Short-term load forecast method based on artificial neural network

Abstract

The invention relates to a short-term load forecast method based on an artificial neural network and belongs to the technical field of electric system load forecasts. The method comprises a network structure improved method and an output result correcting method. The network structure improved method mainly improves an input variable choice. The input variable considers six aspect factors, wherein the six aspect factors respectively are a date type W, a temperature exponent T, a comfortable degree exponent of human body D, an accumulative effect exponent A, a load data L and an economy increasing exponent E. The output result correcting method considers the load increasing or increasing influence brought by atypia day time influence and correct output results. The short-term load forecast method based on the artificial neural network improves load susceptibility to weather exponents, optimizes network nonlinear function fitting parameters, fastens network training speed and improves load forecast accuracy rate.

Description

technical field [0001] The invention belongs to the technical field of power system load forecasting, in particular to a short-term load forecasting method based on network structure improvement and output result correction. Background technique [0002] Power system short-term load forecasting is an important part of load forecasting and the basis for realizing safe and economical operation of the power system, especially in power market transactions. The higher the accuracy of load forecasting, the more beneficial it is to improve the utilization rate of power generation equipment and the effectiveness of economic dispatch; on the contrary, when the load forecasting error is large, it will not only cause a lot of operating costs and profit losses, but even affect the reliability of power system operation. balance of supply and demand in electricity and electricity markets. Therefore, it is very necessary to adopt advanced forecasting methods. [0003] The short-term load...

AI Technical Summary

Problems solved by technology

[0012] Combining the above two aspects, the accuracy of the above-mentioned short-term load forecasting method using artificial neural network based on network structure and output results correction still needs to be improved