INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 06,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1542
ENHANCING ENERGY EFFICIENCY IN GREENHOUSES USING PCM-BASED
THERMAL STORAGE SYSTEMS INTEGRATED WITH ARTIFICIAL
INTELLIGENCE AND BIG DATA TECHNOLOGIES
O..Z. Toirov, D.O. Hojiev
Tashkent State Technical University, Tashkent, Uzbekistan
E
.
T. Juraev
National Research Institute of Renewable Energy Sources under
the Ministry of Energy, Tashkent, Uzbekistan
Abstract:
This paper investigates the role of artificial intelligence (AI) and Big Data
technologies in enhancing energy efficiency in greenhouses equipped with thermal storage
systems based on phase change materials (PCMs). Research indicates that AI can be utilized to
forecast temperature fluctuations and optimize PCM performance, while Big Data supports
identifying the most efficient solutions through analysis of large datasets. Literature reviews
suggest that such integrated systems can reduce energy consumption by 17–25%. However,
their effectiveness varies with climatic conditions and greenhouse design, highlighting the need
for system adaptation to specific environments.
Keywords:
PCM, greenhouse, solar energy, thermal storage, AI, Big Data
Introduction
In recent years, ecological sustainability and energy efficiency have become pressing global
concerns. Rapid population growth, urbanization, and the increasing demand for high-yield
agriculture have significantly expanded the use of greenhouses. As a result, integrating energy-
saving technologies into greenhouse systems has become increasingly necessary, as heating and
cooling consume substantial energy resources.
In this context, thermal storage systems based on phase change materials (PCMs) offer an
effective solution to improve greenhouse energy efficiency. PCMs store and release thermal
energy by changing their physical phase. However, these systems may not function optimally
on their own due to environmental variables such as temperature, solar radiation, humidity, and
local climate.
Advanced technologies such as artificial intelligence (AI) and Big Data analytics have emerged
as powerful tools to manage and optimize such complex systems. This paper explores how
PCM-based systems, managed using AI and Big Data, can enhance energy efficiency in
greenhouses.
Main Content
1. Phase Change Materials (PCMs) and Their Energetic Role
PCMs are materials capable of absorbing or releasing significant amounts of thermal energy
during phase transitions (e.g., from solid to liquid and vice versa). This process helps stabilize
the internal temperature of greenhouses.
Common PCM types include:
Organic materials: paraffins, fatty acids
Inorganic materials: salt hydrates
Eutectic mixtures: combinations of multiple compounds
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 06,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1543
In greenhouses, PCMs help prevent temperature drops during nighttime or early mornings by
absorbing excess heat during the day and releasing it when needed. However, since these
systems are passive and temporary in nature, they are not always effective when operating
independently. Therefore, smart control systems are required.
2. Role of Artificial Intelligence (AI)
AI provides advanced tools for data analysis, prediction, and real-time decision-making. Its role
in managing PCM systems includes:
Temperature forecasting: Machine learning (ML) models, especially artificial neural
networks (ANNs), can predict both internal and external temperature variations.
Real-time control: AI can determine optimal melting and freezing times for PCMs,
enhancing energy efficiency.
Adaptive learning: AI systems can learn and adjust to different seasons or climatic zones,
allowing dynamic PCM operation.
For example, Zhang et al. (2019) demonstrated that using AI to manage PCM-based greenhouse
systems resulted in up to 23% energy savings.
3. Role of Big Data Analytics
Big Data technologies process vast volumes of dynamic, varied data. In greenhouses, typical
datasets include:
Temperature and humidity readings
Solar radiation levels
Current PCM state
Plant growth data
Electricity consumption
These data are used to train AI models and optimize decision-making. Big Data analytics help
determine the most suitable PCM types for various climates and greenhouse designs.
For instance, Kumar & Singh (2020) analyzed more than 20 PCM types across different regions
in India, ranking them based on energy savings, efficiency, and cost-effectiveness.
4. Advantages of the Integrated Approach
Combining AI, Big Data, and PCM technologies offers several benefits:
17–25% energy savings
Stable microclimate for optimal plant growth
Reduced human intervention via automated control
Design customization based on regional climate
However, these systems require initial investment and technical expertise for successful
implementation.
5. Limitations and Future Prospects
Despite their advantages, such advanced systems face some limitations:
Climatic dependency (e.g., snowy or very hot climates)
Inefficiency if PCM’s melting/freezing point is poorly selected
Errors due to inaccurate AI model training
High infrastructure requirements for storing and processing large data volumes
Future research should focus on developing low-cost, eco-friendly PCM alternatives and
improving AI model accuracy and system adaptability.
Conclusion
The analysis above shows that PCM-based thermal storage systems can be effectively managed
using AI and Big Data technologies. This integrated approach allows greenhouses to optimize
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 06,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1544
energy consumption, create ideal plant growth conditions, and reduce human dependency
through automation.
However, successful implementation depends on tailoring the technologies to specific
greenhouse designs and regional climates. Factors such as PCM selection, AI algorithm quality,
and data infrastructure significantly influence overall performance. Therefore, consistent
research in this direction remains essential.
References:
1. Chen, Y., Zhang, G., & Wang, J. (2021). Optimization of Phase Change Material Usage in
Greenhouses Using Artificial Intelligence Algorithms. Renewable Energy Journal, 172,
1154–1163.
2. Kumar, R., & Singh, M. (2020). Big Data Analytics in Smart Agriculture: Enhancing
Energy Efficiency in PCM-based Greenhouses. Journal of Clean Energy Technologies,
8(6), 123–130.
3. Zhang, H., & Li, X. (2019). Thermal Performance Enhancement of PCM Systems Using
Predictive Control Models. Applied Thermal Engineering, 147, 922–930.
4. Lin, Z., et al. (2022). AI-driven Climate Control in Greenhouses with Thermal Energy
Storage. Energy Reports, 8, 4440–4452..
5. International Energy Agency (IEA). (2022). Digitalization and Energy. Retrieved from
