|
Clustering Model For Solar Irradiation Prediction Using Machine Learning Algorithm
[Full Text]
AUTHOR(S)
Prachi Sharma, Dr.Megha Kamble
KEYWORDS
Solar irradiance, machine learning, neural networkprediction,estimation
ABSTRACT
With every year the sources of energy are getting reduced and requirement of energy in increasing every year worldwide. Solar irradiance is renewable source of energy provided by sun naturally. So the research community is also proposing methods to convert solar radiance into energy and use it in place of depleting non-renewable source of energy. In need to understand from where this sun energy can be obtained in huge amount, it is necessary to predict the collection of energy for particular place. Solar irradiance varies with meteorological data longitude, latitude, wind speed and change of weather at different areas. Machine learning is a popular set of techniques to predict solar irradiance using weather forecasting data such as wind speed, wind direction and many such parameters in the day span. This is a survey paper which contains the review of previous work done such as ANN, SVM, NN in the field of predicting solar irradiance using weather data parameters in the different parts of world. This paper will help in understanding the use of different machine learning techniques for predicting solar irradiance and also provide future direction to retain renewable energy source like solar energy. A comparative analysis of different techniques is done using output parameters RSME ,MSE,MAE,MAPE and stated the future direction in this research article.
REFERENCES
[1] Qing, X., & Niu, Y. (2018). Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy, 148, 461-468
[2] Voyant, C., Notton, G., Kalogirou, S., Nivet, M. L., Paoli, C., Motte, F., & Fouilloy, A. (2017). Machine learning methods for solar radiation forecasting: A review. Renewable Energy, 105, 569-582.
[3] Mubiru, J. (2008). Predicting total solar irradiation values using artificial neural networks. Renewable Energy, 33(10), 2329-2332..
[4] Yacef, R., Benghanem, M., & Mellit, A. (2012). Prediction of daily global solar irradiation data using Bayesian neural network: A comparative study. Renewable energy, 48, 146-154.
[5] Tanaka, Y., & Takahashi, M. (2017). SVM-based Multi-point Prediction System of Solar Irradiance using DTW-based Cluster Analysis. Transactions of the Institute of Systems, Control and Information Engineers, 30(8), 305-313..
|
