Artificial Intelligence Assisted Heating Ventilation and Air Conditioning Control and the Unmet Demand for Sensors: Part 2. Prior Information Notice (PIN) Sensor Design and Simulation Results

Abstract

The study continues the theoretical derivation from Part 1, and the experiment is carried out at a bus station equipped with six water-cooled chillers. Between 2012 and 2017, historical data collected from temperature and humidity sensors, as well as the energy consumption data, were used to build artificial intelligence (AI) assisted heating ventilation and air conditioning (HVAC) control models. The AI control system, in conjunction with a specifically designed prior information notice (PIN) sensor, was used to improve the prediction accuracy. This data collected between 2012 and 2016 was used for AI training and PIN sensor testing. During the hottest week of 2017 in Taiwan, the PIN sensor was used to conduct temperature and humidity data predictions. A model-based predictive control was developed to obtain air conditioning energy consumption data. The comparative results between the predictive and actual data showed that the temperature and humidity prediction accuracies were between 95.5 and 96.6%, respectively. Additionally, energy savings amounting to 39.8% were achieved compared to the theoretical estimates of 44.6%, a difference of less than 5%. These results show that the experimental model supports the theoretical estimations. In the future, a PIN sensor will be installed in a chiller to further verify the energy savings of the AI assisted HVAC control.

Artificial intelligence implementation framework development for building energy saving

“…The following three problems are proposed as the unmet demands of AI studies: Lack of a systematic AI implementation methodology for effective energy saving at three building levels.As illustrated in Section 1, none successfully integrated AI at the equipment, facility, and whole building levels. A systematic methodology is expected to solve the first unmet demand and implements AI at three levels for effective building energy saving. A method is needed to demonstrate the energy‐saving effects of AI to building owners.According to References [2–114], 31.9% of studies specifically presented data for energy savings or energy cost savings as percentages. Among these studies, 30.6% used simulations to illustrate the energy consumption differences before and after implementing AI, whereas 69.4% reported results based on experimental data.…”

“…According to References [2–114], 31.9% of studies specifically presented data for energy savings or energy cost savings as percentages. Among these studies, 30.6% used simulations to illustrate the energy consumption differences before and after implementing AI, whereas 69.4% reported results based on experimental data.…”

“…Before implementing AI at three levels in the test site, we have to convince building owner by a reasonable energy‐saving target. By total 113 AI research studies 2‐114 were assigned into 5 categories to plot the AI energy‐saving effect diagrams. With these diagrams, energy and cost savings were determined to predict AI‐based energy‐saving performance.…”

“…Except MAS, the other development of distributed AI is model‐based predictive control (MPC). Surveyed research studies include EnerGis, a geographical information system development to model with sufficient detail the energy services requirements of a given geographical area 57 ; a predictive model development for scheduling control of a bioclimatic building 58 ; a modular optimization model development for energy management of large‐scale building facilities 59 ; MPC development to predict and control whole building heat and moisture transfer 60 ; a hot water demand prediction model for residential energy management systems 61 ; MPC for improving the control performance of air‐conditioning systems 62 ; MPC of HVAC systems for human thermal comfort and energy consumption minimization 63 ; predictive control methods to improve energy efficiency and reduce demand in buildings 64 and a prior information notice sensor development for HVAC control 65 . Above research studies focused on developing MPC.…”

“…AI developments have provided a series of solutions for the whole building. However, a literature survey of 113 studies 2‐114 revealed that energy conservation control for the equipment, facility, and entire site/building accounted for 23.9%, 42.5%, and 33.6%, respectively. None of these studies have successfully integrated AI for saving three‐level building energy conservation, and this may be due to the lack of implementation frameworks.…”