Water consumption prediction method and device based on big data

Abstract

The invention relates to the technical field of water consumption prediction, and specifically relates to a water consumption prediction method and device based on big data, and the method comprises the steps: inputting collected data, and carrying out the data preprocessing through employing a principal component analysis method and a Lasso feature selection model; an annual water consumption prediction model of each region is established; obtaining a water consumption prediction result according to the preprocessed data. According to the invention, a principal component regression model is adopted; the Lasso regression model and the support vector machine regression prediction model are combined. The principal components are further screened by using a lasso algorithm after being analyzed by using the principal components. Compared with the prior art, the method has the advantages that the water consumption with high accuracy can be obtained only by collecting a small number of influence factor data sets, the prediction accuracy of the water consumption is greatly improved, and meanwhile, the water consumption is predicted within a shorter time.

Description

technical field [0001] The invention relates to the technical field of water consumption forecasting, in particular to a water consumption forecasting method and device based on big data. Background technique [0002] Due to the overpopulation, the speed of water use is much faster than the self-purification speed of the environment, which leads to the shortage of fresh water resources and is listed as non-renewable resources. With the rapid development of economy, urban and rural residents have more and more demand for production water and residential water, making water quantity forecasting the key to grasp the future development trend in water resource management. It is of great significance for the future construction and development of urban and rural areas to reasonably predict the water consumption within the time limit of urban and rural planning, so as to make it close to the actual situation of urban and rural development. By predicting future water consumption, o...

AI Technical Summary

Problems solved by technology

If the water consumption forecast is not done well, it will be difficult for our country to formulate the overall plan for the development and utilization of water resources in the medium and long term and the water supply plan, which will affect the realization of the national economic plan

[0003] In the existing technology, only the principal component analysis method is used to select the features, and the influencing factors whose contribution value reaches a certain level are selected for prediction. Although this method is much more convenient and faster than the original method, when the influencing factors are overwhelming When part of the relationship with the dependent variable is relatively close, there are still many features screened out by the principal component analysis method.

[0004] There are often many influencing factors with a high contribution value to the prediction of an event outcome. If only relying on the principal component analysis method to narrow the selection range of influencing factors, this will undoubtedly not play a big role in reducing the calculation burden.

Images