Enhanced Short-Term Power Load Forecasting using SqueezeNet, Wavelet Transform, and Improved Pelican Optimization

This paper presents a novel approach for short-term power load forecasting, which combines the SqueezeNet model with wavelet transform (WT). Additionally, an enhanced pelican optimization (DPO) algorithm is developed to improve the efficiency of the SqueezeNet model. The proposed method is evaluated using real-world regional preliminary billing data, and compared against other existing methods to demonstrate its superiority.

The experimental results indicate that the proposed combination method achieves a higher accuracy than the existing methods, which confirms the effectiveness of the proposed approach. Moreover, the DPO algorithm significantly improves the computational efficiency of the SqueezeNet model, making it more practical for real-world applications.

Overall, this study provides a valuable contribution to the field of short-term power load forecasting by proposing a novel approach that outperforms existing methods. The combination of SqueezeNet model and WT, along with the improved DPO algorithm, demonstrates the potential for further improvements in this area of research.