Water supply network user water consumption prediction method based on random forest and probability density function

Abstract

The invention discloses a water supply network user water consumption prediction method based on a random forest and a probability density function. The algorithm is used for predicting the water consumption of users of a water supply network, firstly, data arrangement is carried out according to user water consumption data within a time span, then, water consumption level division is carried out through a water consumption quartile, then, water consumption level prediction is carried out through a random forest, and finally, water consumption prediction is carried out through a probability density function method. The effectiveness of the method is verified through related experiments.

Description

technical field [0001] The invention relates to a method for predicting water consumption of urban water supply pipe network users. Background technique [0002] With the continuous advancement of urbanization, the scale of the city is also increasing, and the water consumption of users is also increasing. At the same time, with the continuous improvement of the water supply network and the continuous improvement of the technological level of water companies, more and more users measure water with large meters. The instrument is used in users, communities and industrial enterprises, and it becomes easier to obtain user water consumption information. In addition, the analysis and prediction of the water consumption of the pipe network based on the water use information is of great significance for the operation and scheduling of the urban water supply pipe network and the future design and planning. Therefore, the prediction of water consumption for water users is of great s...

AI Technical Summary

Problems solved by technology

[0003] At present, the prediction of water consumption is mostly based on machine learning prediction of short-term water consumption, which is generally based on the prediction of water consumption in the entire water pipe network area, which can only reflect the change of total water consumption, and there are few predictions on user water consumption and its changing trend

At the same time, due to the accuracy of the user's measurement of large tables and data transmission, there are some abnormal data in the large table data, which may lead to a decrease in accuracy and efficiency for machine learning

In addition, when the amount of data is small, it is difficult to construct the required amount of training data such as neural networks, which limits the application of traditional machine learning methods

Images