IDS-Net: A novel framework for few-shot photovoltaic power prediction with interpretable dynamic selection and feature information fusion

TL;DR

IDS-Net is an interpretable, dynamic feature selection framework that improves few-shot photovoltaic power prediction by combining transfer learning, feature fusion, and outlier correction, validated on real datasets.

Contribution

The paper introduces IDS-Net, a novel framework integrating dynamic feature selection, transfer learning, and interpretability for accurate PV power prediction with limited data.

Findings

Effective transfer learning with MMD-based source domain selection

Improved prediction accuracy on PV datasets

Robust outlier correction enhances model stability

Abstract

With the growing demand for renewable energy, countries are accelerating the construction of photovoltaic (PV) power stations. However, accurately forecasting power data for newly constructed PV stations is extremely challenging due to limited data availability. To this end, we propose a novel interpretable dynamic selection network (IDS-Net) based on feature information fusion to achieve accurate few-shot prediction. This transfer learning framework primarily consists of two parts. In the first stage, we pre-train on the large dataset, utilizing Maximum Mean Discrepancy (MMD) to select the source domain dataset most similar to the target domain data distribution. Subsequently, the ReliefF algorithm is utilized for feature selection, reducing the influence of feature redundancy. Then, the Hampel Identifier (HI) is used for training dataset outlier correction. In the IDS-Net model, we first obtain the initial extracted features from a pool of predictive models. Following this, two separate weighting channels are utilized to determine the interpretable weights for each sub-model and the adaptive selection outcomes, respectively. Subsequently, the extracted feature results from each sub-model are multiplied by their corresponding weights and then summed to obtain the weighted extracted features. Then, we perform cross-embedding on the additional features and fuse them with the extracted weighted features. This fused information is then passed through the MLP (Multi-Layer Perceptron) layer to obtain predictions. In the second stage, we design an end-to-end adaptive transfer learning strategy to obtain the final prediction results on the target dataset. We validate the transfer learning process using two PV power datasets from Hebei province, China, to demonstrate the effectiveness and generalization of our framework and transfer learning strategy.