ENERGY AND ECONOMIC EVALUATON OF A HYBRID CAES/WIND POWER PLANT WITH NEURAL NETWORK-BASED WIND SPEED FORECASTING

A model of a hybrid power plant consisting of Compressed Air Exergy Storage (CAES) coupled with a wind farm is presented. The model employs neural network-based wind speed forecasting. By coupling CAES with a wind farm, some of the major limitations of wind power, such as a low power density and an unpredictable nature, can be overcome. The use of time-series neural network-based prediction models aims at reducing the stochastic uncertainty of wind power. As shown in the paper, knowledge of the future incoming energy can be a powerful means for planning the daily operation strategy of the storage system. A detailed economic analysis has been carried out, evaluating investment, maintenance and operational costs using actual energy market prices. The benefits critically depend on the performance of each sub-system, incoming energy, user load and economic regulations. Results show that advantages in terms of Net Present Value, energy savings and CO2 mitigation can be achieved