Electrical load joint prediction method and device, terminal and storage medium

Abstract

The invention relates to an electrical load joint prediction method and device, a terminal and a storage medium, and the method comprises the steps: determining main meteorological factors affecting an electrical load and an air load according to the impact degree of each meteorological factor on the electrical load and the air load; acquiring historical data of the electrical load and the gas load and historical meteorological data corresponding to the main meteorological factors; according to the historical data and the historical meteorological data of the electrical load and the gas load,constructing a long-term and short-term memory network LSTMS model; predicting the electrical load and the gas load according to the constructed LSTMS model to obtain a prediction result; consideringthe influence of meteorological factors on the change of the electrical load and the gas load, predicting the electrical load and the gas load by the LSTMS model so that the prediction precision is high, the change trend of the electrical load and the gas load can be well simulated, and a reference can be provided for making a day-ahead operation strategy for a comprehensive energy system.

Description

technical field [0001] The present invention relates to the technical field of energy load forecasting, in particular to a joint electrical load forecasting method, device, terminal and storage medium. Background technique [0002] Under the current background of energy conservation and emission reduction and the rapid growth of renewable energy, building a clean, low-carbon, and environmentally friendly comprehensive energy system has been put on the course of my country's energy development, and has become an important energy source in the process of energy transformation. way of use. The integrated energy system is an integrated energy network in which multiple energy sources interact and mix, and is an important form of development in the energy field. [0003] Therefore, accurate energy demand forecasting will become an important part of the economic dispatch and optimal operation of the integrated energy system; in traditional energy forecasting problems, usually only ...

AI Technical Summary

Problems solved by technology

[0003] Therefore, accurate energy demand forecasting will become an important part of the economic dispatch and optimal operation of the integrated energy system; in traditional energy forecasting problems, usually only the change of a single In the process, the mutual conversion and pivot relationship between different types of loads are obviously ignored.

[0004] Traditional energy forecasting methods include ARMA time series forecasting method, radial basis function neural network method, BP neural network method, etc. The BP neural network algorithm is easily affected by local minimum values ​​in the calculation process, making the overall generalization low; The basic function neural network algorithm is not capable of data screening and information extraction; the time series algorithm is only based on the historical data of a single energy source for load forecasting, and cannot respond to emergencies and abnormal situations in a timely manner, resulting in low forecasting accuracy

Images