Renewable energy forecasting using computational intelligence techniques
Loading...
Date
item.page.authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The importance of renewable energy has been growing at a fast pace, both because of the need to solve problems related to environmental issues and as a way of helping the increasingly difficult management of electricity grids. The utilization of non-traditional energy sources has seen a significant increase lately, with renewable energy playing a crucial role in the foreseeable future. However, to effectively integrate renewable energy into the conventional power grid, the issue of fluctuating quality and output power of sources like solar and wind must be addressed. This inconsistency poses challenges for system administrators in terms of unit commitment, scheduling, and reserve management. To tackle this, utilities and experts have shown interest in developing new forecasting methods that span different time frames and geographical locations to predict solar irradiance and wind velocity. These forecasting systems employ physical, mathematical, and artificial intelligence techniques, including hybrid methodologies. Accurate energy forecasting algorithms are crucial for the growth of the energy industry and policy formulation. They are based on two main pillars: forecasting energy consumption and managing power supply. In recent times, various prediction models have been used, taking into consideration data availability, efficient energy management operations, and model network mechanisms. This thesis is focused mainly on forecasting solar irradiance, wind speed, wind power, etc of different locations. Various computational intelligence methods have been investigated. In this thesis, different hybrid computational intelligence-based forecasting method of renewable energy has been proposed, which reduces the estimation error substantially.