Atsushi Yona

Application of Recurrent Neural Network to Long-Term-Ahead Generating Power Forecasting for Wind Power Generator

In recent years, there have been problems such as environmental pollution resulting from consumption of fossil fuel, e.g., coal and oil. Thus, introduction of an alternative energy source such as wind energy is expected. Wind speed is not constant and wind power output is proportional to the cube of the wind speed. In order to predict the power output for wind power generators as accurate as possible, it requires the method of wind speed estimation. In this paper, a technique consider the wind speed of each month, and confirm the validity of neural network (NN) to predict wind speed by computer simulations. Since recurrent neural network (RNN) is known as good tool for time-series data forecasting, the authors propose an application of RNN for the wind speed prediction. The proposed method in this paper does not require complicated calculations and mathematical model

Optimal Thermal Unit Commitment Scheme by Including Renewable Energy Sources and Pumped Hydro Energy Storage: Case Study of Niamey Power System, Niger

This paper presents a novel real multi-objective approach for thermal unit commitment (UC) problem solution in Niamey (Niger). The proposed methodology consists of four conventional thermal generating units and imported power from a neighboring country in addition to future inclusion of Photovoltaic (PV) power, Wind Turbine Generators (WTGs), and Pumped Hydro Energy Storage (PHES). Minimization of total daily operating cost and decreasing the maximum daily mismatch between load demand and generation are considered as two objective functions in two cases. In the first case, UC with thermal units considering the imported power (IMP), PV and PHES is determined. In the second case, WTGs are introduced and the IMP is removed in order to get rid of its economical and political problems. ε-MOGA (epsilon Multi-Objective Genetic Algorithm) is used to obtain an optimal unit commitment problem solution with consideration of PV, WTGs and PHES. The effectiveness and robustness of the proposed scheme is verified by numerical simulations using MATLAB environment.