Research On Dispatching For Wind Farm Integrated System Based On Power Forecasting

As a kind of renewable and clean energy, wind power development has very important significance for improving the energy structure, climate change and energy security issues. However, the volatility, intermittency, and uncontrollability of wind energy bring great challenges to the stable operation and generator schedule of the power system with large-scale wind power connected. Therefore study on wind power forecasting and economic dispatch of wind farm integrated power system is important for improving the utilization level of wind power and planning and dispatching power grid. Focusing on dispatching for wind farm integrated system based on power forecasting, the following researches have been carried out in this paper.1. The NW small world neighborhood PSO (SW-PSO) algorithm is proposed, as the NW small world network with high clustering coefficient and short average path length is adopted as the topological structure of PSO. Simulation results show that SW-PSO algorithm has higher efficiency and accuracy on high scales optimization problem, so it is suitable for artificial neural network prediction model optimization and large-scale non-linear programming problem solution.2. BP neural network prediction model based on SW-PSO and wind power curve model are researched, which is applied for forecasting wind power in day advanced with NWP information. Due to wind power prediction accuracy constraint induced by the error from the NWP information, the historical wind power data is combined with the NWP information for short-term rolling forecasting of wind power.3. A dynamic economic dispatch model of power system integrated wind is proposed based on wind power prediction and in consideration of wind power prediction error and wind penetration power in spinning reserve. The model is a multi-constraint, large-scale, non-linear programming problem. The corresponding adjustment strategies to practical demand are proposed to correct the particle optimizing in the feasible region. The results show that SW-PSO is the new effective solution method of the dynamic economic dispatch problem of power system integrated wind.4. Chance constrained programming (CCP) is adopted to establish the mathematical model of dynamic economic dispatch of power system integrated wind. The stochastic optimal dispatch of system is proposed, in which it describes the related constrained condition by probability form. It is solved by Monte-Carlo stochastic simulation strategy and SW-PSO, which is proved feasible and effective by a test system. The research can provide a reasonable plan meeting safe and stable operation of power grid and wind power accommodation demand for decision makers.