Some of the major limitations of renewable energy sources are represented by their low power density and intermittent nature, largely depending upon local site and unpredictable weather conditions. These problems concur to increase the unit costs of wind power, so limiting their diffusion and the benefits due to the reduced exploitation of fossil resources. By coupling storage systems 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. Furthermore, the use of time-series neural network-based prediction models aims at reducing the stochastic uncertainty of wind power. A Matlab/Simulink model of a hybrid power plant consisting of a wind farm coupled with Compressed Air Energy Storage (CAES) is presented. In CAES energy is stored in the form of compressed air in a reservoir during off-peak periods, while it is used on demand during peak periods to generate power with a turbo-generator system. Such plants can offer significant benefits in terms of flexibility in matching a fluctuating power demand, particularly when coupled with renewable sources. The model employs neural network-based wind speed forecasting to determine the optimal daily operation strategy for the storage system. Without predicting the incoming wind energy, the net load, above that provided by wind turbines, would be known only in real time. Thus, the only way to manage CAES storage/generation would be to follow the net load for a prefixed number of hours; the operation of CAES would be function of the load, of the wind power generation and the energy prices. Because wind speed is variable and not predictable, plant management can be a problem. Mainly, user demand might not be satisfied during some periods. So, forecasting the wind contribution could be very helpful for proper system management. Knowing the incoming wind power several hours in advance helps in estimating the net load for the current day and thus determining the management strategy. As shown in the paper, the knowledge of the expected available energy is a key factor to optimize the management strategies of the proposed hybrid power plant. A detailed economic analysis has been carried out: investment and maintenance costs are estimated based on literature data, while operational costs and revenues are calculated according to the energy market prices.

Optimal Management of a Wind/CAES Power Plant by means of Neural Network Wind Speed Forecast

ARSIE, Ivan;MARANO, VINCENZO;RIZZO, Gianfranco;
2007-01-01

Abstract

Some of the major limitations of renewable energy sources are represented by their low power density and intermittent nature, largely depending upon local site and unpredictable weather conditions. These problems concur to increase the unit costs of wind power, so limiting their diffusion and the benefits due to the reduced exploitation of fossil resources. By coupling storage systems 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. Furthermore, the use of time-series neural network-based prediction models aims at reducing the stochastic uncertainty of wind power. A Matlab/Simulink model of a hybrid power plant consisting of a wind farm coupled with Compressed Air Energy Storage (CAES) is presented. In CAES energy is stored in the form of compressed air in a reservoir during off-peak periods, while it is used on demand during peak periods to generate power with a turbo-generator system. Such plants can offer significant benefits in terms of flexibility in matching a fluctuating power demand, particularly when coupled with renewable sources. The model employs neural network-based wind speed forecasting to determine the optimal daily operation strategy for the storage system. Without predicting the incoming wind energy, the net load, above that provided by wind turbines, would be known only in real time. Thus, the only way to manage CAES storage/generation would be to follow the net load for a prefixed number of hours; the operation of CAES would be function of the load, of the wind power generation and the energy prices. Because wind speed is variable and not predictable, plant management can be a problem. Mainly, user demand might not be satisfied during some periods. So, forecasting the wind contribution could be very helpful for proper system management. Knowing the incoming wind power several hours in advance helps in estimating the net load for the current day and thus determining the management strategy. As shown in the paper, the knowledge of the expected available energy is a key factor to optimize the management strategies of the proposed hybrid power plant. A detailed economic analysis has been carried out: investment and maintenance costs are estimated based on literature data, while operational costs and revenues are calculated according to the energy market prices.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11386/3881717
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? ND
social impact