For accuracy limitations in photovoltaic (PV) power prediction due to the intermittent and stochastic nature of PV power generation
this study proposes a short-term PV power prediction model based on spatio-temporal dual-stream networks and multi-attention. The model integrates networks ModernTCN
ITransformer
GRU
and TimesNet networks
effectively exploring the spatial distribution characteristics and temporal dynamics of PV power generation. In addition
the model fuses extracted features
and generates feature vectors rich in Spatio-Temporal information by an iterative cross-attention feature mechanism. Experimental results demonstrate that the model is superior to the current mainstream timing series models in terms of prediction accuracy.
关键词
Keywords
references
KABIR E, KUMAR P, KUMAR S, et al.Solar energy: potential and future prospects[J]. Renewable and sustainable energy reviews, 2018, 82: 894-900.
WANG K J, QI X X, LIU H D.A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network[J]. Applied energy, 2019, 251: 113315.
KRISHNAN N, KUMAR K R, INDA C S.How solar radiation forecasting impacts the utilization of solar energy: a critical review[J]. Journal of cleaner production, 2023, 388: 135860.
FANG B L, XU L, LUO Y J, et al.a method for short-term electric load forecasting based on the FMLP-iTransformer model[J]. Energy reports, 2024, 12: 3405-3411.
ZUO C H, WANG J L, LIU M P, et al.An ensemble framework for short-term load forecasting based on TimesNet and TCN[J]. Energies, 2023, 16(14): 5330.
LUO D H, WANG X. ModernTCN: a modern pure convolution structure for general time series analysis[C]//International Conference on Learning Representations (2024).
YAO D C, TANG B, YANG J W, et al.Patch ModernTCN-Mixer: a dual-task temporal convolutional network framework for hybrid implementation of first prediction time detection and remaining useful life prognosis[J]. Measurement science and technology, 2024, 35(11): 116011.
SHEN J F, CHEN Y F, LIU Y, et al.ICAFusion: Iterative cross-attention guided feature fusion for multispectral object detection[J]. Pattern recognition, 2024, 145: 109913.
XIAO D, MENG Q Y, LI S P, et al.Improving transformers with dynamically composable multi-head attention[C]//International Conference on Machine Learning. 2024.
KHAN Z A, HUSSAIN T, BAIK S W.Dual stream network with attention mechanism for photovoltaic power forecasting[J]. Applied energy, 2023, 338: 120916.