In the heart of Malaysia, researchers are rewriting the future of urban agriculture, one algorithm at a time. Jiazheng Shen, a faculty member at the Universiti Putra Malaysia (UPM), has developed a groundbreaking approach to optimize the path planning of agricultural robots in vertical farms. His work, published in the journal Agriculture, promises to revolutionize the energy efficiency and productivity of these innovative farming systems.
Vertical farming, with its multi-layered structures and controlled environments, offers a sustainable solution to food production in space-constrained urban settings. However, the energy consumption of these farms poses a significant challenge to their economic viability. This is where Shen’s research comes into play. He has developed an improved Jellyfish Search (JS) algorithm, dubbed TLDW-JS, designed to enhance the energy efficiency of vertical farms by optimizing the paths of collaborative robots.
The TLDW-JS algorithm addresses the complex task of multi-robot collaboration in vertical farms, where robots perform tasks such as planting, monitoring, harvesting, and transporting produce. “Inefficient path planning can significantly amplify total energy use,” Shen explains. “Even minor suboptimal routes, repeated daily by multiple robots, accumulate into substantial resource wastage.” By minimizing the path length of these collaborative robots, TLDW-JS aims to reduce overall power consumption, thereby improving the economic return of vertical farms.
The algorithm introduces several key improvements over traditional methods. It uses Tent Chaos to generate a high-quality, diversified initial population, Lévy flight to strengthen global exploration, and a nonlinear dynamically weighted adjustment with logistic functions to balance exploration and exploitation. These enhancements enable TLDW-JS to outperform classic optimization algorithms such as the Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Dung Beetle Optimization (DBO).
In comparative experiments, TLDW-JS achieved a 34.3% reduction in average path length, obtained one of the top three optimal solutions in 74% of cases, and reached convergence within an average of 55.9 iterations. These results validate the efficiency of TLDW-JS in enhancing energy optimization and demonstrate its potential for enabling automated systems in vertical farming.
The implications of this research extend beyond the agricultural sector. The energy savings achieved through optimized path planning can have a significant impact on the broader energy landscape. As vertical farms become more prevalent, the demand for energy-efficient solutions will only grow. TLDW-JS offers a promising avenue for meeting this demand, paving the way for more sustainable and economically viable urban agriculture.
Moreover, the hierarchical scheduling method and real-time performance enhancements introduced in this study can be applied to other fields, such as manufacturing, logistics, and automation. The multi-threading mechanism and priority-based scheduling strategy ensure that urgent tasks are prioritized, improving system responsiveness and operational efficiency.
As we look to the future, the work of Jiazheng Shen and his colleagues at UPM holds the promise of transforming vertical farming and beyond. By optimizing the paths of agricultural robots, TLDW-JS not only enhances energy efficiency but also supports the broader adoption of automated systems in urban agriculture. This research, published in Agriculture, marks a significant step forward in the quest for sustainable and productive food systems in our increasingly urbanized world. The next phase of this research will involve testing TLDW-JS in dynamic environments and extending it to real-world vertical farming settings, further validating and optimizing the proposed methods.