# A hybrid AI model integrating BKA-VMD and deep neural networks for industrial power load prediction

## TL;DR

A new hybrid AI model improves industrial power load prediction by combining optimized data decomposition with deep neural networks, achieving better accuracy than existing methods.

## Contribution

A novel hybrid deep learning model integrating BKA-optimized VMD with a 1DCNN-BiTCN-BiGRU architecture for enhanced power load forecasting.

## Key findings

- The proposed model outperforms existing methods with lower MAE and RMSE on three industrial datasets.
- The attention mechanism and BiTCN-BiGRU combination are critical for capturing complex temporal dependencies.
- Ablation studies confirm the effectiveness of the hybrid neural network components.

## Abstract

Accurate power load prediction is crucial for optimizing energy consumption and enhancing efficiency in industrial environments. However, the highly nonlinear and non-stationary nature of power load time series presents significant challenges. To address this, we propose a novel hybrid deep learning model that integrates optimized data decomposition with advanced sequence modeling to enhance feature extraction and temporal pattern learning. Specifically, Variational Mode Decomposition (VMD) optimized by the Black-Winged Kite Algorithm (BKA) extracts intrinsic mode functions, reducing noise and improving signal representation. The decomposed signals are processed by a hybrid neural network combining a One-Dimensional Convolutional Neural Network (1DCNN) for local feature extraction, a Bidirectional Temporal Convolutional Network (BiTCN) for long-range temporal dependencies, a Bidirectional Gated Recurrent Unit (BiGRU) for sequential pattern learning, and an attention mechanism to emphasize critical features. Extensive experiments, including comparisons with state-of-the-art models and ablation studies, validate our approach across three diverse industrial datasets. The results demonstrate that our model significantly outperforms existing methods, achieving lower Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The ablation study highlights the critical roles of the attention mechanism and the BiTCN-BiGRU combination in capturing complex temporal dependencies. These findings underscore the model’s robustness and adaptability for power load forecasting. Future research should focus on enhancing generalization and validating applicability across diverse industrial settings.