Abstract
A Kalman filter photovoltaic (PV) power prediction model based on forecasting experience is proposed to solve the problem that the accuracy of the prediction method based on historical experience is reduced under anomalous situations. This study uses the hourly solar irradiance forecasting model, numerical weather prediction (NWP) data, and the photoelectric conversion model to calculate the ground irradiance and PV power generation, which are used as the forecasting experience data. The dynamic equation of the Kalman filter model is obtained by fitting the forecasting data to make the prediction model with the future situation information properties while solving the modeling difficulties caused by the transcendental equation characteristic of the photoelectric conversion model. In the iterative process of the Kalman filter algorithm, the measured power is used to correct the prediction error and significantly limit the error variability so as to realize the ultra-short-term accurate prediction of PV power and ultimately improve the management of PV energy storage power stations. The comparative analysis through DKASC data simulation verifies that the results show that the proposed model is effective and can achieve better results in predictive accuracy.
Highlights
In recent years, fossil energy is becoming increasingly depleted worldwide
Different from the existing literature based on historical experience, this study considers solar irradiance as the system state variable and PV power generation as the system observation, uses the aforementioned model results as forecasting experience data to fit the observation equation of the prediction model, and introduces the excitation noise as the control equation input quantity to determine the system differential control equation
A Kalman filter PV power prediction model based on forecasting experience is proposed
Summary
Fossil energy is becoming increasingly depleted worldwide. In order to alleviate the energy crisis and reduce environmental pollution, solar energy has been widely developed and applied as a green and environmentally friendly renewable energy source. This article presents a Kalman filter PV power prediction model based on the hourly solar irradiance model and NWP data. Different from the existing literature based on historical experience, this study considers solar irradiance as the system state variable and PV power generation as the system observation, uses the aforementioned model results as forecasting experience data to fit the observation equation of the prediction model, and introduces the excitation noise as the control equation input quantity to determine the system differential control equation. The forecasting window is updated in real time based on the NWP data of the cloud to achieve the goal of sampling and fitting prediction each hour, making the Kalman filter algorithm meet the criteria of being dynamic and flexible yet reliable. The training data set of the DBN model during prediction is 8,640 sets of data in 30 days, while the Kalman filter model uses real-time prediction, which requires the amount of data such as future weather forecasting and does not require a large amount of historical data
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
