基于相似日和CAPSO-SNN的光伏发电功率预测

针对光伏发电功率预测精度不高的问题,提出一种基于相似日和云自适应粒子群优化(CAPSO)算法优化Spiking神经网络(SNN)的发电功率预测模型。考虑到季节类型、天气类型和气象等主要影响因素,提出以综合相似度指标进行相似日选取;以SNN强大的计算能力和其善于处理时间序列问题的特点为基础,结合CAPSO算法搜索的随机性和稳定性优化SNN的多突触连接权值,减少对权值的约束,提高算法的收敛精度。根据某光伏电站的实测功率数据对所提模型进行测试和评估,结果表明,该模型比传统预测模型具有更高的预测精度和更好的适用性。

Photovoltaic power generation forecasting based on similar day and CAPSO-SNN

Since the forecasting accuracy of PV(PhotoVoltaic) power generation is not high, a forecasting model based on the similar day and SNN(Spiking Neural Network) optimized by CAPSO(Cloud Adaptive Particle Swarm Optimization) algorithm is proposed. The comprehensive similarity index considering the main influencing factors, e. g. season, weather, meteorology, etc.,is adopted for selecting the similar day. Based on the powerful computation ability and efficiency in dealing with the time series problem of SNN, its multiple synaptic connection weights are optimized by the randomness and stability of CAPSO algorithm to loosen the constraint of weight and improve the convergence accuracy of algorithm. The proposed model is tested and evaluated based on the measured power data of a PV station and results show that, it has higher forecasting accuracy and better applicability than traditional forecasting models.