Residential heating, ventilation and air conditioning(HVAC) provides important demand response resources for the new power system with high proportion of renewable energy. Residential HAVC scheduling strategies that a...Residential heating, ventilation and air conditioning(HVAC) provides important demand response resources for the new power system with high proportion of renewable energy. Residential HAVC scheduling strategies that adapt to realtime electricity price signals formulated by demand response program and ambient temperature can significantly reduce electricity costs while ensuring occupants' comfort. However, since the pricing process and weather conditions are affected by many factors, conventional model-based method is difficult to meet the scheduling requirements in complex environments. To solve this problem, we propose an adaptive optimal scheduling strategy for residential HVAC based on deep reinforcement learning(DRL) method. The scheduling problem can be regarded as a Markov decision process(MDP). The proposed method can adaptively learn the state transition probability to make economical decision under the tolerance violations. Specifically, the residential thermal parameters obtained by the leastsquares parameter estimation(LSPE) can provide a basis for the state transition probability of MDP. Daily simulations are verified under the electricity prices and temperature data sets, and numerous experimental results demonstrate the effectiveness of the proposed method.展开更多
Residential air conditioning(RAC)loads have great potential to be included in demand response(DR)programs.This paper studies large-scale RAC loads participating in DR programs,such as modeling,parameters identificatio...Residential air conditioning(RAC)loads have great potential to be included in demand response(DR)programs.This paper studies large-scale RAC loads participating in DR programs,such as modeling,parameters identification,DR characteristics and control strategies.First,an aggregate model of large-scale RAC loads are established based on the buildings’performance with heat storage and insulation,avoiding the calculation of a single RAC model.Then,parameters of the aggregate model are identified based on the RACs’power and outdoor temperatures.Based on the aggregate model,DR characteristics of RAC loads are analyzed,including the dynamic relationship between power,outdoor and indoor temperature,and the potential of DR combined with the users’comfort.Next,the DR control strategies adapted for large-scale RAC loads are established by adjusting the temperature set-points.The DR strategies consider users’comfort and calculate the control signals of each RAC load according to the DR power,including adjustment temperature and adjustment time,which are sent to each RAC load for execution.In the DR process,the control center does not need to obtain the users’indoor temperature,which is conducive to protecting the users’privacy.DR strategies of RAC loads when the control degree within/beyond the DR potential are both proposed,and a load recovery control strategy is also introduced.Finally,the effectiveness and accuracy of the proposed model and DR control strategies are verified by simulation results.展开更多
Space cooling is an important building energy end-use that was found in recent years to be significantly impacted by occupant behaviours.However,the majority of previous studies ignored the interplay between the opera...Space cooling is an important building energy end-use that was found in recent years to be significantly impacted by occupant behaviours.However,the majority of previous studies ignored the interplay between the operation of windows and air conditioners(ACs)on cooling load,particularly in building energy modelling.In addition,studies on the analysis of cooling load characteristics regarding high-rise buildings are insufficient.The vertical effect of high-rise buildings on cooling load remains vague.This study thus aims to examine how window and AC operation behaviours impact the cooling load of high-rise buildings in an urban context demonstrated by a real-life typical 40-floor residential building in Hong Kong.This study investigates window and AC operation behaviours jointly and examines the vertical effect on cooling load by using agent-based building energy modelling(BEM)techniques and initiating stochastic and diverse behaviour modes.A carefully designed questionnaire survey was conducted to help build behaviour modes and validate energy models.Ninety building energy models were established integrating meteorological parameters generated by the computational fluid dynamics(CFD)programme for ten typical floors and nine combinations of window and AC behaviour modes.The results show that comfort-based AC modes and schedule-based window modes yielded the lowest cooling load.Considering the combined effect of AC and window uses,the maximum difference in cooling loads could be 26.8%.Behaviour modes and building height induce up to 32.4%differences in cooling loads.Besides,a deviation between the behaviour modes and height on the cooling load was found.The findings will help develop a thorough energy model inferring occupants’window and AC behaviour modes along with the building height in high-rise residential buildings.The findings indicate that the interaction impact of window and AC behaviour modes and height should be jointly considered in future high-rise building energy modelling,building energy standards,and policymaking.展开更多
基金supported in part by the Fundamental Research Funds for the Central Universities (No. 2018JBZ004)the National Natural Science Foundation of China (No. 52007004)。
文摘Residential heating, ventilation and air conditioning(HVAC) provides important demand response resources for the new power system with high proportion of renewable energy. Residential HAVC scheduling strategies that adapt to realtime electricity price signals formulated by demand response program and ambient temperature can significantly reduce electricity costs while ensuring occupants' comfort. However, since the pricing process and weather conditions are affected by many factors, conventional model-based method is difficult to meet the scheduling requirements in complex environments. To solve this problem, we propose an adaptive optimal scheduling strategy for residential HVAC based on deep reinforcement learning(DRL) method. The scheduling problem can be regarded as a Markov decision process(MDP). The proposed method can adaptively learn the state transition probability to make economical decision under the tolerance violations. Specifically, the residential thermal parameters obtained by the leastsquares parameter estimation(LSPE) can provide a basis for the state transition probability of MDP. Daily simulations are verified under the electricity prices and temperature data sets, and numerous experimental results demonstrate the effectiveness of the proposed method.
基金supported by the Major State Basic Research Development Program of China under Grant No.2016YFB0901100the National Science Foundation of China under Grant No.51577051the Science and Technology Project of SGCC“Research on the system for friendly supply-demand interaction between urban electric power customers and power grid”.
文摘Residential air conditioning(RAC)loads have great potential to be included in demand response(DR)programs.This paper studies large-scale RAC loads participating in DR programs,such as modeling,parameters identification,DR characteristics and control strategies.First,an aggregate model of large-scale RAC loads are established based on the buildings’performance with heat storage and insulation,avoiding the calculation of a single RAC model.Then,parameters of the aggregate model are identified based on the RACs’power and outdoor temperatures.Based on the aggregate model,DR characteristics of RAC loads are analyzed,including the dynamic relationship between power,outdoor and indoor temperature,and the potential of DR combined with the users’comfort.Next,the DR control strategies adapted for large-scale RAC loads are established by adjusting the temperature set-points.The DR strategies consider users’comfort and calculate the control signals of each RAC load according to the DR power,including adjustment temperature and adjustment time,which are sent to each RAC load for execution.In the DR process,the control center does not need to obtain the users’indoor temperature,which is conducive to protecting the users’privacy.DR strategies of RAC loads when the control degree within/beyond the DR potential are both proposed,and a load recovery control strategy is also introduced.Finally,the effectiveness and accuracy of the proposed model and DR control strategies are verified by simulation results.
基金supported by grants from the General Research Fund of the Hong Kong Research Grants Council[No.17203219]the Collaborative Research Fund of the Hong Kong Research Grants Council[No.C7047-20GF].
文摘Space cooling is an important building energy end-use that was found in recent years to be significantly impacted by occupant behaviours.However,the majority of previous studies ignored the interplay between the operation of windows and air conditioners(ACs)on cooling load,particularly in building energy modelling.In addition,studies on the analysis of cooling load characteristics regarding high-rise buildings are insufficient.The vertical effect of high-rise buildings on cooling load remains vague.This study thus aims to examine how window and AC operation behaviours impact the cooling load of high-rise buildings in an urban context demonstrated by a real-life typical 40-floor residential building in Hong Kong.This study investigates window and AC operation behaviours jointly and examines the vertical effect on cooling load by using agent-based building energy modelling(BEM)techniques and initiating stochastic and diverse behaviour modes.A carefully designed questionnaire survey was conducted to help build behaviour modes and validate energy models.Ninety building energy models were established integrating meteorological parameters generated by the computational fluid dynamics(CFD)programme for ten typical floors and nine combinations of window and AC behaviour modes.The results show that comfort-based AC modes and schedule-based window modes yielded the lowest cooling load.Considering the combined effect of AC and window uses,the maximum difference in cooling loads could be 26.8%.Behaviour modes and building height induce up to 32.4%differences in cooling loads.Besides,a deviation between the behaviour modes and height on the cooling load was found.The findings will help develop a thorough energy model inferring occupants’window and AC behaviour modes along with the building height in high-rise residential buildings.The findings indicate that the interaction impact of window and AC behaviour modes and height should be jointly considered in future high-rise building energy modelling,building energy standards,and policymaking.
