Cyber physical biological system in controlled environment agriculture for energy optimization: A comprehensive overview, key challenges, and future outlook

By 2050, the global population is projected to reach 9.7 billion, requiring a 60 % increase in food production to meet rising demand. Controlled environment agriculture (CEA) offers a promising solution for sustainable food production; however, its implementation remains costly, with energy expenses accounting for up to 40 % of total production costs. To address these challenges, the integration of cyber-physical-biological systems (CPBS) presents a significant opportunity, with the potential to reduce excessive energy costs by approximately 25 %. This study reviews traditional climate control methods in CEA and explores innovative strategies to enhance system efficiency and sustainability through CPBS. First, integrating reinforcement learning with robust model predictive control is proposed to create a closed-loop optimization framework that reduces data dependency, adapts to dynamic environments, and minimizes energy consumption through real-time, efficient decision-making. Second, the development of physics-informed 3D control systems addresses limitations of uniform air distribution assumptions, enabling precise microclimate control while optimizing energy use in large-scale greenhouses. Finally, multi-crop greenhouse models are explored to enhance resource efficiency and reduce energy demands, with applications in extreme climates and space farming. Finally, multi-crop greenhouse models are explored to enhance resource efficiency and reduce energy demands, with applications in extreme climates and space farming.