计算机与现代化 ›› 2021, Vol. 0 ›› Issue (10): 94-99.

• 网络与通信 • 上一篇    下一篇

基于多层融合神经网络模型的短期电力负荷预测方法

  

  1. (1.昆明理工大学电力工程学院,云南昆明650504; 2.昆明理工大学机电工程学院,云南昆明650504;
    3.成都国龙信息工程有限责任公司,四川成都610031; 4.云南电网有限责任公司楚雄武定供电局,云南武定651600)
  • 出版日期:2021-10-14 发布日期:2021-10-14
  • 作者简介:郭成(1978—),男,河南范县人,教授级高级工程师,博士,研究方向:电力系统分析与控制,电能质量监测与分析,新能源并网控制,E-mail: gc325@126.com; 通信作者:王宵(1996—),男,江苏泰兴人,硕士研究生,研究方向:智能制造,数字化设计与制造,E-mail: 20192103003@stu.kust.edu.cn; 王波(1982—),男,四川巴县人,工程师,研究方向:信息化支撑技术,系统控制与分析,E-mail: 18908006700@qq.com; 王加富(1987—),男,云南寻甸人,工程师,学士,研究方向:供电可靠性管理,电压质量无功应用,E-mail: 625230739@qq.com。
  • 基金资助:
    国家重点研发计划项目(2017YFB1400301)

A Short-term Power Load Forecasting Method Based on Multi-layer Fusion Neural Network

  1. (1. Faculty of Electrical Power Engineering, Kunming University of Science and Technology, Kunming 650504, China;
    2. Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming 650504, China;
    3. Chengdu Guolong Information Engineering Co., Ltd., Chengdu 610031, China;
    4. Chuxiong Wuding Power Supply Bureau, Yunnan Power Grid Co., Ltd., Wuding 651600, China)
    〖HJ1.1mm〗〖HK163mm〗
  • Online:2021-10-14 Published:2021-10-14

摘要: 针对传统的短期电力负荷预测模型存在的预测精度不高和滞后性的问题,本文提出一种基于卷积神经网络、长短时记忆网络和注意力机制下的混合神经网络模型来进行预测。利用卷积层对多维的电力数据影响特征进行提取,过滤筛选其非重要影响因子,完成电力数据相关特征的映射变换,再通过长短时记忆网络层的循环,对时序性电力数据特征选择性提取,最后利用注意力机制添加重要特征的权重,经Adam算法优化后输出电力负荷预测的结果。依靠GPU强大的算力支撑来解决预测数据时的实时性问题,凭借多融合神经网络的手段来提高其预测精度。经由算例验证,所提出模型真实可靠,预测质量显著优于其他传统模型。

关键词: 短期电力负荷预测, 卷积神经网络, 长短时记忆神经网络, 注意力机制

Abstract: In view of the low accuracy and hysteresis of the traditional short-term power load forecasting model, this paper proposes a hybrid neural network model based on CNN (convolutional neural network), LSTM (long short-time memory network) and attention mechanism. The convolutional layer is used to extract the influence features of multidimensional power data, filter the non-important factors, complete the mapping transformation of relevant features of power data. Then the cycle of the long short-time memory network layer can selectively forget and remember the temporal data. Finally, the attention mechanism is used to add the weight of important features, and the results will be exported by Adam optimization. This method relies on the GPU’s big and powerful computing to solve the real-time problem of prediction, improving its accuracy of prediction by means of multi-fusion neural networks. The proposed model is proved to be true and reliable in the light of an example, and the quality of prediction is significantly better than other traditional models.

Key words: short-term power load forecasting, convolutional neural network, long short-time memory neural network, attention mechanism