A method and system for predicting and optimizing energy consumption of commercial buildings

Abstract

The invention discloses a method and system for predicting and optimizing energy consumption of commercial buildings. It is a training set and a test set; build a random forest model of commercial building energy consumption, and determine the parameters that affect the prediction accuracy of the random forest model; use the parallel ant colony algorithm to optimize the parameters affecting the random forest model using the data of the training set, and get the optimized After the parameters affecting the prediction accuracy of the random forest model are obtained, the optimized random forest model of commercial buildings is obtained; the data of the test set is substituted into the optimized random forest model of commercial buildings, and energy consumption prediction is performed to obtain the energy consumption prediction results of commercial buildings; The invention improves the ant colony algorithm by introducing the idea of ​​parallel sorting, solves the problem of local convergence in the multi-parameter optimization process of random forest, and improves the speed of convergence and the quality of the optimal solution.

Description

technical field [0001] The invention belongs to the technical field of building energy consumption prediction, and in particular relates to a commercial building energy consumption prediction optimization method and system. Background technique [0002] In recent years, with the rapid development of urbanization construction, the energy consumption of commercial buildings has increased significantly, and the research on energy conservation of commercial buildings has become an important direction of energy conservation research; The optimal operation efficiency of the power distribution system provides effective data decision-making; therefore, it is of great practical significance to study the mechanism and law of building energy consumption and establish an accurate and effective prediction model. [0003] At present, most researchers use data-driven methods to establish commercial building energy consumption prediction models; among them, using machine learning algorithms...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the technical problems existing in the prior art, the present invention provides a commercial building energy consumption prediction optimization method and system to solve the problem that the existing random forest algorithm is sensitive to parameter selection, and the optimization process tends to have slow convergence speed and localized Optimum, leading to slow building energy consumption prediction and low prediction accuracy technical problems

Images