Shopping mall cold load prediction method and system oriented to function partition

Abstract

The invention discloses a shopping mall cold load prediction method and system oriented to function partitions, and the method comprises the steps: completing the division of the function partitions according to a target shopping mall building plan and business state space layout, and completing the screening of key influence factors of each function partition according to gray correlation analysis; and establishing an Attention-LSTM cold load prediction model improved based on an attention mechanism; seeking optimal parameters of the cold load model through grid search and a cross validation method; and independently completing regional cold load prediction by each function partition, and finally obtaining a cold load prediction result of the whole shopping mall building through a prediction result summation instruction. According to the functional partition-oriented shopping mall cold load prediction, the fluctuation characteristics of the building cold load are highly extracted, and the problem that in the prior art, shopping mall cold load data have the characteristics of high dimension, nonlinearity, high delay and strong time-varying performance is solved. Therefore, the air-conditioning system can effectively track the load change, and a powerful control basis is provided for the energy efficiency research of the transmission and distribution cooling multi-stage pump system, so that the indoor thermal environment is improved, and the air-conditioning energy consumption is reduced.

Description

technical field [0001] The invention belongs to the technical field of forecasting cooling load of shopping mall building areas, and in particular relates to a method and system for forecasting cooling load of shopping malls oriented to functional partitions. Background technique [0002] At present, energy problems are becoming more and more serious, energy conservation and emission reduction work has become the focus of various countries, and building energy consumption accounts for about 40% of all energy consumption. Air-conditioning is one of the most common energy-consuming equipment in buildings, accounting for about 60% of total power and energy consumption, causing a heavy energy burden and serious environmental pollution to society, and has become a major problem restricting China's sustainable development. [0003] The building structure of a large shopping mall is characterized by a building complex composed of several specialized stores, and each store in the sh...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a method and system for forecasting the cooling load of shopping malls oriented to functional partitions in view of the deficiencies in the above-mentioned prior art, so as to solve the problem of high-dimensionality, nonlinearity, high The characteristics of delay and strong time-varying; the building-level cooling load forecasting model cannot extract the characteristics of building cooling load well and improve the forecasting accuracy; at the same time, the purpose of district cooling load forecasting is to enable the air-conditioning system to effectively track load changes , to provide a powerful control basis for the energy efficiency research of the multi-stage pump system for transmission and distribution cooling, thereby improving the indoor thermal environment and reducing air-conditioning energy consumption

Images