Zhenye Wang
ABSTRACT
Short-term solar radiation prediction plays a crucial role in production and life. There is much room for improvement in the prediction accuracy and stability of traditional models. In order to solve this problem, this paper uses a method based on deep learning to predict solar radiation. A short-term solar radiation prediction model is established for Qinghai Lake combined with a bidirectional long-term memory network and attention mechanism. Based on the historical solar radiation in the past month and the average temperature at 1.5 meters, the solar radiation prediction in the next two weeks is made prediction. The experimental results show that the prediction model combined with the bidirectional long-term memory network and the attention mechanism is superior to the traditional prediction method in predicting accuracy, convergence speed and root mean square error and average absolute error, which can effectively improve. The accuracy and stability of the short-term solar radiation prediction model in local areas.
- Study of Spatio-temporal Variation Characteristics of the Solar Radiation in Growing Season over Northeast China[D]. He Lin, Northeast Normal University, 2013.Google Scholar
- A de La Casiniere A, Bokoye A I, Cabot T. Direct solar spectral irradiance measurem ents and updated simple transmittance models[J]. Journal of Applied Meteorology and Climatolgy, 1997, 36(5):509--520.Google ScholarCross Ref
- Wilks D S, Wilby RL. The weather generation game: a review of stochastic weather models[J]. Progress in Physical Geography, 1999, 23(3):329--357.Google ScholarCross Ref
- Qin J, Chen Z Q, Yang K et al. Estimation of monthly-mean daily global solar radiation based on MODIS and TRMM products[J]. Apply Energy, 2011, 88(7):2480--2489.Google ScholarCross Ref
- Mohandes M, Rehaman S, Halawani TO. Estimation of global solar radiation using artifical nerual networks[J]. Renewable Energy, 1998, 14(1-4):179--184.Google ScholarCross Ref
- Bristow K L, Campbell GS. On the relationship between incoming solar radiation and daily maximum and minmum tempeature[J]. Agricutural and Forecast Meteorolgy, 1984, 31(2):159--166.Google ScholarCross Ref
- Mori H, Takahashi A. A Data Mining Method for Selecting Input Varrables for Forecasting Model of Global Solar Radiation[C]. Transmission and Distribution Conference and Exposition(T&D), 2012 IEEE PES.Google Scholar
- Nomiyama F, Asai J, Murakami T. A Study on Global Solar Radiation Forecasting Models Using Meteorologiacal Data and their Application to Wide Area Forecast[C]. Power System Technology(POWERCON), 2012, IEEE International Conference on, Oct. 30 2012-Nov.2, 2012, 1--6.Google ScholarCross Ref
- Singh V.P, Vijay V, Bhatt M.S, Chaturvedi D.K. Generalized neural network methodology for short term power forecasting[C]. Environment and Electical(EEEEIC) 2013 13th International conference on, 1--3 Nov.2013.Google Scholar
- Trapero J R, Kourentzes N, Martin A. Short-term solar irradiation forecasting based on Dynamic Harmoic Regression[J]. Energy. 2015, 84:289--295.Google ScholarCross Ref
- Chen Changsong, Duan Shanxu, YIN Jinjun. Design of photovoltaic array power generation prediction model based on neural network[J]. Transactions of China Electrotechnical Society, 2009, 24(9): 153--158.Google Scholar
- Fidan M, Hocaoglu F.O, Gerek O.N. Harmonic analysis based hourly solar radiation forecasting model[J]. IET Renewable Power Generation. 2015, 9:218--227.Google ScholarCross Ref
- National Earth System Science Data Sharing Infrastructure, National Science & Technology Infrastructure of China(http://www.geodata.cn)Google Scholar
- Jianyong Wang, Lei Zhang, Quan Guo, et al. Recurrent Neural Networks With Auxiliary Memory Units[C]. IEEE Transactions on Neural Network and Learning System. Vol:29, issue:5, pages:1652--1661, 2018.Google Scholar
- SCHUSTER M, PALIWAL K K. Bidirectional Recurrent Neural Networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11):2673--2681.Google ScholarDigital Library
- Study on relationship classification by Bi-LSTM cyclic neural network combined with attention mechanism [D]. Xing Jiliang, Jilin University, 2018.Google Scholar
- Peng Zhou, Wei Shi, Jun Tian, et al. Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification[C]. //Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2016:207--212.Google Scholar
- Guo Guancheng, Liu Shuming, Li Junxi et al. Research on water quantity prediction method based on two-way long-term neural network[J]. Computer Technology, 2018, 44(3): 123--126.Google Scholar
- Xiangyun Qing, Yugang Niu. Hourly day-ahead solar irradiance prediction using weather forecast by LSTM[J]. Energy, vol:148, 1 April 2018, Pages:461--468.Google Scholar
- Siamak Mehrkanoon. Deep shared representation learning for weather elements forecasting[J]. Knowledge-Based Systems, 2019.Google Scholar
- Jan Scheffel, Kristoffer Lindvall, Hiu Fai Yik. A time-spectral approach to numberical weather prediction[J]. Computer Physics Communications, Volume 226, May 2018, Pages:127--135.Google ScholarCross Ref
- Luis Felipe Costa Sperb, Ming-Chien Sung, Johnnie E.V, et al. Keeping a weather eye on prediction markets: The influences of environmental conditions on forecasting accuracy[J]. International Journal of Forecasting, Volume 35, Issue 1, 2019, Pages:321--335.Google ScholarCross Ref
Index Terms
- Prediction of Solar Radiation in Qinghai Lake Area Based on BiLSTM-Attention Method
Recommendations
Prediction of Short-term Precipitation in Qinghai Lake Based on BiLSTM-Attention Method
ICCPR '19: Proceedings of the 2019 8th International Conference on Computing and Pattern RecognitionThe short-term precipitation forecast plays a crucial role in production and life. The prediction accuracy and stability of the traditional model have a large room for improvement. In order to improve this problem, this paper attempts to establish a ...
Solar radiation prediction using statistical approaches
ICICS'09: Proceedings of the 7th international conference on Information, communications and signal processingStatistical approach is often used in time series analysis. One of its uses is to predict the future trend of a time series. This can be applied in many applications such as solar radiation, economics and other researches related to time series. In this ...
Research on Apparel Trend Prediction Based on CNN-BiLSTM-Attention Model
AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern RecognitionThe existing methods for forecasting clothing trends mostly use traditional time series forecasting methods, and the data sources are mostly sale data from e-commerce websites, which have large errors in forecasting accuracy. This paper proposes a new ...
Comments