Extending the concept of energy delivery efficiency(EDE) of HVAC systems. T Agami Reddy, David E ... more Extending the concept of energy delivery efficiency(EDE) of HVAC systems. T Agami Reddy, David E Claridge, Mingsheng Liu, Srinivas Katipamula ASHRAE Transactions, 1/1998. An energy standard based on a two-zone model ...
Science and Technology for the Built Environment, Dec 20, 2017
Predicting thermal or electric power output from solar collectors requires knowledge of solar irr... more Predicting thermal or electric power output from solar collectors requires knowledge of solar irradiance incident on the collector, known as plane of array irradiance. In the absence of such a measurement, plane of array irradiation can be predicted using relevant transposition models which essentially requires diffuse (or beam) radiation to be to be known along with total horizontal irradiation. The two main objectives of the current study are (1) to evaluate the extent to which the prediction of plane of array irradiance is improved when diffuse radiation is predicted using location-specific regression models developed from on-site measured data as against using generalized models; and (2) to estimate the expected uncertainties associated with plane of array irradiance predictions under different data collection scenarios likely to be encountered in practical situations. These issues have been investigated using monitored data for several U.S. locations in conjunction with the Typical Meteorological Year, version 3 database. An interesting behavior in the Typical Meteorological Year, version 3 data was also observed in correlation patterns between diffuse and total radiation taken from different years which seems to attest to a measurement problem. The current study was accomplished under a broader research agenda aimed at providing energy managers the necessary tools for predicting, scheduling, and controlling various sub-systems of an integrated energy system.
ABSTRACT The objective of this paper is to evaluate the applicability of multiple linear regressi... more ABSTRACT The objective of this paper is to evaluate the applicability of multiple linear regression (MLR) models, based on engineering principles, to measured cooling energy consumption in commercial buildings (with either a dual-duct constant volume (DDCV) or a dual-duct variable air volume (VAV) system). The cooling energy consumption in five large commercial buildings in Texas was modeled and compared on both a daily and an hourly basis. The daily models showed higher coefficients of determination (R2) and lower coefficients of variation (CV) than the hourly models for both the DDCV and VAV systems. The outdoor dry-bulb and dew-point temperatures accounted for most of the variation in the cooling energy consumption. Compared to the base model (two-parameter model with outdoor dry-bulb as the only variable), all the MLR models showed a decrease in the CV between 10 and 66 percent, with an average decrease of about 33 percent, thus clearly indicating the superiority of MLR models.
Proceedings of the 1st International Workshop on Reinforcement Learning for Energy Management in Buildings & Cities
In recent years, reinforcement learning (RL) methods have been greatly enhanced by leveraging dee... more In recent years, reinforcement learning (RL) methods have been greatly enhanced by leveraging deep learning approaches. RL methods applied to building control have shown potential in many applications because of their ability to complement or replace conventional methods such as model-based or rule-based controls. However, RL-based building control software is likely tailored either to one target building system or to a specific RL method so that significant additional effort would be required to customize the RL-based controller for use in other building systems or with other RL approaches. Also, RL-based building controls usually depend on building energy simulations to train controllers, so emulating building dynamics (i.e., thermal dynamics and control dynamics) and capturing sub-hourly dynamic profiles are crucial to further the development of effective RL-based building control methods. To address these challenges, we present an RL-based control software employing a high-fidelity hybrid EnergyPlus-Modelica building energy model that emulates building dynamics at 1 minute resolution. This software consists of decoupled components (environment, building emulator, control agent, and RL algorithm), which allows for quick prototyping and benchmarking of standard RL algorithms in different systems; for example, a single component can be replaced without revising the software. To demonstrate this software framework, we conducted a benchmark study using an EnergyPlus-Modelica building energy model for a Chicago office building with an RL-based controller to dynamically control the chilled water temperature setpoint and the air handling unit supply air temperature setpoints.
Extending the concept of energy delivery efficiency(EDE) of HVAC systems. T Agami Reddy, David E ... more Extending the concept of energy delivery efficiency(EDE) of HVAC systems. T Agami Reddy, David E Claridge, Mingsheng Liu, Srinivas Katipamula ASHRAE Transactions, 1/1998. An energy standard based on a two-zone model ...
Science and Technology for the Built Environment, Dec 20, 2017
Predicting thermal or electric power output from solar collectors requires knowledge of solar irr... more Predicting thermal or electric power output from solar collectors requires knowledge of solar irradiance incident on the collector, known as plane of array irradiance. In the absence of such a measurement, plane of array irradiation can be predicted using relevant transposition models which essentially requires diffuse (or beam) radiation to be to be known along with total horizontal irradiation. The two main objectives of the current study are (1) to evaluate the extent to which the prediction of plane of array irradiance is improved when diffuse radiation is predicted using location-specific regression models developed from on-site measured data as against using generalized models; and (2) to estimate the expected uncertainties associated with plane of array irradiance predictions under different data collection scenarios likely to be encountered in practical situations. These issues have been investigated using monitored data for several U.S. locations in conjunction with the Typical Meteorological Year, version 3 database. An interesting behavior in the Typical Meteorological Year, version 3 data was also observed in correlation patterns between diffuse and total radiation taken from different years which seems to attest to a measurement problem. The current study was accomplished under a broader research agenda aimed at providing energy managers the necessary tools for predicting, scheduling, and controlling various sub-systems of an integrated energy system.
ABSTRACT The objective of this paper is to evaluate the applicability of multiple linear regressi... more ABSTRACT The objective of this paper is to evaluate the applicability of multiple linear regression (MLR) models, based on engineering principles, to measured cooling energy consumption in commercial buildings (with either a dual-duct constant volume (DDCV) or a dual-duct variable air volume (VAV) system). The cooling energy consumption in five large commercial buildings in Texas was modeled and compared on both a daily and an hourly basis. The daily models showed higher coefficients of determination (R2) and lower coefficients of variation (CV) than the hourly models for both the DDCV and VAV systems. The outdoor dry-bulb and dew-point temperatures accounted for most of the variation in the cooling energy consumption. Compared to the base model (two-parameter model with outdoor dry-bulb as the only variable), all the MLR models showed a decrease in the CV between 10 and 66 percent, with an average decrease of about 33 percent, thus clearly indicating the superiority of MLR models.
Proceedings of the 1st International Workshop on Reinforcement Learning for Energy Management in Buildings & Cities
In recent years, reinforcement learning (RL) methods have been greatly enhanced by leveraging dee... more In recent years, reinforcement learning (RL) methods have been greatly enhanced by leveraging deep learning approaches. RL methods applied to building control have shown potential in many applications because of their ability to complement or replace conventional methods such as model-based or rule-based controls. However, RL-based building control software is likely tailored either to one target building system or to a specific RL method so that significant additional effort would be required to customize the RL-based controller for use in other building systems or with other RL approaches. Also, RL-based building controls usually depend on building energy simulations to train controllers, so emulating building dynamics (i.e., thermal dynamics and control dynamics) and capturing sub-hourly dynamic profiles are crucial to further the development of effective RL-based building control methods. To address these challenges, we present an RL-based control software employing a high-fidelity hybrid EnergyPlus-Modelica building energy model that emulates building dynamics at 1 minute resolution. This software consists of decoupled components (environment, building emulator, control agent, and RL algorithm), which allows for quick prototyping and benchmarking of standard RL algorithms in different systems; for example, a single component can be replaced without revising the software. To demonstrate this software framework, we conducted a benchmark study using an EnergyPlus-Modelica building energy model for a Chicago office building with an RL-based controller to dynamically control the chilled water temperature setpoint and the air handling unit supply air temperature setpoints.
Uploads