Intelligent building user energy consumption behavior prediction method based on LSTM neural network

Abstract

The invention relates to an intelligent building user energy consumption behavior prediction method based on an LSTM neural network. The method comprises the following steps of collecting the historical energy consumption data; collecting the daily historical energy consumption data of each user in a building, and obtaining a historical daily load curve of each user; classifying the energy consumption behaviors; adopting a K-Means clustering algorithm to cluster the historical daily load curves of all users, determining the optimal cluster number K of clustering by calculating a contour coefficient and a DBI index, obtaining K clustering results, and adding a user energy consumption behavior label to the data in each clustering result; training a prediction model; according to clustering results, constructing K LSTM neural networks, and training each LSTM neural network by taking the historical daily load curve of the user in each clustering result as a training sample to obtain K energy consumption behavior prediction models; and utilizing the trained K energy consumption behavior prediction models to predict the energy consumption behavior of any user in the future building.

Description

technical field [0001] The invention relates to a method for predicting energy consumption behavior of smart building users based on an LSTM neural network, and belongs to the technical field of electricity consumption behavior prediction. Background technique [0002] Accurate building load forecasting is the basis for safe and economical operation and intelligent scientific management of building power load systems. Smart buildings with "Internet +" as the core will become one of the important directions for energy service providers to develop user-side service management. The analysis and prediction of user energy consumption behavior is an important way for energy suppliers to adapt to the trend of increasing user energy demand and diversification of energy use methods, and it also provides a necessary means for users to formulate personalized energy use solutions. Therefore, it is very urgent to conduct an in-depth analysis of user-side energy consumption behavior. [...

AI Technical Summary

Problems solved by technology

This method is only effective when the data before and after the recognition input and output are not related, but when the data that is related before and after the recognition is identified, if the previous data is not used as the input variable of the latter data, the algorithm cannot mine the data in essence. generated pattern

The problem is that it lacks consideration of the time correlation of time series data, and it is necessary to artificially add time features to ensure the predicted results

Images