| 引用本文: | 余凯峰,吐松江·卡日,张紫薇,等.基于级联MCNN-MMLP双残差网络的短期负荷预测[J].电力系统保护与控制,2025,53(02):151-162.[点击复制] |
| YU Kaifeng,TUSONGJIANG·Kari,ZHANG Ziwei,et al.Short-term load forecasting based on a cascade MCNN-MMLP double residual network[J].Power System Protection and Control,2025,53(02):151-162[点击复制] |
|
| 摘要: |
| 为了解决负荷特性复杂导致负荷预测精度低的问题，提出了一种GWO-VMD和级联MCNN-MMLP双残差网络的短期负荷预测模型。首先，利用由灰狼算法(grey wolf optimize, GWO)优化的变分模态分解(variational mode decomposition, VMD)对原始负荷数据进行处理，降低原始负荷数据的复杂程度。其次，使用多尺度卷积神经网络(multiscale convolutional neural networks, MCNN)和多层感知机(multi-layer perception, MLP)结合的双残差神经网络对各个模态进行迁移学习训练和预测，并在MLP网络中引入多头注意力机制弥补网络信息瓶颈问题。最后，再次使用MCNN-MMLP双残差模型对初步预测的误差进行预测并校正初值，从而进一步提升预测精确度。通过对实际负荷数据进行分析，本模型的均方误差为5.024(MW)2、均方根误差为2.241MW、平均绝对百分比误差为0.160%，决定系数为0.996，各性能指标均优于其他传统及智能负荷预测方法。 |
| 关键词: 负荷预测 多尺度卷积神经网络 双残差神经网络 多头注意力机制 迁移学习 |
| DOI：10.19783/j.cnki.pspc.240538 |
| 投稿时间：2024-05-05修订日期：2024-07-11 |
| 基金项目:国家自然科学基金项目资助(52067021，52207165)；新疆维吾尔自治区自然科学基金面上项目资助(2022D01C35)；新疆维吾尔自治区优秀青年科技人才培养项目资助(2019Q012) |
|
| Short-term load forecasting based on a cascade MCNN-MMLP double residual network |
| YU Kaifeng1,TUSONGJIANG·Kari1,ZHANG Ziwei2,MA Xiaojing1,WANG Zhigang1 |
| (1. School of Electrical Engineering, Xinjiang University, Urumqi 830049, China;
2. Sichuan Energy Internet Research Institute, Tsinghua University, Chengdu 610213, China) |
| Abstract: |
| There is an issue of decreased accuracy in load forecasting due to the complexity of load characteristics, so a short-term load forecasting model based on GWO-VMD and cascaded MCNN-MMLP residual networks is proposed. First, the original load data is processed using variational mode decomposition (VMD) optimized by grey wolf optimization (GWO) to reduce the complexity of the original load data. Secondly, a dual residual neural network combining multiscale convolutional neural networks (MCNN) and a multi-layer perceptron (MLP) is employed for transfer learning training and prediction of each mode. A multi-head attention mechanism is introduced into the MLP network to address the information bottleneck issue. Lastly, the MCNN-MMLP double residual model is used to predict and correct the errors in the preliminary prediction, thereby further improving the accuracy of the forecast. The proposed model outperforms the traditional and intelligent load forecasting models. It achieves a mean square error of 5.024 MW2, root mean square error of 2.241 MW, mean absolute percentage error of 0.160%, and coefficient of determination of 0.996 based on actual load data. |
| Key words: load forecasting multiscale convolutional neural network double residual neural network multi-head attention mechanism transfer learning |
