基于深度学习的矿山电力负荷预测模型

Deep learning-based model for mine power load forecasting

  • 摘要: 针对现有矿山电力负荷预测方法对瞬时突变、长时序依赖衰减及多工况漂移等特征的协同建模能力不足的问题,构建了一种基于深度学习的矿山电力负荷预测模型。该模型以卷积神经网络(CNN)和双向长短期记忆网络(BiLSTM)为基础框架,从输入特征、网络结构、超参数3个方面进行改进:引入最大信息系数自适应筛选输入特征;在卷积层后引入挤压与激励(SE)注意力机制,对关键特征通道进行自适应加权,以增强对负荷局部波动与突变特征的表征能力,并在时序建模阶段将部分长短期记忆网络(LSTM)替换为门控循环单元(GRU),并引入残差连接,以增强模型对矿山电力负荷变化趋势的拟合能力;以平均绝对百分比误差(MAPE)为优化目标,利用贝叶斯优化(BO)迭代搜索较优超参数组合,提高模型参数与矿山负荷时序特征的适配性。实验结果表明:该模型预测矿山电力负荷的平均绝对误差(MAE)、均方根误差(RMSE)、平均绝对百分比误差(MAPE)分别为19.87 kW,25.68 kW,2.18%,决定系数R2达0.983;在负荷节点突变时的预测准确率可达95.21%,且相对误差平均值仅为3.57%,对连续运行24 h的尖峰负荷预测误差平均值低至3.39%,时间序列一致性指标平均值为0.988;单轮训练耗时为20.8 s,单次预测耗时为118.6 ms,实现了预测精度与效率的平衡。

     

    Abstract: To address the limited ability of existing mine power load forecasting methods to jointly model sudden changes, attenuation of long-term temporal dependencies, and drift across operating conditions, a deep learning-based mine power load forecasting model was developed. Based on a Convolutional Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BiLSTM) network, the model was improved in three aspects: input features, network architecture, and hyperparameters. The maximal information coefficient was introduced to adaptively select input features. A Squeeze-and-Excitation (SE) attention mechanism was introduced after the convolutional layers to adaptively weight key feature channels, enhancing the representation of local load fluctuations and sudden changes. During temporal modeling, some Long Short-Term Memory (LSTM) units were replaced with Gated Recurrent Units (GRUs), and residual connections were introduced to improve the model's ability to fit trends in mine power load variations. Using Mean Absolute Percentage Error (MAPE) as the optimization objective, Bayesian Optimization (BO) was employed to iteratively search for better hyperparameter combinations, improving the match between model parameters and the temporal characteristics of mine loads. Experimental results showed values of 19.87 kW, 25.68 kW, and 2.18% for Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and MAPE, respectively, with the coefficient of determination R2 reaching 0.983. When sudden changes occurred at load nodes, prediction accuracy reached 95.21%, with a mean relative error of only 3.57%. During 24 h of continuous operation, the mean peak load prediction error was as low as 3.39%, and the mean time series consistency index was 0.988. The training time per epoch was 20.8 s, and the time per prediction was 118.6 ms, the balance between prediction accuracy and efficiency is achieved.

     

/

返回文章
返回