Heat load prediction method, device, readable medium and electronic device

Abstract

The invention discloses a heat load forecasting method and a device. The method comprises the following steps: a plurality of forecasting states and corresponding error thresholds are set to form a forecasting model; the prediction model predicts the first heat load level corresponding to the target steam user when the boiler steam is used in a plurality of test periods; a relative prediction error corresponding to each test period is determined according to each first thermal load level; a state transition probability matrix is formed according to each relative prediction error, and the state probabilities of each future time period with respect to each predicted state are determined according to the state transition probability matrix. The prediction model predicts the second heat loadlevel corresponding to each future time period; for each future time period, the corresponding heat load interval is determined according to the corresponding second heat load level, the state probability with respect to the various predicted states and the error threshold corresponding to the various predicted states, respectively. Through the technical proposal of the invention, the boiler steamcan be conveniently dispatched more efficiently in the follow-up.

Description

technical field [0001] The invention relates to the technical field of electrical engineering, in particular to a thermal load prediction method, device, readable medium and electronic equipment. Background technique [0002] In order to realize the efficient dispatching of the steam of the steam equipment, it is usually necessary to predict the heat load corresponding to the steam users using the steam in each future time period. [0003] At present, the autoregressive integrated moving average model (Autoregressive Integrated Moving Average Model, ARIMA model) is usually used to predict the respective heat load levels corresponding to steam users using steam equipment steam in various future time periods. [0004] The ARIMA model can only predict the heat load level corresponding to steam users using steam in each future time period, that is, when a specific value is predicted, for irregular use of steam equipment in multiple consecutive historical time periods For a stea...

AI Technical Summary

Problems solved by technology

[0004] The ARIMA model can only predict the heat load level corresponding to steam users using steam in each future time period, that is, when a specific value is predicted, for irregular use of steam equipment in multiple consecutive historical time periods For a steam user of steam, there may be a large gap between one or more heat load levels predicted by the steam user and the current heat load level corresponding to the steam user actually using the steam of the steam equipment in the corresponding future time period. Differences, excessive single-point errors occur, resulting in the inability to efficiently dispatch the steam of the steam equipment in the subsequent process

Images