Scenario generation of aggregated Wind, Photovoltaics and small Hydro production for power systems applications

Abstract

This paper proposes a methodology for an efficient generation of correlated scenarios of Wind, Photovoltaics (PV) and small Hydro production considering the power system application at hand. The merits of scenarios obtained from a direct probabilistic forecast of the aggregated production are compared with those of scenarios arising from separate production forecasts for each energy source, the correlations of which are modeled in a later stage with a multivariate copula. It is found that scenarios generated from separate forecasts reproduce globally better the variability of a multi-source aggregated production. Aggregating renewable power plants can potentially mitigate their uncertainty and improve their reliability when they offer regulation services. In this context, the first application of scenarios consists in devising an optimal day-ahead reserve bid made by a Wind-PV-Hydro Virtual Power Plant (VPP). Scenarios are fed into a two-stage stochastic optimization model, with chance-constraints to minimize the probability of failing to deploy reserve in real-time. Results of a case study show that scenarios generated by separately forecasting the production of each energy source leads to a higher Conditional Value at Risk than scenarios from direct aggregated forecasting. The alternative forecasting methods can also significantly affect the scheduling of future power systems with high penetration of weather-dependent renewable plants. The generated scenarios have a second application here as the inputs of a two-stage stochastic unit commitment model. The case study demonstrates that the direct forecast of aggregated production can effectively reduce the system operational cost, mainly through better covering the extreme cases. The comprehensive application-based assessment of scenario generation methodologies in this paper informs the decision-makers on the optimal way to generate short-term scenarios of aggregated RES production according to their risk aversion and to the contribution of each source in the aggregation.

Probabilistic Forecasting of Regional Wind Power Generation for the EEM20 Competition: a Physics-oriented Machine Learning Approach

“…Instead of investigating a model able to perform a regression in the large dimension of the complete original data set, we chose to focus on the creation of a relatively small set of information-rich features used as input into a machine learning algorithm, namely Quantile Regression Forests (QRF), which has proven its skills in probabilistic forecasting of aggregated renewable production [13]. Creating and selecting a few inputs has the advantage of shortening the computation time, thus giving us the possibility to try multiple models and combinations of inputs, and to better scale the influencing factors with the observed response.…”

The future of forecasting for renewable energy

“…Forecasts based on power curve models are necessary where no data are available to estimate a statistical model, such as when a wind or solar farm is first commissioned, but generally produce poorer quality forecasts than statistical postprocessing. Similar principals may be applied to run-of-river hydro (Camal, Teng, Michiorri, Kariniotakis, & Badesa, 2019), but for dispatchable hydro, water inflow to storage reservoirs would be the forecast variable (Maier & Dandy, 2000).…”

Scenario reduction based on correlation sensitivity and its application in microgrid optimization

“…The scenario‐based method, as a mainstream topic of stochastic programming in recent decades, can accurately describe the uncertainties by generating a series of large‐scale discrete scenarios with probabilities. Research on scenario generation is prevalent in renewable energy applications, including generating correlated wind‐power production and load scenarios, 12,13 correlated wind, photovoltaic (PV) and hydro production scenarios, 14 multiple wind speed/power and PV scenarios, 15‐17 etc. A detailed overview of RES dependence modeling for scenario generation is given in the literature 18 .…”