Machine learning based on reliable and sustainable electricity supply from renewable energy sources in the agriculture sector

Abstract

Electricity is essential for several agricultural operations, including handling, processing, and storing cattle. However, non-renewable energy sources account for most of the industry's electricity today, posing significant environmental and financial challenges. The report emphasizes that the agriculture business needs an uninterrupted supply of power from renewable energy sources to tackle this issue. This study addresses the urgent need for a sustainable energy supply by exploring renewable energy sources in agriculture. The study proposes an artificial neural network (ANN) model to predict the energy requirements of agricultural operations based on factors such as GDP, population, renewable energy consumption, and electricity costs. The ANN model effectively captures the complex relationships between these variables, utilizing historical meteorological data and energy consumption patterns to forecast energy output from renewable sources. The Adam optimizer is employed to enhance ANN training. The results indicate a strong model performance, with an R² value of 0.95, demonstrating that the model accounts for approximately 95% of the variance in energy needs. Additionally, the model achieved a root mean square error (RMSE) of 0.051 and a mean square error (MSE) of 0.0026, confirming its predictive accuracy. Compared to traditional benchmark methods, the Adam optimized ANN outperforms them in accuracy and efficiency. The RF model achieved an R² of 0.88, RMSE of 0.091, and MSE of 0.0081; the LSTM model achieved R² of 0.94, RMSE of 0.053, and MSE of 0.0028; the Gradient Boosting model produced an R² of 0.82, RMSE of 0.089, and MSE of 0.008; and the SVM model delivered an R² of 0.75, RMSE of 0.1, and MSE of 0.01. This research contributes to enhancing the sustainability of agriculture by promoting the adoption of renewable energy solutions, ultimately supporting resilience against climate change and fostering sustainable growth in the sector.