Due to the large number of grid connection of distributed power supply, the existing scheduling methods can not meet the demand gradually. The proposed virtual power plant provides a new idea to solve this problem. The photovoltaic power prediction provides the data basis for the scheduling of the virtual power plant. Prediction intervals of photovoltaic power is a powerful statistical tool used for quantifying the uncertainty of photovoltaic power generation in power systems. To improve the interval prediction accuracy during the non-stationary periods of photovoltaic power, this paper proposes a probabilistic ensemble prediction model, which combines the modules of data preprocessing, non-stationary period discrimination, feature extraction, deterministic prediction, uncertainty prediction, and optimization integration into a general framework. More specifically, in the non-stationary period discrimination module, the method of discriminating the difference of the power ratio difference is introduced and applied for identifying the non-stationary period of the data of photovoltaic output; in the deterministic point prediction module, a stacking- long-short-term memory neural network model is used for point forecasts; in the uncertainty interval prediction module, a BAYES neural network is introduced for probabilistic forecasts; in the optimization integration module, an optimization algorithm named Non-dominated Sorting Genetic Algorithm-II is applied for integrating and optimizing the results of the point forecast and probabilistic forecast. The proposed model is tested using two photovoltaic outputs and weather data measured from a grid-connected photovoltaic system. The results show that the proposed model outperforms conventional forecast methods to predict short-term photovoltaic power outputs and associated uncertainties. The interval width is reduced by 10–20%, and the prediction accuracy is improved by at least 10%; this can be a useful tool for photovoltaic power forecasting.

No abstract

The release of transmitter from the vesicle, its diffusion through the fusion pore, and the cleft and its interaction with the carbon electrode were simulated using the Monte Carlo method. According to the simulation the transmitter release is largely determined by geometric factors--the ratio of the fusion pore cross-sectional and vesicular areas, if the diffusion constant is as in the aqueous solution--but the speed of transmitter dissociation from the gel matrix plays an important role during the rise phase of release. Transmitter is not depleted near the entrance to the fusion pore and there is no cleft-to-vesicle feedback, but the depletion becomes evident if the diffusion constant is reduced, especially if the pore is wide. In general, the time course of amperometric currents closely resembles the time course of the simulated transmitter concentration in the cleft and the time course of release. Surprisingly, even a tenfold change of the electrode efficiency has only a marginal effect on the amplitude or the time course of amperometric currents. Greater electrode efficiency however lowers the cleft concentration, but only if the cleft is narrow. As the cleft widens the current amplitudes diminish and rise times lengthen, but the decay times are less affected. Moreover, the amplitude dependence of the rise and decay times becomes steeper as the cleft widens and/or as the release kinetics slows. Finally, lower diffusion constant of transmitter in the narrow cleft does not further prolong the amperometric currents, whose slow time course reflects slow release kinetics.

The intermittence and fluctuation of renewable energy bring significant uncertainty to the power system, which enormously increases the operational risks of the power system. The development of efficient interval prediction models can provide data support for decision making and help improve the economy and reliability of energy interconnection operation. The performance of Bayesian deep learning models and Bayesian shallow neural networks in short-term interval prediction of photovoltaic power is compared in this study. Specifically, an LSTM Approximate Bayesian Neural Network model (ABNN-I) is built on the basis of the deep learning and Monte Carlo Dropout method. Meanwhile, a Feedforward Bayesian Neural Network (ABNN-II) model is introduced by Feedforward Neural Network and the Markov Chain Monte Carlo method. To better compare and verify the interval prediction capability of the ABNN models, a novel clustering method with three-dimensional features which include the number of peaks and valleys, the average power value, and the non-stationary measurement coefficient is proposed for generating sunny and non-sunny clustering sets, respectively. Results show that the ABNN-I model has an excellent performance in the field of photovoltaic short-term interval forecasting. At a 95% confidence level, the interval coverage from ABNN-I to ABNN-II can be increased by up to 3.1% and the average width of the interval can be reduced by 56%. Therefore, with the help of the high computational capacity of deep learning and the inherent ability to quantify uncertainty of the interval forecast from Bayesian methods, this research provides high-quality interval prediction results for photovoltaic power prediction and solves the problem of difficult modeling for over-fitting that exists in the training process, especially on the non-sunny clustering sets.

No abstract