Regional forecasts and smoothing effect of photovoltaic power generation in Japan: An approach with principal component analysis

Accurate photovoltaic (PV) power forecasting is an essential tool that enables the efficient integration of solar electricity and energy trading. This work proposes a novel methodology for the implementation of a forecasting tool that provides aggregated PV production day‐ahead forecasts for the PV systems installed at a distribution level. Specifically, the tool is a cloud‐based platform, comprising of a data quality block, a weather forecasting model, a machine learning power prediction step and an up‐scaling aggregation stage. In this context and in the absence of a fully observable distribution system, the aggregated PV generation was estimated using a clustering approach and up‐scaling the measured generation of reference systems to the aggregated installed capacity. The results demonstrated that the implemented tool exhibited high forecasting accuracies, lower than 10% given by the mean absolute percentage error when applied to the distribution system of Cyprus. Furthermore, the comparative benchmarking of the up‐scaling techniques against the estimated aggregated PV generation demonstrated that the best‐performing approach was the hybrid model, which provided a normalised root mean square error of 10.29% and mean absolute percentage error of 9.11%. Finally, useful information is provided for establishing a robust day‐ahead forecasting methodology that is based on an optimal supervised learning and hybrid up‐scaling approach.

show abstract

“…The effect of spatial smoothing of the input features was extensively investigated in refs. [46,[58][59][60][61].…”

Section: Resultsmentioning

confidence: 99%

A hybrid methodology for distribution level photovoltaic power production forecasting verified at the distribution system of Cyprus

Theocharides

Spanias

Papageorgiou

et al. 2021

IET Renewable Power Gen

View full text Add to dashboard Cite

show abstract

“…A small forecast error induces two negative effects: the network operator can receive high penalties because the inaccurate forecast did not allow to reach the predicted production profile and the use of back-up generators is more important for compensating the gap between predicted and real production [18,31]. A solution consists in using local storage in combination with ISRES in order to compensate deviations between forecasted and produced electricity [18][19]22,31] or in combining several ISRES spread over a large area in such a way that individual prediction errors of each ISRES are independent and the overall forecast error is reduced (aggregate effect) [32].…”

Section: Predicting Isres Production: a Necessity For A Better Integrmentioning

confidence: 99%

Intermittent and stochastic character of renewable energy sources: Consequences, cost of intermittence and benefit of forecasting

Notton

Nivet

Voyant

et al. 2018

Renewable and Sustainable Energy Reviews

334

134

View full text Add to dashboard Cite

Solar and wind energy are inherently time-varying sources of energy on scales from minutes to seasons. Thus, the incorporation of such intermittent and stochastic renewable energy systems (ISRES) into an electricity grid provides some new challenges in managing a stable and safe energy supply, in using energy storage and/or 'back-up' energy from other sources. In such cases, the ability to accurately forecast the output of "unpredictable" energy facilities is essential for ensuring an optimal management of the energy production means. This review syntheses the reasons to predict solar or wind fluctuations, it shows that variability and stochastic variation of renewable sources have a cost, sometimes high. It provides useful information on the intermittence cost and on the decreasing of this cost due to an efficient forecasting of the source fluctuation; this paper is for engineers and researchers who are not necessarily familiar with the issue of the notions of cost and economy and justify future investments in the ISRES production forecasting.

show abstract

“…Other PV-related papers that use SVRs, the main ML tool here, are [14], where SVR models coupled with a PCA-based features are built to predict regional PV energy in Japan, [15], where SVRs are applied over atmospheric motion vectors derived from satellite data to predict several PV energy related variables, [16] and [17], which use SVRs for oneday ahead PV energy predictions from NWP data, and [18], where short term (less than an hour) PV energy forecasts are derived from local data. Also of interest are [19], where the authors use a hybrid SVR model to predict Global Horizontal Irradiance (GHI) monthly values, or [20], which focuses on predicting a set of expected solar power production values for future time intervals using SVRs.…”

Section: Introductionmentioning

confidence: 99%

Combining Numerical Weather Predictions and Satellite Data for PV Energy Nowcasting

Catalina

Alaíz

Dorronsoro

2020

IEEE Trans. Sustain. Energy

View full text Add to dashboard Cite

show abstract

Regional forecasts and smoothing effect of photovoltaic power generation in Japan: An approach with principal component analysis

Cited by 45 publications

References 12 publications

A hybrid methodology for distribution level photovoltaic power production forecasting verified at the distribution system of Cyprus

A hybrid methodology for distribution level photovoltaic power production forecasting verified at the distribution system of Cyprus

Intermittent and stochastic character of renewable energy sources: Consequences, cost of intermittence and benefit of forecasting

Combining Numerical Weather Predictions and Satellite Data for PV Energy Nowcasting

Contact Info

Product

Resources

About