PV Plant Power Nowcasting: A Real Case Comparative Study With an Open Access Dataset

Leva, Sonia; Nespoli, Alfredo; Pretto, Silvia; Mussetta, Marco; Ogliari, Emanuele

doi:10.1109/access.2020.3031439

Cited by 21 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As compared to the benchmark model, an 8% improvement was obtained. Furthermore, to evaluate the MAE's improvement of the proposed method compared to the single, combinations of fewer singles via RNN ensemble, and benchmark method, Equations ( 22) and ( 23) are used below [52,53]:…”

Section: Performance Of the Proposed Ensemble Modelmentioning

confidence: 99%

Stacking Ensemble Method with the RNN Meta-Learner for Short-Term PV Power Forecasting

et al. 2021

View full text Add to dashboard Cite

Photovoltaic (PV) power forecasting urges in economic and secure operations of power systems. To avoid an inaccurate individual forecasting model, we propose an approach for a one-day to three-day ahead PV power hourly forecasting based on the stacking ensemble model with a recurrent neural network (RNN) as a meta-learner. The proposed approach is built by using real weather data and forecasted weather data in the training and testing stages, respectively. To accommodate uncertain weather, a daily clustering method based on statistical features, e.g., daily average, maximum, and standard deviation of PV power is applied in the data sets. Historical PV power output and weather data are used to train and test the model. The single learner considered in this research are artificial neural network, deep neural network, support vector regressions, long short-term memory, and convolutional neural network. Then, RNN is used to combine the forecasting results of each single learner. It is also important to observe the best combination of the single learners in this paper. Furthermore, to compare the performance of the proposed method, a random forest ensemble instead of RNN is used as a benchmark for comparison. Mean relative error (MRE) and mean absolute error (MAE) are used as criteria to validate the accuracy of different forecasting models. The MRE of the proposed RNN ensemble learner model is 4.29%, which has significant improvements by about 7–40%, 7–30%, and 8% compared to the single models, the combinations of fewer single learners, and the benchmark method, respectively. The results show that the proposed method is promising for use in real PV power forecasting systems.

show abstract

Section: Performance Of the Proposed Ensemble Modelmentioning

confidence: 99%

Stacking Ensemble Method with the RNN Meta-Learner for Short-Term PV Power Forecasting

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Following the prediction provided by the 24 h ahead methodology, some improvements can be performed thanks to the information collected during the plant operation: new data regarding the production of the plant and the actual measurements of environmental parameters can be beneficial to increase the model accuracy. In particular, as demonstrated in [35], they allow increasing the accuracy of the prediction of the following 3 h. Hence, this procedure is iteratively performed every hour and given the current time t, the refinement P f ,t+h is provided for the following 3 h (h ∈ [1, 2,3]).…”

Section: Intradaymentioning

confidence: 99%

“…As previously explained, the radiation level and hence the PV production depends on two main factors, the first one deterministic while the second one is purely stochastic. The formulation proposed in [35] addresses the first one, rewriting Equation (1) to the following:…”

Section: Nowcastingmentioning

confidence: 99%

Implementation of Different PV Forecast Approaches in a MultiGood MicroGrid: Modeling and Experimental Results

et al. 2021

Self Cite

View full text Add to dashboard Cite

Microgrids represent a flexible way to integrate renewable energy sources with programmable generators and storage systems. In this regard, a synergic integration of those sources is crucial to minimize the operating cost of the microgrid by efficient storage management and generation scheduling. The forecasts of renewable generation can be used to attain optimal management of the controllable units by predictive optimization algorithms. This paper introduces the implementation of a two-layer hierarchical energy management system for islanded photovoltaic microgrids. The first layer evaluates the optimal unit commitment, according to the photovoltaic forecasts, while the second layer deals with the power-sharing in real time, following as close as possible the daily schedule provided by the upper layer while balancing the forecast errors. The energy management system is experimentally tested at the Multi-Good MicroGrid Laboratory under three different photovoltaic forecast models: (i) day-ahead model, (ii) intraday corrections and (iii) nowcasting technique. The experimental study demonstrates the capability of the proposed management system to operate an islanded microgrid in safe conditions, even with inaccurate day-ahead photovoltaic forecasts.

show abstract

“…The input is organized by the methods in the literature, including encoding and vector form. • Nowcasting A strategy to update day-ahead forecasting employing nowcasting as presented in [15] is adopted. The refinement provides for forecasting of the following 3 h. However, because of its weak correlation with the load, the irradiation is deleted.…”

Section: Benchmarksmentioning

confidence: 99%

Online refinement of day‐ahead forecasting using intraday data for campus‐level load

Yang

Geng

et al. 2021

IET Generation Trans & Dist

View full text Add to dashboard Cite

Day-ahead forecasting for campus-level load is important for better energy management, but especially difficult to be accurate, compared to large-scale loads such as cities or regions. This is because irregular and unpredictable behavior of individual loads in small-scale loads cannot be fully smoothed out and thus pose a negative impact on forecasting accuracy. This paper presents an online refinement strategy for day-ahead forecasting using intraday data for a campus-level load, focusing on self-adapting correction of forecasting considering load pattern. First, according to the load pattern forecasted by Classification and Regression Trees (CART) one day ahead, the correction parameter group is assigned to the correction model. If the correction conditions are met, the forecasting results for the rest of the day will be updated. After all-day load data is achieved, the actual load pattern can be identified and used to train CART model. To confirm the effectiveness of the proposed strategy, the model is evaluated by two datasets, a real-life dataset of an industrial park in Shanghai China and a public dataset of an institute campus in Delhi, India. The results demonstrate that the proposed strategy can improve short-term forecasting accuracy.

show abstract

PV Plant Power Nowcasting: A Real Case Comparative Study With an Open Access Dataset

Cited by 21 publications

References 35 publications

Stacking Ensemble Method with the RNN Meta-Learner for Short-Term PV Power Forecasting

Stacking Ensemble Method with the RNN Meta-Learner for Short-Term PV Power Forecasting

Implementation of Different PV Forecast Approaches in a MultiGood MicroGrid: Modeling and Experimental Results

Online refinement of day‐ahead forecasting using intraday data for campus‐level load

Contact Info

Product

Resources

About