Power generation fuel supply prediction method

Abstract

The invention discloses a power generation fuel supply prediction method, comprising the following steps of implementing stationary processing; implementing model recognition and order determination, i.e. establishing a prediction model according to an autocorrelogram and a partial autocorrelogram to determine model parameters; evaluating the model parameters, i.e. determining the related parameters of the model according to the autocorrelogram, the partial autocorrelogram and stationarity; testing model adaptability, i.e. implementing a residue independence test or a heteroskedasticity test, and modifying the prediction model till a residue sequence is a white noise sequence, and all useful information is extracted. According to the power generation fuel supply prediction method based on a multiplicative seasonal model provided by the invention, the prediction model is a combination of a random seasonal model and an ARIMA (Autoregressive Integrated Moving Average) model; under the premise of considering historical data and influencing factors, the seasonal factors of power generation fuel supply are reflected better, so that the power generation fuel prediction precision is improved.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

The inventors developed an improved way that uses both models from Random Season Model (RSM) and Artificial Intelligence Imaging Group(AIM). These two types of models help improve the ability to accurately estimate future energy production levels over time compared to previous methods such as linear regression or machine learning techniques.

Problems solved by technology

This patents discuss various techniques that help estimate how much electricity needs are supplied during different timescales or months depending upon changing environmental conditions like temperature or humidity levels. These estimations may involve categorizing them according to their importance (strict) or noncriticism approach. Statistically speaking, these approaches aim to simplify the process of fitting an accurate equation relating production capacity versus renewable resources under varying climatic scenarios.

Images