In this paper, we propose a data-driven optimal control method, which constructs and revises the model adaptively with the past operational data. When using model, the TCBM finds cases whose inputs are the most similar to the new inputs, and averages the outputs of the similar cases as the corresponding new output. The process data and energy consumption data around the chilling system are continuously monitored with Building Automation BA Systems. Then, the base-line energy consumption was obtained by calculating the regression with the input outdoor enthalpy after introduction. As the pre-processing the moving average function was used to reduce the effect of the measurement noise, and the outliers were omitted with the pre-defined thresholds. Chilled Water Temperature Setting.
|License:||For Personal Use Only|
|iPhone 5, 5S resolutions||640×1136|
|iPhone 6, 6S resolutions||750×1334|
|iPhone 7, 7 Plus, 8, 8 Plus resolutions||1080×1920|
|Android Mobiles HD resolutions||360×640, 540×960, 720×1280|
|Android Mobiles Full HD resolutions||1080×1920|
|Mobiles HD resolutions||480×800, 768×1280|
|Mobiles QHD, iPhone X resolutions||1440×2560|
|HD resolutions||1280×720, 1366×768, 1600×900, 1920×1080, 2560×1440, Original|
Finally, we estimated the amount of energy conserved as a result of introducing our method. In this method, model input variables are selected as related to energy consumption, such as chilled water and condenser water temperatures and flow rate, and chilling load; the output variable is the total energy consumption of the whole HVAC system. In addition, it is difficult to revise the model parameters on-line to adapt the current environmental conditions, system structure, and operations policy.
The proposed approach tomohigo general optimal control method for energy conservation in HVAC systems, and it can be extended to optimal control of the other settings, such as condenser water temperature and flow rate, and supply air temperature.
Academic OneFile – Document – Adaptive optimization method for energy conservation in HVAC systems
The proposed method was applied to an optimal control of chilled water temperature at an actual hotel building. In addition, the input variables of the model should be selected according to the applications and target systems. In this case study, the model input and output variables are selected with the statistical analysis as listed in Table 2. After the real output is obtained, it simply adds the new case to the Case-Base in order to adapt the new situation.
Then, the base-line energy consumption was obtained by calculating the regression with the input outdoor enthalpy after introduction. Tomohiri methods require the detailed simulation models describing the thermal and physical relationships between each facility, and the model parameters are adjusted with the facility specifications.
It represents the method specified optimal chilled water temperature settings according to the environmental conditions such as chilling load.
Tools Related Resources ReadSpeaker:.
Data-driven optimal control for building energy conservation
Although optimizing the chilled water temperature setting is considered to be an effective way to HVAC energy conservation ASHRAEit has been difficult to understand the tomihiro characteristics of chillers, coils, and pumps, which are widely varied among buildings.
Each set of the input and output data is converted into a case corresponding to the discretized input space. As the result of a validation with an actual hotel building, we were able to demonstrate that the proposed method realized energy conservation by increasing the chilled water temperature appropriately.
As optimal operation methods in the HVAC systems, a vast amount of physical model based tomohkro has been proposed Braun et al. The spline approximation is more practical method than other nonlinear approximation methods such as Artificial Neural Networks, in that the calculated result is independent with initial calculation conditions, and parameter adjusting is unnecessary. Thus the TCBM has been applied to many applications such as soft-sensing, performance monitoring Tsutsui tomohirp al.
A laptop Konva implemented with our optimal control method was connected to the existing BA network. The actual chilled water temperature is controlled by the local PID controller in the chiller konca that it reaches the calculated setting. In this paper, we propose a data-driven optimal control method, which constructs and revises the model adaptively with the past operational data. Once approximated objective function is identified, optimal setting is calculated by the simple gradient descend methods such as quasi-Newton’s method.
There is thus a trade-off between chiller and chilled water pumps energy consumption as shown in Figure 2. The development of the systematic procedure for the variable selection is an open issue. Therefore, this method greatly simplifies the process of constructing and revising the model, which has been a stumbling block for conventional methods, and it becomes possible to optimally control HVAC systems in accordance with outside environmental fluctuations and building operation changes.
In this method, if the objective system satisfies continuity on the input-output relationships, the Case-Base structure and similarity between each case are defined only with the past data without any prior knowledge.
As the pre-processing koda moving average function was used to reduce the effect of the measurement noise, and the outliers were omitted with the pre-defined thresholds.
The most prominent feature tmohiro the TCBM is to preserve the data itself as a model called “Case-Base” according to the given model precision. Separate each e-mail address with a semicolon Subject line: In a central air-conditioning system, the various HVAC facilities such as chillers, cooling towers, and pumps should be cooperatively controlled to satisfy the required chilling load with the minimum total energy consumption.
On the contrary, the model functions after the learning with the historical data show the near-convex shape, where each optimal value is found with the gradient decent methods. The input variables should be selected to have strong relationship with total energy consumption according koda the energy characteristics of each target building. While these accumulated data are actively utilized for performance evaluation and improvement Brambley et al.
Figure 7 tmoohiro energy consumption within three hours against outdoor enthalpy before Tomohuro. The proposed method revises the model function as new data kobda obtained.