基于TOPSIS-GRNN的机理-数据混合驱动光伏电站功率预测

Power prediction of mechanism-data hybrid drive photovoltaic power plant based on TOPSIS-GRNN

针对传统光伏功率预测精度比较低的问题,文章提出了基于TOPSIS-GRNN的机理-数据混合驱动光伏电站功率预测模型。首先,对多个气象指标和光伏电站的输出功率进行了相关性分析,并选取了相关度较高的气象数据作为模型的输入因子,利用TOPSIS算法选择出最优相似日;然后,将光伏电站输出功率理论值和气象数据建立GRNN预测模型;最后,结合DKASC网站上的历史气象数据和功率数据,对该模型进行了仿真试验并验证。试验结果得出功率预测精度RMSE平均值为0.8269 kW,MAPE平均值为3.45%,MAE平均值为0.0195 kW。该预测方法的预测精度明显高于单一预测模型,具有一定的理论和实用价值。

The article addresses the problem of relatively low accuracy of traditional PV power prediction and proposes a hybrid TOPSIS-GRNN based mechanism-data driven PV plant power prediction model.Firstly,the correlation analysis of several meteorological indicators and the output power of PV power plant is carried out,and the meteorological data with high correlation is selected as the input factor of the model.The TOPSIS algorithm was used to select the optimal similar days,and then the theoretical values of their PV plant output power and meteorological data were used to build the GRNN prediction model.Finally,the model was simulated and validated by combining the historical meteorological data and power data on the DKASC website.The final test results yielded an average power prediction accuracy of 0.8269 kW for RMSE,3.45%for MAPE and 0.0195 kW for MAE.The prediction accuracy of this forecasting method is significantly higher than that of a single forecasting model and has some theoretical and practical value.