A Review on Energy Forecasting Algorithms Crucial for Energy Industry Development and Policy Design

ABSTRACT

The power extracted from non-conventional energy sources has increased significantly in recent days, and power extracted from renewable energy will play an essential part in the near future. To improve renewable energy in the traditional electrical network, it must deliver liabilities due to the erratic quality of solar, wind, etc. Inconsistency in output power is a critical issue for structure administrators because of its effects on unit commitment, scheduling, and reserve management. The utilities and specialists have demonstrated their enthusiasm for developing new forecasting approaches across many temporal and latitudinal horizons to anticipate solar irradiance and wind velocity. Physical, mathematical, and artificial brainpower have been utilized in vital forecasting systems, i.e., artificial intelligence approaches and hybrid methodologies. Energy forecasting algorithms are essential for the development of the energy industry and policy design. The two main pillars of energy planning are forecasting energy consumption and managing power supply. In the recent past, a wide range of prediction models has been employed. The availability of data, efficient energy management operation, and model network mechanism are all determined. This paper includes a comprehensive and systematic review of renewable forecast models. Forecasting intervals are divided into three categories: short-term, medium-term, and long-term. The assessment considers two renewable energy sources: wind and solar power. This study has orchestrated a sharp audit of forecasting methods in this literature vindication for prediction in power networks. Similarly, methods for improving prediction precision and prediction issues and emerging trends have been provided. Again, strategies for improving forecast accuracy have been devised to deal with dynamic forecast problems and emerging trends.

KEYWORDS-:

• Ramp events
• reserves management
• scheduling
• unit commitment
• forecasting
• artificial intelligence

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Manish Babu

Manish Kumar Babu is born in Sambalpur, Odisha, India in 1993. He has received his Bachelor of Technology (Electrical Engineering) degree and Master of Technology (Power and Energy Systems) degree from Kalinga Institute of Industrial technology, Bhubaneswar (deemed to be university), Odisha in 2014 and 2016 respectively. Currently he is pursuing his Ph.D. degree from Veer Surendra Sai University of Technology (Govt. University), Burla, Odisha. His research interests include renewable energy forecasting, application of computational intelligence techniques in forecasting and cost optimization analysis of microgrids.

Papia Ray

Papia Ray is born in Shillong, Meghalaya, India in 1978. She has received her Bachelor of Engineering (Electrical Engineering) degree from Government Engineering College, Bihar and Master of Technology (Power Systems) from National Institute of Technology, Jamshedpur and Ph.D degree from Indian Institute of Technology, Delhi in 2013. She is presently serving as Associate Professor in Electrical Engineering Department of Veer Surendra Sai University of Technology (Govt. Univ), Burla, Odisha. She has 18 years of teaching experience. She has 45 research publications in journals like IET, Elsevier, Wiley etc. She is a senior member of IEEE, member of Institution of Engineers and Life Member of ISTE. Her research interest includes power system protection, wide area measurement systems, biomedical engineering etc.