Fractal theory-based building energy consumption prediction method

Abstract

The invention discloses a building energy consumption prediction method based on a fractal theory, and the method comprises the steps: collecting energy consumption data, carrying out the selection ofa similar day, and ranking the similarity in the first three days as a prediction reference day; drawing an energy consumption curve of a reference date, selecting an extreme point and an inflectionpoint on the energy consumption curve as interpolation points, constructing an iterative function IFS in a complete interval according to the given interpolation points, and enabling the IFS to meet afractal collage theorem; solving the value of a vertical scale factor di of each similar day by adopting a random factor method; obtaining an attractor of the IFS according to the determined ith affine transformation of the IFS and each parameter of the IFS, and then obtaining a stable interpolation curve through multiple iterations; solving an attractor by adopting a deterministic iterative algorithm; and evaluating a prediction result by adopting the average relative error MRE and the root mean square error RMSE to realize building energy consumption prediction. The method has good prediction precision, universality and applicability, and is especially suitable for large fractal characteristic public buildings with periodically changing energy consumption.

Description

technical field [0001] The invention belongs to the technical field of new energy and energy saving, and in particular relates to a method for predicting building energy consumption based on fractal theory. Background technique [0002] Public buildings consume a relatively high level of energy in buildings, accounting for more than 25% of the total energy consumption of civil buildings. According to statistics, from 2009 to 2015, the energy consumption of public buildings in my country has increased at an average annual rate of The rate of growth is 12.29%. Large public buildings generally have problems of high energy consumption and low energy efficiency. Therefore, changing its energy consumption state is an important issue of building energy conservation in our country. [0003] Building energy consumption prediction is an important part of the building energy management process. It is a key task to achieve building energy conservation. Correct and reasonable prediction ...

AI Technical Summary

Problems solved by technology

However, these models have various problems that make the prediction accuracy not ideal

For example, the learning speed of the artificial neural network algorithm is not high enough, and it is easy to produce local optimum and overfitting phenomenon; support vector machine is difficult to use in a large number of samples, and it is difficult to solve multi-classification problems; the probability of the decision tree model is easily influenced by human , the accuracy of decision-making is reduced; the calculation amount and calculation difficulty of the mixed model are high, etc.

The above prediction algorithms only focus on the prediction of energy consumption by their own algorithms, but fail to fully consider the complex characteristics of building energy consumption, resulting in unsatisfactory prediction results

Images