Optimum daily operation of a wind-hydro hybrid system

Abstract

Due to the negative effects of fossil fuels on the environment and health, energy supply is shifting towards renewables. The integration of renewable energy systems is challenging due to the intermittent nature of renewables, however this can be mitigated through storage. Uncertainty in electricity prices in spot markets further complicates the operation of these systems. Pumped storage hydropower is currently the most viable form of large-scale energy storage, and operation of renewable energy systems together with pumped storage hydropower plants is highly efficient. In this study, optimum daily operation strategies are developed for a wind-hydro hybrid system. A long short-term memory network to forecast electricity prices in the day-ahead spot electricity market is coupled with an optimization model to maximize daily revenue. Various scenarios are considered to investigate the benefits of future electricity price estimations. For the wind-hydro hybrid system with 25 MW wind turbine, the net revenue for one-year test period increased 3.5% when forecasted electricity prices with the proposed long short-term memory network is used instead of electricity prices of the previous day. It is observed that increasing the installed capacity of wind turbines compensates for the loss resulting from the poor forecasting of electricity prices; however, the operation schedules of the pump and the hydro turbine do not change when the optimization model uses a simulation duration of one day with hourly time steps.