基于智能算法的大型风电场功率爬坡预测方法研究

发布时间：2018-06-30 05:02

本文选题：风电功率爬坡预测 + 自适应稀疏时频分析　；参考：《上海电机学院》2017年硕士论文

【摘要】：风电爬坡是指在短时间尺度内,风电功率的大幅度波动。随着大规模波动性风电并网,风电功率爬坡对电力系统安全稳定的影响逐渐突出。特别是在极端气象条件下,风功率爬坡会使电力系统很难维持短时间内的原有功率平衡和频率稳定,造成停电事故。本文针对风电功率爬坡预测精度较低和稳定性较差问题,提出了风电功率爬坡的预测方法,具体研究内容如下:(1)分析风电功率爬坡事件发生的机理和爬坡特性,研究风电场风速、风向、温度、湿度和压强与发电功率爬坡之间的关系,确定了对风电功率爬坡预测的特征参数。(2)应用自适应稀疏时频分析,对风电功率爬坡量进行本征模态分解,结合数值天气预报的气象信息,利用极限学习机神经网络建立风机功率爬坡预测模型,通过算例仿真验证了该模型能够提高预测精度。(3)为了提高算法的收敛性和防止过早收敛性能,采用了基于信息分享机制的粒子群算法加强粒子间信息交流,以及通过混沌和反向学习策略增加粒子的多样性,从而优化算法的寻优路径,跳出局部最优值。通过测试函数进行测试分析,验证了改进策略的有效性。(4)建立了风场功率爬坡的组合预测模型,并利用改进的粒子群算法优化该模型权重。结合实际工程应用,进行了功率爬坡预测系统的设计与软件开发,并通过工程实例验证了预测模型可行性。
[Abstract]:Wind power climbing refers to the large fluctuation of wind power in a short time scale. With large-scale fluctuating wind power connected to the grid, the influence of wind power climbing on power system safety and stability is becoming more and more prominent. Especially under extreme weather conditions, wind power climbing will make it difficult for power system to maintain the original power balance and frequency stability in a short period of time, resulting in power failure. In this paper, aiming at the problems of low precision and poor stability of wind power climbing, a prediction method of wind power climbing is proposed. The main contents of this paper are as follows: (1) the mechanism and characteristics of wind power climbing events are analyzed. The relationship between wind speed, wind direction, temperature, humidity and pressure in wind farm is studied, and the characteristic parameters of wind power climbing prediction are determined. (2) Adaptive sparse time-frequency analysis is used. The intrinsic mode decomposition of wind and electric power climbing is carried out. Combined with the meteorological information of numerical weather forecast, the prediction model of fan power climbing is established by using the extreme learning machine neural network. The simulation results show that the model can improve the prediction accuracy. (3) in order to improve the convergence of the algorithm and prevent premature convergence, the particle swarm optimization algorithm based on information sharing mechanism is used to enhance the information exchange between particles. The chaos and reverse learning strategies are used to increase the diversity of particles so as to optimize the optimization path of the algorithm and jump out of the local optimal value. The effectiveness of the improved strategy is verified by test function. (4) the combined prediction model of wind power climbing is established, and the weight of the model is optimized by using improved particle swarm optimization algorithm. Combined with the practical engineering application, the design and software development of the power climbing prediction system are carried out, and the feasibility of the prediction model is verified by an engineering example.
【学位授予单位】：上海电机学院
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TM614

【参考文献】