基于人工神经网络和粒子群算法的风能预测模型

A prediction model for wind farm power generation based on neural network and particle swarm optimization

作为一种可再生清洁能源,风能被认为是电力系统中重要的替代发电能源。随着越来越多的风力发电机接入电网,风能预测变得越来越重要。文章应用人工神经网络提出了一种短期风能预测模型,并应用粒子群算法来优化其参数。模型采用实际风电场的数据进行了实例验证,并将其结果与无参数优化的人工神经网络模型进行了比较。

As a renewable energy source, wind turbine generators are considered to be important generation alternatives in electric power systems because of their non-exhaustible nature. As wind power penetration increases, power forecasting is crucially important for integrating wind power in a conventional power grid. A short-term wind farm power output prediction model is presented using a neural network optimized by particle swarm optimization a^gofithm. Using wind data from an existed wind farm, a power forecasting map is illustrated, and a comparison of models based on a Back-Propagation （BP） neural network and a PSO-BP neural network is undertaken.