This page has only limited features, please log in for full access.
The proliferation of solar power systems could cause instability within existing power grids due to the variable nature of solar power. A well-defined statistical model is important for managing the supply-and-demand dynamics of a power system that contains a significant variable renewable energy component. It is furthermore important to consider the inherent uncertainty in the data when modeling such a complex power system. Gaussian process regression has the potential to address both of these concerns: the probabilistic modeling of solar radiation data could assist in managing the variability of solar power, as well as provide a mechanism to deal with uncertainty. In this paper, solar radiation data was obtained from the Southern African Universities Radiometric Network and used to train a Gaussian process regression model which was developed especially for this purpose. Attention was given to constructing an appropriate Gaussian process kernel. It was found that a carefully constructed kernel allowed for the successful interpolation of global horizontal irradiance data, with a root-mean-squared error of 82.2W/m2. Gaps in the data, due to possible meter failure, were also bridged by the Gaussian process with a root-mean-squared error of 94.1 W/m2 and accompanying confidence intervals. A root-mean-squared error of 151.1 W/m2 was found when forecasting the global horizontal irradiance with a forecasting horizon of five days. These results, achieved in modeling solar radiation data using Gaussian process regression, could open new avenues in the development of probabilistic renewable energy management systems. Such systems could aid smart grid operators and support energy trading platforms, by allowing for better-informed decisions that incorporate the inherent uncertainty of stochastic power systems.
Foster Lubbe; Jacques Maritz; Thomas Harms. Evaluating the Potential of Gaussian Process Regression for Solar Radiation Forecasting: A Case Study. Energies 2020, 13, 5509 .
AMA StyleFoster Lubbe, Jacques Maritz, Thomas Harms. Evaluating the Potential of Gaussian Process Regression for Solar Radiation Forecasting: A Case Study. Energies. 2020; 13 (20):5509.
Chicago/Turabian StyleFoster Lubbe; Jacques Maritz; Thomas Harms. 2020. "Evaluating the Potential of Gaussian Process Regression for Solar Radiation Forecasting: A Case Study." Energies 13, no. 20: 5509.
Gathering quality wind speed data can be time-consuming and expensive. The present study established whether interval-deficient wind speed data could be rendered useful for wind power assessments. The effect of interval deficiency on the quality of the wind speed data was investigated by studying the behaviour of the Weibull scale and shape factors as the interval size between wind speed measurements increased. Five wind speed data sets obtained from the Southern African Universities Radiometric Network (Sauran) were analysed, based on a proposed procedure to find the true Weibull parameters from an interval-deficient wind speed data set. It was found that the relative errors in the Weibull parameters were, on average, less than 1%, compared with the Weibull parameters computed from a wind speed data set that complies with the IEC 61400-12-1:2005(E) standard. This finding may contribute to time and cost reduction in wind power assessments. It may also promote the application of statistical methods in the renewable energy sector.
F. Lubbe; T. Harms; J. Maritz. A statistical exploration of interval-deficient wind speed data for application to wind power assessments. Journal of Energy in Southern Africa 2019, 30, 13 -25.
AMA StyleF. Lubbe, T. Harms, J. Maritz. A statistical exploration of interval-deficient wind speed data for application to wind power assessments. Journal of Energy in Southern Africa. 2019; 30 (4):13-25.
Chicago/Turabian StyleF. Lubbe; T. Harms; J. Maritz. 2019. "A statistical exploration of interval-deficient wind speed data for application to wind power assessments." Journal of Energy in Southern Africa 30, no. 4: 13-25.
Measurement and Verification (M&V) aims to quantify savings achieved as part of energy efficiency and energy management projects. M&V depends heavily on metered energy data, modelling parameters and uncertainties that govern the energy system under consideration. M&V therefore requires a stringent handle on the inherent uncertainties in the calculated savings. The Bayesian framework of data analysis in the form of non-parametric, nonlinear Gaussian Process (GP) regression provides a mechanism by which these uncertainties can be quantified thoroughly, and is therefore an attractive alternative to the more traditional frequentist approach. It is important to select appropriate kernels to construct the prior when performing GP regression. This paper aims to construct a guideline for a practical GP regression within the energy M&V framework. It does not attempt to quantify energy losses or savings, but rather presents a case study that could act as a road map for energy managers and M&V professionals to apply the GP regression as a Bayesian alternative to base-line adjustment. Special attention will be given to the selection of appropriate kernels for the application of baseline adjustment and energy savings quantification in a model-independent manner.
Jacques Maritz; Foster Lubbe; Louis Lagrange. A Practical Guide to Gaussian Process Regression for Energy Measurement and Verification within the Bayesian Framework. Energies 2018, 11, 935 .
AMA StyleJacques Maritz, Foster Lubbe, Louis Lagrange. A Practical Guide to Gaussian Process Regression for Energy Measurement and Verification within the Bayesian Framework. Energies. 2018; 11 (4):935.
Chicago/Turabian StyleJacques Maritz; Foster Lubbe; Louis Lagrange. 2018. "A Practical Guide to Gaussian Process Regression for Energy Measurement and Verification within the Bayesian Framework." Energies 11, no. 4: 935.