An Industrial Photovoltaic Prediction Model Based on Probabilistic Sparse Attention Mechanism of Temporal Convolution Network

DOI

10.2991/978-94-6463-570-6_131How to use a DOI?

Keywords

multiple universe optimizer; photovoltaic; signal decomposition

Abstract

This paper presents an advanced predictive model, termed C-PASST, which synergizes signal decomposition, sophisticated deep learning algorithms, and cutting-edge optimization techniques to enhance the accuracy of short-term power forecasts for photovoltaic systems. The process commences with the dissection of original photovoltaic data sequences through a comprehensive empirical modal decomposition method augmented by adaptive noise (C-DAN), adept at distilling temporal characteristics through a probabilistic sparse self-attention framework. Following this, the refined photovoltaic sequences are entrusted to specialized temporal convolutional networks (TCN) for prognostication. In the final stage, an innovative multiple universe optimizer (MVO) approach, informed by the principles of NNCT, is harnessed to integrate weight coefficients derived from the TCN models, culminating in the reconstruction of the ultimate forecasting outcomes.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Na Zhang
AU  - Shichang Lu
PY  - 2024
DA  - 2024/11/22
TI  - An Industrial Photovoltaic Prediction Model Based on Probabilistic Sparse Attention Mechanism of Temporal Convolution Network
BT  - Proceedings of the 2024 5th International Conference on Management Science and Engineering Management (ICMSEM 2024)
PB  - Atlantis Press
SP  - 1309
EP  - 1315
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-570-6_131
DO  - 10.2991/978-94-6463-570-6_131
ID  - Zhang2024
ER  -