Forecasting and power quality enhancement of hybrid wind and solar energy connected to grid using soft computing techniques

Abstract

High penetration of solar and wind power in the electricity system provides a number of challenges to the grid such as grid stability and security, system operation, and market economics. Ones of the considerable problems of solar and wind systems, they depend on the weather, as compared to the conventional generation. As we know, the balance in managing load and generated power in energy system is very important. If the power which is supplied from solar and wind perfectly predictable, the extra cost of operating power system with a large penetration of renewable energy will be reduced. Since, the accurate and reliable forecasting system for renewable sources represents an important topic as a major contribution for increasing non-programmable renewable on over the world. Therefore, this work presents a Substantial Power Evolution Strategy (SPES) and Resilient Back Propagation Neural Network (RBPN) model to produce solar and wind power Short Term Forecasting (STF). newlineHowever, STF is very complex for handling due to solar irradiance and wind speed under variable weather conditions. But the proposed Substantial Power Evolution Strategy (SPES) and Resilient Back Propagation Neural Network (RBPN) is suitable for STF modeling and also the proposed forecasting system is directly connected to IEEE-9 bus to reduce Total Harmonics Distortion (THD) and also reduces the power quality issues in various conditions, such as voltage unbalance control, active and reactive power control. The performance of the proposed forecasting system is validated through simulation developed by using Matlab Simulink software. newline