To improve the short-term wind speed forecasting accuracy of wind farms, a prediction model based on back propagation (BP) neural network combining ant colony algorithm is built to predict short-term wind speed. The input variables of BP neural network predictive model are historical wind speeds, temperature, and air pressure. Ant colony algorithm is used to optimize the weights and bias of BP neural networks. Using the ant colony optimization BP neural network model to predict the future 1h wind speed, the simulation results show that the proposed method offers the advantages of high precision and fast convergence in contrast with BP neural network.
First of all, I would like to extend my sincere gratitude to my Ph. D supervisor Dr. Siek Liter for his guidance and encouragement throughout my Ph. D journey. His advice helped to overcome numerous difficulties that I faced during my research. Next, I am grateful to MediaTek and Economic Development Board of Singapore (EDB) for awarding me with the Joint Industry Programme (JIP) Scholarship. I am also grateful to the funding support from NTU-A*Star Silicon Technologies Centre of Excellence under the program grant no.11235100003. This research would not be possible without the strong support provided by them. Throughout my research, I am glad to have the opportunity to collaborate with numerous researchers, especially Sun Zhuochao, Zhang Xiang. Many ideas and solutions would be difficult to come by if selfless mutual sharing sessions and discussions between us were absent. I would also like to thank the staffs in VIRTUS for their kind assistance in providing a conducive environment for research and to conduct laboratory measurements. Finally, I would like to express my greatest gratitude to my wife for her utmost support and encouragement for my research.
Frequency influencing factors in small weak receiving power grid with wind power penetration during the disturbance of power shortage are analyzed in this paper, such as wind power penetration rate, wind turbine types, inertia control loop and wind power fluctuation. Based on the influencing factors above, in the light of the phenomenon of large dive depth and long duration of the frequency first swing after fault, the coordination scheme of load shedding and under-frequency load shedding based on the simulation system is proposed: load shedding time and load shedding ratio coordination scheme. Simulation results verify the correctness of the theoretical analysis and the rationality and feasibility of the coordination scheme proposed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.