In the heart of India, researchers at the School of Electrical Engineering, KIIT Deemed to be University in Bhubaneswar have developed a groundbreaking solution that could revolutionize energy management in greenhouse farming. Led by Soumya Ranjan Biswal, the team has combined the power of the Internet of Things (IoT) and hybrid machine learning models to create a system that optimizes energy consumption while maintaining optimal growing conditions for crops. This innovation, published in the IEEE Access journal, translates to “IEEE Open Access” in English, holds significant promise for the energy sector and sustainable agriculture.
Greenhouse farming is a double-edged sword. On one hand, it enhances agricultural productivity by providing controlled environments for crops. On the other hand, it is highly energy-intensive, with heating, cooling, and lighting systems consuming substantial power. Traditional load forecasting and demand-side management (DSM) methods often struggle to adapt to the dynamic and highly variable environmental conditions within greenhouses. This is where Biswal’s team comes in.
The researchers hypothesized that combining hybrid machine learning models with IoT-based DSM could optimize energy consumption while maintaining critical microclimatic conditions for crop growth. They proposed a hybrid predictive model that integrates Extreme Gradient Boosting (XGBoost) for static feature learning and Long Short-Term Memory (LSTM) for sequential pattern recognition. This model is coupled with a priority-based DSM framework deployed on a Raspberry Pi IoT platform.
The results are impressive. The model was trained and tested using one year of real-world greenhouse data, achieving a Mean Absolute Percentage Error (MAPE) of just 5.3%. This level of accuracy translates into a 7.1% reduction in grid energy dependency and a 17.3% lowering of average electricity costs. “This is a significant step forward in intelligent energy management for greenhouse environments,” says Biswal. “Our system offers a scalable, economically viable, and sustainable solution that could transform the way we approach controlled agriculture.”
The team also developed a laboratory-scale prototype for physical verification using an EcoSense 500W solar microgrid, Raspberry Pi 3B+, relay modules, current sensors, and load simulators. This practical application underscores the potential for real-world implementation and commercial impact.
The implications for the energy sector are substantial. As the world grapples with the challenges of climate change and the need for sustainable energy solutions, innovations like this one offer a glimmer of hope. By optimizing energy consumption in greenhouse farming, we can reduce the carbon footprint of agriculture, promote food security, and increase the utilization of renewable energy sources.
“This work contributes directly to Sustainable Development Goals (SDGs) 2, 7, and 12 by promoting food security, increasing renewable energy utilization, and enhancing responsible resource consumption in greenhouse farming,” Biswal explains. The integration of AI and DSM technologies in controlled agriculture is a significant advancement, and this research could shape future developments in the field.
As we look to the future, the potential for scaling this technology across different agricultural sectors is immense. The energy sector stands to benefit from the reduced demand and increased efficiency, while farmers can enjoy lower operational costs and enhanced productivity. This is not just a win for agriculture; it’s a win for the planet.
In the ever-evolving landscape of agritech and energy management, Biswal’s research shines as a beacon of innovation. It’s a testament to the power of interdisciplinary collaboration and the potential for technology to drive sustainable change. As we continue to explore the possibilities, one thing is clear: the future of agriculture is smart, sustainable, and increasingly interconnected.