Abstract: Wind power generation is increasing very rapidly all around the world. The available wind energy depends on the wind speed, which is a random variable and depends on the location and weather conditions. For the wind-farm operator, this uncertainty creates a difficulty in the system scheduling and energy dispatching, due to not knowing the wind-power generation in advance. This paper presents an artificial neural network approach for wind speed forecasting at Jaipur, India. The Back propagation (BP) learning of neural network is used for training. The accuracy of the wind speed forecasting attained with the proposed approach is evaluated by reporting the numerical results from a real-world case study. The proposed approach for wind speed forecast has the accuracy of 95% and above.

• Publication Date: 12-Mar-2012
• DOI: 10.15224/978-981-07-1847-3-838
• Views: 0
• Downloads: 0

Abstract: Harmonic Elimination in the output voltage of inverters is an important consideration as the presence of harmonics result in several undesirable secondary effects along with distorted waveforms. Most of the off-line PWM techniques use Newton-Raphson method for determination of trigger pulse-positions. This paper uses a combination of Evolutionary strategies and Artificial Neural Networks for design of Intelligent Selective Harmonic Elimination (SHE) controller. The controller calculates the trigger pulse positions intelligently by searching in the given solution space bounded by the practical constraints. The result analysis shows a significant decrement in harmonic components, while improvement in the fundamental voltage component, effectively reducing the Total Harmonic Distortion.

• Publication Date: 12-Mar-2012
• DOI: 10.15224/978-981-07-1847-3-841
• Views: 0
• Downloads: 0