Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants

Luo，Xing1,2; Zhang，Dongxiao1,3; Zhu，Xu2,4

2022-02-01

10.1016/j.renene.2021.12.104

RENEWABLE ENERGY   影响因子和分区

0960-1481

1879-0682

Photovoltaic power generation (PVPG) forecasting has attracted increasing research and industry attention due to its significance for energy management, infrastructure planning, and budgeting. Emerging deep learning (DL) models based on historical data have provided effective solutions for PVPG forecasting with great success. However, newly-constructed photovoltaic (NCPV) plants often lack collections of historical data, and thus it is difficult to forecast their future generation accurately. In this work, combining transfer learning (TL) and DL models, we initially propose two parameter-transferring strategies and a constrained long short-term memory (C-LSTM) model, to address the hourly day-ahead PVPG forecasting problem of NCPV plants. The K-nearest neighbors (KNN) algorithm is utilized to extract prior knowledge as physical constraints, which can guide the training process of C-LSTM. The performances of different TL methods combined with C-LSTM are evaluated specifically, and appropriate ones are determined accordingly. The proposed models are evaluated based on real-life datasets collected from actual PV plants in Australia. The results demonstrate that the proposed C-LSTM model outperforms the standard LSTM model with higher forecasting accuracy. In addition, the results also indicate that significant improvements in forecasting accuracy and stability can be obtained by the proposed TL strategies combined with C-LSTM, regardless of different sky conditions (i.e., clear sky, partly cloudy sky, and overcast sky), compared to the conventional machine learning and statistical models in the literature. The forecasting skill of the combined model has improved up to 68.4% compared with the reference persistence model.

Constrained LSTM Newly-constructed PV plant Power generation Transfer learning

SCI ; EI

英语

通讯

Science & Technology - Other Topics ; Energy & Fuels

Green & Sustainable Science & Technology ; Energy & Fuels

WOS:000778562500001

PERGAMON-ELSEVIER SCIENCE LTD

20220111428768

Brain ; Budget control ; Forecasting ; Industrial research ; Nearest neighbor search ; Solar energy

Biomedical Engineering:461.1 ; Solar Energy and Phenomena:657.1 ; Engineering Research:901.3 ; Industrial Engineering:912.1 ; Optimization Techniques:921.5

ENGINEERING

2-s2.0-85122161751

Scopus

1.Intelligent Energy Lab,Peng Cheng Laboratory,Shenzhen,518 055,China
2.School of Electronic and Information Engineering,Harbin Institute of Technology,Shenzhen,518 055,China
3.School of Environmental Science and Engineering,Southern University of Science and Technology,Shenzhen,518 055,China
4.Department of Electrical Engineering and Electronics,University of Liverpool,Liverpool,L69 3GJ,United Kingdom

Luo，Xing,Zhang，Dongxiao,Zhu，Xu. Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants[J]. RENEWABLE ENERGY,2022,185:1062-1077.

Luo，Xing,Zhang，Dongxiao,&Zhu，Xu.(2022).Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants.RENEWABLE ENERGY,185,1062-1077.

Luo，Xing,et al."Combining transfer learning and constrained long short-term memory for power generation forecasting of newly-constructed photovoltaic plants".RENEWABLE ENERGY 185(2022):1062-1077.