Long Short-Term Memory Neural Network Model for the Control of Temperature in A Multi-Circuit Air Conditioning System

Temperature control is important in energy management of buildings. Air conditioning system contributes a high percentage the total consumption, compressor, which major component system, utilizes up to 90% energy. This can drastically be reduced by varying frequency compressor with respect required indoor temperature, as such, reducing overall usage air system. The combination well-tuned controller and variable drive used achieve this. It develop good model design controller. Although there are published research works development models for systems, seems lack study area multi-circuit centralized In this study, two were developed using Long Short Term Memory Neural Network Recurrent Network, utilizing speed temperature water cooled packaged unit input output respectively. Comparing models, results shows that Short-Term performed better across evaluation metrics such R-squared, Mean Squared Error Absolute Error, value 0.9638, 0.0049, 0.0190 respectively