Short-Term Spanish Aggregated Solar Energy Forecast

Abstract

Abstract. This work presents and compare six short-term forecasting methods for hourly aggregated solar generation. The methods forecast one day ahead hourly values of Spanish solar generation. Three of the models are based on MLP network and the other three are based on NARX. The two different types of NN use to forecast the same NWP data, comprising solar radiation, solar irradiation and the cloudiness index weighted with the installed solar power for the whole country. In addition of the NWP data the models are fed with the aggregated solar energy generation in hourly step given by the System Operator.The results of the two types of NN are compared and discussed in the conclusions as much as the error variability along the day hours. The results obtained by the six methods are evaluated, concluding that the most accurate result is the one given by the developed NARX irradiance forecast method; achieving the lowest one day-ahead Mean Average Daily Error of 16.64%. IntroductionThe installation of power plants based on renewable energy sources have increased exponentially in the recent years [1]. The fuel-based energy generation price increase along with the subsidies promoting the construction of clean energies made the installation of renewables a profitable business for many particulars and companies [2]. The expansion of these technologies and the policies adopted by the Spanish national government to integrate them into the electrical power system has brought a fussy market situation. The integration of the electric energy generated by these power plants into electric power system is priority. According with the current legislation, the power generated by green sources is fed into the system in preferential order within the Spanish energy generation mix. This energy mix is result of a counter clockwise energy auction held one day-ahead.In order to always ensure the renewable energy acceptance into the system the energy bids [2] for such technologies are placed at the legal minimum, 0€ € /MWh and its retribution would be an addition of the final auction price and the generation subsidy agreed with the government. This fact may lead into situations where the energy demand is fewer than the energy generation by technologies offering their energy at the minimum price, being the final auction price 0€ € /MWh.

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

“…The ANN models have been used in many studies for electric power forecasting [ 6 , 39 , 44 , 46 , 48 , 53 , 54 , 55 , 57 , 58 , 59 , 60 , 61 , 62 , 65 , 70 , 75 , 77 , 81 , 82 , 86 , 108 , 153 , 155 , 165 , 175 , 176 ] and have reached a forcasting accuracy with an average MAPE value of 3.781%.…”

Solar district heating and cooling: A review

“…In order to operate the power plant efficiently, it is required to forecast accurately the solar generation from the field. To achieve such estimation for ST generation, it is needed to forecast the solar irradiation and take into consideration the aging of the solar collectors . The forecast information can be used on a power plant simulator aiming to improve generation strategies, reduce generation expenses, and maximize revenues in generation.…”