当前在光伏电站出力短期预测方面较多的采用BP或者优化的BP神经网络算法,存在采用的优化算法单一、缺乏多种优化算法比较选优、预测误差大的问题。基于本地5 k W小型分布式光伏电站,综合考虑影响光伏出力的太阳光辐射强度、环境温度、...当前在光伏电站出力短期预测方面较多的采用BP或者优化的BP神经网络算法,存在采用的优化算法单一、缺乏多种优化算法比较选优、预测误差大的问题。基于本地5 k W小型分布式光伏电站,综合考虑影响光伏出力的太阳光辐射强度、环境温度、风速气象相关因素和光伏电站历史发电数据,分别采用BP以及遗传算法和粒子群算法优化的BP神经网络算法—GA-BP和POS-BP构建了晴天、多云、阴雨三种天气条件下光伏出力短期预测模型。实测结果表明,三种神经网络算法预测模型在三种不同天气条件下均达到了一定的预测精度。其中GA-BP、POS-BP相比传统的BP预测模型降低了预测误差,且POS算法相比GA算法对于BP神经网络预测模型的优化效果更好,进一步降低了预测误差,适用性更强。展开更多
Considering the instability of the output power of photovoltaic(PV)generation system,to improve the power regulation ability of PV power during grid-connected operation,based on the quantitative analysis of meteorolog...Considering the instability of the output power of photovoltaic(PV)generation system,to improve the power regulation ability of PV power during grid-connected operation,based on the quantitative analysis of meteorological conditions,a short-term prediction method of PV power based on LMD-EE-ESN with iterative error correction was proposed.Firstly,through the fuzzy clustering processing of meteorological conditions,taking the power curves of PV power generation in sunny,rainy or snowy,cloudy,and changeable weather as the reference,the local mean decomposition(LMD)was carried out respectively,and their energy entropy(EE)was taken as the meteorological characteristics.Then,the historical generation power series was decomposed by LMD algorithm,and the hierarchical prediction of the power curve was realized by echo state network(ESN)prediction algorithm combined with meteorological characteristics.Finally,the iterative error theory was applied to the correction of power prediction results.The analysis of the historical data in the PV power generation system shows that this method avoids the influence of meteorological conditions in the short-term prediction of PV output power,and improves the accuracy of power prediction on the condition of hierarchical prediction and iterative error correction.展开更多
The degree of accuracy in predicting the photovoltaic power generation plays an important role in appropriate allocations and economic operations of the power plants based on the generating capacity data gathered from...The degree of accuracy in predicting the photovoltaic power generation plays an important role in appropriate allocations and economic operations of the power plants based on the generating capacity data gathered from the geographically separated photovoltaic plants through network. In this paper, a forecasting model is designed with an optimization algorithm which is developed with the combination of PSO （Particle Swarm Optimization） and BP （Back Propagation） neural network. The proposed model is further validated and the experiment results show that the predication model assures the prediction accuracy regardless the day type transitions and other relevant factors, in the proposed model, the prediction error rate is worth less than 20% in all different climatic conditions and most of the prediction error accuracy is less than 10% in sunny day, and whose precision satisfies the management requirements of the power grid companies, reflecting the significance of the proposed model in engineering applications.展开更多
文摘当前在光伏电站出力短期预测方面较多的采用BP或者优化的BP神经网络算法,存在采用的优化算法单一、缺乏多种优化算法比较选优、预测误差大的问题。基于本地5 k W小型分布式光伏电站,综合考虑影响光伏出力的太阳光辐射强度、环境温度、风速气象相关因素和光伏电站历史发电数据,分别采用BP以及遗传算法和粒子群算法优化的BP神经网络算法—GA-BP和POS-BP构建了晴天、多云、阴雨三种天气条件下光伏出力短期预测模型。实测结果表明,三种神经网络算法预测模型在三种不同天气条件下均达到了一定的预测精度。其中GA-BP、POS-BP相比传统的BP预测模型降低了预测误差,且POS算法相比GA算法对于BP神经网络预测模型的优化效果更好,进一步降低了预测误差,适用性更强。
基金supported by National Natural Science Foundation of China(No.516667017).
文摘Considering the instability of the output power of photovoltaic(PV)generation system,to improve the power regulation ability of PV power during grid-connected operation,based on the quantitative analysis of meteorological conditions,a short-term prediction method of PV power based on LMD-EE-ESN with iterative error correction was proposed.Firstly,through the fuzzy clustering processing of meteorological conditions,taking the power curves of PV power generation in sunny,rainy or snowy,cloudy,and changeable weather as the reference,the local mean decomposition(LMD)was carried out respectively,and their energy entropy(EE)was taken as the meteorological characteristics.Then,the historical generation power series was decomposed by LMD algorithm,and the hierarchical prediction of the power curve was realized by echo state network(ESN)prediction algorithm combined with meteorological characteristics.Finally,the iterative error theory was applied to the correction of power prediction results.The analysis of the historical data in the PV power generation system shows that this method avoids the influence of meteorological conditions in the short-term prediction of PV output power,and improves the accuracy of power prediction on the condition of hierarchical prediction and iterative error correction.
基金the National Natural Science Foundation of China under Grant No.61261016，Wuhan Science and technology project for the Solar energy intelligent management system development and application demonstration
文摘The degree of accuracy in predicting the photovoltaic power generation plays an important role in appropriate allocations and economic operations of the power plants based on the generating capacity data gathered from the geographically separated photovoltaic plants through network. In this paper, a forecasting model is designed with an optimization algorithm which is developed with the combination of PSO （Particle Swarm Optimization） and BP （Back Propagation） neural network. The proposed model is further validated and the experiment results show that the predication model assures the prediction accuracy regardless the day type transitions and other relevant factors, in the proposed model, the prediction error rate is worth less than 20% in all different climatic conditions and most of the prediction error accuracy is less than 10% in sunny day, and whose precision satisfies the management requirements of the power grid companies, reflecting the significance of the proposed model in engineering applications.
