Abstract
Renewable energy is now in high demand due to the deterioration of the global climate and the depletion of conventional sources. Renewable energy sources (RES) such as wind and solar are extremely intermittent, making it impossible to sustain system reliability with an unacceptably high proportion of renewable energy injection. An intrinsic attribute common to all renewable power plants is that the production of energy relies on environmental conditions such as temperature, pressure, wind speed, humidity, clouds, etc. Therefore, the power from RES cannot be completely regulated or pre-planned. It is important to forecast the amount of electricity that can be produced in a power grid for future demand. Machine learning (ML) is an emerging technology and used in all fields nowadays to perform different tasks. In this paper, the applications of machine learning in renewable energy sources are discussed. These ML techniques are mainly used to predict the power from renewable energy sources like wind, solar, hydro, biomass, tidal, and geothermal. Fault detection is a significant aspect in renewable energy systems to reduce the operation and maintenance cost and to deliver the continuous power to the loads. This paper also focusses on the use of ML techniques in predicting the faults before it occurs, early detection of faults and also to diagnose the faults in renewable energy systems. Along with the above-mentioned applications, these ML techniques used in RES for different purposes are also discussed.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
Pulavarthi Satya Venkata Kishore
Pulavarthi Satya Venkata Kishore received BE from Andhra University, India and MTech from National Institute of Technology, Calicut, India in 2009 and 2013, respectively. Further, he is currently pursuing PhD at National Institute of Technology (NIT), Andhra Pradesh, India. His research interests include multi-level inverters, high power factor converters and power electronics.
Jami Rajesh
Jami Rajesh received BTech degree from Jawaharlal Nehru Technological University, Hyderabad, India and Master of Engineering from Andhra University College of Engineering, Visakhapatnam, India in 2007 and 2012, respectively. He is currently pursuing PhD at National Institute of Technology (NIT), Andhra Pradesh, India. His research interests include multi-level inverters, high power factor converters and power electronics. Email: [email protected]
Nakka Jayaram
Nakka Jayaram received BTech from Jawaharlal Nehru Technological University, Hyderabad, India and MTech from Vellore Institute of Technology, Vellore, India in 2007 and 2009, respectively. He received the PhD degree in electrical engineering from Indian Institute of Technology, Roorkee, India in 2014. Currently, he is with the Department of Electrical Engineering, National Institute of Technology, Andhra Pradesh, India. His research interests include multi-level inverters, high power converters, and renewable energy systems. Email: [email protected]
Sukanta Halder
Sukanta Halder is presently serving Electrical Engineering faculty at Sardar Vallabhbhai National Institute of Technology (SVNIT), Surat. He received his PhD in electrical engineering from Indian Institute of Technology (IIT) Roorkee, India in 2017. He did his MTech from IIT Roorkee. After PhD, he joined Rolls-Royce@NTU Corporate Lab, Nanyang Technological University, Singapore as a post-doctoral fellow. Later, he moved to Charge Lab, University of Windsor, Ontario, Canada for his second postdoc in 2019. His research interests include WBG (SiC & GaN) inverter development, gate driver design, electric vehicle, PMSM drives, multi-level inverters, machine learning-based motor control and sensor less drives. Email: [email protected]