Probabilistic forecasts of solar irradiance using stochastic differential equations

Iversen, Emil B.; Morales, Juan M.; Møller, Jan Kloppenborg; Madsen, Henrik

doi:10.1002/env.2267

Cited by 70 publications

(49 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, the design and the study of renewable power plants with deterministic approaches are object of several academic courses and handbooks (Patel, 2014). Iversen et al, (2014) proposed an analytical model to forecast the solar irradiance, whereas Iqbal et al (2014) and Mellit et al (2014) present data-driven statistical learning methods to predict the effects of the renewable resources onto the power plants operations. In a previous work, Chiacchio et al (2018) analyzed the performance of photovoltaic power plant using a SHyFTA model, but they did not use this modelling technique to evaluate the service availability of the system.…”

Section: Dynamic Reliability Modelling With Stochastic Hybrid Fault Tmentioning

confidence: 99%

Performance assessment of domestic photovoltaic power plant with a storage system

Chiacchio

D’Urso

Aizpurua³

et al. 2018

IFAC-PapersOnLine

View full text Add to dashboard Cite

Grid-connected low voltage photovoltaic power plants cover the majority of the power capacity installed in Italy. They offer an important contribution to the power demand of the utilities connected but, due to the nature of the solar resource, the night time consumption can be satisfied only withdrawing the energy by the national grid, at the price of the energy distributor. Thanks to the improvement of storage technologies and the decreasing of costs, the installation of a system of battery looks a promising solution. In this paper, a model-based approach to analyze and discuss the performance of a domestic photovoltaic power plant with a storage system is presented.

show abstract

Section: Dynamic Reliability Modelling With Stochastic Hybrid Fault Tmentioning

confidence: 99%

Performance assessment of domestic photovoltaic power plant with a storage system

Chiacchio

D’Urso

Aizpurua³

et al. 2018

IFAC-PapersOnLine

View full text Add to dashboard Cite

show abstract

“…Literature [32] systematic method to optimize the operation of the feeder and to ensure the voltage quality, to determine the photovoltaic active and reactive power output of residential roofs. Literature [33] used the framework of stochastic differential equations to predict the probability of solar irradiation. Literature [34] first predicted the probability distribution of the hourly clear sky index through Bayesian autoregressive time series model, and then calculated the probability distribution of PV output by random sampling of the clear sky index by Monte Carlo simulation.…”

Section: Distributed Photovoltaic Output Forecastmentioning

confidence: 99%

A Review of Distributed PV Operation Analysis and Demand Response Research

Cheng

et al. 2018

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Abstract. The large-scale access of the distributed photovoltaic power supply to the grid will bring great challenge to the safe operation of power grid, thus adversely affecting the further development of distributed photovoltaic. First of all, from the aspects of structure, power quality, network loss and relay protection, this paper summarizes the influence of distributed photovoltaic system on distribution network. Secondly, the distributed photovoltaic output is summarized and summarized from two aspects of distributed photovoltaic output performance analysis and output forecast. In addition, from the perspective of photovoltaic user demand response can improve the photovoltaic extinction rate, this paper also combs the analysis and research of PV user demand response modelling and electricity price mechanism. Finally, some suggestions on the key areas for future research are put up. IntroductionThe development prospect of distributed photovoltaic power generation is broad [1], it advocates the spontaneous use of electricity, the rest of the internet, there is no step-up and long-distance transportation problem, directly facing the terminal power consumers[2], in the power market reform and energy-saving emission reduction situation, has got more and more attention and development. With the increase of the distributed PV network capacity, the safe and stable operation of the power system will be influenced by the non-negligible [3]. The accurate characteristic analysis and output prediction of distributed PV are the important foundation to solve these problems and ensure the safe operation of the power grid [4]. At the same time, a lot of researches have been done on demand side participation in distribution network, the purpose of which is to adjust shifting and increase PV extinction rate by using demand response of PV users [5][6][7][8][9].Based on the influence of photovoltaic power grid on distribution network, this paper collated the research of PV power generation characteristics analysis and output prediction, and then it has further combed the research on PV user demand response, which has provided some reference for readers.

show abstract

“…Our proposed method is district from the existing probabilistic solar forecasting methods like [6,7] because we use literally different base regression models rather than using a single base model with different parameters or bootstrapping. The good results offered by it can be attributed to the soundness of the seven base regression models themselves and the effectiveness of our carefully-crafted ensemble strategies, especially in the case of the normal distribution with additional features method.…”

Section: Our Contributionsmentioning

confidence: 99%

“…Iversen et al [6] proposed a framework for calculating the probabilistic forecasts of solar irradiance using stochastic differential equations (SDE). They construct a process that is limited to a bounded state space, and it assigns zero probability to all of the events outside this state space.…”

Section: Probabilistic Forecastingmentioning

confidence: 99%

Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation

Mohammed¹,

Aung²

2016

Energies

View full text Add to dashboard Cite

Probabilistic forecasting accounts for the uncertainty in prediction that arises from inaccurate input data due to measurement errors, as well as the inherent inaccuracy of a prediction model. Because of the variable nature of renewable power generation depending on weather conditions, probabilistic forecasting is well suited to it. For a grid-tied solar farm, it is increasingly important to forecast the solar power generation several hours ahead. In this study, we propose three different methods for ensemble probabilistic forecasting, derived from seven individual machine learning models, to generate 24-h ahead solar power forecasts. We have shown that while all of the individual machine learning models are more accurate than the traditional benchmark models, like autoregressive integrated moving average (ARIMA), the ensemble models offer even more accurate results than any individual machine learning model alone does. Furthermore, it is observed that running separate models on the data belonging to the same hour of the day vastly improves the accuracy of the results. Getting more accurate forecasts will help the stakeholders come up with better decisions in resource planning and control when large-scale solar farms are integrated into the power grid.

show abstract

Probabilistic forecasts of solar irradiance using stochastic differential equations

Cited by 70 publications

References 41 publications

Performance assessment of domestic photovoltaic power plant with a storage system

Performance assessment of domestic photovoltaic power plant with a storage system

A Review of Distributed PV Operation Analysis and Demand Response Research

Ensemble Learning Approach for Probabilistic Forecasting of Solar Power Generation

Contact Info

Product

Resources

About