| Summary: | 碩士 === 國立彰化師範大學 === 工業教育與技術學系 === 105 === The main purpose of this thesis is to forecast renewable energy generations and load demand using artificial neural network, and the predictions were used to solve the optimal network reconfiguration of microgrids after fault occurred. In this thesis, the historical data of temperature, humidity, power generations of photovoltaic, and load demands were used to forecast the future power generations and load demands, and the indicators, such as RMSE, MSE, and MAPE were used to assess the forecasting capabilities. Furthermore, the particle swarm optimization algorithm was used to solve the multi-objective nonlinear function and related constraints of the optimal reconfiguration problem. In this thesis, a series of simulation analysis was carried out by using the test system to verify the feasibility of the proposed method. The simulation results demonstrated that the prediction accuracy affected the subsequent scheduling and real-time dispatch. Consequently, the accuracy of renewable energy power generation and load demand forecasting were extremely important for microgrids operations. The method proposed in this thesis can effectively predict the renewable energy generation and load demands. Moreover, it can be applied to solve the reconfiguration problem of microgrids after fault occurred.
|
|---|
