Journal of Chinese Society of Power Engineering
|
2026, 46(1): 77-84,102
Short-term Prediction of PV Power Based on BSimilar Optimized PTransformer
Full
Affiliations
Published: 2026-01-15
doi: 10.19805/j.cnki.jcspe.2026.240722
Outline
To enhance the accuracy of short-term photovoltaic power forecasting, a segmented multi-channel independent short-term photovoltaic power prediction method optimized by a similar day algorithm with consideration of photovoltaic equipment performance degradation factors was proposed. Firstly, the photovoltaic input data were processed in PTransformer model with time period and channel independent methods to reduce the spatial complexity and improve the attention of long-term data series. Secondly, the encoder model of Transformer was applied to capture the dependencies between photovoltaic sequence features through its own attention mechanism for short-term photovoltaic power prediction. Finally, the PTransformer model was optimized using its power data to improve the lag of the power data by applying the angle cosine distance to calculate the similarity and considering the performance degradation factors of the photovoltaic equipment to determine the similar day. Results show that compared with typical short-term photovoltaic power prediction method, the proposed method has faster training speed, higher prediction accuracy and better prediction results for photovoltaic power under complex weather conditions.
photovoltaic power
/
short-term forecast
/
performance degradation
/
Bayesian analysis
/
Transformer
/
similar day
.
基于BSimilar优化PTransformer的光伏功率短期预测.
动力工程学报,
2026
, 46
(1)
: 77
-84,102
.
DOI: 10.19805/j.cnki.jcspe.2026.240722
.
Short-term Prediction of PV Power Based on BSimilar Optimized PTransformer[J].
Journal of Chinese Society of Power Engineering,
2026
, 46
(1)
: 77
-84,102
.
DOI: 10.19805/j.cnki.jcspe.2026.240722
Year 2026 volume 46 Issue 1
79
22
Cite this Article
BibTeX
Article Info
doi: 10.19805/j.cnki.jcspe.2026.240722
- Receive Date:2024-11-19
- Online Date:2026-11-05
- Published:2026-01-15