Digital twins, an emerging technology, are widely used in various industries. It builds a virtual space by mirroring a physical space and performs different simulations to solve problems that are complicated or impossible to solve in the physical space. Livestock farming in agriculture is evolving rapidly with the introduction of various information and communication technologies for digital farming. However, only few studies have examined the digital twin in terms of HVAC systems directly related to productivity in livestock farming. Here, we propose a novel digital twin framework for livestock farming focusing on pig houses. Livestock farming is one of perspective areas where digital twins can provide benefits for the growth of livestock and their operation in an efficient manner. To validate effect of the proposed digital twin framework for a pig house, we perform various simulations using a real-world dataset of a pig house. As a result of analyzing the energy demands for heating in pigsty based on the digital twin framework, the fan-coil unit was found to be the most energy efficient. In addition, when the optimal control of the HVAC system was applied, it was found to be more energy efficient than the conventional control method. The results obtained in this study show that our approach is superior to existing operational conventions, particularly in terms of energy efficiency.

As the pig industry develops rapidly, various problems are appearing both inside and outside the pig houses. In particular, in the case of pig houses, it is difficult to solve the main problems even if automation and mechanization are applied with ICT technology. The main current issues are: (1) preventing infectious diseases amongst livestock, (2) reducing the emission of harmful gas and odors, (3) improving the growth environment inside the pig house, (4) reducing energy costs, (5) improving the farm management and operating system, and 6) improving the livestock product quality. Air recirculation technology can be applied as a technology that can solve these typical problems in the pig industry. An air-recirculated ventilation system can minimize the inflow of air from outdoors and recycle the internal thermal energy of the pig house. The air-recirculated ventilation system consists of (1) an air scrubber module, (2) external air-mixing module, (3) UV cleaning module, (4) solar heat module, and (5) air-distribution module. First, in this study, the field data were collected to analyze the main problems of the target piglet house for the application of the air-recirculated ventilation system. In addition, a computational fluid dynamics (CFD) model was developed and validated for seasonal aerodynamic analysis. The applicability of the air-recirculated ventilation system was evaluated based on the CFD computed results for various environmental conditions. As a result of evaluating the internal environment according to the ventilation rates and external-air-mixing ratio of the air-recirculated ventilation system, the required ventilation rate and external air-mixing ratio to maintain the proper temperature and gas concentration were determined.

The internal rearing environment of livestock houses has become an important issue in the last few years due to the rapid increase in meat consumption. As the number of days of heat waves increase continuously, problems caused by abnormal weather changes steadily occurred. Thus, the main goal of this study is to develop a technology that can automatically calculate heat stress for livestock by considering weather forecast data. Specifically, a web-based heat stress forecasting system for the evaluation of heat stress in broilers was developed. The field experiments were carried out at the selected broiler house to measure and analyze the external weather, the internal environment, and the ventilation flow rate of fans used in tunnel ventilation. The developed model was validated by comparing the field and simulated thermal environment values. Based on a reliable model, Land-Atmosphere Modeling Package (LAMP) weather forecast data was used to show the stress index on the internal rearing environment with a heat stress index suitable for South Korea. When the users input the farm location, structure and equipment, and rearing information, users responded after receiving heat stress from the broiler raised in a mechanically ventilated broiler house.

Carbon dioxide (CO₂) emissions from the livestock industry are expected to increase. A response strategy for CO₂ emission regulations is required for pig production as this industry comprises a large proportion of the livestock industry and it is projected that per capita pork consumption will rise. A CO₂ emission response strategy can be established by accurately measuring the CO₂ concentrations in pig facilities. Here, we compared and evaluated the performance of three different machine learning (ML) models (ElasticNet, random forest regression (RFR), and support vector regression (SVR)) designed to predict CO₂ concentration and internal air temperature (T_i) values in the pig house used to regulate a heating, ventilation, and air conditioning (HVAC) control system. For each ML model, the hyperparameter was optimised and the predictive accuracy was evaluated. The order of predictive accuracy for the ML models was ElasticNet < SVR < RFR. Hence, random forest regression provided superior prediction performance. Based on the test dataset, for T_i prediction by RFR, R² ≥ 0.848 and the root mean square error (RMSE) and mean absolute error (MAE) were 0.235 °C and 0.160 °C, respectively, whilst for CO₂ concentration prediction by RFR, R² ≥ 0.885 and the RMSE and MAE were 64.39 ppm and ≤ 46.17 ppm, respectively.