M3S-Net: Multimodal Feature Fusion Network Based on Multi-scale Data for Ultra-short-term PV Power Forecasting

TL;DR

M3S-Net is a novel multimodal neural network that integrates multi-scale visual and meteorological data with advanced feature extraction and interaction mechanisms to improve ultra-short-term photovoltaic power forecasting accuracy.

Contribution

This paper introduces M3S-Net, a new multimodal fusion architecture with multi-scale partial convolutions and a dynamic cross-modal interaction module, addressing limitations of previous shallow fusion methods.

Findings

Achieves 6.2% MAE reduction in 10-minute PV power forecasts.

Effectively captures fine-grained cloud optical features.

Models complex spatiotemporal coupling between modalities.

Abstract

The inherent intermittency and high-frequency variability of solar irradiance, particularly during rapid cloud advection, present significant stability challenges to high-penetration photovoltaic grids. Although multimodal forecasting has emerged as a viable mitigation strategy, existing architectures predominantly rely on shallow feature concatenation and binary cloud segmentation, thereby failing to capture the fine-grained optical features of clouds and the complex spatiotemporal coupling between visual and meteorological modalities. To bridge this gap, this paper proposes M3S-Net, a novel multimodal feature fusion network based on multi-scale data for ultra-short-term PV power forecasting. First, a multi-scale partial channel selection network leverages partial convolutions to explicitly isolate the boundary features of optically thin clouds, effectively transcending the precision limitations of coarse-grained binary masking. Second, a multi-scale sequence to image analysis network employs Fast Fourier Transform (FFT)-based time-frequency representation to disentangle the complex periodicity of meteorological data across varying time horizons. Crucially, the model incorporates a cross-modal Mamba interaction module featuring a novel dynamic C-matrix swapping mechanism. By exchanging state-space parameters between visual and temporal streams, this design conditions the state evolution of one modality on the context of the other, enabling deep structural coupling with linear computational complexity, thus overcoming the limitations of shallow concatenation. Experimental validation on the newly constructed fine-grained PV power dataset demonstrates that M3S-Net achieves a mean absolute error reduction of 6.2% in 10-minute forecasts compared to state-of-the-art baselines. The dataset and source code will be available at https://github.com/she1110/FGPD.