Otwarty dostęp

An Bayesian Learning and Nonlinear Regression Model for Photovoltaic Power Output Forecasting

Wengen Gao

Wengen Gao

Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education, AnHui Polytechnic UniversityChina
Wyszukaj tego autora
Sciendo|Google Scholar
Gao, Wengen
 oraz 
Qigong Chen

Qigong Chen

Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment, Ministry of Education, AnHui Polytechnic UniversityChina
Wyszukaj tego autora
Sciendo|Google Scholar
Chen, Qigong
  
15 wrz 2020
An Bayesian Learning and Nonlinear Regression Model for Photovoltaic Power Output Forecasting's Cover Image
O artykule
Poprzedni artykuł
Następny artykuł
Zacytuj
Pobierz okładkę
Data publikacji: 15 wrz 2020
Zakres stron: 531 - 542
Otrzymano: 24 lut 2020
Przyjęty: 26 maj 2020
DOI: https://doi.org/10.2478/amns.2020.2.00032
Słowa kluczowe
© 2020 Wengen Gao et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Fig. 1

The collected PV power outputs data
The collected PV power outputs data

Fig. 2

The collected Quantized weather data
The collected Quantized weather data

Fig. 3

The forecasting PV power outputs in sunny days
The forecasting PV power outputs in sunny days

Fig. 4

The forecasting PV power outputs in sunny/cloudy days
The forecasting PV power outputs in sunny/cloudy days

Fig. 5

The forecasting PV power outputs in rainy/cloudy days
The forecasting PV power outputs in rainy/cloudy days

The detailed RMSE of three different situations in two regression methods

SituationsSunnySunny/CloudyRainy/Cloudy
RMSE of PR-SBL1.14511.8618.343
RMSE of SVM22.29022.28118.715

Poisson Kernel Regression Based Sparse Bayesian Learning

1: Input the training set {{xitν,Pitν}i=1N}t=1M\left\{{\left\{{x_{it}^\nu,P_{it}^\nu} \right\}_{i = 1}^N} \right\}_{t = 1}^M ;
2: Set the convergence criterion for ω by using the difference between the current estimation and the next estimation;
3: Set η = 1 and the maximum iteration number to be ηmax = 50;
4: Initialize the parameter ω;
5: Initialize the threshold value ωth;
6: Initialize the RVs matrix by setting PRV = P;
7: while Maximum iteration or convergence criteria is reached do
8:   Creating the kernel matrix according to (6);
9:   Calculate the inverse covariance matrix of ω according to (26);
10:   Calculate the mean vector according to (25);
11:   Updating the hyper-paramter as λi(η+1)=1−λi(η)Λi−1μi2{\bf{\lambda}}_i^{\left({\eta + 1} \right)} = {{1 - {\bf{\lambda}}_i^{\left(\eta \right)}{\bf{\Lambda}}_i^{- 1}} \over {{\bf{\mu}}_i^2}} ;
12:   Eliminate the ωi and the samples Pi with ωi > ωth;
13:   Updating kernel matrix by using the eliminated samples;
14: end while
15: Output the estimation of ω and λ
Język:
Angielski
Częstotliwość wydawania:
1 razy w roku
Dziedziny czasopisma:
Nauki biologiczne, Nauki biologiczne, inne, Matematyka, Matematyka stosowana, Matematyka ogólna, Fizyka, Fizyka, inne
Kanał RSS czasopisma