Renewable Generation (Wind/Solar) and Load Modeling through Modified Fuzzy Prediction Interval

Abstract

The accuracy of energy management system for renewable microgrid, either grid-connected or isolated, is heavily dependent on the forecasting precision such as wind, solar, and load. In this paper, an improved fuzzy prediction horizon forecasting method is developed to address the issue of intermittence and uncertainty problem related to renewable generation and load forecast. In the first phase, a Takagi-Sugeno type fuzzy system is trained with many evolutionary optimization algorithms and established coverage grade indicator to check the accuracy of interval forecast. Secondly, a wind, solar, and load forecaster is developed for renewable microgrid test bed which is located in Beijing, China. One day and one step ahead results for the proposed forecaster are expressed with lowest RMSE and training time. In order to check the efficiency of the proposed method, a comparison is carried out with the existing models. The fuzzy interval-based model for the microgrid test bed will help to formulate the energy management problem with more accuracy and robustness.

Review on Fuzzy and Neural Prediction Interval Modelling for Nonlinear Dynamical Systems

“…For example, in [20] different tuning parameters were proposed for the upper and lower bounds (α and α respectively), achieving a non-symmetrical interval around the prediction value. This version of the method has been applied in [20] for the identification of intervals for traffic measurements, and in [21], [22] for the forecasting of renewable generation and demand data from an installed microgrid. Later, a third version of this method was proposed in [23], where the tuning parameters can also vary depending of the instant k when the predictions are made (α k ).…”

Energy management system design and testing for smart buildings under uncertain generation (wind/photovoltaic) and demand

“…By contrast, in this paper, an evolutionary-based training method for linear regressors in the fuzzy interval is described to improve the accuracy of the proposed approach in comparison with the existing Back Propagation (BP)-based methods; performance indicators, such as the CG, and interval bands for lower and upper intervals are also introduced to check the quality of forecast. To approximate function families for various sets of intervals using fuzzy prediction interval, the authors calculate forecasting intervals with a certain interval bandwidth σ and a fuzzy co-variance model of error because the deterministic solution is not reliable in renewable/load predictions [12] .…”

“…For a more in-depth analysis of the forecast scheme used in this paper, readers can refer to Ref. [12].…”

Fuzzy-based prediction of solar PV and wind power generation for microgrid modeling using particle swarm optimization

“…The estimation of wind and solar power generation based on a modified fuzzy prediction interval using fuzzyregression (FR), firefly algorithm (FF), cultural algorithm (CA), genetic algorithm, and particle swarm optimization is developed in Ref. [ 19 ]. According to this model, for a short prediction interval (less than 1 day), the GA-based fuzzy prediction model provides a better prediction accuracy (RMSE of 1.88), whereas, for a longer prediction interval (>1day), the PSO-based fuzzy prediction model has better performance (RMSE of 7.5) [ 19 ].…”