To meet the challenge of mismatches between power supply and demand,modern buildings must schedule flexible energy loads in order to improve the efficiency of power grids.Furthermore,it is essential to understand the ...To meet the challenge of mismatches between power supply and demand,modern buildings must schedule flexible energy loads in order to improve the efficiency of power grids.Furthermore,it is essential to understand the effectiveness of flexibility management strategies under different climate conditions and extreme weather events.Using both typical and extreme weather data from cities in five major climate zones of China,this study investigates the energy flexibility potential of an office building under three short-term HVAC management strategies in the context of different climates.The results show that the peak load flexibility and overall energy performance of the three short-term strategies were affected by the surrounding climate conditions.The peak load reduction rate of the pre-cooling and zone temperature reset strategies declined linearly as outdoor temperature increased.Under extreme climate conditions,the daily peak-load time was found to be over two hours earlier than under typical conditions,and the intensive solar radiation found in the extreme conditions can weaken the correlation between peak load reduction and outdoor temperature,risking the ability of a building’s HVAC system to maintain a comfortable indoor environment.展开更多
In heating, ventilating and air-conditioning （HVAC） systems, there exist severe nonlinearity, time-varying nature, disturbances and uncertainties. A new predictive functional control based on Takagi-Sugeno （T-S） f...In heating, ventilating and air-conditioning （HVAC） systems, there exist severe nonlinearity, time-varying nature, disturbances and uncertainties. A new predictive functional control based on Takagi-Sugeno （T-S） fuzzy model was proposed to control HVAC systems. The T-S fuzzy model of stabilized controlled process was obtained using the least squares method, then on the basis of global linear predictive model from T-S fuzzy model, the process was controlled by the predictive functional controller. Especially the feedback regulation part was developed to compensate uncertainties of fuzzy predictive model. Finally simulation test results in HVAC systems control applications showed that the proposed fuzzy model predictive functional control improves tracking effect and robustness. Compared with the conventional PID controller, this control strategy has the advantages of less overshoot and shorter setting time, etc.展开更多
Ice thermal storage is a promising technology to reduce energy costs by shifting the cooling cost from on-peak to off-peak periods. The paper investigates the application of ice thermal storage and its impact on energ...Ice thermal storage is a promising technology to reduce energy costs by shifting the cooling cost from on-peak to off-peak periods. The paper investigates the application of ice thermal storage and its impact on energy consumption, demand and total energy cost. Energy simulation software along with a chiller model is used to simulate the energy consumption and demand for the existing office building located in central Florida. Furthermore, the study presents a case study to demonstrate the cost saving achieved by the ice storage applications. The results show that although the energy consumption may increase by using ice thermal storage, the energy cost drops significantly, mainly depending on the local utility rate structure. It found that for the investigated system the annual energy consumption increases by about 12% but the annual energy cost drops by about 3 6%.展开更多
Owing to the fluctuant renewable generation and power demand,the energy surplus or deficit in nanogrids embodies differently across time.To stimulate local renewable energy consumption and minimize long-term energy co...Owing to the fluctuant renewable generation and power demand,the energy surplus or deficit in nanogrids embodies differently across time.To stimulate local renewable energy consumption and minimize long-term energy costs,some issues still remain to be explored:when and how the energy demand and bidirectional trading prices are scheduled considering personal comfort preferences and environmental factors.For this purpose,the demand response and two-way pricing problems concurrently for nanogrids and a public monitoring entity(PME)are studied with exploiting the large potential thermal elastic ability of heating,ventilation and air-conditioning(HVAC)units.Different from nanogrids,in terms of minimizing time-average costs,PME aims to set reasonable prices and optimize profits by trading with nanogrids and the main grid bi-directionally.Such bilevel energy management problem is formulated as a stochastic form in a longterm horizon.Since there are uncertain system parameters,time-coupled queue constraints and the interplay of bilevel decision-making,it is challenging to solve the formulated problems.To this end,we derive a form of relaxation based on Lyapunov optimization technique to make the energy management problem tractable without forecasting the related system parameters.The transaction between nanogrids and PME is captured by a one-leader and multi-follower Stackelberg game framework.Then,theoretical analysis of the existence and uniqueness of Stackelberg equilibrium(SE)is developed based on the proposed game property.Following that,we devise an optimization algorithm to reach the SE with less information exchange.Numerical experiments validate the effectiveness of the proposed approach.展开更多
Heating, ventilation, and air conditioning (HVAC) system is significant to the energy efficiency in buildings. In this paper, temperature control of HVAC system is studied in winter operation season. The physical mode...Heating, ventilation, and air conditioning (HVAC) system is significant to the energy efficiency in buildings. In this paper, temperature control of HVAC system is studied in winter operation season. The physical model of the zone, the fan, the heating coil and sensor are built. HVAC is a non-linear, strong disturbance and coupling system. Linear active-rejection-disturbance-control is an appreciate control algorithm which can adapt to less information, strong-disturbance influence, and has relative-fixed structure and simple tuning process of the controller parameters. Active-rejection-disturbance-control of the HVAC system is proposed. Simulation in Matlab/Simulink was done. Simulation results show that linear active-rejection-disturbance-control was prior to PID and integral-fuzzy controllers in rising time, overshoot and response time of step disturbance. The study can provide fundamental basis for the control of the air-condition system with strong-disturbance and high-precision needed.展开更多
As mentioned by National Geographic(2017),70%of world’s population is expected to live in large apartment buildings by 2050.Today,buildings in cities generate 30%of world’s greenhouse gas emission or GHG(National Ge...As mentioned by National Geographic(2017),70%of world’s population is expected to live in large apartment buildings by 2050.Today,buildings in cities generate 30%of world’s greenhouse gas emission or GHG(National Geographic,2017).Major urban centers are committed to reducing greenhouse gases by 80%by 2050(IEA,2021).However,achieving such goals in rental properties is not easy.Landlords are hesitant to use high-efficiency technologies because,typically,tenants pay the utilities bill.However,that situation is rapidly changing.For example,New York City like other US cities,is considering a carbon cap on all large buildings(Local Law 97,2019).That means landlords will pay a carbon penalty if the building’s carbon footprint exceeds certain threshold no matter who uses that carbon.The Pacific Northwest National Laboratory(PNNL)has received funds from DOE(US Department of Energy)with the collaboration of a commercial partner to address emerging energy efficiency market opportunity in multi-family or rental housing as discussed above.It has partnered with a large national real estate owner in order to test a novel energy optimization method at a rental property in Tempe,Arizona.By using a seamless-integrated method of acquiring building’s operating data,the optimization approach essentially resets setpoints of different energy consuming equipment such as chillers,boilers,pumps,and fans.Data-driven optimization approach is pragmatic and easily transferrable to other buildings.The authors shall share the problem background,technical approach,and preliminary results.展开更多
With the increasing demand for a better life, people have higher and higher requirements for the quality of indoor environment for work and life. In order to improve the quality of indoor environment, HVAC system has ...With the increasing demand for a better life, people have higher and higher requirements for the quality of indoor environment for work and life. In order to improve the quality of indoor environment, HVAC system has become an indispensable part of building system. But at the same time, the energy consumption of HVAC system also accounts for 50~60% of the total energy consumption of buildings, and it is a major contributor to the total energy consumption of buildings. Therefore, it is of great significance to carry out research on energy-saving technology of HVAC system and improve energy efficiency for achieving the goal of "double carbon". Based on this, this paper takes the urgency and importance of the application of energy-saving measures of HVAC system as the starting point, expounds the energy-saving design principles of building HVAC system, and puts forward some main energy-saving measures of HVAC system for reference.展开更多
Heating,ventilation,and air conditioning system runtime is a crucial metric for establishing the connection between system operation and energy performance.Similar homes in the same location can have varying runtime d...Heating,ventilation,and air conditioning system runtime is a crucial metric for establishing the connection between system operation and energy performance.Similar homes in the same location can have varying runtime due to different factors.To understand such heterogeneity,this study conducted an energy signature analysis of heating and cooling system runtime for 5,014 homes across the US>using data from ecobee smart thermostats.Two approaches were compared for the energy signature analysis:(1)using daily mean outdoor temperature and(2)using the difference between the daily mean outdoor temperature and the indoor thermostat setpoint(delta T)as the independent variable.The best-fitting energy signature parameters(balance temperatures and slopes)for each house were estimated and statistically analyzed.The results revealed significant differences in balance temperatures and slopes across various climates and individual homes.Additionally,we identified the impact of housing characteristics and weather conditions on the energy signature parameters using a long absolute shrinkage and selection operator(LASSO)regression.Incorporating delta T into the energy signature model significantly enhances its ability to detect hidden impacts of various features by minimizing the influence of setpoint preferences.Moreover,our cooling slope analysis highlights the significant impact of outdoor humidity levels,underscoring the need to include latent loads in building energy models.展开更多
Heating,ventilation,and air conditioning(HVAC)systems constitute a significant portion of the office building load and are important flexibility resources.However,the HVAC loads are often inaccessible to the utility o...Heating,ventilation,and air conditioning(HVAC)systems constitute a significant portion of the office building load and are important flexibility resources.However,the HVAC loads are often inaccessible to the utility or load aggregators who only have total load data.Most existing studies require subloads for supervised disaggregation or prior knowledge for unsupervised disaggregation,but such information is hard to obtain.It is necessary to develop an effective,completely unsupervised non-intrusive monitoring method to obtain the HVAC load data.In this study,a multiple seasonal-trend decomposition using the LOESS(MSTL)method is proposed to disaggregate the HVAC load from the total metered electricity data of office buildings.The effects of periodic types(daily,weekly,monthly,etc.),periodic sequences,and parallel/serial structures are analyzed.The proposed method is verified based on the historical electricity data of ten buildings.The results show that the proposed MSTL can accurately disaggregate the HVAC load with a coefficient of variation of the root mean square error(CVRMSE)of 10.94%,a normalized root mean squared error(NRMSE)of 2.1%,and a weighted absolute percentage error(WAPE)of 8.52%.Compared to single-cycle STL,the proposed method can significantly improve load disaggregation performance,with a maximum reduction of 16.36%in CVRMSE,5.3%in NRMSE,and 12.91%in WAPE.Backward-chain-based MSTL is recommended with higher accuracy and robustness.The proposed method provides an effective solution for utilities or load aggregators to improve demand response management and grid stability.展开更多
Heating,ventilation and air conditioning(HVAC)systems maintain personal thermal comfort(PTC)and serve as key demand response(DR)resources.Given the challenges of uncertain environments,varied user preferences,and lega...Heating,ventilation and air conditioning(HVAC)systems maintain personal thermal comfort(PTC)and serve as key demand response(DR)resources.Given the challenges of uncertain environments,varied user preferences,and legal requirements for transparent control strategies,this paper proposes an explainable reinforcement learning(XRL)solution for household multi-zone HVAC systems.This approach aims to optimize energy costs,ensure users’PTC,and maintain the explainability of the DR strategy under uncertainty.Firstly,an XRL-based optimization framework is proposed.The framework utilizes XRL’s online learning capabilities to handle uncertainties and meet the PTC requirements of different zones while maintaining the explainability of the optimization strategy.Then,we propose an explainable proximal policy optimization(XPPO)algorithm as an instantiation of XRL for optimizing household multi-zone HVAC systems,using interpretable continuous control trees as actor networks of the XPPO.Moreover,we design state space,action space,reward,learning network,and learning algorithm of the XPPO in detail for the needs of HVAC operational optimization.Simulation results show that our method is explainable and thus can fulfill the requirements of the laws.At the same time,the proposed method consumes 22.4%less energy cost compared to scenarios without DR.Furthermore,the optimization of DR for a typical 4-zone household can be achieved within 15 min on an i7-12700 CPU.展开更多
The prediction of building energy consumption offers essential technical support for intelligent operation and maintenance of buildings,promoting energy conservation and low-carbon control.This paper focused on the en...The prediction of building energy consumption offers essential technical support for intelligent operation and maintenance of buildings,promoting energy conservation and low-carbon control.This paper focused on the energy consumption of heating,ventilation and air conditioning(HVAC)systems operating under various modes across different seasons.We constructed multi-attribute and high-dimensional clustering vectors that encompass indoor and outdoor environmental parameters,along with historical energy consumption data.To enhance the K-means algorithm,we employed statistical feature extraction and dimensional normalization(SFEDN)to facilitate data clustering and deconstruction.This method,combined with the gated recurrent unit(GRU)prediction model employing adaptive training based on the Particle Swarm Optimization algorithm,was evaluated for robustness and stability through k-fold cross-validation.Within the clustering-based modeling framework,optimal submodels were configured based on the statistical features of historical 24-hour data to achieve dynamic prediction using multiple models.The dynamic prediction models with SFEDN cluster showed a 11.9%reduction in root mean square error(RMSE)compared to static prediction,achieving a coefficient of determination(R2)of 0.890 and a mean absolute percentage error(MAPE)reduction of 19.9%.When compared to dynamic prediction based on single-attribute of HVAC systems energy consumption clustering modeling,RMSE decreased by 12.6%,R2 increased by 4.0%,and MAPE decreased by 26.3%.The dynamic prediction performance demonstrated that the SFEDN clustering method surpasses conventional clustering method,and multi-attribute clustering modeling outperforms single-attribute modeling.展开更多
Fault detection and diagnosis(FDD)of heating,ventilation,and air conditioning(HVAC)systems can help to improve the energy saving in building energy systems.However,most data-driven trained FDD models have limited gene...Fault detection and diagnosis(FDD)of heating,ventilation,and air conditioning(HVAC)systems can help to improve the energy saving in building energy systems.However,most data-driven trained FDD models have limited generalizability and can only be applied to specific systems.The diversity of HVAC systems and the high cost of data acquisition present challenges for the practical application of FDD.Transfer learning technology can be employed to mitigate this problem by training a model on systems with sufficient data and then transfer it to other systems with limited data.In this study,a novel transfer learning approach for HVAC FDD is proposed.First,the transformer model is modified to incorporate one encoder and two decoders connected,enabling two outputs.This modified transformer model accommodates absent features in the target domain and serves as a robust foundation for transfer learning.It has effective performance in complex systems and achieves an accuracy of 91.38%for a system with 16 faults and multiple fault severity levels.Second,the adapter-based parameter-efficient transfer learning method,facilitating the transfer of trained models simply by inserting small adapter modules,is investigated as the transfer learning strategy.Results demonstrate that this adapter-based transfer learning approach achieves satisfactory performance similar to full fine-tuning with fewer trainable parameters.It works well with limited data amount in target domain.Furthermore,the findings highlight the significance of adapters positioned near the bottom and top layers,emphasizing their critical role in facilitating successful transfer learning.展开更多
The on-going COVID-19 pandemic has wrecked havoc in our society,with short and long-term consequences to people’s lives and livelihoods-over 651 million COVID-19 cases have been confirmed with the number of deaths ex...The on-going COVID-19 pandemic has wrecked havoc in our society,with short and long-term consequences to people’s lives and livelihoods-over 651 million COVID-19 cases have been confirmed with the number of deaths exceeding 6.66 million.As people stay indoors most of the time,how to operate the Heating,Ventilation and Air-Conditioning(HVAC)systems as well as building facilities to reduce airborne infections have become hot research topics.This paper presents a systematic review on COVID-19 related research in HVAC systems and the indoor environment.Firstly,it reviews the research on the improvement of ventilation,filtration,heating and air-conditioning systems since the onset of COVID-19.Secondly,various indoor environment improvement measures to minimize airborne spread,such as building envelope design,physical barriers and vent position arrangement,and the possible impact of COVID-19 on building energy consumption are examined.Thirdly,it provides comparisons on the building operation guidelines for preventing the spread of COVID-19 virus from different countries.Finally,recommendations for future studies are provided.展开更多
基金National Key R&D Program of China of the 13th Five-Year Plan(No.2018YFD1100704)。
文摘To meet the challenge of mismatches between power supply and demand,modern buildings must schedule flexible energy loads in order to improve the efficiency of power grids.Furthermore,it is essential to understand the effectiveness of flexibility management strategies under different climate conditions and extreme weather events.Using both typical and extreme weather data from cities in five major climate zones of China,this study investigates the energy flexibility potential of an office building under three short-term HVAC management strategies in the context of different climates.The results show that the peak load flexibility and overall energy performance of the three short-term strategies were affected by the surrounding climate conditions.The peak load reduction rate of the pre-cooling and zone temperature reset strategies declined linearly as outdoor temperature increased.Under extreme climate conditions,the daily peak-load time was found to be over two hours earlier than under typical conditions,and the intensive solar radiation found in the extreme conditions can weaken the correlation between peak load reduction and outdoor temperature,risking the ability of a building’s HVAC system to maintain a comfortable indoor environment.
基金This work was supported by Young Scientists Fundamental Research Program of Shandong Province of China (No. 031B5147).
文摘In heating, ventilating and air-conditioning （HVAC） systems, there exist severe nonlinearity, time-varying nature, disturbances and uncertainties. A new predictive functional control based on Takagi-Sugeno （T-S） fuzzy model was proposed to control HVAC systems. The T-S fuzzy model of stabilized controlled process was obtained using the least squares method, then on the basis of global linear predictive model from T-S fuzzy model, the process was controlled by the predictive functional controller. Especially the feedback regulation part was developed to compensate uncertainties of fuzzy predictive model. Finally simulation test results in HVAC systems control applications showed that the proposed fuzzy model predictive functional control improves tracking effect and robustness. Compared with the conventional PID controller, this control strategy has the advantages of less overshoot and shorter setting time, etc.
文摘Ice thermal storage is a promising technology to reduce energy costs by shifting the cooling cost from on-peak to off-peak periods. The paper investigates the application of ice thermal storage and its impact on energy consumption, demand and total energy cost. Energy simulation software along with a chiller model is used to simulate the energy consumption and demand for the existing office building located in central Florida. Furthermore, the study presents a case study to demonstrate the cost saving achieved by the ice storage applications. The results show that although the energy consumption may increase by using ice thermal storage, the energy cost drops significantly, mainly depending on the local utility rate structure. It found that for the investigated system the annual energy consumption increases by about 12% but the annual energy cost drops by about 3 6%.
基金Supported by the National Key Research and Development Program of China(2018YFB1702300)the National Natural Science Foundation of China(61731012)。
文摘Owing to the fluctuant renewable generation and power demand,the energy surplus or deficit in nanogrids embodies differently across time.To stimulate local renewable energy consumption and minimize long-term energy costs,some issues still remain to be explored:when and how the energy demand and bidirectional trading prices are scheduled considering personal comfort preferences and environmental factors.For this purpose,the demand response and two-way pricing problems concurrently for nanogrids and a public monitoring entity(PME)are studied with exploiting the large potential thermal elastic ability of heating,ventilation and air-conditioning(HVAC)units.Different from nanogrids,in terms of minimizing time-average costs,PME aims to set reasonable prices and optimize profits by trading with nanogrids and the main grid bi-directionally.Such bilevel energy management problem is formulated as a stochastic form in a longterm horizon.Since there are uncertain system parameters,time-coupled queue constraints and the interplay of bilevel decision-making,it is challenging to solve the formulated problems.To this end,we derive a form of relaxation based on Lyapunov optimization technique to make the energy management problem tractable without forecasting the related system parameters.The transaction between nanogrids and PME is captured by a one-leader and multi-follower Stackelberg game framework.Then,theoretical analysis of the existence and uniqueness of Stackelberg equilibrium(SE)is developed based on the proposed game property.Following that,we devise an optimization algorithm to reach the SE with less information exchange.Numerical experiments validate the effectiveness of the proposed approach.
文摘Heating, ventilation, and air conditioning (HVAC) system is significant to the energy efficiency in buildings. In this paper, temperature control of HVAC system is studied in winter operation season. The physical model of the zone, the fan, the heating coil and sensor are built. HVAC is a non-linear, strong disturbance and coupling system. Linear active-rejection-disturbance-control is an appreciate control algorithm which can adapt to less information, strong-disturbance influence, and has relative-fixed structure and simple tuning process of the controller parameters. Active-rejection-disturbance-control of the HVAC system is proposed. Simulation in Matlab/Simulink was done. Simulation results show that linear active-rejection-disturbance-control was prior to PID and integral-fuzzy controllers in rising time, overshoot and response time of step disturbance. The study can provide fundamental basis for the control of the air-condition system with strong-disturbance and high-precision needed.
文摘As mentioned by National Geographic(2017),70%of world’s population is expected to live in large apartment buildings by 2050.Today,buildings in cities generate 30%of world’s greenhouse gas emission or GHG(National Geographic,2017).Major urban centers are committed to reducing greenhouse gases by 80%by 2050(IEA,2021).However,achieving such goals in rental properties is not easy.Landlords are hesitant to use high-efficiency technologies because,typically,tenants pay the utilities bill.However,that situation is rapidly changing.For example,New York City like other US cities,is considering a carbon cap on all large buildings(Local Law 97,2019).That means landlords will pay a carbon penalty if the building’s carbon footprint exceeds certain threshold no matter who uses that carbon.The Pacific Northwest National Laboratory(PNNL)has received funds from DOE(US Department of Energy)with the collaboration of a commercial partner to address emerging energy efficiency market opportunity in multi-family or rental housing as discussed above.It has partnered with a large national real estate owner in order to test a novel energy optimization method at a rental property in Tempe,Arizona.By using a seamless-integrated method of acquiring building’s operating data,the optimization approach essentially resets setpoints of different energy consuming equipment such as chillers,boilers,pumps,and fans.Data-driven optimization approach is pragmatic and easily transferrable to other buildings.The authors shall share the problem background,technical approach,and preliminary results.
文摘With the increasing demand for a better life, people have higher and higher requirements for the quality of indoor environment for work and life. In order to improve the quality of indoor environment, HVAC system has become an indispensable part of building system. But at the same time, the energy consumption of HVAC system also accounts for 50~60% of the total energy consumption of buildings, and it is a major contributor to the total energy consumption of buildings. Therefore, it is of great significance to carry out research on energy-saving technology of HVAC system and improve energy efficiency for achieving the goal of "double carbon". Based on this, this paper takes the urgency and importance of the application of energy-saving measures of HVAC system as the starting point, expounds the energy-saving design principles of building HVAC system, and puts forward some main energy-saving measures of HVAC system for reference.
基金supported by the National Science Foundation(award OAC-2005572)the State of Illinois,USA.
文摘Heating,ventilation,and air conditioning system runtime is a crucial metric for establishing the connection between system operation and energy performance.Similar homes in the same location can have varying runtime due to different factors.To understand such heterogeneity,this study conducted an energy signature analysis of heating and cooling system runtime for 5,014 homes across the US>using data from ecobee smart thermostats.Two approaches were compared for the energy signature analysis:(1)using daily mean outdoor temperature and(2)using the difference between the daily mean outdoor temperature and the indoor thermostat setpoint(delta T)as the independent variable.The best-fitting energy signature parameters(balance temperatures and slopes)for each house were estimated and statistically analyzed.The results revealed significant differences in balance temperatures and slopes across various climates and individual homes.Additionally,we identified the impact of housing characteristics and weather conditions on the energy signature parameters using a long absolute shrinkage and selection operator(LASSO)regression.Incorporating delta T into the energy signature model significantly enhances its ability to detect hidden impacts of various features by minimizing the influence of setpoint preferences.Moreover,our cooling slope analysis highlights the significant impact of outdoor humidity levels,underscoring the need to include latent loads in building energy models.
文摘Heating,ventilation,and air conditioning(HVAC)systems constitute a significant portion of the office building load and are important flexibility resources.However,the HVAC loads are often inaccessible to the utility or load aggregators who only have total load data.Most existing studies require subloads for supervised disaggregation or prior knowledge for unsupervised disaggregation,but such information is hard to obtain.It is necessary to develop an effective,completely unsupervised non-intrusive monitoring method to obtain the HVAC load data.In this study,a multiple seasonal-trend decomposition using the LOESS(MSTL)method is proposed to disaggregate the HVAC load from the total metered electricity data of office buildings.The effects of periodic types(daily,weekly,monthly,etc.),periodic sequences,and parallel/serial structures are analyzed.The proposed method is verified based on the historical electricity data of ten buildings.The results show that the proposed MSTL can accurately disaggregate the HVAC load with a coefficient of variation of the root mean square error(CVRMSE)of 10.94%,a normalized root mean squared error(NRMSE)of 2.1%,and a weighted absolute percentage error(WAPE)of 8.52%.Compared to single-cycle STL,the proposed method can significantly improve load disaggregation performance,with a maximum reduction of 16.36%in CVRMSE,5.3%in NRMSE,and 12.91%in WAPE.Backward-chain-based MSTL is recommended with higher accuracy and robustness.The proposed method provides an effective solution for utilities or load aggregators to improve demand response management and grid stability.
基金supported by the National Key R&D Program of China(Grant No.2018AAA0103300)the National Natural Science Foundation of China(Grant No.62122093)the Key Project of Scientific Research Fund of Hunan Provincial Education Department,China(Grant No.23A0142).
文摘Heating,ventilation and air conditioning(HVAC)systems maintain personal thermal comfort(PTC)and serve as key demand response(DR)resources.Given the challenges of uncertain environments,varied user preferences,and legal requirements for transparent control strategies,this paper proposes an explainable reinforcement learning(XRL)solution for household multi-zone HVAC systems.This approach aims to optimize energy costs,ensure users’PTC,and maintain the explainability of the DR strategy under uncertainty.Firstly,an XRL-based optimization framework is proposed.The framework utilizes XRL’s online learning capabilities to handle uncertainties and meet the PTC requirements of different zones while maintaining the explainability of the optimization strategy.Then,we propose an explainable proximal policy optimization(XPPO)algorithm as an instantiation of XRL for optimizing household multi-zone HVAC systems,using interpretable continuous control trees as actor networks of the XPPO.Moreover,we design state space,action space,reward,learning network,and learning algorithm of the XPPO in detail for the needs of HVAC operational optimization.Simulation results show that our method is explainable and thus can fulfill the requirements of the laws.At the same time,the proposed method consumes 22.4%less energy cost compared to scenarios without DR.Furthermore,the optimization of DR for a typical 4-zone household can be achieved within 15 min on an i7-12700 CPU.
基金supported by the National Natural Science Foundation of China(No.52108074)the National Natural Science Foundation of China(No.52078144).
文摘The prediction of building energy consumption offers essential technical support for intelligent operation and maintenance of buildings,promoting energy conservation and low-carbon control.This paper focused on the energy consumption of heating,ventilation and air conditioning(HVAC)systems operating under various modes across different seasons.We constructed multi-attribute and high-dimensional clustering vectors that encompass indoor and outdoor environmental parameters,along with historical energy consumption data.To enhance the K-means algorithm,we employed statistical feature extraction and dimensional normalization(SFEDN)to facilitate data clustering and deconstruction.This method,combined with the gated recurrent unit(GRU)prediction model employing adaptive training based on the Particle Swarm Optimization algorithm,was evaluated for robustness and stability through k-fold cross-validation.Within the clustering-based modeling framework,optimal submodels were configured based on the statistical features of historical 24-hour data to achieve dynamic prediction using multiple models.The dynamic prediction models with SFEDN cluster showed a 11.9%reduction in root mean square error(RMSE)compared to static prediction,achieving a coefficient of determination(R2)of 0.890 and a mean absolute percentage error(MAPE)reduction of 19.9%.When compared to dynamic prediction based on single-attribute of HVAC systems energy consumption clustering modeling,RMSE decreased by 12.6%,R2 increased by 4.0%,and MAPE decreased by 26.3%.The dynamic prediction performance demonstrated that the SFEDN clustering method surpasses conventional clustering method,and multi-attribute clustering modeling outperforms single-attribute modeling.
基金supported by the National Natural Science Foundation of China(Grant Nos.:52293413 and 52076161).
文摘Fault detection and diagnosis(FDD)of heating,ventilation,and air conditioning(HVAC)systems can help to improve the energy saving in building energy systems.However,most data-driven trained FDD models have limited generalizability and can only be applied to specific systems.The diversity of HVAC systems and the high cost of data acquisition present challenges for the practical application of FDD.Transfer learning technology can be employed to mitigate this problem by training a model on systems with sufficient data and then transfer it to other systems with limited data.In this study,a novel transfer learning approach for HVAC FDD is proposed.First,the transformer model is modified to incorporate one encoder and two decoders connected,enabling two outputs.This modified transformer model accommodates absent features in the target domain and serves as a robust foundation for transfer learning.It has effective performance in complex systems and achieves an accuracy of 91.38%for a system with 16 faults and multiple fault severity levels.Second,the adapter-based parameter-efficient transfer learning method,facilitating the transfer of trained models simply by inserting small adapter modules,is investigated as the transfer learning strategy.Results demonstrate that this adapter-based transfer learning approach achieves satisfactory performance similar to full fine-tuning with fewer trainable parameters.It works well with limited data amount in target domain.Furthermore,the findings highlight the significance of adapters positioned near the bottom and top layers,emphasizing their critical role in facilitating successful transfer learning.
文摘The on-going COVID-19 pandemic has wrecked havoc in our society,with short and long-term consequences to people’s lives and livelihoods-over 651 million COVID-19 cases have been confirmed with the number of deaths exceeding 6.66 million.As people stay indoors most of the time,how to operate the Heating,Ventilation and Air-Conditioning(HVAC)systems as well as building facilities to reduce airborne infections have become hot research topics.This paper presents a systematic review on COVID-19 related research in HVAC systems and the indoor environment.Firstly,it reviews the research on the improvement of ventilation,filtration,heating and air-conditioning systems since the onset of COVID-19.Secondly,various indoor environment improvement measures to minimize airborne spread,such as building envelope design,physical barriers and vent position arrangement,and the possible impact of COVID-19 on building energy consumption are examined.Thirdly,it provides comparisons on the building operation guidelines for preventing the spread of COVID-19 virus from different countries.Finally,recommendations for future studies are provided.
