Application of XGS Decision Model in Agricultural Electrical Automation Mapping

Abstract

For intelligent agricultural decision-making such as cultivation, equipment automation, and plant development, conserving energy is essential. The Internet of Things (IoT), artificial intelligence (AI) and large amounts of information are examples of industrial 4.0 technologies that are utilized to manage energy consumption and enhance environments. This research suggests implementing an extended galactic swarm (XGS) decision model for agricultural electrical automation mapping by maximizing the efficiency of the energy consumption forecasting procedure. Data about energy is gathered form a variety of agricultural production and environmental monitors and employed to evaluate and train the XGS model. By removing the noisy data, we apply the min-max normalization approach to normalize the raw data samples. The random forest (RF) approach is then used to forecast the amount of energy used. By adjusting the hyperparameters, the XGS model is used to improve the RF method’s performance. The suggested model is implemented on the python platform, and its performance is examined using several measures. The proposed XGS-based prediction framework delivers the highest efficiency in the energy consumption forecasting process when compared to other current models. For intelligent managers of agriculture or farmers who seek to address the issues of agricultural energy more cheaply and ecologically, this article offer a workable agricultural electrical automation mapping solution.