A Novel Approach for Wind Speed Forecasting Using LSTM-ARIMA Deep Learning Models

A Novel Approach for Wind Speed Forecasting Using LSTM-ARIMA Deep Learning Models

Vikram Bali (JSS Academy of Technical Education, Noida, India), Ajay Kumar (JSS Academy of Technical Education, Noida, India) and Satyam Gangwar (JSS Academy of Technical Education, Noida, India)
DOI: 10.4018/IJAEIS.2020070102


The term which is used to predict wind speed to produce wind power is wind speed forecasting. Deep learning, is a form of AI, basically indulging in artificial intelligence and thus can greatly increase the precision rate on larger datasets. In this research paper, the two techniques are being used together to obtain the better forecasting results. Both the techniques are forecasting based and combining LSTM and deep learning can increase the forecast rate because of the pattern remembering attribute of LSTM over a longer interval/period of time. If there is the inclusion of the ARIMA model the likelihood of a future value lying between two indicated limits is increased. So, overall if both the techniques are hybridized than it is most probable that the obtained results should be more accurate than both the techniques used separately. So, the main focus of this research article is on the efficiency and evaluation of hybridized LSTM-ARIMA model to predict wind speed forecasting.
Article Preview


Nowadays, the extensive use of non-renewable resources has become a major problem, as these resources are present in limited quantity and it’s a need of time to save them for the future generation and certain measures must be taken for this purpose. Due to extensively availability of wind and low operating cost makes it the perfect natural resource that can utilize for the development of alternative source for the production of power so the better estimating will situate wind for better development and entrance into the worldwide vitality blend.

Motivation Behind the Research Work

The main motive of this research work is to find the alternative energy resources to meet up the need of time i.e. to save the energy resources for future generation. As we know that the natural resources are declining too fast, so as to save them, we have to take certain steps to use them for longer duration. Also maximum use of fossil fuels is polluting the environment, so the development of alternative energy resource is compulsory for the betterment of the earth but also development of these types of models in the modern era has become a basic need, as the traditional models are not quite up to the mark in terms of accuracy and costs.

Importance of Wind Prediction

As the energy demand is increasing quite rapidly and in contrary to it energy resources available at present is in less quantity, so as to overcome such problem, this type of alternative resources are used to kept consideration to meet the need of resource requirement. Since wind is renewable form of energy and is present everywhere, therefore can be utilized for the power production. The availability of wind is everywhere and free of cost which can be used as a proper tool to generate the power in useful manner (Wang, J. et al., 2017). Projecting wind speed is wind power estimation, and this is useful in energy epoch. And it is also performed to maintain the gap between energy usage and power generation. Also, the power generated from the wind energy is having low operating cost and thus help the users to use that power at a quite reasonable cost and thus results in providing power in the electricity prone area. This step can enhance the power production at a quite reasonable cost, and it will end up the balancing of the power production and power usage.

Complete Article List

Search this Journal:
Open Access Articles
Volume 12: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 2 Issues (2012)
Volume 2: 2 Issues (2011)
Volume 1: 2 Issues (2010)
View Complete Journal Contents Listing