AutoPV: Automatically Design Your Photovoltaic Power Forecasting Model

TL;DR

AutoPV introduces an automated neural architecture search framework tailored for photovoltaic power forecasting, enabling efficient and superior model design without extensive domain expertise.

Contribution

The paper presents a novel NAS-based framework with a specialized search space for PVPF, improving model construction efficiency and performance over existing predefined models.

Findings

AutoPV constructs architectures faster than manual methods.

AutoPV's architectures outperform state-of-the-art predefined models.

The framework effectively bridges NAS and time series forecasting for PVPF.

Abstract

Photovoltaic power forecasting (PVPF) is a critical area in time series forecasting (TSF), enabling the efficient utilization of solar energy. With advancements in machine learning and deep learning, various models have been applied to PVPF tasks. However, constructing an optimal predictive architecture for specific PVPF tasks remains challenging, as it requires cross-domain knowledge and significant labor costs. To address this challenge, we introduce AutoPV, a novel framework for the automated search and construction of PVPF models based on neural architecture search (NAS) technology. We develop a brand new NAS search space that incorporates various data processing techniques from state-of-the-art (SOTA) TSF models and typical PVPF deep learning models. The effectiveness of AutoPV is evaluated on diverse PVPF tasks using a dataset from the Daqing Photovoltaic Station in China. Experimental results demonstrate that AutoPV can complete the predictive architecture construction process in a relatively short time, and the newly constructed architecture is superior to SOTA predefined models. This work bridges the gap in applying NAS to TSF problems, assisting non-experts and industries in automatically designing effective PVPF models.