Nonparametric short-term probabilistic forecasting for solar radiation
Introduction
As it has been emphasized at the most recent 2015 Paris Climate Conference (COP21), at the face of increasingly dramatic impact of global warming on our ecosystem, “green power” resources such as wind, sunlight, wave and tides that quickly replenish themselves are now broadly recognized as the critical path toward future sustainability and reducing the environmental footprint. Many countries have accelerated their climate and energy policies with an aim to minimize the greenhouse gas emissions and pollution. For instance, the Australian Government has set a target for reducing greenhouse gas emissions by 26–28% below 2005 levels by 2030 (Commonwealth of Australia, 2015) while China commits to cap rising emissions by 2030 (Change Authority, 2015). The European Union commits to reduce emissions of at least 40% below 1990 levels by 2030, and similar initiatives are announced by the US and Brazil at the recent joint summit in June 2015. However, one of the key obstacles on the way of efficient and reliable integration of renewable energy into electric power systems is its natural intermittency and volatility, or as The New York Times mentioned, “the dirty secret of clean energy is that while generating it is getting easier, moving it to market is not” (Wald, 2008). This in turn has boosted a substantial interest in developing new methods for modeling clean energy resources and, particularly, in statistical procedures that construct a full predictive density of “green power” at various forecasting horizons, and thus allow to assess a wide range of uncertainties and facilitate decision-making. However, the vast majority of such methods focus on probabilistic wind power forecasting (see, for example, reviews by Chen et al., 2013, Pinson, 2013, Gneiting and Katzfuss, 2014, De Greve et al., 2014, Erdem et al., 2014, Zhang et al., 2014, Wan et al., 2013, Zamo et al., 2014, and references therein), while systematic addressing uncertainty in solar energy prediction remains largely unexplored. For instance, recently Zhang et al. (2015) evaluate utility of various metrics for classification of uncertainties in a solar irradiation forecast but do not discuss methodology for constructing a full predictive density. Zamo et al. (2014) study probabilistic forecasting of photovoltaic (PV) electricity production based on an ensemble output from a numerical weather prediction (NWP) model. A related work of Ngoko et al. (2014) deals with synthetic generation of solar radiation sequences, thus implicitly using similar tools to those needed for prediction interval construction. Most recently, Boland and Soubdhan (2015) employs Autoregressive Conditional Heteroscedastic (ARCH) techniques to construct parametric prediction intervals for hourly and ten minute solar forecasts based on a normal distribution.
Nonparametric probabilistic forecasting for solar PV power has been recently examined by Golestaneh et al., 2016, Le Cadre et al., 2015. Pinson and Kariniotakis (2010) propose to generate prediction intervals for wind power using a nonparametric approach called adaptive resampling. Similarly to our method for constructing a full predictive density (see Section 4), the approach of Pinson and Kariniotakis (2010) places errors into bins based on influential variables, for example predicted power level, in order to deal with the variation in variance of wind power at different power ranges. Recently, Gel et al. (2016) consider a nonparametric sieve bootstrap for generating probabilistic forecasts of wind speed.
This paper breaks through the current practice of point forecasting of solar radiance and proposes a new computationally efficient and data-driven method for constructing a full nonparametric predictive density for short term forecasting of solar radiation, using nonparametric bootstrap and a map of sun positions. What we demonstrate here is probabilistic forecasting of solar radiation on an hourly basis but the proposed methodology can be altered to cater for any predictive horizon from five minute to a few hours. Our study is primarily motivated by a project run by the Australian National Electricity Market (NEM), where dispatch decisions are made every five minutes and market clearing takes place on a half hour basis. Moreover, one of the authors (Boland) is part of a team developing the Australian Solar Energy Forecasting System (ASEFS) for the Australian Energy Market Operator (AEMO) which aims to enhance integration of solar energy generation at all scales into the Australian national grid. One of the primary ASEFS goals is to develop an operational system that employs forecasting techniques for all the AEMO-required forecasting time frames, which range from five minutes to two years. The new statistical procedures for probabilistic forecasting of solar power that we propose in this paper are thus expected to be implemented for operational use by AEMO. In view of the results on utility of a nonparametric sieve bootstrap (Bühlmann, 2002, Bühlmann, 1997, Alonso et al., 2002, Chen et al., 2011), the bootstrap methodology proposed in this paper is expected to be applicable to a broad range of other time scales and forecasting horizons for global horizontal irradiation as well as for generating a full predictive density for PV output.
The paper is organized as follows. Description of the solar irradiation data is given in Section 2. Section 3 details a model for point forecasting. In Section 4 we present the new bootstrap methodology for probabilistic forecasting of solar irradiation. We evaluate the new probabilistic forecasting methodology in Section 5. The paper is concluded by discussion and future work in Section 6.
Section snippets
Data description
The solar irradiation data used in this study are recorded in Mildura, Australia (Latitude 34.11° S, Longitude 142.09° E). A map of Australia with Mildura’s location is shown in Fig. 1. According to the Köppen-Geiger climate classification system (Peel et al., 2007), Mildura’s climate is classified as semi-arid with hot summers and cool winters.
The data set consists of 87,600 () hourly global horizontal irradiation (GHI) values from 1995 to 2004 with units of watts per square meter, Wh m−2
Point forecasting
We start from providing a brief overview of methods for point forecasting of solar radiation on various time scales (for recent comprehensive reviews see Hossain et al., 2013, Inman et al., 2013, Diagne et al., 2013, Madsen et al., 2014, Patrick et al., 2016, and references therein). Forecasting approaches can be generally classified as physical methods, statistical methods or combined approaches. Physical methods are based on (deterministic) physical considerations, such as outputs of
Density forecasting
Now we turn to developing a full predictive density for GHI without imposing any parametric assumptions on the underlying distribution structure of GHI. Our key idea is based on nonparametric bootstrap of innovative noise in (1) while accounting for heterogeneous structure of GHI. In particular, we start from assuming that heteroscedasticity of noise in (1) is driven by a specific sun position. The errors may depend on something else but our sky position method is an easy and transferable
Performance evaluation
To validate performance of the developed bootstrap ensemble, we employ standard criteria and diagnostic tools for probabilistic forecasting such as coverage probability, average width of prediction intervals, Continuous Rank Probability Score (CRPS), and verification rank histograms (for the comprehensive reviews on verification procedures see Gneiting and Katzfuss (2014) and the report WWRP (2016) by the Joint Working Group on Forecast Verification Research of the World Weather Research
Conclusion and discussion
In this paper we propose a new data-driven method for probabilistic forecasting of solar energy based on nonparametric bootstrap and a map of sun positions accounting for heteroscedasticity of solar irradiation. While probabilistic forecasts are now a widely adopted tool for wind energy prediction, most of solar energy modeling procedures still primarily focus on point forecasting. In addition, many solar power integration studies implicitly assume that a solar-related variable such as global
References (61)
- et al.
Forecasting time series with sieve bootstrap
J. Stat. Plann. Inference
(2002) - et al.
Online short-term solar power forecasting
Solar Energy
(2009) - et al.
Spatial-temporal forecasting of solar radiation
Renew. Energy
(2015) - et al.
Study of forecasting solar irradiance using neural networks with preprocessing sample data by wavelet analysis
Energy
(2006) - et al.
Study of hourly and daily solar irradiation forecast using diagonal recurrent wavelet neural networks
Energy Convers. Manage.
(2008) - et al.
GARCH in mean type models for wind power forecasting
- et al.
Solar energy forecasting and resource assessment
- et al.
Review of solar irradiance forecasting methods and a proposition for small-scale insular grids
Renew. Sustain. Energy Rev.
(2013) - et al.
Post-processing of solar irradiance forecasts from WRF model at Reunion Island
Solar Energy
(2014) - et al.
Short-term solar irradiance forecasting using exponential smoothing state space model
Energy
(2013)