CN117474173B - Multi-water source dynamic allocation device and system for plain river network area - Google Patents
Multi-water source dynamic allocation device and system for plain river network area Download PDFInfo
- Publication number
- CN117474173B CN117474173B CN202311561339.4A CN202311561339A CN117474173B CN 117474173 B CN117474173 B CN 117474173B CN 202311561339 A CN202311561339 A CN 202311561339A CN 117474173 B CN117474173 B CN 117474173B
- Authority
- CN
- China
- Prior art keywords
- water resource
- training
- time sequence
- water
- vectors
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 320
- 239000013598 vector Substances 0.000 claims abstract description 152
- 238000001704 evaporation Methods 0.000 claims abstract description 56
- 230000008020 evaporation Effects 0.000 claims abstract description 56
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 15
- 238000009826 distribution Methods 0.000 claims abstract description 13
- 238000005457 optimization Methods 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims description 111
- 239000011159 matrix material Substances 0.000 claims description 35
- 230000006870 function Effects 0.000 claims description 32
- 238000000605 extraction Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000013527 convolutional neural network Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 14
- 238000001556 precipitation Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 claims description 2
- 238000011176 pooling Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 19
- 238000005192 partition Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000013468 resource allocation Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000002156 mixing Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000003621 irrigation water Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000000007 visual 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
- 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
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/06313—Resource planning in a project environment
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Biodiversity & Conservation Biology (AREA)
- Educational Administration (AREA)
- Remote Sensing (AREA)
- Water Supply & Treatment (AREA)
Abstract
The invention discloses a multi-water source dynamic allocation device and system for plain river network areas. Firstly, acquiring rainfall and evaporation capacity of a plurality of water resource areas for a plurality of days in a preset time period, then acquiring a plurality of space distance values between the plurality of water resource areas and an area to be supplied with water, then carrying out water resource time sequence analysis on the rainfall and evaporation capacity of the plurality of water resource areas for a plurality of days in the preset time period to obtain a plurality of water resource time sequence fluctuation feature vectors, then carrying out feature distribution guidance and optimization on the plurality of water resource time sequence fluctuation feature vectors based on the plurality of space distance values to obtain a plurality of space corrected water resource supply feature vectors, and finally, determining a plurality of water resource supply proportion values based on the plurality of space corrected water resource supply feature vectors. Thus, the water resources among different users can be distributed fairly.
Description
Technical Field
The application relates to the field of water resource allocation, in particular to a multi-water source dynamic allocation device and system for plain river network areas.
Background
Water resources are an important basis for human survival and development, and are also important limiting factors for socioeconomic development. In plain river network areas, there is a certain imbalance in the supply of water resources due to the limitations of topography and hydrologic conditions. Because the topography is flat, the water flow speed is low, the river channel is relatively wide, the water resources are unevenly distributed in the plain area, and the water quantity in different areas can be different.
Meanwhile, the requirements of different users are different. That is, the water demand varies from industry to industry, from region to region of different population density. For example, agriculture requires a large amount of irrigation water resources, industry requires water resources for production and cooling, and residential water includes domestic water, drinking water, and the like.
Such a current situation results in an imbalance in the supply and demand relationships of water resources, and thus a multi-water source dynamic deployment scheme for plain river network areas is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a multi-water source dynamic allocation device and a system for plain river network areas, which can comprehensively utilize and analyze time-space change information of water resources, and perform intelligent water resource allocation according to the availability of the water resources so as to realize water resource fair allocation among different water users.
According to one aspect of the present application, there is provided a multi-water source dynamic deployment device for plain river network regions, comprising:
The water resource data acquisition module is used for acquiring rainfall and evaporation capacity of a plurality of water resource areas in a preset time period for a plurality of days;
The space distance value acquisition module is used for acquiring a plurality of space distance values between the plurality of water resource areas and the area to be supplied with water;
The water resource time sequence analysis module is used for carrying out water resource time sequence analysis on rainfall and evaporation in a plurality of days in a preset time period in the plurality of water resource areas so as to obtain a plurality of water resource time sequence fluctuation feature vectors;
the optimizing module is used for conducting characteristic distribution guiding and optimizing on the water resource time sequence fluctuation characteristic vectors based on the space distance values so as to obtain a plurality of spatially corrected water resource supply characteristic vectors; and
And the water resource supply proportion analysis module is used for determining a plurality of water resource supply proportion values based on the plurality of spatially corrected water resource supply characteristic vectors.
According to another aspect of the present application, there is provided a multi-water source dynamic deployment system for plain river network regions, comprising: the multi-water source dynamic allocation device is used for plain river network areas.
Compared with the prior art, the multi-water source dynamic allocation device and system for the plain river network area provided by the application are characterized in that firstly, rainfall and evaporation capacity of a plurality of water resource areas are obtained for a plurality of days in a preset time period, then, a plurality of space distance values between the plurality of water resource areas and an area to be supplied with water are obtained, then, water resource time sequence analysis is carried out on the rainfall and evaporation capacity of the plurality of water resource areas for a plurality of days in the preset time period to obtain a plurality of water resource time sequence fluctuation feature vectors, then, feature distribution guidance and optimization are carried out on the plurality of water resource time sequence fluctuation feature vectors based on the plurality of space distance values to obtain a plurality of space corrected water resource supply feature vectors, and finally, a plurality of water resource supply proportion values are determined based on the plurality of space corrected water resource supply feature vectors. Thus, the water resources among different users can be distributed fairly.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly introduced below, the following drawings not being drawn to scale with respect to actual dimensions, emphasis instead being placed upon illustrating the gist of the present application.
FIG. 1 is a block diagram of a multi-water source dynamic deployment device for plain river network areas according to an embodiment of the present application.
Fig. 2 is a schematic block diagram of the water resource time sequence analysis module used in the multi-water source dynamic allocation device in plain river network area according to the embodiment of the application.
Fig. 3 is a schematic block diagram of the data preprocessing unit used in the multi-water source dynamic allocation device for plain river network areas according to the embodiment of the application.
FIG. 4 is a block diagram of the optimization module used in the multi-water source dynamic deployment device in plain river network areas according to an embodiment of the application.
FIG. 5 is a flow chart of a method for dynamically allocating multiple water sources in a plain river network area according to an embodiment of the present application.
FIG. 6 is a schematic diagram of a system architecture for a method for dynamically deploying multiple water sources in a plain river network area according to an embodiment of the present application.
Fig. 7 is an application scenario diagram of a multi-water source dynamic deployment device for plain river network areas according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Aiming at the technical problems, the technical concept of the application is to comprehensively utilize and analyze the time-space change information of the water resources, and intelligently allocate the water resources according to the availability of the water resources so as to realize the fair allocation of the water resources among different water users.
Based on this, fig. 1 is a schematic block diagram of a multi-water source dynamic allocation device for plain river network areas according to an embodiment of the present application. As shown in fig. 1, a multi-water source dynamic deployment device 100 for plain river network areas according to an embodiment of the present application includes: a water resource data acquisition module 110 for acquiring rainfall and evaporation of a plurality of water resource areas for a plurality of days in a predetermined time period; a space distance value obtaining module 120, configured to obtain a plurality of space distance values between the plurality of water resource areas and the area to be supplied with water; the water resource time sequence analysis module 130 is used for performing water resource time sequence analysis on rainfall and evaporation of the plurality of water resource areas in a preset time period for a plurality of days to obtain a plurality of water resource time sequence fluctuation feature vectors; the optimizing module 140 is configured to perform feature distribution guiding and optimizing on the plurality of water resource time sequence fluctuation feature vectors based on the plurality of spatial distance values to obtain a plurality of spatially corrected water resource supply feature vectors; and a water resource supply ratio analysis module 150 for determining a plurality of water resource supply ratio values based on the plurality of spatially corrected water resource supply feature vectors.
Specifically, in the technical scheme of the application, firstly, rainfall and evaporation capacity of a plurality of water resource areas in a preset time period for a plurality of days are obtained; and simultaneously, acquiring a plurality of space distance values between the water resource areas and the area to be supplied with water. It should be appreciated that rainfall and evaporation are two important factors affecting water resource supply. The increase and decrease of water resources in different time periods can be known through rainfall information and evaporation amount information. In addition, the water resource allocation work of different water resource areas and the areas to be supplied with water also needs to consider the influence of space distance, namely, the transportation of water needs to consider factors such as transportation distance, transportation cost and the like. The different spatial distances between the different water resource areas and the areas to be supplied with water may affect the priority of water resource allocation and the quantitative supply relationship. These spatial distance information also provide important data support for determining the deployment scenario of the water resource.
And then, carrying out water resource time sequence analysis on the rainfall and evaporation capacity of the water resource areas in a plurality of days in a preset time period to obtain a plurality of water resource time sequence fluctuation feature vectors. Here, it is considered that the supply of water resources is affected by natural factors such as rainfall and evaporation, which may vary somewhat in time. By time sequence analysis of rainfall and evaporation, time-varying characteristics and fluctuation conditions of the water resource, such as seasonal, annual and long-term trends of the water resource, can be known. More specifically, there may be significant differences in rainfall and evaporation from season to season, and long-term climate change may also have an effect on the supply of water resources. By identifying the information such as the periodical change and the trend change of the water resource, more accurate basis can be provided for the dynamic allocation of the water resource.
In a specific example of the present application, the encoding process for performing water resource time sequence analysis on rainfall and evaporation of the plurality of water resource areas for a plurality of days in a predetermined time period to obtain a plurality of water resource time sequence fluctuation feature vectors includes: firstly, respectively arranging rainfall and evaporation capacity of the water resource areas in a plurality of days in a preset time period into input vectors according to a time dimension to obtain a plurality of rainfall time sequence input vectors and a plurality of evaporation capacity time sequence input vectors; then, respectively calculating position-based differences between each group of precipitation time sequence input vectors and each group of evaporation time sequence input vectors to obtain a plurality of water resource time sequence fluctuation input vectors; and then the plurality of water resource time sequence fluctuation input vectors respectively pass through a time sequence feature extractor based on a one-dimensional convolution layer to obtain a plurality of water resource time sequence fluctuation feature vectors.
Accordingly, as shown in fig. 2, the water resource timing analysis module 130 includes: a data preprocessing unit 131, configured to perform data preprocessing on rainfall and evaporation in a plurality of days in a predetermined time period in the plurality of water resource areas to obtain a plurality of water resource time sequence fluctuation input vectors; and a time sequence feature extraction unit 132 for passing the plurality of water resource time sequence fluctuation input vectors through a time sequence feature extractor based on a one-dimensional convolution layer to obtain the plurality of water resource time sequence fluctuation feature vectors. It should be understood that the water resource timing analysis module 130 includes two main units, namely a data preprocessing unit 131 and a timing feature extraction unit 132. The main function of the data preprocessing unit 131 is to perform data preprocessing on the rainfall and evaporation amounts of a plurality of water resource areas for a plurality of days in a predetermined time period, and the object of this unit is to prepare input data so that it is suitable for subsequent time series feature extraction. The data preprocessing may include the steps of: data cleaning: removing abnormal values, missing values or erroneous data; smoothing data: using filtering or smoothing techniques to reduce noise or fluctuations in the data; data normalization: scaling the data to the same range for comparison or merging in subsequent processing; data conversion: the data is transformed, e.g., logarithmically transformed or differentially computed, to better capture timing characteristics. The output of the data preprocessing unit 131 is a plurality of water resource timing fluctuation input vectors, which will be used for subsequent timing feature extraction. The main function of the timing feature extraction unit 132 is to extract timing features from a plurality of water resource timing fluctuation input vectors, which is typically implemented using a one-dimensional convolution layer based timing feature extractor that can effectively capture local patterns and trends in the timing data. The output of the timing feature extraction unit is a plurality of water resource timing fluctuation feature vectors containing timing features extracted from the raw data. These feature vectors may be used for further analysis, modeling or prediction tasks. In summary, the data preprocessing unit is used for preparing the original data and converting the original data into input vectors suitable for time sequence analysis. The timing feature extraction unit extracts meaningful timing features from the input vectors for further analysis and application.
As shown in fig. 3, the data preprocessing unit 131 includes: a vectorization subunit 1311, configured to arrange rainfall and evaporation capacity of the multiple water resource areas in multiple days in a predetermined time period as input vectors according to a time dimension, so as to obtain multiple rainfall time sequence input vectors and multiple evaporation time sequence input vectors; and a difference calculating subunit 1312 configured to calculate position-by-position differences between each set of the precipitation time-series input vector and the evaporation time-series input vector, respectively, to obtain the plurality of water resource time-series fluctuation input vectors. It should be appreciated that the data preprocessing unit 131 includes two sub-units, a vectoring sub-unit 1311 and a difference calculating sub-unit 1312. The vectorization subunit 1311 has a main function of arranging the rainfall and the evaporation amount of a plurality of water resource areas for a plurality of days in a predetermined time period in a time dimension as input vectors, specifically, the subunit arranges the rainfall and the evaporation amount of each water resource area in a time sequence to form a plurality of rainfall time sequence input vectors and a plurality of evaporation time sequence input vectors. For example, assume that there are 3 water resource zones, each zone having 10 days of rainfall and evaporation data. The vectorization subunit will arrange these data into 3 precipitation timing input vectors and 3 evaporation timing input vectors, each vector containing data for 10 time points. The outputs of vectoring subunit 1311 are a plurality of precipitation timing input vectors and a plurality of evaporation timing input vectors, which will be inputs for subsequent difference calculations. The main function of the difference calculation subunit 1312, which calculates the difference by position between each set of precipitation and evaporation time series input vectors to thereby obtain a plurality of water resource time series fluctuation input vectors, is to perform subtraction operation on the precipitation and evaporation at each point in time to calculate the difference therebetween. For example, assume that there are 3 precipitation timing input vectors and 3 evaporation timing input vectors, each vector containing data of 10 points in time. The difference calculation subunit calculates the position difference of the vectors to obtain 3 water resource time sequence fluctuation input vectors, wherein each vector contains difference data of 10 time points. The output of the difference computation subunit 1312 is a plurality of water resource timing fluctuation input vectors that contain the difference between the rainfall and evaporation amounts for subsequent timing feature extraction. In summary, the vectorization subunit arranges the rainfall and evaporation amount data in a time dimension as time sequence input vectors, and the difference value calculation subunit calculates the difference value between the vectors to generate a water resource time sequence fluctuation input vector. These processing steps help convert the raw data into an input format suitable for time series analysis and capture the wave characteristics of the water resource time series data.
And then, based on the plurality of spatial distance values, performing feature distribution guiding and optimizing on the plurality of water resource time sequence fluctuation feature vectors to obtain a plurality of spatially corrected water resource supply feature vectors. That is, the spatial distance information is taken into consideration of water resource supply, and the spatial distance relation between each water resource area and the area to be supplied with water is taken as guiding information to optimize the characteristic distribution of the dynamic time sequence change of the water resource expressed by the time sequence fluctuation characteristic vectors of the plurality of water resources.
In a specific example of the present application, based on the plurality of spatial distance values, a coding process for performing feature distribution guidance and optimization on the plurality of water resource time sequence fluctuation feature vectors to obtain a plurality of spatially corrected water resource supply feature vectors includes: firstly constructing the plurality of spatial distance values into a spatial degree matrix, and then obtaining a spatial degree feature matrix through a spatial feature extractor based on a convolutional neural network model; and then respectively carrying out matrix multiplication on the spatial degree characteristic matrix and each water resource time sequence fluctuation characteristic vector in the plurality of water resource time sequence fluctuation characteristic vectors to obtain a plurality of spatially corrected water resource supply characteristic vectors. The convolutional neural network has good feature extraction capability in the aspect of processing images and spatial data, and can learn a time sequence distribution mode and an association relation in space.
Accordingly, as shown in fig. 4, the optimizing module 140 includes: a space degree matrix construction unit 141 for constructing the plurality of space distance values as a space degree matrix; a spatial feature extraction unit 142, configured to perform feature extraction on the spatial feature matrix by using a deep learning network model to obtain a spatial feature matrix; and a matrix multiplication unit 143, configured to perform matrix multiplication on the spatial degree feature matrix and each of the water resource time sequence fluctuation feature vectors in the plurality of water resource time sequence fluctuation feature vectors to obtain the plurality of spatially corrected water resource supply feature vectors.
In one example, in the spatial feature extraction unit 142, the deep learning network model is a spatial feature extractor based on a convolutional neural network model; the spatial feature extractor based on the convolutional neural network model comprises an input layer, a convolutional layer, an activation layer, a pooling layer and an output layer. Specifically, the spatial feature extraction unit 142 is configured to: and passing the space degree matrix through the space feature extractor based on the convolutional neural network model to obtain the space degree feature matrix.
Further, the plurality of spatially corrected water resource supply feature vectors are input into a Softmax function to obtain a plurality of probability values, and the plurality of probability values are subjected to maximum value-based normalization processing to obtain a plurality of water resource supply proportion values. Here, the plurality of spatially corrected water resource supply feature vectors are converted into probability values by a Softmax function to represent the supply probability of each water resource region. By applying the Softmax function, a probability value for each water resource region feed can be obtained. These probability values reflect the relative importance or contribution of the various regions in the supply deployment. In addition, these probability values may be normalized for more intuitive results. Maximum-based normalization is a common method that scales the largest value of a plurality of probability values to 1 and the other values.
Accordingly, the water resource supply ratio analysis module 150 is configured to: and inputting the plurality of spatially corrected water resource supply characteristic vectors into a Softmax function to obtain a plurality of probability values, and carrying out maximum value-based normalization processing on the plurality of probability values to obtain a plurality of water resource supply proportion values.
Further, in the technical scheme of the application, the multi-water source dynamic allocation device for plain river network areas further comprises a training module for training the time sequence feature extractor based on the one-dimensional convolution layer and the spatial feature extractor based on the convolution neural network model. It should be understood that the training module is used for training the time sequence feature extractor based on the one-dimensional convolution layer and the space feature extractor based on the convolution neural network model, and the main function of the training module is to learn and adjust parameters of the models by using the existing labeling data set, so that the training module can be better adapted to specific water resource allocation tasks. Specifically, the training module uses a labeled training dataset that contains known water resource deployment conditions and corresponding input features. These input features may include time series data, spatial data, and other relevant environmental or hydrologic information. The training module calculates an error between the predicted and actual results of the model by providing the input features to the temporal and spatial feature extractors and then comparing with the labeled target values. Based on the error, the training module adjusts parameters of the model using a back-propagation algorithm and an optimization algorithm (e.g., gradient descent) to minimize the error and improve the performance of the model. Through repeated iterative training processes, the training module can help the time sequence feature extractor and the space feature extractor learn more accurate and more representative feature representation, and improve the prediction capability and generalization capability of the time sequence feature extractor and the space feature extractor to water resource allocation tasks. The training process of the training module is a key step, which enables the multi-water source dynamic allocation device to learn and extract features and modes suitable for practical application from historical data. Through the training of the training module, the device can better understand the characteristics of the input data and make more accurate water resource allocation decisions.
Wherein, in one example, the training module comprises: a training data acquisition unit configured to acquire training data including training rainfall and training evaporation amounts of a plurality of water resource areas for a plurality of days within a predetermined time period, a plurality of training space distance values between the plurality of water resource areas and an area to be supplied with water, and a real value of a plurality of water resource supply proportion values; the training data vectorization unit is used for respectively arranging the training rainfall capacity and the training evaporation capacity of the plurality of water resource areas for a plurality of days in a preset time period into input vectors according to a time dimension so as to obtain a plurality of training rainfall capacity time sequence input vectors and a plurality of training evaporation capacity time sequence input vectors; the training difference value calculation unit is used for calculating position-based differences between each group of training precipitation time sequence input vectors and each group of training evaporation time sequence input vectors so as to obtain a plurality of training water resource time sequence fluctuation input vectors; the training time sequence feature extraction unit is used for enabling the plurality of training water resource time sequence fluctuation input vectors to respectively pass through the time sequence feature extractor based on the one-dimensional convolution layer so as to obtain a plurality of training water resource time sequence fluctuation feature vectors; the training space feature extraction unit is used for constructing the training space distance values into a training space degree matrix and then obtaining a training space degree feature matrix through the space feature extractor based on the convolutional neural network model; the training matrix multiplication unit is used for respectively carrying out matrix multiplication on the training space degree characteristic matrix and each training water resource time sequence fluctuation characteristic vector in the training water resource time sequence fluctuation characteristic vectors so as to obtain a plurality of training space corrected water resource supply characteristic vectors; a specific loss function value calculation unit for calculating specific loss function values of the plurality of training water resource time sequence fluctuation feature vectors and the plurality of training space corrected water resource supply feature vectors; the probability loss function value calculation unit is used for inputting the water resource supply characteristic vectors after the training space correction into a Softmax function to obtain a plurality of probability loss function values; and a loss training unit for training the one-dimensional convolutional layer-based temporal feature extractor and the convolutional neural network model-based spatial feature extractor with a weighted sum of the specific loss function value and the plurality of probability loss function values as a loss function value.
Here, each training water resource time sequence fluctuation feature vector in the plurality of training water resource time sequence fluctuation feature vectors expresses local time sequence correlation features of training precipitation and training evaporation of a corresponding water resource region, that is, expresses the water resource time sequence fluctuation feature in a time sequence direction, so that after the plurality of training space distance values are constructed into a training space degree matrix, the training space degree feature matrix is obtained through a space feature extractor based on a convolutional neural network model, and when the training space degree feature matrix is respectively subjected to matrix multiplication with each training water resource time sequence fluctuation feature vector in the plurality of training water resource time sequence fluctuation feature vectors, the obtained plurality of training space corrected water resource supply feature vectors can express space-time mixing fluctuation correlation feature representation of the water resource time sequence fluctuation feature of the corresponding water resource region under the space degree feature of each water resource region.
However, considering that the training space corrected water resource supply feature vector still needs to promote the sharing of the time sequence associated features with the training water resource time sequence fluctuation feature vector under the space-time mixing dimension, so as to avoid the distribution sparsification of the key time sequence features under the space-time mixing dimension, the applicant of the application introduces a specific loss function for sharing the key feature reinforcement for each group of training water resource time sequence fluctuation feature vector and training space corrected water resource supply feature vector.
Accordingly, in one example, the specific loss function value calculation unit is further configured to: calculating the specific loss function values of the plurality of training water resource time sequence fluctuation feature vectors and the plurality of training space corrected water resource supply feature vectors by using the following specific loss calculation formula; wherein, the specific loss calculation formula is:
wherein V 1 is each training water resource time sequence fluctuation feature vector of the plurality of training water resource time sequence fluctuation feature vectors, V 2 is each training space corrected water resource supply feature vector of the plurality of training space corrected water resource supply feature vectors, I [ 1 ] and I [ 2 ] are respectively 1 norm and 2 norm of the feature vector, epsilon is a boundary threshold superparameter, and the feature vectors are all in the form of row vectors, Representing vector multiplication,/>Representing vector subtraction, (·) T represents the transpose operation,Is the specific loss function value.
Specifically, the strengthening of the shared key feature between the training water resource time sequence fluctuation feature vector and the training space corrected water resource supply feature vector can be regarded as the distributed information compression of the global feature set, and the distribution sparsification control of the key feature is performed on the basis of reconstructing the relative shape relation of the original feature manifold based on the structural representation between the training water resource time sequence fluctuation feature vector and the training space corrected water resource supply feature vector, so that the geometric representation of the sparse but meaningful fusion manifold of the training space corrected water resource supply feature vector can be obtained while strengthening the shared key feature between the training water resource time sequence fluctuation feature vector and the training space corrected water resource supply feature vector, so that the expression effect of the training space corrected water resource supply feature vector is improved, and the accuracy of the probability value obtained by regression through a Softmax function is improved.
In summary, the multi-water source dynamic allocation device 100 for plain river network areas according to the embodiments of the present application is illustrated, which can achieve fair allocation of water resources among different users.
As described above, the multi-water source dynamic allocation apparatus 100 for a plain river network area according to the embodiment of the present application may be implemented in various terminal devices, for example, a server or the like having the multi-water source dynamic allocation algorithm for a plain river network area according to the embodiment of the present application. In one example, the multi-water source dynamic deployment device 100 for plain river network regions according to embodiments of the present application may be integrated into a terminal device as one software module and/or hardware module. For example, the multi-water source dynamic deployment device 100 for plain river network areas according to the embodiment of the present application may be a software module in the operating system of the terminal device, or may be an application program developed for the terminal device; of course, the multi-water source dynamic allocation apparatus 100 for plain river network areas according to the embodiment of the present application may also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the multi-water source dynamic allocation apparatus 100 for a plain river network area according to an embodiment of the present application may be a separate device from the terminal device, and the multi-water source dynamic allocation apparatus 100 for a plain river network area may be connected to the terminal device through a wired and/or wireless network and transmit interactive information according to a agreed data format.
Further, in the application, a multi-water source dynamic allocation system for the plain river network area is also provided, which comprises the multi-water source dynamic allocation device for the plain river network area.
FIG. 5 is a flow chart of a method for dynamically allocating multiple water sources in a plain river network area according to an embodiment of the present application. FIG. 6 is a schematic diagram of a system architecture for a method for dynamically deploying multiple water sources in a plain river network area according to an embodiment of the present application. As shown in fig. 5 and 6, the method for dynamically allocating multiple water sources in a plain river network area according to an embodiment of the present application includes: s110, acquiring rainfall and evaporation capacity of a plurality of water resource areas in a preset time period for a plurality of days; s120, acquiring a plurality of space distance values between the water resource areas and the area to be supplied with water; s130, carrying out water resource time sequence analysis on rainfall and evaporation in a plurality of days in a preset time period in the plurality of water resource areas to obtain a plurality of water resource time sequence fluctuation feature vectors; s140, based on the plurality of spatial distance values, conducting feature distribution guiding and optimizing on the plurality of water resource time sequence fluctuation feature vectors to obtain a plurality of spatially corrected water resource supply feature vectors; and S150, determining a plurality of water resource supply proportion values based on the plurality of spatially corrected water resource supply characteristic vectors.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described method for dynamically allocating multiple water sources for a plain river network region have been described in detail in the above description for the apparatus 100 for dynamically allocating multiple water sources for a plain river network region with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
Fig. 7 is an application scenario diagram of a multi-water source dynamic deployment device for plain river network areas according to an embodiment of the present application. As shown in fig. 7, in this application scenario, first, a rainfall and evaporation amount of a plurality of water resource areas for a plurality of days in a predetermined time period (for example, D1 illustrated in fig. 7) and a plurality of spatial distance values between the plurality of water resource areas and an area to be supplied with water (for example, D2 illustrated in fig. 7) are acquired, then the rainfall and evaporation amount of the plurality of water resource areas for a plurality of days in the predetermined time period and the plurality of spatial distance values are input to a server (for example, S illustrated in fig. 7) where a multi-water-source dynamic allocation algorithm for a plain river network area is deployed, wherein the server is capable of processing the rainfall and evaporation amount of the plurality of water resource areas for a plurality of days in the predetermined time period using the multi-water-source dynamic allocation algorithm for a plain river network area and the plurality of spatial distance values to obtain a plurality of water-source supply ratio values.
It should be understood that the application also discloses a water resource informatization management technology. The water resource informatization management technology mainly researches the application of GIS (geographic information management system) in the aspect of water resource data management and inquiry. And carrying out database management and data visualization on the water resource condition of the research area by utilizing a GIS technology. The water resource data management and inquiry are simplified, and the water demand, water supply and water discharge situation analysis chart can be formed, so that the water resource management decision is facilitated. And establishing a study area space database and a corresponding attribute database by using a GIS space database technology. The space database consists of a basic geographic database and a water supply engineering space database. Both databases were constructed by investigation, measurement.
The attribute database consists of a basic attribute database sub-database, an intermediate database sub-database and a result database sub-database. The basic attribute database mainly comprises an annual hydrologic (precipitation, evaporation and runoff) database, a socioeconomic database and the like in a research area. The intermediate database mainly comprises calculation parameters, calculation data and the like required by the model. The result database mainly comprises data which are generated after the model is run and can be used for decision making or other systems and need to be saved.
The water circulation process and the function are divided into areas as the primary steps, and the water resource is partitioned according to the water resource circulation characteristics; and according to the distribution of the water supply engineering, partitioning the water supply of the investigation region. The water resource partition mainly reflects the natural characteristics of the area, and the water supply partition mainly reflects the manual and social types of the area. The two regions were cross-treated to determine the study partition. And selecting a proper water circulation simulation sub-model and a manual water system sub-model for different partitions according to the water circulation characteristics and practical requirements of each partition. And establishing a primary configuration model of water resources of the 'supply-discharge' relationship of each partition by utilizing the hydraulic correlation among different partition sub-models, and simulating the time and space variation rules of the water resources of each partition. Based on the regulation lakes and the main water supply engineering thereof in the area, a water resource secondary scheduling model for the manual intervention of the regulation capacity of the reaction lakes and the water resource scheduling system is established. The calibration of model parameters mainly depends on historical hydrologic observation data and water efficiency experimental data. On the basis of realizing model parameter calibration, the water resource space scheduling model is subjected to relevant debugging. And under the condition of determining input, comparing the simulation result with the actual observation result to judge the simulation performance of the model. The model with poor simulation performance must be modified, which includes verification of model behavior, verification of model parameters, re-identification of model association relations, and the like. And continuously putting the corrected model into test operation, and carrying out multiple feedback with the test result to finally realize the simulation target of the model. After each calculation partition result reaches the simulation requirement and the total water consumption of the area reaches the total control requirement, the area water resource allocation and the river and lake water consumption allocation research are carried out, and the data interface and the visual interface of the water resource informatization management system are completed, so that a decision system model supporting the water resource management is formed.
The technology establishes a distributed rainfall runoff model based on space geographic information, integrates the internal quantitative relation of a natural water circulation process and an artificial side branch circulation process on each partition and each link, determines the available amount of surface water resources, establishes a space geographic information database by utilizing a GIS technology, and visualizes water resource information.
The application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present application and is not to be construed as limiting thereof. Although a few exemplary embodiments of this application have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this application. Accordingly, all such modifications are intended to be included within the scope of this application as defined in the following claims. It is to be understood that the foregoing is illustrative of the present application and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The application is defined by the claims and their equivalents.
Claims (5)
1. A multi-water source dynamic allocation device for plain river network areas, which is characterized by comprising:
The water resource data acquisition module is used for acquiring rainfall and evaporation capacity of a plurality of water resource areas in a preset time period for a plurality of days;
The space distance value acquisition module is used for acquiring a plurality of space distance values between the plurality of water resource areas and the area to be supplied with water;
The water resource time sequence analysis module is used for carrying out water resource time sequence analysis on rainfall and evaporation in a plurality of days in a preset time period in the plurality of water resource areas so as to obtain a plurality of water resource time sequence fluctuation feature vectors;
the optimizing module is used for conducting characteristic distribution guiding and optimizing on the water resource time sequence fluctuation characteristic vectors based on the space distance values so as to obtain a plurality of spatially corrected water resource supply characteristic vectors; and
The water resource supply proportion analysis module is used for determining a plurality of water resource supply proportion values based on the plurality of spatially corrected water resource supply characteristic vectors;
Wherein, the water resource time sequence analysis module comprises:
the data preprocessing unit is used for preprocessing data of rainfall and evaporation in a plurality of days in a preset time period in the plurality of water resource areas to obtain a plurality of water resource time sequence fluctuation input vectors; and
The time sequence feature extraction unit is used for respectively enabling the plurality of water resource time sequence fluctuation input vectors to pass through a time sequence feature extractor based on a one-dimensional convolution layer to obtain a plurality of water resource time sequence fluctuation feature vectors;
Wherein, the data preprocessing unit includes:
The vectorization subunit is used for respectively arranging rainfall and evaporation capacity of the plurality of water resource areas in a plurality of days in a preset time period into input vectors according to a time dimension to obtain a plurality of rainfall time sequence input vectors and a plurality of evaporation capacity time sequence input vectors; and
The difference value calculating subunit is used for respectively calculating position-based differences between each group of precipitation time sequence input vectors and each group of evaporation time sequence input vectors so as to obtain a plurality of water resource time sequence fluctuation input vectors;
Wherein, the optimization module includes:
a space degree matrix construction unit for constructing the plurality of space distance values as a space degree matrix;
the spatial feature extraction unit is used for extracting features of the spatial degree matrix by using a deep learning network model so as to obtain a spatial degree feature matrix; and
Matrix multiplication unit, which is used to multiply the space degree characteristic matrix with each water resource time sequence fluctuation characteristic vector in the plurality of water resource time sequence fluctuation characteristic vectors to obtain the plurality of water resource supply characteristic vectors after space correction;
wherein, the water resource supply proportion analysis module is used for:
And inputting the plurality of spatially corrected water resource supply characteristic vectors into a Softmax function to obtain a plurality of probability values, and carrying out maximum value-based normalization processing on the plurality of probability values to obtain a plurality of water resource supply proportion values.
2. The multi-water source dynamic deployment device for plain river network areas according to claim 1, wherein the deep learning network model is a spatial feature extractor based on a convolutional neural network model;
The spatial feature extractor based on the convolutional neural network model comprises an input layer, a convolutional layer, an activation layer, a pooling layer and an output layer.
3. The multi-water source dynamic allocation device for plain river network areas according to claim 2, wherein the spatial feature extraction unit is configured to:
And passing the space degree matrix through the space feature extractor based on the convolutional neural network model to obtain the space degree feature matrix.
4. The multi-water source dynamic deployment device for plain river network regions according to claim 3, further comprising a training module for training the one-dimensional convolutional layer-based temporal feature extractor and the convolutional neural network model-based spatial feature extractor;
wherein, training module includes:
a training data acquisition unit configured to acquire training data including training rainfall and training evaporation amounts of a plurality of water resource areas for a plurality of days within a predetermined time period, a plurality of training space distance values between the plurality of water resource areas and an area to be supplied with water, and a real value of a plurality of water resource supply proportion values;
The training data vectorization unit is used for respectively arranging the training rainfall capacity and the training evaporation capacity of the plurality of water resource areas for a plurality of days in a preset time period into input vectors according to a time dimension so as to obtain a plurality of training rainfall capacity time sequence input vectors and a plurality of training evaporation capacity time sequence input vectors;
The training difference value calculation unit is used for calculating position-based differences between each group of training precipitation time sequence input vectors and each group of training evaporation time sequence input vectors so as to obtain a plurality of training water resource time sequence fluctuation input vectors;
the training time sequence feature extraction unit is used for enabling the plurality of training water resource time sequence fluctuation input vectors to respectively pass through the time sequence feature extractor based on the one-dimensional convolution layer so as to obtain a plurality of training water resource time sequence fluctuation feature vectors;
the training space feature extraction unit is used for constructing the training space distance values into a training space degree matrix and then obtaining a training space degree feature matrix through the space feature extractor based on the convolutional neural network model;
The training matrix multiplication unit is used for respectively carrying out matrix multiplication on the training space degree characteristic matrix and each training water resource time sequence fluctuation characteristic vector in the training water resource time sequence fluctuation characteristic vectors so as to obtain a plurality of training space corrected water resource supply characteristic vectors;
A specific loss function value calculation unit for calculating specific loss function values of the plurality of training water resource time sequence fluctuation feature vectors and the plurality of training space corrected water resource supply feature vectors;
the probability loss function value calculation unit is used for inputting the water resource supply characteristic vectors after the training space correction into a Softmax function to obtain a plurality of probability loss function values; and
A loss training unit for training the one-dimensional convolutional layer-based temporal feature extractor and the convolutional neural network model-based spatial feature extractor with a weighted sum of the specific loss function value and the plurality of probability loss function values as a loss function value.
5. A multi-water source dynamic allocation system for plain river network areas, comprising: the multi-water source dynamic allocation device for plain river network areas according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311561339.4A CN117474173B (en) | 2023-11-22 | 2023-11-22 | Multi-water source dynamic allocation device and system for plain river network area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311561339.4A CN117474173B (en) | 2023-11-22 | 2023-11-22 | Multi-water source dynamic allocation device and system for plain river network area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117474173A CN117474173A (en) | 2024-01-30 |
| CN117474173B true CN117474173B (en) | 2024-06-21 |
Family
ID=89632802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311561339.4A Active CN117474173B (en) | 2023-11-22 | 2023-11-22 | Multi-water source dynamic allocation device and system for plain river network area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117474173B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544024A (en) * | 2018-11-30 | 2019-03-29 | 北京科技大学 | A kind of method of suitable small watershed river multi-water resources water quality and quantity scheduling |
| CN114548546A (en) * | 2022-02-18 | 2022-05-27 | 郑州大学 | Optimized scheduling method for water quantity of water transfer project |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288269A (en) * | 2019-07-04 | 2019-09-27 | 中国水利水电科学研究院 | A kind of water operation method of multilayer water resources management |
-
2023
- 2023-11-22 CN CN202311561339.4A patent/CN117474173B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544024A (en) * | 2018-11-30 | 2019-03-29 | 北京科技大学 | A kind of method of suitable small watershed river multi-water resources water quality and quantity scheduling |
| CN114548546A (en) * | 2022-02-18 | 2022-05-27 | 郑州大学 | Optimized scheduling method for water quantity of water transfer project |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117474173A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610280B (en) | Short-term prediction method, model, device and system for power load | |
| CN112418482B (en) | Cloud computing energy consumption prediction method based on time series clustering | |
| CN112101480B (en) | Multivariate clustering and fused time sequence combined prediction method | |
| CN107609141B (en) | Method for performing rapid probabilistic modeling on large-scale renewable energy data | |
| CN111080032A (en) | Load prediction method based on Transformer structure | |
| Claveria et al. | A new approach for the quantification of qualitative measures of economic expectations | |
| CN107146009B (en) | Water supply pipe network operation state evaluation method | |
| CN111639823B (en) | Building cold and heat load prediction method constructed based on feature set | |
| CN109635245A (en) | A kind of robust width learning system | |
| CN117132135A (en) | Urban informatization management system and method based on digital twinning | |
| Salam et al. | Energy consumption prediction model with deep inception residual network inspiration and LSTM | |
| CN104050547A (en) | Non-linear optimization decision-making method of planning schemes for oilfield development | |
| CN114777192A (en) | Secondary network heat supply autonomous optimization regulation and control method based on data association and deep learning | |
| CN116245019A (en) | Load prediction method, system, device and storage medium based on Bagging sampling and improved random forest algorithm | |
| CN114492742A (en) | Neural network structure searching method, model issuing method, electronic device, and storage medium | |
| CN114091776A (en) | K-means-based multi-branch AGCNN short-term power load prediction method | |
| CN117474173B (en) | Multi-water source dynamic allocation device and system for plain river network area | |
| CN109886316B (en) | Transformer state parameter combination prediction method based on cloud system similarity weight distribution | |
| CN116415732A (en) | User side power load data processing method based on improved ARNN | |
| CN116307206A (en) | Natural gas flow prediction method based on segmented graph convolution and time attention mechanism | |
| CN114970698B (en) | Metering equipment operation performance prediction method based on improved LWPS | |
| CN116578858A (en) | Air compressor fault prediction and health degree evaluation method and system based on graphic neural network | |
| CN115169521A (en) | Graph neural network interpretation method for keeping prediction sequence and structure dependency relationship | |
| Wang | A new variable selection method for soft sensor based on deep learning | |
| Shchetinin | Improving the efficiency of energy consumption in smart grids with application of artificial intellect |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |