Short‐term photovoltaic power dynamic weighted combination forecasting based on least squares method

Yang, Ming; Li, Meng

doi:10.1002/tee.22999

Cited by 8 publications

(6 citation statements)

References 27 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The bayesian framework allows to obtain confidence intervals and estimate the error line predicted by the NN, which helps to simplify the network structure and learning process. In [68], researchers adopted the periodic graph method to extract the random component of photovoltaic power and the least square (LS) method to determine the dynamic weight value of each NN. The random component of photovoltaic is predicted through the combined model, and then superimposed it with the periodic component to obtain the final photovoltaic prediction result.…”

Section: ) Single-site Photovoltaic Forecasting Methods Based On Hist...mentioning

confidence: 99%

A Review of Multitemporal and Multispatial Scales Photovoltaic Forecasting Methods

Liu

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Reliable photovoltaic(PV) forecasting can provide important data support for power system operation, which is the key to realize the large-scale consumption of solar energy resources. PV forecasting task becomes crucial to ensure power system stability and economic operation. This paper reviews the existing research of PV forecasting methods from the perspective of multi-temporal scale and multi-spatial scale. Firstly, according to the forecasting process, demand, temporal and spatial scale, the forecasting methods are classified and the evaluation indicators involved in the research are listed. Secondly, based on the temporal scale of PV power generation, the results are combed through the three kind of scale of ultra-short-term, short-term and medium and long-term prediction. Thirdly, on each kind of temporal scale, the results are subdivided into single-site prediction and regional prediction to sort out in detail. Finally, the results are analyzed on the basis of the predicted temporal scale, spatial scale and input data. It has been observed that most recent papers highlight the importance of short-term predictions. The machine learning method shows excellent nonlinear description ability in short-term prediction, the prediction results are satisfactory. The spatial average effect of regional prediction reduces the variability of solar energy, the prediction results are reliable.

show abstract

Section: ) Single-site Photovoltaic Forecasting Methods Based On Hist...mentioning

confidence: 99%

A Review of Multitemporal and Multispatial Scales Photovoltaic Forecasting Methods

Liu

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Therefore, many examples of PV power forecasting can be found in the literature. Taking into account the time horizon of forecasts, they can be divided into very short-term, limited to second and hour forecasts [4], short-term, characteristic for daily forecasts [5], and medium-term, covering weeks or months. Longterm forecasts, in turn, cover years [6].…”

Section: Literature Reviewmentioning

confidence: 99%

Modeling the Photovoltaic Power Generation in Poland in the Light of PEP2040: An Application of Multiple Regression

Rybak,

Kolev

2023

Energies

View full text Add to dashboard Cite

This paper presents the results of research on the development of photovoltaic systems in Poland. The authors’ goal was to identify factors that can potentially shape the dynamics of solar energy development in Poland and that will affect the implementation of the PEP2040 goals. The authors also wanted to find a forecasting method that would enable the introduction of many explanatory variables—a set of identified factors—into the model. After an initial review of the literature, the ARMAX and MLR models were considered. Finally, taking into account MAPE errors, multiple regression was used for the analysis, the error of which was 0.87% (minimum 3% for the ARMAX model). The model was verified based on Doornik–Hansen, Breusch–Pagan, Dickey–Fuller tests, information criteria, and ex post errors. The model indicated that LCOE, CO2 emissions, Cu consumption, primary energy consumption, patents, GDP, and installed capacity should be considered statistically significant. The model also allowed us to determine the nature of the variables. Additionally, the authors wrote the WEKR 2.0 program, which allowed to determine the necessary amount of critical raw materials needed to build the planned PV energy generating capacity. Solar energy in Poland currently covers about 5% of the country’s electricity demand. The pace of development of photovoltaic installations has exceeded current expectations and forecasts included in the Polish Energy Policy until 2040 (PEP2040). The built model showed that if the explanatory variables introduced into the model continue to be subject to the same trends shaping them, a dynamic increase in photovoltaic energy production should be expected by 2025. The model indicates that the PEP2040 goal of increasing the installed capacity to 16 GW by 2040 can be achieved already in 2025, where the PV production volume could reach 8921 GWh. Models were also made taking into account individual critical raw materials such as Cu, Si, Ge, and Ga. Each of them showed statistical significance, which means that access to critical raw materials in the future will have a significant impact on the further development of photovoltaic installations.

show abstract

“…The data-driven ensemble model can be applied to situations where a large amount of data needs to be processed and performs better than the other forecasting techniques. In [16], a model called short-term PV power dynamic weighted combination forecasting based on the least squares (LS) model is proposed. This model is superior to other single models in forecasting PV power.…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Model for Short-term PV Output Forecasting Based on PCA-GWO-GRNN

Xian

Yan

et al. 2020

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

High-precision day-ahead short-term photovoltaic (PV) output forecasting is essential in PV integration to the smart distribution networks and multi-energy system, and provides the foundation for the security, stability, and economic operation of PV systems. This paper proposes a hybrid model based on principal component analysis, grey wolf optimization and generalized regression neural network (PCA-GWO-GRNN) for day-ahead short-term PV output forecasting, considering the features of multiple influencing factors and strong uncertainty. This paper first uses the PCA to reduce the dimension of meteorological features. Then, the high-precision day-ahead short-term PV output forecasting based on GWO-GRNN model is realized. GRNN is used to regressively analyze the input features after dimension reduction, and the parameter of GRNN is optimized by using GWO, which has strong global searching ability and fast convergence. The proposed PCA-GWO-GRNN model effectively achieves a high precision in day-ahead shortterm PV output forecasting, which is demonstrated in a case study on a real PV plant in Jiangsu province, China. The results have validated the accuracy and applicability of the proposed model in real scenarios. Index Terms-Photovoltaic output forecasting, principal component analysis (PCA), grey wolf optimization (GWO), generalized regression neural network (GRNN).

show abstract

Short‐term photovoltaic power dynamic weighted combination forecasting based on least squares method

Cited by 8 publications

References 27 publications

A Review of Multitemporal and Multispatial Scales Photovoltaic Forecasting Methods

A Review of Multitemporal and Multispatial Scales Photovoltaic Forecasting Methods

Modeling the Photovoltaic Power Generation in Poland in the Light of PEP2040: An Application of Multiple Regression

A Hybrid Model for Short-term PV Output Forecasting Based on PCA-GWO-GRNN

Contact Info

Product

Resources

About