Computation of Daily Global Solar Radiation by Using Decision Tree Algorithm
R. Saranya1, N. Selvam2
1R.Saranya, Electrical and Electronics Engineering, M. Kumarasamy College of Engineering, Karur, (Tamil Nadu), India.
2N. Selvam, Electrical and Electronics Engineering, M. Kumarasamy College of Engineering, Karur, (Tamil Nadu), India.
Manuscript received on 23 March 2019 | Revised Manuscript received on 30 March 2019 | Manuscript published on 30 March 2019 | PP: 1964-1968 | Volume-7 Issue-6, March 2019 | Retrieval Number: F2799037619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Consumption of electricity is increasing day by day, for the of electricity both the renewable and non renewable energy resources is utilized. The renewable energy of production wind, solar and tidal energy is preferred. Among these energy resources solar energy is most commonly used for production of electricity. In solar energy system the prime important parameter is Global Solar Radiation (GSR).While the global solar radiation data’s and its records are not available in many places due to the high cost and maintenance of the corresponding instrument is also quite difficult.The main aim of this work is the Prediction of Solar Radiation by using machine learning algorithm of Decision Tree. Both Classification and prediction of attributes is possible by decision tree. The benefit of this algorithm is, it provides predictive model for the corresponding data with the tree structure. MATLAB is used for analysis and prediction of solar radiation using 365 data samples. The data is collected from the website of open Government of India and Government of India. The data set is divided into the ratio of 10:90. The ten percent of data is used for testing the data and the remaining ninety percent is used as training data. The different type of error is estimated for the data set.
Keywords: Solar radiation, Decision tree, Standard Deviation, Standard deviation reduction, Predictor Importance, Training data, Testing data.
Scope of the Article: Computational Economics, Digital Photogrammetric