Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPhotovoltaic Model-Based Solar Irradiance Estimators: Performance Comparison and Application to Maximum Power Forecasting
225
0
0.0
(
0
)
Added by
Enrica Scolari
Publication date
2017
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Due to the increasing proportion of distributed photovoltaic (PV) production in the generation mix, the knowledge of the PV generation capacity has become a key factor. In this work, we propose to compute the PV plant maximum power starting from the indirectly-estimated irradiance. Three estimators are compared in terms of i) ability to compute the PV plant maximum power, ii) bandwidth and iii) robustness against measurements noise. The approaches rely on measurements of the DC voltage, current, and cell temperature and on a model of the PV array. We show that the considered methods can accurately reconstruct the PV maximum generation even during curtailment periods, i.e. when the measured PV power is not representative of the maximum potential of the PV array. Performance evaluation is carried out by using a dedicated experimental setup on a 14.3 kWp rooftop PV installation. Results also proved that the analyzed methods can outperform pyranometer-based estimations, with a less complex sensing system. We show how the obtained PV maximum power values can be applied to train time series-based solar maximum power forecasting techniques. This is beneficial when the measured power values, commonly used as training, are not representative of the maximum PV potential.
rate research
Read More
We analyse the time series of solar irradiance measurements using chaos theory. The False Nearest Neighbour method (FNN), one of the most common methods of chaotic analysis is used for the analysis. One year data from the weather station located at Nanyang Technological University (NTU) Singapore with a temporal resolution of $1$ minute is employed for the study. The data is sampled at $60$ minutes interval and $30$ minutes interval for the analysis using the FNN method. Our experiments revealed that the optimum dimension required for solar irradiance is $4$ for both samplings. This indicates that a minimum of $4$ dimensions is required for embedding the data for the best representation of input. This study on obtaining the embedding dimension of solar irradiance measurement will greatly assist in fixing the number of previous data required for solar irradiance forecasting.
We present a nonlinear equivalent resistance tracking method to optimize the power output for solar arrays. Tracking an equivalent resistance results in nonlinear voltage step sizes in the gradient descent search loop. We introduce a new model for the combined solar module along with a DC-DC converter which results in a highly nonlinear dynamical system due to the inherent non-linearity of the PV cell topology and the switched DC-DC converter system. To guarantee stability over a range of possible operating regimes, we utilize a feedback linearization control approach to exponentially converge to the setpoint. Simulations are presented to illustrate the performance and robustness of the proposed technique.
Rising penetration levels of (residential) photovoltaic (PV) power as distributed energy resource pose a number of challenges to the electricity infrastructure. High quality, general tools to provide accurate forecasts of power production are urgently needed. In this article, we propose a supervised deep learning model for end-to-end forecasting of PV power production. The proposed model is based on two seminal concepts that led to significant performance improvements of deep learning approaches in other sequence-related fields, but not yet in the area of time series prediction: the sequence to sequence architecture and attention mechanism as a context generator. The proposed model leverages numerical weather predictions and high-resolution historical measurements to forecast a binned probability distribution over the prognostic time intervals, rather than the expected values of the prognostic variable. This design offers significant performance improvements compared to common baseline approaches, such as fully connected neural networks and one-block long short-term memory architectures. Using normalized root mean square error based forecast skill score as a performance indicator, the proposed approach is compared to other models. The results show that the new design performs at or above the current state of the art of PV power forecasting.
Ahead-of-time forecasting of incident solar-irradiance on a panel is indicative of expected energy yield and is essential for efficient grid distribution and planning. Traditionally, these forecasts are based on meteorological physics models whose parameters are tuned by coarse-grained radiometric tiles sensed from geo-satellites. This research presents a novel application of deep neural network approach to observe and estimate short-term weather effects from videos. Specifically, we use time-lapsed videos (sky-videos) obtained from upward facing wide-lensed cameras (sky-cameras) to directly estimate and forecast solar irradiance. We introduce and present results on two large publicly available datasets obtained from weather stations in two regions of North America using relatively inexpensive optical hardware. These datasets contain over a million images that span for 1 and 12 years respectively, the largest such collection to our knowledge. Compared to satellite based approaches, the proposed deep learning approach significantly reduces the normalized mean-absolute-percentage error for both nowcasting, i.e. prediction of the solar irradiance at the instance the frame is captured, as well as forecasting, ahead-of-time irradiance prediction for a duration for upto 4 hours.
We analyzed the cross-correlation of Photovoltaic (PV) output fluctuation for the actual PV output time series data in both the Tokyo area and the whole of Japan using the principal component analysis with the random matrix theory. Based on the obtained cross-correlation coefficients, the forecast error for PV output was estimated with/without considering the cross-correlations. Then operation schedule of thermal plants is calculated to integrate PV output using our unit commitment model with the estimated forecast error. The cost for grid integration of PV system was also estimated. Finally, validity of the concept of local production for local consumption of renewable energy and alternative policy implications were also discussed.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
