Multi-dimensional expansion prediction method and device for non-stationary time series data

Abstract

The invention relates to a multi-dimensional expansion prediction method and device for non-stationary time series data, and the method comprises the following steps: collecting original meter readingdata, processing the original meter reading data, and expanding data dimensions to construct a meter reading data set; constructing RNN sequence expression models with different sequence dependent lengths, carrying out model training by adopting total data, and determining the optimal dependent length according to model performance expression; establishing an RNN sequence model based on the optimal sequence dependence length, and performing model training based on the meter reading data set to obtain optimized RNN sequence model parameters; predicting the latest remote transmission data of each meter by using the optimized RNN sequence model parameters; and comparing the predicted remote transmission data value with the actual remote transmission data value, obtaining a correction value according to a strategy, and recording the correction value into a database. According to the method, the non-stationary time sequence can be modeled, and meanwhile, the information dimension of the difference time step length can be fused, so that the time sequence model has stronger expression capability.

Description

technical field [0001] The invention relates to the technical field of time series data prediction, in particular to a method and device for multi-dimensional expansion prediction of non-stationary time series data. Background technique [0002] In the existing regression analysis methods related to time series data, the processing and prediction of stationary time series data are mostly based on fixed time intervals, and it is impossible to deal with the situation of irregular time intervals in the data. At the same time, the modeling dimension of the classic time series model is mainly concentrated in the absolute time scale and sampling value dimension, and lacks the modeling of other information dimensions such as irregular time interval differences. With certain limitations, it is not competent for time series forecasting tasks under complex conditions. Contents of the invention [0003] The purpose of the present invention is to improve the deficiencies existing in ...

AI Technical Summary

Problems solved by technology

[0002] In the existing regression analysis methods related to time series data, the processing and prediction of stationary time series data are mostly based on fixed time intervals, and it is impossible to deal with the situation of irregular time intervals in the data.

At the same time, the modeling dimension of the classic time series model mainly focuses on the absolute scale of time and the dimension of sampling value, and lacks the modeling of other information dimensions such as irregular time interval differences. The level and depth of the model are insufficient in the feature extraction process, and the model expression ability With certain limitations, it is not competent for time series forecasting tasks under complex conditions

Images