assigned to an independent computing unit using each submodel as Map operation and from right
Corresponding data are extracted in the partitioned file answered to be calculated, and then close the calculated result of model in Reduce operation
And calculate analysis.
A kind of method and system of intelligent irrigation model optimization based on big data of the invention compared with prior art, has
Have it is following the utility model has the advantages that
This method is directed to agricultural water resources reasonable distribution difficulty problem, provides all kinds of mass datas of model calculation needs simultaneously
It is grouped processing to it, traditional irrigation model calculation process is optimized in the way of parallel computation, and is tied to calculating
Fruit data carry out Dynamic Integration and evaluation and test, substantially increase the quality for irrigating model, the precision of computational efficiency and calculated result.
Big data pretreatment and storage based on GIS, the calling and service of Distributed Parallel Computing and a variety of models are all kinds of
Data are classified partition based on GIS geography information to embody the otherness in region, thus expand the regional scope of model application, mention
The popularity of high model application;Under the limitation of server system performance, this method and system are due to having used distributed document
System rapidly can provide a large amount of related data of irrigating for each submodel and irrigate the extensive of model application region convenient for improving
Property and its simulation accuracy, and to solve super large file process difficult and imitate for the application of MapReduce parallel computation engine
The lower deficiency of rate improves model computational efficiency.
Detailed description of the invention
Fig. 1 is the flow chart of the intelligent irrigation model optimization method the present invention is based on big data.
Specific embodiment
The present invention is further explained in the light of specific embodiments.
A method of the intelligent irrigation model optimization based on big data, this method are based on big data and handle and store, on
The a large amount of all kinds of irrigation related datas passed are pre-processed by distributed memory system.
In one embodiment of the invention, big data processing and storage are big data processing and storage based on GIS, institute
Stating a large amount of all kinds of irrigation related datas includes climatic data, environmental data and supply and demand water number evidence.Wherein, the data packet of climatic factor
Include rainfall, temperature, humidity and illumination;The data of environmental factor include soil, crop, underground water and river;Water supply needs regimen condition
Data include that the total water supply situation in area and regional other need regimen condition.Various types of data, which is based on GIS geography information, will be classified partition
It embodies the otherness in region, thus expands the regional scope of model application, improve the popularity of model application.
A large amount of all kinds of irrigation related datas are pre-processed by distributed storage system, correspondingly according to its by data
Reason information and attribute carry out classification partition and carry out deleting to change looking into exceptional value;
By being grouped, the data in same region arrange sequentially in time to be stored the irrigation related data of different regions
It is managed in identical region, the exceptional values of some apparent errors is subjected to deleting to change and look under rule;
These data are stored in the database after pretreatment, and by functions such as query search, related data can
It is accurately extracted rapidly and carries out calculating analysis.
In addition, multidimensional analysis instrument and instrument can be passed through based on the distributed big data processing and storage system, user
Disk is directly realized by and shows to the flexible analysis of data and Visual Chart.
In the method, intelligent irrigation model uses Distributed Parallel Computing, decomposes to calculating task, by each submodule
Type be assigned to an independent computing unit as Map operation and extracted from corresponding partitioned file corresponding data into
Row calculates, and the calculated result of model is then merged calculating analysis in Reduce operation.
For the calling and service of intelligent irrigation model, a new calculating can all be started every time in systems by, which calling, appoints
Business, and asynchronous call mode is used, avoid long-time numerical behavior from blocking model client end.The operation returns after starting task,
And the unique identifying number of task is exported, and model client end according to the identification number query task state or can execute other behaviour
Make.
In one embodiment of the invention, the intelligent irrigation model is mainly made of three submodels: climate model,
Crop modeling and water supply distribution model, wherein
Climate model mainly calculates the effective precipitation that soil can store;Crop modeling simulates various crops under varying environment
In the optimal water requirement of different stages of growth;The natural supply situation in the regional underground water of water supply distribution model combination and river,
Always water supply situation and other regional work need regimen condition to optimize distribution simulation to Agricultural Irrigation Water amount to Qu.
By Distributed Parallel Computing by the climate model and crop modeling separate computations to improve computational efficiency, then will
The result data obtained carries out the Optimized Simulated of Agricultural Irrigation Water amount as the part input data of water supply distribution model.?
In the calculating process of MapReduce, calculating task is decomposed first, is assigned to each submodel as a Map operation
One independent computing unit simultaneously extracts corresponding data from corresponding partitioned file and is calculated, then by the calculating of model
As a result calculating analysis is merged in Reduce operation.
This method mainly for agricultural water resources reasonable distribution hardly possible problem, it is a set of by making rational planning for, designing and building
The method for irrigating model using the intelligent optimization of big data technology, in different regions, the difference of soil property and crop species
Different and regulatory requirement optimizes agricultural irrigation model in conjunction with the corresponding design data in each department, passes through the irrigation model after optimization, mould
Quasi- water requirement of the Different Crop under different regions and Different climate environment, to solve the problems, such as that regional water lacks and water provides
The determination of source reasonable distribution scheme provides theoretical foundation.
In one embodiment of the invention, also disclose a kind of intelligent irrigation model optimization based on big data is
System, including data memory module and data computation analysis module.
Data memory module is used to irrigate the storage of related big data and a large amount of simulation output data, using distributed number
According to processing and storage;
Using distributed file system, a large amount of related data of irrigating rapidly can be provided convenient for raising for each submodel
Irrigate the popularity of model application region and its accuracy of simulation;In addition, by distributed file system, user can pass through
Multidimensional analysis instrument and instrument board are directly realized by and show to the flexible analysis of data and Visual Chart.
The data memory module specifically includes:
The data management function of Hadoop database is provided, including data source connection, builds library and builds table, subregion, column family, data
Additions and deletions change and look into and upload downloading data online management function;
Distributed file system is provided, is deposited for the magnanimity to structural data, semi-structured data, unstructured data
Storage.
Rapid computations and interpretation of result of the data computation analysis module for intelligent irrigation model, using distributed parallel meter
It calculates;
Using MapReduce parallel computation engine, it is able to solve the problem that super large file process is difficult and efficiency is lower, is mentioned
High model computational efficiency.
The data computation analysis module specifically includes:
With to mass data distributed computation ability, using Hadoop MapReduce distributed computing engine and
The function of definition and the scheduling of calculating task;
Have the function of quoting measured data calculation optimization model parameter in large database concept automatically.
Wherein, the data memory module is pretreatment and storage based on GIS big data, a large amount of all kinds of irrigations of upload
Related data includes climatic data, environmental data and supply and demand water number evidence, and climatic data, environmental data and supply and demand water number are according to through excessive
Cloth stocking system is pre-processed, and data are carried out classification partition and to exceptional value according to its corresponding geography information and attribute
It carries out deleting to change looking into.By being grouped, the data in same region arrange the irrigation related data of different regions sequentially in time
It is stored in identical region and is managed, deleting to change and look under rule is carried out to the exceptional values of some apparent errors.These
Data are stored in the database after pretreatment, by functions such as query search, related data can rapidly accurately by
It extracts and carries out calculating analysis.
The intelligent irrigation model is mainly made of three submodels: climate model, crop modeling and water supply distribution model.
Wherein, climate model mainly calculates the effective precipitation that soil can store, and crop modeling simulates under varying environment, various crops
In the optimal water requirement of different stages of growth, water supply distribution model then combines the natural supply situation in regional underground water and river,
And the total water supply situation in area and other regional work need regimen condition to optimize distribution simulation to Agricultural Irrigation Water amount.Distribution
Climate model and crop modeling separate computations are improved computational efficiency by formula parallel computation, then using the result data obtained as water supply
The part input data of distribution model carries out the Optimized Simulated of Agricultural Irrigation Water amount.It is first in the calculating process of MapReduce
First calculating task is decomposed, is assigned to an independent computing unit using each submodel as Map operation and from right
Corresponding data are extracted in the partitioned file answered to be calculated, and then close the calculated result of model in Reduce operation
And calculate analysis.
For the calling and service of intelligent irrigation model, a new calculating can all be started every time in systems by, which calling, appoints
Business, and asynchronous call mode is used, avoid long-time numerical behavior from blocking model client end.The operation returns after starting task,
And the unique identifying number of task is exported, and model client end according to the identification number query task state or can execute other behaviour
Make.
By using the system, efficiently solve it is existing because model caused by data available is insufficient and dispersion is localized and
The problem of the problem of simulating authenticity and super large file data processing time length, low efficiency, which proposes that one kind can mention
For enough crop structure related datas and it is widely used in the high-efficient treatment methods of each department, and can solve at super large file
Reason difficulty and the lower deficiency of efficiency, improve the accuracy and computational efficiency of modeling.
The technical personnel in the technical field can readily realize the present invention with the above specific embodiments,.But it answers
Work as understanding, the present invention is not limited to above-mentioned specific embodiments.On the basis of the disclosed embodiments, the technical field
Technical staff can arbitrarily combine different technical features, to realize different technical solutions.
Claims (10)
1. a kind of method of the intelligent irrigation model optimization based on big data, it is characterised in that this method be based on big data handle and
A large amount of all kinds of irrigation related datas of storage, upload are pre-processed by distributed memory system;
Intelligent irrigation model uses Distributed Parallel Computing, decomposes to calculating task, grasps each submodel as a Map
It is assigned to an independent computing unit and extracts corresponding data from corresponding partitioned file and calculated, then by mould
The calculated result of type merges calculating analysis in Reduce operation.
2. a kind of method of intelligent irrigation model optimization based on big data according to claim 1, it is characterised in that right
In the calling and service of intelligent irrigation model, calls start a new calculating task in systems every time, and use asynchronous tune
Use mode.
3. a kind of method of intelligent irrigation model optimization based on big data according to claim 1, it is characterised in that institute
It states big data processing and storage is big data processing and storage based on GIS, a large amount of all kinds of irrigation related datas include gas
Wait data, environmental data and supply and demand water number evidence.
4. a kind of method of intelligent irrigation model optimization based on big data according to claim 1 or 3, it is characterised in that
A large amount of all kinds of irrigation related datas are pre-processed by distributed storage system, by data according to its corresponding geography information and
Attribute carries out classification partition and carries out deleting to change looking into exceptional value;
For the irrigation related data of different regions by being grouped, the data in same region arrange sequentially in time is stored in phase
With region in be managed, the exceptional values of some apparent errors is subjected to deleting to change and look under rule;
These data are stored in the database after pretreatment, and by functions such as query search, related data can be rapid
It is accurately extracted and carries out calculating analysis.
5. a kind of method of intelligent irrigation model optimization based on big data according to claim 1 or 2 or 3, feature
It is that the intelligent irrigation model is mainly made of three submodels: climate model, crop modeling and water supply distribution model,
In,
Climate model mainly calculates the effective precipitation that soil can store;Various crops are not under crop modeling simulation varying environment
With the optimal water requirement of growth phase;Water supply distribution model combines the natural supply situation of regional underground water and river, area total
Water supply situation and other regional work need regimen condition to optimize distribution simulation to Agricultural Irrigation Water amount;
By Distributed Parallel Computing by the climate model and crop modeling separate computations, then using the result data obtained as
The part input data of water supply distribution model carries out the Optimized Simulated of Agricultural Irrigation Water amount.
6. a kind of system of the intelligent irrigation model optimization based on big data, it is characterised in that including data memory module and data
Computation analysis module,
Data memory module is used to irrigate the storage of related big data and a large amount of simulation output data, at distributed data
Reason and storage;
Rapid computations and interpretation of result of the data computation analysis module for intelligent irrigation model, using Distributed Parallel Computing.
7. a kind of system of intelligent irrigation model optimization based on big data according to claim 6, it is characterised in that institute
Data memory module is stated to specifically include:
The data management function of Hadoop database is provided, including data source connection, builds the increasing for building table, subregion, column family, data in library
It revises and looks into and upload downloading data online management function;
There is provided distributed file system, for structural data, semi-structured data, unstructured data mass memory.
8. a kind of system of intelligent irrigation model optimization based on big data according to claim 6, it is characterised in that institute
Data computation analysis module is stated to specifically include:
With to mass data distributed computation ability, using Hadoop MapReduce distributed computing engine and calculating
The function of definition and the scheduling of task;
Have the function of quoting measured data calculation optimization model parameter in large database concept automatically.
9. a kind of system of intelligent irrigation model optimization based on big data according to claim 7, it is characterised in that institute
Stating data memory module is pretreatment and storage based on GIS big data, and a large amount of all kinds of irrigation related datas of upload include gas
Data, environmental data and supply and demand water number evidence are waited, the irrigation related data of different regions by being grouped, press by the data in same region
It is stored in identical region and is managed according to time sequencing arrangement, the exceptional value of some apparent errors is carried out under rule
It deletes to change and look into.
10. a kind of system of intelligent irrigation model optimization based on big data according to claim 8 or claim 9, feature exist
It is mainly made of three submodels in the intelligent irrigation model: climate model, crop modeling and water supply distribution model, it is distributed
Parallel computation is by climate model and crop modeling separate computations, then using the result data obtained as the part of water supply distribution model
The Optimized Simulated of input data progress Agricultural Irrigation Water amount.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811532193.XA CN109685258A (en) | 2018-12-14 | 2018-12-14 | A kind of method and system of the intelligent irrigation model optimization based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811532193.XA CN109685258A (en) | 2018-12-14 | 2018-12-14 | A kind of method and system of the intelligent irrigation model optimization based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109685258A true CN109685258A (en) | 2019-04-26 |
Family
ID=66186845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811532193.XA Pending CN109685258A (en) | 2018-12-14 | 2018-12-14 | A kind of method and system of the intelligent irrigation model optimization based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109685258A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135046A (en) * | 2019-05-09 | 2019-08-16 | 浪潮软件集团有限公司 | A kind of water supply and drainage model optimization method and device based on big data |
CN110472840A (en) * | 2019-07-29 | 2019-11-19 | 重庆邮电大学 | A kind of agricultural water conservancy dispatching method and system based on nerual network technique |
CN110987061A (en) * | 2019-11-05 | 2020-04-10 | 西安科成新果信息科技有限公司 | Intelligent agricultural condition information monitoring method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455633A (en) * | 2013-09-24 | 2013-12-18 | 浪潮齐鲁软件产业有限公司 | Method of distributed analysis for massive network detailed invoice data |
US20150074043A1 (en) * | 2013-09-10 | 2015-03-12 | Nice-Systems Ltd. | Distributed and open schema interactions management system and method |
CN108510102A (en) * | 2018-02-07 | 2018-09-07 | 青岛农业大学 | A kind of water-fertilizer integral control method of irrigation using big data calculative strategy |
CN108984972A (en) * | 2018-08-24 | 2018-12-11 | 浪潮软件集团有限公司 | Water quality mathematical model optimization method based on big data and parallel computation |
-
2018
- 2018-12-14 CN CN201811532193.XA patent/CN109685258A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150074043A1 (en) * | 2013-09-10 | 2015-03-12 | Nice-Systems Ltd. | Distributed and open schema interactions management system and method |
CN103455633A (en) * | 2013-09-24 | 2013-12-18 | 浪潮齐鲁软件产业有限公司 | Method of distributed analysis for massive network detailed invoice data |
CN108510102A (en) * | 2018-02-07 | 2018-09-07 | 青岛农业大学 | A kind of water-fertilizer integral control method of irrigation using big data calculative strategy |
CN108984972A (en) * | 2018-08-24 | 2018-12-11 | 浪潮软件集团有限公司 | Water quality mathematical model optimization method based on big data and parallel computation |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110135046A (en) * | 2019-05-09 | 2019-08-16 | 浪潮软件集团有限公司 | A kind of water supply and drainage model optimization method and device based on big data |
CN110135046B (en) * | 2019-05-09 | 2023-06-23 | 浪潮软件集团有限公司 | Water supply and drainage model optimization method and device based on big data |
CN110472840A (en) * | 2019-07-29 | 2019-11-19 | 重庆邮电大学 | A kind of agricultural water conservancy dispatching method and system based on nerual network technique |
CN110472840B (en) * | 2019-07-29 | 2022-03-22 | 重庆邮电大学 | Agricultural water conservancy scheduling method and system based on neural network technology |
CN110987061A (en) * | 2019-11-05 | 2020-04-10 | 西安科成新果信息科技有限公司 | Intelligent agricultural condition information monitoring method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021184550A1 (en) | Target soil property content prediction method based on soil transfer function | |
CN109685258A (en) | A kind of method and system of the intelligent irrigation model optimization based on big data | |
CN103425772B (en) | A kind of mass data inquiry method with multidimensional information | |
Liu et al. | Construction and application of a refined index for measuring the regional matching characteristics between water and land resources | |
CN107808253B (en) | Irrigation area channel system real-time water distribution method based on coordination algorithm | |
CN101916337B (en) | Method for dynamically predicting potential productivity of paddy rice based on geographical information system | |
CN105260791A (en) | Planting plan optimization system and method based on agricultural Internet of Things and big data analysis | |
CN104521699A (en) | Field intelligent irrigation on-line control management method | |
Kaiyong et al. | The research on impact factors and characteristic of cultivated land resources use efficiency---take henan province, China as a case study | |
CN115530054A (en) | Irrigation control method and device, electronic equipment and storage medium | |
CN108984972A (en) | Water quality mathematical model optimization method based on big data and parallel computation | |
CN108984995A (en) | A kind of ecology garden landscape design method of evaluation simulation | |
Yuan et al. | A SAFSA-and metabolism-based nonlinear grey Bernoulli model for annual water consumption prediction | |
CN115685799A (en) | Digital twin remote control method and platform for ecological irrigation area informatization | |
Saleh et al. | A prediction of grain yield based on hybrid intelligent algorithm | |
CN111563661A (en) | Method, device and equipment for determining water saving and displacement reduction capacity | |
CN201595053U (en) | Fuzzy irrigation control system | |
CN109426901A (en) | Long-term power consumption prediction method and device in one kind | |
Zheng | Evaluation model of ecological economic benefits based on discrete mathematical algorithm | |
CN109388873A (en) | Garden landscape planing method based on mountainous region mima type microrelief temperature | |
CN113793006A (en) | Agricultural water-saving potential analysis method and system based on scale effect | |
CN110135046B (en) | Water supply and drainage model optimization method and device based on big data | |
Zhai et al. | Decision-making technology based on knowledge engineering and experiment on the intelligent water-fertilizer irrigation system | |
Chen et al. | Application of Artificial Intelligence Technology in Water Resouces Planning of River Basin | |
Li et al. | Research on Innovative Strategies of Accurate Development Model of Regional Agricultural Economy under Big Data Coordination |
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: 20190426 |