Deep learning-based multi-step solar forecasting for PV ramp-rate control using sky images

Wen, Haoran, Du, Yang, Chen, Xiaoyang, Lim, Enggee, Wen, Huiqing, Jiang, Lin, and Xiang, Wei (2021) Deep learning-based multi-step solar forecasting for PV ramp-rate control using sky images. IEEE Transactions on Industrial Informatics, 17 (2). pp. 1397-1406.

[img] PDF (Accepted Publisher Version) - Accepted Version
Restricted to Repository staff only

View at Publisher Website:


Solar forecasting is one of the most promising approaches to address the intermit PV power generation by providing predictions before upcoming ramp events. In this paper, a novel multi-step forecasting (MSF) scheme is proposed for PV power ramp-rate control (PRRC). This method utilizes an ensemble of deep ConvNets without additional time-series models and exogenous variables, thus more suitable for industrial applications. The MSF strategy can make multiple predictions in comparison with a single forecasting point produced by a conventional method while maintaining the same high temporal resolution. Besides, stacked sky images that integrate temporal-spatial (ST) information of cloud motions are used to further improve the forecasting performance. The results demonstrate a favorable forecasting accuracy in comparison to the existing forecasting models with the highest skill score of 17.7%. In the PRRC application, the MSF-based PRRC can detect more ramp-rates violations with a higher control rate of 98.9% compared with the conventional forecasting based control. Thus, the PV generation can be effectively smoothed with less energy curtailment on both clear and cloudy days using the proposed approach.

Item ID: 62859
Item Type: Article (Research - C1)
ISSN: 1941-0050
Copyright Information: (c) 2020 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission
Funders: Jiangsu Science and Technology Programme (JSTP), National Natural Science Foundation of China (NNSFC)
Projects and Grants: JSTP 10.13039/501100001809, NNSFC Research development fund of XJTLU, NNSFC Key Program Special Fund in XJTLU
Date Deposited: 02 Sep 2020 03:33
FoR Codes: 40 ENGINEERING > 4008 Electrical engineering > 400803 Electrical energy generation (incl. renewables, excl. photovoltaics) @ 60%
46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461102 Context learning @ 40%
SEO Codes: 85 ENERGY > 8505 Renewable Energy > 850504 Solar-Photovoltaic Energy @ 100%
Downloads: Total: 4
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page