Research on Optimization of Crop Planting Strategies and Multi-Factor Analysis Based on Edge Computing and Cloud Computing

Abstract

This study aims to address the challenges in agricultural development by combining communication technologies with multi-factor analysis to optimize crop planting strategies and improve agricultural production efficiency. Leveraging edge computing and cloud computing technologies, this research achieves real-time data collection, transmission, and intelligent processing of agricultural data, constructing a comprehensive optimization model. By collecting historical sales data of 41 crops and calculating the Pearson correlation coefficient, the study identifies a strong complementary relationship between soybeans and black beans, as well as substitution relationships between wheat and corn, and between Chinese cabbage and bok choy. Furthermore, the Manhattan distance is introduced to quantify the yield differences between crops, and complementary benefit and substitution loss modules are incorporated into the objective function, effectively coordinating the allocation of planting areas for different crops. Through an analysis of the price elasticity of demand for grain, vegetable, and edible fungus crops, it is found that grain crops exhibit the weakest price sensitivity, while edible fungi show the strongest sensitivity. The most significant changes in crop yields occur within the price fluctuation range of -10% to 10%. This study provides a scientific basis for optimizing agricultural planting strategies, promotes the development of smart agriculture, and offers strong support for the efficient allocation of agricultural resources and the maximization of economic benefits.