The increasing liberalization of European electricity markets, the growing proportion of intermittent renewable energy being fed into the energy grids, and also new challenges in the patterns of energy consumption (such as electric mobility) require flexible and intelligent power grids capable of providing efficient, reliable, economical, and sustainable energy production and distribution. From the supplier side, particularly, the integration of renewable energy sources (e.g., wind and solar) into the grid imposes an engineering and economic challenge because of the limited ability to control and dispatch these energy sources due to their intermittent characteristics. Time-series prediction of wind speed for wind power production is a particularly important and challenging task, wherein prediction intervals (PIs) are preferable results of the prediction, rather than point estimates, because they provide information on the confidence in the prediction. In this paper, two different machine learning approaches to assess PIs of time-series predictions are considered and compared: 1) multilayer perceptron neural networks trained with a multiobjective genetic algorithm and 2) extreme learning machines combined with the nearest neighbors approach. The proposed approaches are applied for short-term wind speed prediction from a real data set of hourly wind speed measurements for the region of Regina in Saskatchewan, Canada. Both approaches demonstrate good prediction precision and provide complementary advantages with respect to different evaluation criteria.

针对大规模风电机组(wind turbine,WT)接入电网,导致电网惯量响应能力和调频备用容量不足,进而造成电网频率稳定性下降的问题,文章提出一种风储系统与等容量同步发电机等惯量响应能力的储能(energy storage,ES)配置方法。方法旨在实现WT取代同步发电机接入电网前后,电网惯量响应能力和调频能力不变。并在此基础上,根据WT在不同风速下,具有不同的调频能力这一特性,文章进一步提出了风储协调控制策略,该策略既能在低风速下提供惯量响应支持,又能在中风速下辅助WT转速恢复,避免频率二次跌落。仿真结果表明,仅配置风电场额定功率5%的容量,既可补偿电网惯量响应能力,又能满足WT转速恢复所需功率,大大提升了电网频率运行稳定性。

Large-scale wind power connected to the power grid leads to the decrease of inertia response capacity and frequency-regulation reserve capacity of the power grid, and then the frequency stability of power grid is decreased. A method for energy storage (ES) configuration helps wind power units to provide the same inertia response capacity as equal capacity synchronous generator is proposed. The aim is to realize that the inertia response capacity of the grid and the overall frequency-regulation capacity of the system remain unchanged before and after wind power units instead of the synchronous generator connecting with the grid. On this basis, wind power units have different frequency-regulation ability under different wind speeds. Furthermore, a coordinated control strategy of combined wind and storage system is proposed, which can not only provide inertia response support at low wind speeds, but also assist wind power units to recover their rotating speed at medium wind speed to avoid secondary frequency drops. The simulation results show that energy storage with the capacity equalled to only 5% of the rated power of the wind farm can compensate the inertia response capacity of the power grid, as well as the power needed to restore the wind power units’ speed, which greatly improves the operation frequency stability of the power grid.

风电的大规模并网给电力系统带来了惯量降低和一次调频能力不足等问题,可减载运行且具备调频功能的风电场可有效应对该问题。为此,提出了一种风电场减载方案以及相应的一次调频策略。首先,介绍了综合惯性控制和桨距角控制的原理,并分析了风电场减载运行的必要性。然后,研究了不同风速下风机减载能力的差异性并制定了风电场内减载功率分配方案,根据制定的减载方案,提出了相应的一次调频策略,以充分利用风电场的调频能力并避免频率的二次跌落。最后,基于Matlab/Simulink搭建了仿真系统模型,仿真结果表明所述减载方案和调频策略可以合理分配减载功率并提升风电场的调频效果。

The large-scale wind power integration brings some problems such as the reduction of inertia and the shortage of primary frequency-regulation capability to the power system. Wind farms with deloading operation and frequency-regulation function could effectively deal with these problems. Therefore, a deloading scheme and the corresponding primary frequency regulation strategy of wind farm are proposed. Firstly, the principle of integrated inertia control and pitch-angle control is introduced, and the necessity of deloading operation of wind farm is analyzed. Then the difference of deloading capability of wind turbines with different wind speeds is studied and the deloading power distribution scheme of wind farm is formulated. Furthermore, according to the deloading power distribution scheme, the corresponding primary frequency regulation strategy is proposed to make full use of the frequency regulation capability of wind farm and avoid the secondary frequency drop. The simulation system model is built based on Matlab/Simulink, and the simulation results show that the deloading scheme and frequency regulation strategy could reasonably distribute the deloading power and improve the frequency regulation effect of wind farm.