Heat supply load prediction method and device

Abstract

The embodiment of the invention provides a heat supply load prediction method and device. The method comprises the steps of: determining the indoor temperature prediction range of a target time periodaccording to current indoor environment parameters and an indoor temperature prediction model; and determining the heat supply load prediction range of the target time period according to the indoortemperature prediction range, the outdoor prediction environment parameters of the target time period and a heat supply load prediction model. With the heat supply load prediction method and device ofthe invention adopted, heat supply load can be changed into a heat supply load interval from a traditional load curve on the premise of meeting the comfort requirement of a human body, so that totalheat supply load has elasticity in each time period, and therefore, the peak regulation of a thermoelectric unit can be more accurate and flexible.

Description

technical field [0001] The present application relates to the field of power systems, and in particular to a heating load forecasting method and device. Background technique [0002] Due to the cold winter in the northern region, ensuring the heating of residents is an essential task every year. At present, cogeneration units are mostly used for central heating, and most of the units operate in the "heat-constant power" mode, which limits the peak-shaving capacity of thermal power units in winter, greatly reduces the space for wind power to be connected to the grid, and causes serious wind curtailment. In actual projects, heating companies often use heating methods that are higher than the heat load demand of residents, resulting in a waste of resources. [0003] The inventors found that in the prior art, the fine-grained solution of heat load on the user side mostly adopts the modeling method of pipelines and buildings, which is not only complicated in calculation, but als...

AI Technical Summary

Problems solved by technology

At present, cogeneration units are mostly used for central heating, and most of the units operate in the mode of "heat-constant power", which limits the peak-shaving capacity of thermal power units in winter, greatly reduces the space for wind power to be connected to the grid, and causes serious wind curtailment.

In actual projects, heating companies often use heating methods that are higher than the heat load demand of residents, resulting in waste of resources

[0003] The inventors found that in the prior art, the fine-grained solution of heat load on the user side mostly adopts the modeling method of pipelines and buildings, which is not only complicated in calculation, but also requires a large number of parameters such as pipelines and building structures, which makes it difficult in actual operation

[0004] At the same time, with the development of neural network, it is more and more used in load forecasting, but the traditional neural network method has the disadvantage of slow convergence speed and easy to fall into local optimum.

Images