Solar power integration, neural network, spinning reserve, Improved-Levenberg-Marquardt (ILM) algorithm

Abstract

the inherent factors, uncertainty and variability, are always existed in intermittent power resources such as wind and solar. Because of blind construction and lack of planning, the number of renewable generation plants are increasing dramatically, the transmission system could not afford such large capacity over such long distance. This paper proposes a novel spinning reserve decision-making model for power system with solar power integration. A new PV power generation forecasting model is established. The training target of neural network contains both accuracy section and maximum deviation section. In addition, Improved-Levenberg-Marquardt (ILM) algorithm is achieved for neural network training. A numerical study with practical data is presented and the result shows that new PV power generation forecasting model can reduce cost of construction of standby power plant with acceptable accuracy level. The proposed approach for spinning reserve decision-making with solar power integration power system is tested in a modified IEEE 9-bus 3-machine Benchmark Network.