Research On Methods Of Joint Energy And Thermal Comfort Management In Smart Buildings Under Uncertainties

Building energy consumption accounts for up to 40% of the total energy consumption in a country.With the growth of population and rapid increase of purchasing power in new economies as well as many developed countries,building energy demand in 2050 would increase by 50% compared with that in 2016.Due to the limitation of traditional energies(e.g.,coal,oil,natural gas),the growing energy demand in buildings will lead to increasing national energy crisis,environment impact,and economic burden for building owners.Since about 40% of building energy consumption is attributed to Heating,Ventilation,and Air Conditioning(HVAC)systems,the most direct way of reducing building energy consumption is to decrease input power of HVAC systems,which may affect the thermal comfort of occupants.Thus,it is very necessary to consider the joint energy and thermal comfort management for buildings.In addition,with the development of Internet of Things technologies,the current buildings are gradually evolved into smart buildings,which bring more opportunities for the joint energy and thermal comfort management.Although there are many opportunities,it is very challenging to develop efficient methods for the joint energy and thermal comfort management in smart buildings due to the existence of multiple-source uncertainties and the difficulty of developing a building thermal dynamics model that is both accurate and efficient enough for effective HVAC control.To overcome these challenges,this paper studies the joint energy and comfort management in smart buildings under uncertainties.Firstly,we investigate a long-term total cost minimization problem for an HVAC system in a multi-zone commercial building,where the total cost is the sum of energy cost and thermal discomfort cost.Due to the existence of uncertain parameters(e.g.,electricity price,outdoor temperature,the most comfortable temperature of occupants,and thermal disturbance),temporally-coupled constraints related to indoor temperatures,as well as spatially-coupled constraints related to all zone air supply rates,it is very challenging to solve the formulated problem.To address the challenge,we propose a real-time distributed HVAC control algorithm based on the framework of Lyapunov optimization technique.The proposed algorithm does not require any prior knowledge of uncertain parameters,protects user privacy,and has high scalability.Extensive simulation results show the effectiveness of the proposed algorithm.Secondly,we investigate an energy cost minimization problem for a smart home in the absence of a building thermal dynamics model with the consideration of a comfortable temperature range.Due to the existence of uncertain parameters(e.g.,renewable generation output,non-shiftable power demand,outdoor temperature,and electricity price)and temporally-coupled operational constraints related to the energy storage system and indoor temperature,it is very challenging to solve the formulated problem.To overcome these challenges,we propose an energy management algorithm for the problem based on Deep Deterministic Policy Gradients(DDPG).It is worth mentioning that the proposed algorithm does not require the prior knowledge of uncertain parameters and building thermal dynamics model.Simulation results based on real-world traces demonstrate that the proposed algorithm could reduce energy cost by 8.1%-15.21% without sacrificing thermal comfort.Moreover,it can provide a more practical and flexible tradeoff than the perfect information algorithm.Finally,we summarize the main contents in this dissertation and propose several directions for future research.