住宅短期电力负荷预测是一种关键应用场景,能够为电力公司和用户提供实时且准确的用电负荷预估,实现最优调度并合理分配电力资源.提出了一种基于双向长短期记忆(Bi-directional Long Short-Term Memory,BiLSTM)和卷积神经网络(Convolu-tional Neural Network,CNN)的CNN-BiLSTM预测模型.利用CNN对原始负载数据进行特征提取,以降低输入数据的维度并提高模型的运行效率;将提取的特征输入BiLSTM和CNN-BiLSTM模型中进行预测.该方法已在实际住宅负荷数据集上进行了验证,预测结果好于传统的基于时间序列的预测方法.这表明该方法在短期住宅负荷预测领域中具有广泛的应用前景.
Residential Short-Term Load Forecasting Based on BiLSTM and CNN-BiLSTM
Residential short-term power load forecasting is a key application scenario that can provide real-time and accurate power load estimation for power companies and users,and achieve optimal dispatch and rationally allocate power resources.A CNN BiLSTM prediction model based on Bidirectional Long Short Term Memory(BiLSTM)and Convolu-tional Neural Network(CNN)is proposed.CNN is used to extract features from raw load data to reduce the dimensionali-ty of input data and improve the operational efficiency of the model.The extracted features are fed into BiLSTM and CNN-BiLSTM models for prediction.This method has been validated on actual residential load datasets,and the predic-tion results are better than traditional time series based prediction methods.This indicates that the method has broad application prospects in the field of short-term residential load forecasting.
bi-directional long short-term memoryload forecastingoptimal schedulingfeature extractionconv-olutional neural network
NETL
NSTL
万方数据
