CN109816142A - A kind of water resource precision dispensing system and distribution method - Google Patents
A kind of water resource precision dispensing system and distribution method Download PDFInfo
- Publication number
- CN109816142A CN109816142A CN201811547458.3A CN201811547458A CN109816142A CN 109816142 A CN109816142 A CN 109816142A CN 201811547458 A CN201811547458 A CN 201811547458A CN 109816142 A CN109816142 A CN 109816142A
- Authority
- CN
- China
- Prior art keywords
- water
- data
- module
- water resource
- dispensing system
- 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
Abstract
A kind of water resource precision dispensing system, for controlling water resource scheduling, the water resource precision dispensing system includes: basic data input module, and the original history for obtaining the water resources dispatch system dispatches data；Data processing module dispatches data for obtaining the original history from the basic data input module, and carries out error correction to the original history scheduling data and obtain amendment history scheduling data；Model generation module dispatches data for obtaining the amendment history from the data processing module, and generates Water Demand Prediction model；The traffic order for being based on the Water Demand Prediction model and predetermined period output scheduling order, and is transferred to the water resources dispatch system by prediction result output module.The present invention provides a kind of water resource precision dispensing system and distribution method, the water requirement in intake area domain is accurately predicted by Water Demand Prediction model and algorithm, to realize the accurate distribution of water resource.
Description
[technical field]
The present invention relates to water sources to distribute rationally and key water control project Optimum Scheduling Technology field, specifically a kind of water resource
Precision dispensing system and distribution method.
[background technique]
Distruting water transregionally is matched by water resource spatial and temporal distributions characteristic between change basin to across basin water resources again
It sets, the supply and demand water contradiction of shortage of water resources area production and living is effectively relieved, improve by water area ecological environment.However, with
Inter-Basin Water Transfer Project is frequently built, water transfer and contradiction, different zones and the inter-sectoral competition in basin with water outside basin
It will be become increasingly conspicuous with the contradiction of water.For more than half a century, domestic and international experts and scholars propose the planning of many Inter-Basin Water Transfer Projects,
The decision model and method of management operating, two major classes can be divided by being summed up: first is that tune across basin to complexity by various methods
Water system carries out after simplifying, and planning, the pipe of Inter-Basin Water Transfer Project are carried out using single mathematical programming model or simulation model
Manage operational decisions research；Second is that Large system optimization decision model and method are directlyed adopt, by first establishing various types of big systems
System hierarchical structure model, the method for solving then combined again with a variety of Mathematical Plannings or analogue technique carry out such engineering
Planning management tactics research.
In recent years, with the novel theoretical, method such as fuzzy mathematics, DSS and expert system, neural network
Continuous development and perfect, people start to explore these new theories, method is ground in Inter-Basin Water Transfer Project planning management decision
A possibility that studying carefully middle application.Currently, both at home and abroad research focus mostly in analysis distruting water transregionally to the water head site downstream hydrology, ecology
It influences, less quantitative study water head site downstream controllable fators can play the role of in distruting water transregionally.
Therefore, current methods are when handling across basin water resources optimization allocations, it is difficult to give full play to watershed control
Property Reservoir Operation comprehensive benefit, and cannot be considered in terms of outside basin that water demand, efficiency are lower in water transfer and basin.
[summary of the invention]
In order to solve deficiency in the prior art, the present invention provides a kind of water resource precision dispensing system and distribution method,
The water requirement in intake area domain is accurately predicted by Water Demand Prediction model and algorithm, to realize the accurate distribution of water resource.
To achieve the goals above, the present invention use the specific scheme is that
A kind of water resource precision dispensing system, for controlling water resources dispatch system, the water resource precision dispensing system
It include: basic data input module, the original history for obtaining the water resources dispatch system dispatches data；Data processing mould
Block is dispatched data for obtaining the original history from the basic data input module, and is dispatched to the original history
Data carry out error correction and obtain amendment history scheduling data；Model generation module, described in being obtained from the data processing module
It corrects history and dispatches data, and generate Water Demand Prediction model；Prediction result output module, for pre- based on the water requirement
Model and predetermined period output scheduling order are surveyed, and the traffic order is transferred to the water resources dispatch system.
Preferably, described predetermined period is divided into long predetermined period and short predetermined period.
Preferably, the unit of described long predetermined period is year.
Preferably, the unit of described short predetermined period be season, the moon, day or when.
Preferably, the model generation module is also connected with machine learning module, the machine learning module also with it is described
Water resources dispatch system is connected, and the machine learning module is used to obtain Real-Time Scheduling number from the water resources dispatch system
According to, and the Real-Time Scheduling data are transferred to the model generation module to repair to the Water Demand Prediction model
Just.
Preferably, the prediction result output module is also connected with abnormal data analysis module, the abnormal data analysis
Module is used to carry out error correction to the traffic order.
A kind of distribution method of water resource precision dispensing system, includes the following steps:
S1, the basic data input module obtain the original history scheduling data of the water resources dispatch system, and
The original history scheduling data are input to the data processing module；
S2, the data processing module are modified the original history scheduling data, obtain amendment history scheduling number
According to；
S3, the model generation module dispatch data according to the amendment history and generate Water Demand Prediction model；
S4, the prediction result output module obtain described long predetermined period or described short predetermined period, are then based on
The Water Demand Prediction model generates long middle and later periods traffic order or short cycle traffic order, and the long period is dispatched
Order or the short cycle traffic order are transferred to the water resources dispatch system.
Preferably, in S4, method that the prediction result output module generates the long period traffic order are as follows:
WhereinAdd up urban water consumption, x for the prediction time1 (0)For starting year urban water consumption, a, b be-it interior changes
Amount, parameter to be identified.
Preferably, in S4, method that the prediction result output module generates the short cycle traffic order are as follows:
Q=T*S*C*I,
Wherein, Q is water requirement, and T is long-term trend variation, and S is seasonal move.
The present invention is adjusted and is corrected to algorithm using machine learning by Water Demand Prediction model and algorithm,
The preparation of prediction model is continuously improved in use, accurately predicts intake area domain water requirement, to reach accurate water resource point
The purpose matched, it is especially suitable in water resources shortage area.
[Detailed description of the invention]
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the overall structure block diagram of distribution system of the present invention.
[specific embodiment]
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, Fig. 1 is the overall structure block diagram of distribution system of the present invention.
A kind of water resource precision dispensing system, for controlling water resources dispatch system, water resource precision dispensing system includes
Basic data input module, data processing module, model generation module, prediction result output module, machine learning module and different
Regular data analysis module.
Basic data input module, the original history for obtaining water resources dispatch system dispatch data.It is supervised including water
The data collecting card of instrument, model PCIe7100 are surveyed, the master control of exclusive data interface and water resources dispatch system is then passed through
Machine communication connection.
Data processing module is dispatched data for obtaining original history from basic data input module, and is gone through to original
History scheduling data carry out error correction and obtain amendment history scheduling data.Data processing module uses sqlserver database, front end skill
Art uses vue, and caching uses redis, and distributed aspect uses zookeeper, and operating system is win2012 standard edition.
Model generation module dispatches data for obtaining amendment history from data processing module, and it is pre- to generate water requirement
Survey model.
Prediction result output module, for being based on Water Demand Prediction model and predetermined period output scheduling order, and will
Traffic order is transferred to water resources dispatch system.
Predetermined period is divided into long predetermined period and short predetermined period, and the unit of long predetermined period is year, short predetermined period
Unit be season, the moon, day or when.Scheduling scheme for areal, same water source be in different durations it is unused, because
Duration is divided into two classes by this present invention, can effectively improve the accuracy of scheduling result.
Model generation module is also connected with machine learning module, and machine learning module is also connected with water resources dispatch system
It connects, machine learning module is used to obtain Real-Time Scheduling data from water resources dispatch system, and Real-Time Scheduling data are transferred to
Model generation module is to be modified Water Demand Prediction model.By the way that machine learning model is arranged, using being produced in use process
Raw new data is modified fixed Demand Forecast model, and Demand Forecast model is continuously improved in use
Accuracy.
Prediction result output module is also connected with abnormal data analysis module, and abnormal data analysis module is dragged out a miserable existence for exchanging
It enables and carries out error correction.
A kind of distribution method of water resource precision dispensing system, including S1 to S4.
The original history that S1, basic data input module obtain water resources dispatch system dispatches data, and goes through original
History scheduling data are input to data processing module.
S2, data processing module are modified original history scheduling data, obtain amendment history scheduling data.
S3, model generation module generate Water Demand Prediction model according to amendment history scheduling data.
S4, prediction result output module obtain long predetermined period or short predetermined period, are then based on Water Demand Prediction mould
Type generates long middle and later periods traffic order perhaps short cycle traffic order and by long period traffic order or short cycle scheduling life
Order is transferred to water resources dispatch system.
In S4, the method that prediction result output module generates long period traffic order is based on grey forecasting model, passes through knowledge
The different degree of development trend, is associated analysis between other system factor, carries out generation processing to initial data to find and is
The rule that system changes is specific to state are as follows:
WhereinAdd up urban water consumption, x for the prediction time1 (0)For starting year urban water consumption, a, b be-it interior changes
Amount, parameter to be identified.
In S4, prediction result output module generates the method for short cycle traffic order based on the multiplication of time series analysis method
Model, by time and observed value two parts analysis things cyclically-varying rule, the characteristics of phenomenon development and change can be analyzed and knot
Fruit, trend and regularity are studied and connect degree between phenomenon each other and change relationship, to predict future.Specific table
It states are as follows:
Q=T*S*C*I,
Wherein, Q is water requirement, and T is long-term trend variation, and S is seasonal move.
The present invention is adjusted and is corrected to algorithm using machine learning by Water Demand Prediction model and algorithm,
The preparation of prediction model is continuously improved in use, accurately predicts intake area domain water requirement, to reach accurate water resource point
The purpose matched, it is especially suitable in water resources shortage area.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (9)
1. a kind of water resource precision dispensing system, for controlling water resource scheduling, it is characterised in that: the water resource is accurately distributed
System includes:
Basic data input module, the original history for obtaining the water resources dispatch system dispatch data；
Data processing module dispatches data for obtaining the original history from the basic data input module, and to institute
It states original history scheduling data progress error correction and obtains amendment history scheduling data；
Model generation module dispatches data for obtaining the amendment history from the data processing module, and generation needs water
Measure prediction model；
Prediction result output module, for being based on the Water Demand Prediction model and predetermined period output scheduling order, and will
The traffic order is transferred to the water resources dispatch system.
2. a kind of water resource precision dispensing system as described in claim 1, it is characterised in that: described predetermined period is divided into long pre-
Survey period and short predetermined period.
3. a kind of water resource precision dispensing system as claimed in claim 2, it is characterised in that: the unit of described long predetermined period
For year.
4. a kind of water resource precision dispensing system as claimed in claim 2, it is characterised in that: the unit of described short predetermined period
For season, the moon, day or when.
5. a kind of water resource precision dispensing system as described in claim 1, it is characterised in that: the model generation module also connects
It is connected to machine learning module, the machine learning module is also connected with the water resources dispatch system, the machine learning mould
Block is used to obtain Real-Time Scheduling data from the water resources dispatch system, and the Real-Time Scheduling data are transferred to the mould
Type generation module is to be modified the Water Demand Prediction model.
6. a kind of water resource precision dispensing system as described in claim 1, it is characterised in that: the prediction result output module
It is also connected with abnormal data analysis module, the abnormal data analysis module is used to carry out error correction to the traffic order.
7. a kind of distribution method of water resource precision dispensing system as claimed in claim 2, it is characterised in that: including walking as follows
It is rapid:
S1, the basic data input module obtain the original history scheduling data of the water resources dispatch system, and by institute
It states original history scheduling data and is input to the data processing module；
S2, the data processing module are modified the original history scheduling data, obtain amendment history scheduling data；
S3, the model generation module dispatch data according to the amendment history and generate Water Demand Prediction model；
S4, the prediction result output module obtain described long predetermined period or described short predetermined period, are then based on described
Water Demand Prediction model generates long middle and later periods traffic order or short cycle traffic order, and by the long period traffic order
Or the short cycle traffic order is transferred to the water resources dispatch system.
8. distribution method as claimed in claim 7, it is characterised in that: in S4, described in the prediction result output module generation
The method of long period traffic order are as follows:
WhereinAdd up urban water consumption, x for the prediction time1 (0)For starting year urban water consumption, a, b are-endogenous variable, to
Identified parameters.
9. distribution method as claimed in claim 7, it is characterised in that: in S4, described in the prediction result output module generation
The method of short cycle traffic order are as follows:
Q=T*S*C*I,
Wherein, Q is water requirement, and T is long-term trend variation, and S is seasonal move.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811547458.3A CN109816142A (en) | 2018-12-18 | 2018-12-18 | A kind of water resource precision dispensing system and distribution method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811547458.3A CN109816142A (en) | 2018-12-18 | 2018-12-18 | A kind of water resource precision dispensing system and distribution method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109816142A true CN109816142A (en) | 2019-05-28 |
Family
ID=66602115
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811547458.3A Pending CN109816142A (en) | 2018-12-18 | 2018-12-18 | A kind of water resource precision dispensing system and distribution method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816142A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111178658A (en) * | 2019-09-26 | 2020-05-19 | 深圳市东深电子股份有限公司 | Planned water use management method and system based on big data analysis |
| CN111832790A (en) * | 2019-10-28 | 2020-10-27 | 吉林建筑大学 | Method and system for predicting medium and long-term water demand of water supply pipe network |
| CN113112125A (en) * | 2021-03-22 | 2021-07-13 | 浙江和达科技股份有限公司 | Artificial intelligence-based water resource management method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916335A (en) * | 2010-08-19 | 2010-12-15 | 河北农业大学 | Prediction method of city water-requirement time series-exponent smoothing model |
| US20110288899A1 (en) * | 2010-05-20 | 2011-11-24 | Piramal Enterprises Limited | Control system for a water distribution system |
| CN104680252A (en) * | 2015-02-13 | 2015-06-03 | 北京清控人居环境研究院有限公司 | Online architecture system and online architecture system-based real-time water supply scheduling method |
| CN104715292A (en) * | 2015-03-27 | 2015-06-17 | 上海交通大学 | City short-term water consumption prediction method based on least square support vector machine model |
| CN105956690A (en) * | 2016-04-25 | 2016-09-21 | 广州东芝白云自动化系统有限公司 | Water supply prediction method and water supply prediction system |
| US20160275629A1 (en) * | 2015-03-20 | 2016-09-22 | Accenture Global Solutions Limited | Method and system for water production and distribution control |
-
2018
- 2018-12-18 CN CN201811547458.3A patent/CN109816142A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110288899A1 (en) * | 2010-05-20 | 2011-11-24 | Piramal Enterprises Limited | Control system for a water distribution system |
| CN101916335A (en) * | 2010-08-19 | 2010-12-15 | 河北农业大学 | Prediction method of city water-requirement time series-exponent smoothing model |
| CN104680252A (en) * | 2015-02-13 | 2015-06-03 | 北京清控人居环境研究院有限公司 | Online architecture system and online architecture system-based real-time water supply scheduling method |
| US20160275629A1 (en) * | 2015-03-20 | 2016-09-22 | Accenture Global Solutions Limited | Method and system for water production and distribution control |
| CN104715292A (en) * | 2015-03-27 | 2015-06-17 | 上海交通大学 | City short-term water consumption prediction method based on least square support vector machine model |
| CN105956690A (en) * | 2016-04-25 | 2016-09-21 | 广州东芝白云自动化系统有限公司 | Water supply prediction method and water supply prediction system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111178658A (en) * | 2019-09-26 | 2020-05-19 | 深圳市东深电子股份有限公司 | Planned water use management method and system based on big data analysis |
| CN111178658B (en) * | 2019-09-26 | 2023-04-07 | 深圳市东深电子股份有限公司 | Planned water use management method and system based on big data analysis |
| CN111832790A (en) * | 2019-10-28 | 2020-10-27 | 吉林建筑大学 | Method and system for predicting medium and long-term water demand of water supply pipe network |
| CN113112125A (en) * | 2021-03-22 | 2021-07-13 | 浙江和达科技股份有限公司 | Artificial intelligence-based water resource management method and system |
| CN113112125B (en) * | 2021-03-22 | 2024-04-12 | 浙江和达科技股份有限公司 | Water resource management method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Clean energy consumption of power systems towards smart agriculture: roadmap, bottlenecks and technologies | |
| CN102402726B (en) | Method for predicting electric quantity of large-scale distribution network based on regional load analysis | |
| Sarmas et al. | ML-based energy management of water pumping systems for the application of peak shaving in small-scale islands | |
| Yue et al. | Achieving sustainable development goals in agricultural energy-water-food nexus system: An integrated inexact multi-objective optimization approach | |
| Gan et al. | Data-driven energy management system with Gaussian process forecasting and MPC for interconnected microgrids | |
| CN102682349A (en) | Electricity consumption intelligent prediction system and method | |
| Niu et al. | Parallel computing and swarm intelligence based artificial intelligence model for multi-step-ahead hydrological time series prediction | |
| CN109816142A (en) | A kind of water resource precision dispensing system and distribution method | |
| Li et al. | An improved risk-benefit collaborative grey target decision model and its application in the decision making of load adjustment schemes | |
| Ji et al. | Inexact stochastic risk-aversion optimal day-ahead dispatch model for electricity system management with wind power under uncertainty | |
| JP7395605B2 (en) | Non-intrusive load monitoring using machine learning and processed training data | |
| Zhao et al. | A deep reinforcement learning approach to resource management in hybrid clouds harnessing renewable energy and task scheduling | |
| CN105574586A (en) | General airplane air-material demand prediction method based on MPSO-BP network | |
| Ganguly et al. | Short term load forecasting using fuzzy logic | |
| CN104636834B (en) | A kind of improved joint probability plan model system optimization method | |
| Leithon et al. | Task scheduling strategies for utility maximization in a renewable-powered IoT node | |
| Mellios et al. | A multivariate analysis of the daily water demand of Skiathos Island, Greece, implementing the artificial neuro-fuzzy inference system (ANFIS) | |
| Kefer et al. | Simulation-based optimization of residential energy flows using white box modeling by genetic programming | |
| Vijayalakshmi et al. | An ensemble learning model for estimating the virtual energy storage capacity of aggregated air-conditioners | |
| Zois et al. | Integrated platform for automated sustainable demand response in smart grids | |
| Wu et al. | Design of A battery energy management system for capacity charge reduction | |
| CN109978237A (en) | A kind of area power grid Short Term Load Forecasting System based on fining meteorological data | |
| CN102509177B (en) | Locally weighted linear regression projection operation method based on cloud platform | |
| Jithish et al. | A neuro-fuzzy approach for domestic water usage prediction | |
| Spiller et al. | Mapping diversity of urban metabolic functions: a planning approach for more resilient cities |
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 |