According to the issues that the predict errors of chaotic sequences rapidly accumulated in multi-step forecasting which affects the predict accuracy, we proposed a new predict algorithm based on local modeling with v...According to the issues that the predict errors of chaotic sequences rapidly accumulated in multi-step forecasting which affects the predict accuracy, we proposed a new predict algorithm based on local modeling with variable frame length and interpolation points. The core idea is that, using interpolation method to increase the available sample data, then modeling the chaos dynamics system with least square algorithm which based on the Bernstein polynomial to realize the forecasting. We use the local modeling method, looking for the optimum frame length and interpolation points in every frame to improve the predict peformance. The experimental results show that the proposed algorithm can improve the predictive ability effectively, decreasing the accumulation of iterative errors in multi-step prediction.展开更多
针对复杂多因素(气象信息、时间序列的混沌特性等)影响风电功率的短期预测,及风电时间序列的长期依赖问题,提出基于相空间重构和双向长短期记忆(bidirectional long short-term memories,BiLSTM)神经网络的风电功率短期预测方法。以全...针对复杂多因素(气象信息、时间序列的混沌特性等)影响风电功率的短期预测,及风电时间序列的长期依赖问题,提出基于相空间重构和双向长短期记忆(bidirectional long short-term memories,BiLSTM)神经网络的风电功率短期预测方法。以全球能源预测竞赛的数据集为背景,基于嵌入定理从风电功率序列中重构出相空间,以展示其内在的混沌特性,其中相空间重构的参数依据C-C法确定;对选取的气象预测数据(未来风速、风向)进行归一化处理,并组合重构后的风电功率数据作为BiLSTM的输入量,重构前的功率数据作为输出量,训练预测模型。在全球能源预测竞赛2012提供的wf1数据集上进行日前预测实验,测试集前30 d的平均均方根误差为0.1194,测试集107 d的平均均方根误差为0.1409,相较于ANN、BiLSTM、RF和KNN,相空间重构-BiLSTM(Re-BiLSTM)的预测准确度和精度更高,验证了所提出的短期风电功率预测模型的有效性、适用性和泛化性。展开更多
文摘According to the issues that the predict errors of chaotic sequences rapidly accumulated in multi-step forecasting which affects the predict accuracy, we proposed a new predict algorithm based on local modeling with variable frame length and interpolation points. The core idea is that, using interpolation method to increase the available sample data, then modeling the chaos dynamics system with least square algorithm which based on the Bernstein polynomial to realize the forecasting. We use the local modeling method, looking for the optimum frame length and interpolation points in every frame to improve the predict peformance. The experimental results show that the proposed algorithm can improve the predictive ability effectively, decreasing the accumulation of iterative errors in multi-step prediction.
