Cloud motion tracking for short-term on-site cloud coverage prediction

Solar Energy is the feedstock for various applications of renewable energy sources; thus, the knowledge of the intensity of the incident solar irradiance is essential for monitoring the performance of such systems. The major unpredictable factor in defining the solar irradiance and the performance of solar systems is the presence of clouds in the sky. So far, various researchers proposed several models to correlate solar irradiance to cloud coverage and cloud type. The present work describes the development of a simple method for cloud detection and computation of short-term cloud motion. The minimum accuracy of the model was 95% for the prediction of the cloud location seven timesteps in advance with only three cloud images processed. When including the dimensions of the cloud to the accuracy calculation, the minimum accuracy was 88%.

Download Full-text

Comparison of Algorithms for Short-term Cloud Coverage Prediction

2018 IX National Conference with International Participation (ELECTRONICA) ◽

10.1109/electronica.2018.8439356 ◽

2018 ◽

Author(s):

Stefan Hensel ◽

Marin B. Marinov

Keyword(s):

Short Term ◽

Cloud Coverage ◽

Comparison Of Algorithms ◽

Coverage Prediction

Download Full-text

Sky Image-Based Localized, Short-Term Solar Irradiance Forecasting for Multiple PV Sites via Cloud Motion Tracking

International Journal of Photoenergy ◽

10.1155/2021/9973010 ◽

2021 ◽

Vol 2021 ◽

pp. 1-27

Author(s):

Lasanthika H. Dissawa ◽

Roshan I. Godaliyadda ◽

Parakrama B. Ekanayake ◽

Ashish P. Agalgaonkar ◽

Duane Robinson ◽

...

Keyword(s):

Motion Tracking ◽

Ground Level ◽

Forecasting Model ◽

Time Interval ◽

Solar Pv ◽

Short Term ◽

Forecasting Accuracy ◽

Cloud Motion ◽

The Individual ◽

Operational Issues

Power generation through solar photovoltaics has shown significant growth in recent years. However, high penetration of solar PV creates power system operational issues as a result of solar PV variability and uncertainty. Short-term PV variability mainly occurs due to the intermittency of cloud cover. Therefore, to mitigate the effects of PV variability, a sky-image-based, localized, global horizontal irradiance forecasting model was introduced considering the individual cloud motion, cloud thicknesses, and the elevations of clouds above the ground level. The proposed forecasting model works independently of any historical irradiance measurements. Two inexpensive sky camera systems were developed and placed in two different locations to obtain sky images for cloud tracking and cloud-based heights. Then, irradiance values for onsite and for a PV site located with a distance of 2 km from the main camera were forecasted for 1 minute, 5 minutes, and 15 minutes ahead of real-time. Results show that the three-level cloud categorization and the individual cloud movement tracking method introduced in this paper increase the forecasting accuracy. For partially cloudy and sunny days, the forecasting model for 15 min forecasting time interval achieved a positive skill factor concerning the persistent model. The accuracy of determining the correct irradiance state for a 1 min forecasting time interval using the proposed model is 81%. The average measures of RMSE, MAE, and SF obtained using the proposed method for 15 min forecasting time horizon are 101 Wm-2, 64 Wm-2, and 0.26, respectively. These forecasting accuracy levels are much higher than the other benchmarks considered in this paper.

Download Full-text

Sky Image forecasting with Generative Adversarial Networks for cloud coverage prediction

2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA) ◽

10.1109/iisa.2019.8900774 ◽

2019 ◽

Author(s):

George Andrianakos ◽

Dimitrios Tsourounis ◽

Spiros Oikonomou ◽

Dimitris Kastaniotis ◽

George Economou ◽

...

Keyword(s):

Generative Adversarial Networks ◽

Cloud Coverage ◽

Adversarial Networks ◽

Coverage Prediction

Download Full-text

An On-Line Low-Cost Irradiance Monitoring Network with Sub-Second Sampling Adapted to Small-Scale PV Systems

Sensors ◽

10.3390/s18103405 ◽

2018 ◽

Vol 18 (10) ◽

pp. 3405 ◽

Cited By ~ 6

Author(s):

Manuel Espinosa-Gavira ◽

Agustín Agüera-Pérez ◽

Juan González de la Rosa ◽

José Palomares-Salas ◽

José Sierra-Fernández

Keyword(s):

Sensor Networks ◽

Low Cost ◽

Monitoring Network ◽

Absolute Error ◽

Small Scale ◽

Photovoltaic Systems ◽

Real Time Control ◽

Short Term ◽

Time Control ◽

Cloud Motion

Very short-term solar forecasts are gaining interest for their application on real-time control of photovoltaic systems. These forecasts are intimately related to the cloud motion that produce variations of the irradiance field on scales of seconds and meters, thus particularly impacting in small photovoltaic systems. Very short-term forecast models must be supported by updated information of the local irradiance field, and solar sensor networks are positioning as the more direct way to obtain these data. The development of solar sensor networks adapted to small-scale systems as microgrids is subject to specific requirements: high updating frequency, high density of measurement points and low investment. This paper proposes a wireless sensor network able to provide snapshots of the irradiance field with an updating frequency of 2 Hz. The network comprised 16 motes regularly distributed over an area of 15 m × 15 m (4 motes × 4 motes, minimum intersensor distance of 5 m). The irradiance values were estimated from illuminance measurements acquired by lux-meters in the network motes. The estimated irradiances were validated with measurements of a secondary standard pyranometer obtaining a mean absolute error of 24.4 W/m 2 and a standard deviation of 36.1 W/m 2 . The network was able to capture the cloud motion and the main features of the irradiance field even with the reduced dimensions of the monitoring area. These results and the low-cost of the measurement devices indicate that this concept of solar sensor networks would be appropriate not only for photovoltaic plants in the range of MW, but also for smaller systems such as the ones installed in microgrids.

Download Full-text

Prediction of Solar Power Using Near-Real Time Satellite Data

Energies ◽

10.3390/en14185865 ◽

2021 ◽

Vol 14 (18) ◽

pp. 5865

Author(s):

Abhnil Amtesh Prasad ◽

Merlinde Kay

Keyword(s):

Real Time ◽

Satellite Data ◽

Solar Power ◽

Short Term ◽

Motion Vectors ◽

Clear Sky ◽

Cloud Motion ◽

Visible Images ◽

Grid Operators ◽

Short Term Prediction

Solar energy production is affected by the attenuation of incoming irradiance from underlying clouds. Often, improvements in the short-term predictability of irradiance using satellite irradiance models can assist grid operators in managing intermittent solar-generated electricity. In this paper, we develop and test a satellite irradiance model with short-term prediction capabilities using cloud motion vectors. Near-real time visible images from Himawari-8 satellite are used to derive cloud motion vectors using optical flow estimation techniques. The cloud motion vectors are used for the advection of pixels at future time horizons for predictions of irradiance at the surface. Firstly, the pixels are converted to cloud index using the historical satellite data accounting for clear, cloudy and cloud shadow pixels. Secondly, the cloud index is mapped to the clear sky index using a historical fitting function from the respective sites. Thirdly, the predicated all-sky irradiance is derived by scaling the clear sky irradiance with a clear sky index. Finally, a power conversion model trained at each site converts irradiance to power. The prediction of solar power tested at four sites in Australia using a one-month benchmark period with 5 min ahead prediction showed that errors were less than 10% at almost 34–60% of predicted times, decreasing to 18–26% of times under live predictions, but it outperformed persistence by >50% of the days with errors <10% for all sites. Results show that increased latency in satellite images and errors resulting from the conversion of cloud index to irradiance and power can significantly affect the forecasts.

Download Full-text