Enhancing Sustainability in Agriculture using Hybrid Grey Wolf and Cuckoo Search Algorithm

To increase production and efficiency, modern agriculture makes use of the latest innovations including artificial intelligence (AI), cloud/fog/edge (CFE) computing, and agricultural robots. However, the data transfer and center operations of traditional cloud-based systems result in considerable CO2 emissions. To combat this, reducing CO2 emissions from microgrids in agriculture is vital for sustainable farming practices. To address this, an Integrated Grey Wolf and Cuckoo Search (IGWCS) architectural paradigm is proposed for energy-efficient smart agriculture. This paradigm employs a hierarchical approach, utilizing edge, fog, and cloud layers for real-time data processing. By distributing processing tasks, energy consumption is reduced. However, the challenge of energy-efficient offloading of IoT applications remains NP-hard. Hence, a heuristic algorithm, IGWCS-CFE, is developed. This heuristic leverages the combined optimization power of Grey Wolf and Cuckoo Search algorithms to efficiently allocate tasks in the CFE algorithm. It provides fast, practical solutions and validates results obtained from Mixed-Integer Linear Programming (MILP) approaches, particularly vital for large-scale problems where MILP is impractical. By minimizing energy consumption, IGWCS-CFE indirectly reduces CO2 emissions associated with non-clean energy sources used in cloud data centers. Thus, the proposed approach not only enhances energy efficiency but also contributes to mitigating the environmental impact of agricultural operations. Through this integration of heuristic algorithms and advanced architectural design, IGWCS-CFE strives to optimize smart agriculture systems for sustainability and productivity in the face of evolving technological demands and environmental challenges. Based on data from agriculture sensors, proposed algorithm surpasses traditional cloud-based systems by lowering energy consumption and carbon emissions. Due to high CO2 emissions from microgrids, this study advocates for utilizing the IGWCS paradigm in agriculture. This approach employs IGWCS-CFE heuristic algorithm to lower energy consumption and environmental impact. By optimizing productivity through efficient task allocation, it aims to mitigate the environmental footprint associated with traditional cloud-based systems. This integrated strategy promises to enhance sustainability while maintaining high levels of agricultural productivity.