IoT-driven load forecasting with machine learning for logistics planning

Abstract

Forecasting electricity load in logistics is crucial for managing dynamic energy demands. This research introduces the Integrated Load Forecasting System (ILFS), integrating IoT-driven load forecasting with advanced machine learning. As pioneers in logistics-focused electricity load forecasting, we acknowledge challenges posed by operational metrics, external factors, and diverse features. Starting with thorough preparation, including managing missing data and normalization, ILFS incorporates novel approaches such as Hybrid Boruta with XGBoost (BXG) for feature selection and Uniform Manifold Projection and Approximation (UMAP) for lower dimensionality. In the classification phase, we introduce a pioneering approach: the Hybrid Huber Regression with ResNet (HRRN) model, fine-tuned using the Coyote Optimization Algorithm (COA). Demonstrating scalability and interpretability, ILFS adjusts to various electricity load data scenarios, capturing trends in logistics supply warehouses across different days. Validation metrics underscore ILFS’s efficacy, achieving 98% accuracy, 4 MAE, 12 MSE, 5 RMSE, and 0.99 R-squared ($R^2$). With an average execution time of 7.2 s, ILFS outperforms current techniques, and rigorous statistical analyses support this superiority. ILFS emerges as a pivotal solution, meeting the necessities of precise electricity load forecasting in logistics driven by IoT technologies. This research strides towards harmonious integration of load forecasting, IoT, and logistics planning, ushering in advancements in the field.