Analysis of Agricultural Electrical Automation Mapping Using XGS Decision Model

Abstract

Energy conservation is crucial for intelligent agricultural decision-making, including plant development, automation of equipment, and cultivation. Industrial 4.0 technologies include the Internet of Things (IoT), artificial intelligence (AI), and big data. We use these technologies to control energy consumption and enhance the environment. This study proposes to apply an extended galactic swarm (XGS) decision model for agricultural electrical automation mapping by optimizing the effectiveness of the energy consumption forecasting process. We collect energy-related data from a range of environmental and agricultural production sensors to assess and train the XGS model. We normalize the raw data samples by eliminating the noisy data using the min-max normalization strategy. We then predict the energy usage amount using the random forest (RF) technique. Using the XGS model to modify the hyper-parameters can enhance the performance of the RF approach. We implement the proposed model on the Python platform and assess its success using several metrics. When compared to other existing models, the suggested XGS-based prediction framework provides the best efficiency in the energy consumption forecasting process. This article provides a practical agricultural electrical automation mapping solution for astute agricultural managers or farmers who wish to solve agricultural energy concerns more affordably and sustainably. When compared to current techniques, our proposed XGS-RF produced the lowest results in terms of RMSE (1998.12), RMPSE (6.53), and MAE (1384.15).