Multi-dimensional data-based traction energy consumption reasonable interval prediction method

Abstract

The invention discloses a multi-dimensional data-based traction energy consumption reasonable interval prediction method, which comprises the following steps: carrying out data acquisition: acquiring historical and real-time multi-dimensional characteristic data of energy consumption of an energy system; splitting the data, namely splitting the data into multi-dimensional data of different single items according to the difference of data types; carrying out data preprocessing: performing data preprocessing on the multi-dimensional data of each single item; carrying out data modeling: designing a data model for each piece of single-item multi-dimensional data; carrying out data training: training the established data model, and optimizing the data model; and carrying out data prediction: performing data prediction on real-time data according to the trained and optimized data model. According to the invention, interval prediction is carried out on multi-dimensional traction energy consumption data in the smart urban rail through an artificial intelligence algorithm and a distributed frame structure, multi-step prediction can be carried out according to historical data and real-time data, and auxiliary guidance is provided for traction equipment decision making.

Description

technical field [0001] The invention relates to the field of rail transit energy consumption, in particular to a reasonable interval prediction method for traction energy consumption based on multidimensional data. Background technique [0002] The power energy saving industry is a basic industrial industry that converts various types of primary energy into electric energy through corresponding various power generation equipment, and provides end users with electric energy of different voltage levels and different reliability requirements, as well as other electric auxiliary services. my country is a large energy producer and consumer in the power industry, and strengthening energy conservation and emission reduction in the power industry is of great significance to achieve the overall goal of energy conservation and emission reduction for the whole society. Energy-saving technical supervision is an important technical force supporting energy-saving and emission-reduction wo...

AI Technical Summary

Problems solved by technology

[0004] The present invention is to overcome the problems in the prior art that the energy consumption prediction is based on the data fitting of the off-line data to obtain the regular decision-making, which does not have the accuracy of real-time and long-term operation, and provides a traction force energy consumption based on multi-dimensional data Reasonable interval prediction method, using artificial intelligence algorithm and distributed framework structure to perform interval prediction on multi-dimensional traction energy consumption data in smart urban rail, it can perform multi-step prediction based on historical data and real-time data and provide auxiliary guidance for traction equipment decision-making

Images