Post-Processing of NWP Forecasts Using Kalman Filtering With Operational Constraints for Day-Ahead Solar Power Forecasting in Thailand

被引：7
|
作者：
Suksamosorn, Supachai [1 ]
Hoonchareon, Naebboon [1 ]
Songsiri, Jitkomut [1 ]
机构：
[1] Chulalongkorn Univ, Smart Grid Res Unit, Fac Engn, Dept Elect Engn, Bangkok 10330, Thailand
来源：
IEEE ACCESS | 2021年 / 9卷
关键词：
Predictive models; Forecasting; Weather forecasting; Mathematical model; Atmospheric modeling; Data models; Adaptation models; Solar irradiance forecasting; numerical weather prediction; WRF; Kalman filter; model output statistics; NUMERICAL WEATHER PREDICTION; IRRADIANCE FORECASTS; NEURAL-NETWORK; OUTPUT; MODEL; TERM; ENSEMBLE;
D O I：
10.1109/ACCESS.2021.3099481
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Solar power forecasting with a day-ahead horizon has played an important role in the operational planning of generating units in power system operations. We aim to develop a solar power forecasting model suitable for a tropical climate, using Thailand as a model, and hence present a linear recursive regression model as a post-processing step for reducing the errors obtained from the Weather Research and Forecasting (WRF) model. This model consists of submodels, each of which predicts the solar irradiance of a particular time of the day. By using a stepwise regression method, we found that WRF forecasts of irradiance, temperature, relative humidity, and the solar zenith angle were selected as highly relevant inputs of the model. The regression model coefficients are updated according to a Kalman filtering (KF) scheme so that the model can flexibly adapt to fluctuations in the solar irradiance. We then modify the KF update formula to accommodate the limitation in measurement availability at the time of executing the forecasts. The proposed KF formula can be generalized to find the optimal prediction given that the available measurements are mapped by an affine transformation. The obtained results using actual data from a solar rooftop system located in the central region of Thailand showed that the normalized root-mean-square error (NRMSE) of solar power prediction was about 12-13%, which was decreased from the NRMSE of the WRF model by 7-12% on average. This improvement was the best out of similar post-processing methods based on the model output statistics framework.
引用
收藏
页码：105409 / 105423
页数：15
相关论文
共 50 条
  • [21] Day-Ahead Solar Power Forecasting with Pattern Analysis and State Transition
    Hu, Yi-Liang
    2021 IEEE 3RD GLOBAL POWER, ENERGY AND COMMUNICATION CONFERENCE (IEEE GPECOM2021), 2021, : 148 - 153
  • [22] Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM
    Qing, Xiangyun
    Niu, Yugang
    ENERGY, 2018, 148 : 461 - 468
  • [23] Forecasting Day-ahead Solar Radiation Using Machine Learning Approach
    Hassan, M. Z.
    Ali, K. M. E.
    Ali, A. B. M. Shawkat
    Kumar, Jashnil
    2017 4TH ASIA-PACIFIC WORLD CONGRESS ON COMPUTER SCIENCE AND ENGINEERING (APWCONCSE 2017), 2017, : 252 - 258
  • [24] Day-ahead Solar Power Plant Forecasting Accuracy Improvement on the Hourly Basis
    Snegirev, Denis A.
    Eroshenko, Stanislav A.
    Khalyasmaa, Alexandra I.
    Dubailova, Valeria V.
    Stepanova, Alina I.
    PROCEEDINGS OF THE 2019 IEEE CONFERENCE OF RUSSIAN YOUNG RESEARCHERS IN ELECTRICAL AND ELECTRONIC ENGINEERING (EICONRUS), 2019, : 1088 - 1091
  • [25] A Simplified LSTM Neural Networks for One Day-Ahead Solar Power Forecasting
    Liu, Chun-Hung
    Gu, Jyh-Cherng
    Yang, Ming-Ta
    IEEE ACCESS, 2021, 9 : 17174 - 17195
  • [26] The effect of wind and solar power forecasts on day-ahead and intraday electricity prices in Germany
    Guertler, Marc
    Paulsen, Thomas
    ENERGY ECONOMICS, 2018, 75 : 150 - 162
  • [27] Forecasting of solar power ramp events: A post-processing approach
    Abuella, Mohamed
    Chowdhury, Badrul
    RENEWABLE ENERGY, 2019, 133 : 1380 - 1392
  • [28] Forecasting and uncertainty analysis of day-ahead photovoltaic power using a novel forecasting method
    Gu, Bo
    Shen, Huiqiang
    Lei, Xiaohui
    Hu, Hao
    Liu, Xinyu
    APPLIED ENERGY, 2021, 299
  • [29] Probabilistic forecasting of day-ahead solar irradiance using quantile gradient boosting
    Verbois, Hadrien
    Rusydi, Andrivo
    Thiery, Alexandre
    SOLAR ENERGY, 2018, 173 : 313 - 327
  • [30] Day-ahead forecasting of solar power output from photovoltaic plants in the American Southwest
    Larson, David P.
    Nonnenmacher, Lukas
    Coimbra, Carlos F. M.
    RENEWABLE ENERGY, 2016, 91 : 11 - 20
12345