Implementing Machine Learning – Artificial Intelligence for Optimizing Solar PV with Conventional Grid
Arpita De1, Anoop Kumar De2

1Arpita De*, Energy Centre, Maulana Azad National Institute of Technology (MANIT), Bhopal, India.
2Anoop Kumar De, Data Analytics, Genpact, Texas, USA.
Manuscript received on March 02, 2020. | Revised Manuscript received on March 21, 2020. | Manuscript published on March 30, 2020. | PP: 2992-2998 | Volume-8 Issue-6, March 2020. | Retrieval Number: F8451038620/2020©BEIESP | DOI: 10.35940/ijrte.F8451.038620

Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: The present conventional sources of energy have been rapidly decreasing. There is an ever-increasing demand of energy which can be fulfilled only by taking into consideration, alternative sources of energy that are also environment friendly. For integrating the renewable energy source such as Solar PV with the grid, several factors must be kept in mind for ensuring the health of the grid. In the past, this task was effectively handled with different computational algorithms such as Ant Colony, Particle Swarm Optimization. But with the advent of Big Data technologies and Machine learning techniques, this task is handled even more effectively. This paper will review different studies in which Artificial Intelligence will be used to make effective decisions regarding the load demand, optimal sizing and positioning of Solar PV energy generating stations.
Keywords: Renewable energy sources (RES), Distributed Generation, Hybrid Energy Systems, Optimal placement techniques, System performance.
Scope of the Article: Machine Learning.