Enhanced Photovoltaic Power Forecasting: An iTransformer and LSTM-Based Model Integrating Temporal and Covariate Interactions

TL;DR

This paper introduces a novel PV power forecasting model combining iTransformer, LSTM, and cross-attention mechanisms to better capture complex temporal and covariate interactions, leading to improved accuracy across seasons.

Contribution

The paper presents a new hybrid model integrating iTransformer, LSTM, and cross-attention for enhanced PV power forecasting, addressing limitations of existing models in capturing complex relationships.

Findings

Improved forecasting accuracy across four seasons.

Effective capture of seasonal variations in PV power.

Demonstrated superiority over existing models on public datasets.

Abstract

Accurate photovoltaic (PV) power forecasting is critical for integrating renewable energy sources into the grid, optimizing real-time energy management, and ensuring energy reliability amidst increasing demand. However, existing models often struggle with effectively capturing the complex relationships between target variables and covariates, as well as the interactions between temporal dynamics and multivariate data, leading to suboptimal forecasting accuracy. To address these challenges, we propose a novel model architecture that leverages the iTransformer for feature extraction from target variables and employs long short-term memory (LSTM) to extract features from covariates. A cross-attention mechanism is integrated to fuse the outputs of both models, followed by a Kolmogorov-Arnold network (KAN) mapping for enhanced representation. The effectiveness of the proposed model is validated using publicly available datasets from Australia, with experiments conducted across four seasons. Results demonstrate that the proposed model effectively capture seasonal variations in PV power generation and improve forecasting accuracy.