Energy-saving Optimal Control Based On Indoor Thermal Comfort

The construction industry is an important industry in national economies and is related to people’s livelihoods and national comprehensive strength.With the accelerated construction of smart cities and the increasing energy consumption of buildings,advanced requirements for building energy-saving technologies are being proposed.Additionally,the main living environment is indoors,and people have strict requirements for indoor environmental comfort.To create a comfortable indoor thermal environment,a large amount of heat energy needs to be consumed.Building HVAC(Heating,Ventilating and Air Conditioning)systems are used to maintain indoor thermal environment and ensure the thermal comfort of personnel.The main components of a building can account for up to 30% of the total energy consumption of the building.In fact,it is extremely difficult to balance the satisfactory indoor thermal comfort and the energy consumption of the air-conditioning system;this issue has become a bottleneck in the development of optimal control strategies for building energy conservation.In traditional building energy-saving optimization methods,the individual requirements of personnel comfort are generally not considered,global optimization is lacking,and the applied theories are singular,thus making it difficult to effectively resolve the conflict between comfort and energy consumption.Therefore,this thesis conducts in-depth research on building energy consumption prediction,the meeting of comfort requirements and building cooling energy-saving control strategies,and simulation-based system experiments are performed.The main research contents and contributions of this paper are as follows.(1)Research based on comprehensive prediction models of building energy consumption and BP(Back Propagation)neural networks is performed.The BP neural network model is improved,and genetic algorithm and particle swarm optimization algorithm are introduced to optimize the neural network parameters.A comprehensive optimization algorithm of energy consumption is proposed to find the best value in the multiple prediction results.With the air-conditioning energy consumption and meteorological data for a building in Laixi,a comprehensive prediction model of building energy consumption based on the BP neural network is established to achieve accurate and reliable predictions of building energy consumption.(2)Research on energy-saving optimization control strategies based on indoor comfort is conducted.Various comfort prediction models are analyzed,and the influence of the number of indoor personnel is assessed.Then,a method that considers the thermal comfort of personnel is established.to balance building indoor thermal comfort and energy consumption,an energy-saving optimization control strategy is proposed,and the optimal compressor speed and indoor temperature in a building with an air-conditioning system can be obtained under comfort and value constraints.(3)Simulation research on building energy-saving optimization control systems is conducted.A building air-conditioning system simulation was performed in the laboratory,and the proposed optimal control strategy was used to determine the best values of air-conditioning system operating parameters.The operation results indicate that the control strategy has the potential to achieve energy savings.This study has a wide range of application value in assessments of cooling and energy savings related to public building air-conditioning systems.