Comparison Analysis of Machine Learning Techniques for Photovoltaic Prediction Using Weather Sensor Data

Abstract

Over the past few years, solar power has significantly increased in popularity as a renewable energy. In the context of electricity generation, solar power offers clean and accessible energy, as it is not associated with global warming and pollution. The main challenge of solar power is its uncontrollable fluctuation since it is highly depending on other weather variables. Thus, forecasting energy generation is important for smart grid operators and solar electricity providers since they are required to ensure the power continuity in order to dispatch and properly prepare to store the energy. In this study, we propose an efficient comparison framework for forecasting the solar power that will be generated 36 h in advance from Yeongam solar power plant located in South Jeolla Province, South Korea. The results show a comparative analysis of the state-of-the-art techniques for solar power generation.

Symmetrical Pole Placement Method-Based Unity Proportional Gain Resonant and Gain Scheduled Proportional (PR-P) Controller With Harmonic Compensator for Single Phase Grid-Connected PV Inverters

“…The only changing parameters is the resonant frequencies. The resonant frequency for the fundamental component is 50 Hz ( ), for the 3rd order harmonic component 150 Hz ( 3) and for the 5th order harmonic component 250 Hz (5 ). The magnitude and phase responses of the designed PR controller with 3rd and 5th harmonics compensator is given in Figure 10:…”

“…Photovoltaic (PV) energy is a clean, renewable source of direct current (DC) energy generated from the sunlight, which attracts considerable attention due to remarkable advantages such as reliability and long-life, advanced manufacturing process, static and noise-free operations, increasing efficiency, decreasing prices, flexibility of construction and availability of government support and incentives [3], [4]. The increasing demand of PV energy systems has leaded to comprehensive studies in this field, common ground of these studies aims at achieving the increase in the efficiency, reliability and useful life-span of the PV systems and on the contrary the reduction in cost and space from generation to delivering of the energy [5], [6]. Singlephase PV inverter systems have been widely applied in photovoltaic power generation.…”

Arquitectura Neuronal Para Predicción De Radiación Solar en Base a Variables Meteorológicas

“…Las técnicas de aprendizaje automatizado y en especial las de aprendizaje profundo dependen de un histórico de datos y predicen el comportamiento futuro sobre esa base. Para la predicción de radiación solar, el histórico de datos utilizado consta de variables observadas mediante estaciones meteorológicas desplegadas sobre un territorio o región (Carrera and Kim 2020;Kim et al 2019), de imágenes de satélite (Babar et al 2019;Ghimire et al 2019), de imágenes del cielo (Pedro et al 2019) (tomadas desde la superficie para analizar la claridad de la atmósfera) y modelos físicos (Yang et al 2019). En las aproximaciones al problema se han usado las fuentes de datos de forma independiente o mezclando variables procedentes de las diferentes fuentes (Tao et al 2021;Aguiar et al 2016;Lotfi et al 2020).…”

Inverter Efficiency Analysis Model Based on Solar Power Estimation Using Solar Radiation

“…Some studies are ongoing with the goal of estimating solar radiation to predict future power output [30][31][32]. There are also studies on power output estimation based on ambient temperature, wind velocity, and incident light [33][34][35]. The method is based on historical weather data; there is a high correlation between the weather conditions in the present or past, and the solar power generation in the future.…”