计算机与现代化 ›› 2024, Vol. 0 ›› Issue (12): 59-65.doi: 10.3969/j.issn.1006-2475.2024.12.009

• 算法设计与分析 • 上一篇    下一篇

多尺度时间编码的工业园区短期负荷预测







  

  1. (西安工程大学计算机科学学院/陕西省服装设计智能化实验室,陕西 西安 710048)
  • 出版日期:2024-12-31 发布日期:2024-12-31
  • 基金资助:
    陕西省自然科学基础研究计划项目(2023-JC-YB-558); 陕西省教育厅科研计划项目(23JS028)
       

Short-term Load Forecasting in Industrial Parks with Multi-scale Time Coding

  1. (School of Computer Science, Xi’an Polytechnic University/Shaanxi Key Laboratory of Clothing Intelligence, Xi’an 710048, China) 
  • Online:2024-12-31 Published:2024-12-31

摘要: 针对工业园区短期负荷存在耦合性、非线性和随机性等问题,为了提升工业园区短期负荷预测精度,提出一种基于自编码器的自适应噪声完备集合经验模态分解和卷积神经网络-Transformer的短期负荷预测模型。考虑到真实场景中突发事件和紧急情况有时会造成负荷数据出现异常波动,首先,基于滑动时间窗口方法对异常数据进行检测与修正。其次,利用频域分解算法将历史负荷数据分为多尺度频域分量解决负荷数据的耦合性。再次,基于自编码器和特征工程方法生成与选取负荷波动相关性较大的外源特征与分量一起作为输入。然后,利用卷积神经网络对输入进行局部特征和潜在特征分析与特征融合,将结果输入Transformer网络,结合其编码能力和多头注意力机制捕获时间序列的特性。最后,叠加各子模块输出作为最终预测结果。结合真实负荷数据集进行实验验证,结果表明本文模型有效地提高了短期负荷预测精度。

关键词: 工业园区短期负荷预测, 自适应噪声完备集合经验模态分解, 自编码器, 特征融合, Transformer

Abstract:  To enhance the accuracy of short-term load prediction in industrial parks, a model based on complete ensemble empirical mode decomposition with adaptive noise with auto-encoder and convolutional neural network-Transformer is proposed. The model addresses the issues of coupling, nonlinearity, and stochasticity of short-term loads. Given that sudden events and emergencies in real scenarios can cause abnormal fluctuations in load data, the sliding time window method is used to firstly detect and correct any anomaly data. Secondly, the frequency domain decomposition algorithm is utilized to resolve the coupling of the load data by dividing the historical load data into multi-scale frequency domain components. Thirdly exogenous features with high correlation to be selected load fluctuations are generated using auto-encoder and feature engineering methods and used as inputs along with the components. Then a convolutional neural network is used to analyze latent features and fuse them with the inputs. The results are fed into the Transformer network, which combines its coding capability and multi-attention mechanism to capture the characteristics of the time series. The final prediction result is obtained by super-imposing the final output of each sub-module. Using the real load dataset as an example, the results demonstrate that the proposed model significantly enhances short-term load forecasting accuracy.

Key words: short-term load forecasting in industrial parks, complete ensemble empirical mode decomposition with adaptive noise, auto-encoder, feature fusion, Transformer

中图分类号: