A data-driven two-stage stochastic optimization model for solving short-term hydro-thermal-wind coordination scheduling problem with complicated time-coupled and space-related characteristics is proposed in this paper. The generation, emission and power fluctuation costs in the day-ahead scheduling stage and power regulation costs by hydro-thermal units, wind curtailment and load shedding costs in the real-time scheduling stage is formulated as the objective function of proposed model. Moreover, a dynamic extreme scenario generation and reduction method is introduced to deal with wind power uncertainty. The relationship between hydropower output, volume, inflow, discharge and upstream water for the multi-reservoir cascaded hydro plants is converted into a series of linear constraints, and the practical constraints of prohibited operation zones for thermal units are taken into account. As a result, the proposed model can be transformed into a mixed-integer linear programming problem to solve. Finally, case studies are carried out on the modified IEEE 24-bus system comprising of six thermal units, a multi-chain cascade of four hydro plants and one wind farm, and simulation results verify the effectiveness of the proposed coordination scheduling model and method.

提出了一种基于数据驱动的两阶段随机优化模型，用于求解具有复杂的时间耦合和空间相关特性的短期水热风协调调度问题。将日调度阶段的发电，排放和电力波动成本以及水热机组的功率调节成本，实时调度阶段的风电削减和减负荷成本作为模型的目标函数。此外，引入了动态极端情景生成和减少方法来应对风力发电的不确定性。多水库梯级水电站的水力发电量，流量，流入量，流量与上游水量之间的关系转换为一系列线性约束，并考虑了热单元禁止运行区域的实际限制。结果，所提出的模型可以转化为混合整数线性规划问题来解决。最后，对改进的IEEE 24总线系统进行了案例研究，该系统包括6个热力单元，4个水力发电厂的多链级联和1个风电场，仿真结果验证了所提出的协调调度模型和方法的有效性。