Economic Load-Reduction Strategy of Central Air Conditioning Based on Convolutional Neural Network and Pre-Cooling

Central air conditioning in large buildings is an important demand-response resource due to its load power and strong controllability. Demand-response-oriented modeling needs calculate the room temperature. The temperature calculation models commonly used existing research cannot easily accurately change of buildings. Therefore, order obtain a building corresponding potential, this paper first proposes model based on CNN (convolutional neural network). Then, fully apply potential central load, puts forward evaluation method load-reduction cluster pre-cooling develops economic strategy according different energy consumption stage. Finally, multiple examples with parameters comfort ranges are set up, advantages proposed illustrated by Cplex solution examples.