Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines

TLDR

Renewable energy demand has driven rapid growth of photovoltaic systems, yet their power output varies with weather, making accurate forecasting essential for reliability and large‑scale deployment. This study proposes algorithms that forecast PV power output using weather classification and support vector machines. The approach classifies weather into clear, cloudy, foggy, and rainy, then builds a one‑day‑ahead forecasting model for a single station using weather forecasts, historical power data, and SVM principles. When applied to a 20 kW grid‑connected PV station in China, the model demonstrated effective and promising forecasting performance.

Abstract

Due to the growing demand on renewable energy, photovoltaic (PV) generation systems have increased considerably in recent years. However, the power output of PV systems is affected by different weather conditions. Accurate forecasting of PV power output is important for system reliability and promoting large-scale PV deployment. This paper proposes algorithms to forecast power output of PV systems based upon weather classification and support vector machines (SVM). In the process, the weather conditions are divided into four types which are clear sky, cloudy day, foggy day, and rainy day. In this paper, a one-day-ahead PV power output forecasting model for a single station is derived based on the weather forecasting data, actual historical power output data, and the principle of SVM. After applying it into a PV station in China (the capability is 20 kW), results show the proposed forecasting model for grid-connected PV systems is effective and promising.