Daily water consumption prediction method based on phase-space reconstruction and gene expression programming

Abstract

The invention provides a daily water consumption prediction method based on phase-space reconstruction and gene expression programming. The method comprises the steps of collecting historical water consumption data of a water supply network, and forming a training set; for any point in the training set, calculating mutual information and false adjacent points based on a phase-space reconstruction method to obtain optimal delay time and embedded dimensions, and reconstructing the training set; and training the reconstructed training set by using a gene expression programming model, constructing an angle-based convergence function, training until convergence, finally obtaining a functional expression for predicting the water consumption, and predicting the daily water consumption by using the functional expression. According to the daily water consumption prediction method based on phase-space reconstruction and gene expression programming, related technicians can be guided to strengthen cognition of a water supply system by utilizing a phase-space reconstruction method, and meanwhile, an optimal target can be quickly converged.

Description

【Technical field】 [0001] The invention relates to the technical field of water supply pipe networks, in particular to a method for predicting daily water consumption based on phase space reconstruction and gene expression programming. 【Background technique】 [0002] Water consumption forecasting is divided into short-term forecasting and medium- and long-term forecasting. Medium and long-term forecasts are usually monthly and annual water consumption forecasts, which are mainly used for the optimization of urban water supply network construction. Short-term forecasts are usually hourly and daily water consumption forecasts, which are mainly used to optimize the allocation of water supply systems. Accurate daily water consumption forecast can improve the management efficiency of the water supply system and reduce dispatching costs to save resources. In recent years, data-driven methods have been widely used in water consumption forecasting. In forecasting, a large number o...

AI Technical Summary

Problems solved by technology

However, most of these models have the problems of too many model parameters, time-consuming training, and require a high sampling frequency

It is not suitable for the water consumption prediction task of the pipe network that only collects one data per day

Images