Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Urban water consumption prediction method based on GA-BP neural network

A BP neural network, GA-BP technology, applied in the field of urban water consumption prediction based on GA-BP neural network, can solve problems such as too fast convergence speed

Pending Publication Date: 2019-11-12
XIAN UNIV OF SCI & TECH
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the weights and thresholds of the model are randomly obtained during the prediction process of the BP neural network, which makes the network prone to local optimum and excessive convergence speed.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Urban water consumption prediction method based on GA-BP neural network
  • Urban water consumption prediction method based on GA-BP neural network
  • Urban water consumption prediction method based on GA-BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] refer to Figure 1-5 , an urban water consumption prediction method based on GA-BP neural network, the GA-BP water consumption prediction algorithm includes:

[0089] Step 1. Construction of BP neural network structure:

[0090] 1.1 Construct BP neural network: Determine the number of nodes in the network layer according to the influencing factors and forecasted amount of daily water consumption. The input of the forecasting model is the time series of daily water consumption, and the output of the forecasting model is the hourly water consumption in the future period. The input layer constructed Both the variables of the input layer and the output layer are water consumption, the number of input layer nodes is 24, that is, the water consumption in 24 hours a day, and the output node is the water consumption at a certain time of the next day, so the number of input and output nodes of the neural network is determined to be 24 and 1 respectively ;

[0091] 1.2 Determin...

Embodiment 2

[0153] The simulation is carried out on a PC with Inter(R) Core(TM) i5-4590T CPU@2.00GHz, 4G memory, Windows 7 Ultimate 64-bit system, and the running platform is MATLAB 2015b. The model structure of the GA-BP water consumption prediction algorithm is 24-9-1, the expected error is set to E=0.005, and the maximum number of training times is r=5000. The population size of the genetic algorithm is 50, the crossover probability is 0.4, the mutation probability is 0.1, and the number of iterations is 100 generations.

[0154] Use the GA-BP water consumption prediction algorithm to predict the urban water consumption, select the water consumption data for a week from April 16 to 22 as a training sample, and use the sample data to train the BP water consumption prediction model and the GA-BP water consumption prediction model to predict Daily water consumption of residents in the coming week. The model has been trained many times (the maximum number of training r=5000), and the outp...

Embodiment 3

[0166] For the urban construction of Xi'an, the water supply system combines the water resources of the water plant, the pipe network model and the water consumption of users, and rationally allocates water resources from the perspectives of system-wide safety and reliability, economic operation and water supply feasibility to achieve the overall optimal system , more suitable for the existing Xi'an water supply system. Through the analysis of the optimal scheduling model of Xi’an’s water supply system, and according to the actual water supply situation, the optimal scheduling model of water supply is established. On the basis of satisfying the water consumption and pressure of citizens, the water pressure and flow of the water supply factory are optimized, and the goal of energy saving optimization is obtained.

[0167] The actual outlet flow of the water plant is compared with the outlet flow of the water plant at this moment, which is optimized under the constraint condition...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the field of neural networks and urban water consumption prediction, in particular to an urban water consumption prediction method based on a GA-BP neural network. The methodcomprises the following steps: step 1, constructing a BP neural network structure; step 2, carrying out GA optimization on the initial weight of the BP neural network; step 3, training and predictinga GA-BP neural network; and step 4, applying the trained GA-BP neural network to prediction of urban water consumption. According to the GA-BP neural network-based urban water consumption prediction method, the difficulty of optimizing the initial weight of the neural network is overcome, and the prediction precision of analysis is improved.

Description

technical field [0001] The invention relates to the fields of neural network and urban water forecasting, in particular to a method for forecasting urban water consumption based on GA-BP neural network. Background technique [0002] With the continuous increase of urban population, the urban water supply system gradually shows its deficiencies. For example, the water pressure of some high-rise buildings is low during the peak water consumption period, which cannot meet people's basic living needs. However, my country's traditional water supply scheduling system also has major problems, such as water resource scheduling consumes a lot of energy, and water resources are wasted more. Therefore, in order to meet the needs of the urban population, we must optimize the water system, and the premise of optimization is the need for accurate water consumption forecasting. [0003] my country's water consumption prediction research is at a relatively low level as a whole. From the be...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/06G06N3/08
CPCG06N3/084G06Q10/04G06Q50/06
Inventor 武风波赵盼吕茜彤范梦宁刘兆琦刘贝刘瑶
Owner XIAN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com