基于张量链的电网大数据多模态预测方法  

Multi-modal prediction method of power grid big data based on tensor chain

作　　者：陈彬 徐欢 邹文景 CHEN Bin;XU Huan;ZOU Wenjing(Digital Department,Digital Power Grid Research Institute Co.,Ltd.of China Southern Power Grid,Guangzhou 510700,Guangdong,China)

机构地区：[1]南方电网数字电网研究院有限公司数字化部,广东广州510700

出　　处：《沈阳工业大学学报》2024年第1期13-18,共6页Journal of Shenyang University of Technology

基　　金：国家自然科学基金项目(61501285);南方电网数字电网研究院有限公司科技项目(ZBKJXM00000012)。

摘　　要：为了优化大数据预测系统的准确率和运算耗时,在张量理论的基础上,提出了一种适用于电网领域的多模态预测方法。通过综合运用张量和马尔科夫理论,设计了一种具有较强适应性的多元多阶马尔科夫模型,以及无假设前提的马尔科夫转移方法。在此基础上,基于张量链理论的短期预测和长期预测算法,提出了具有较低计算复杂度的大数据多模态预测方法。相关仿真验证结果表明,与经典马尔科夫预测方法相比,基于张量链的多模态预测方法具有更高的预测准确率与更少的运算耗时。In order to optimize the accuracy and computing time of big data prediction system,a multi-modal prediction method based on tensor theory for power grid was proposed.By employing the tensor and Markov theories,a multi-variate and multi-order Markov model with strong adaptability and a Markov transfer method without hypothesis were designed.On this basis,the short-term and long-term prediction algorithms based on tensor chain theory were constructed,thus the multi-modal prediction method of big data with low computational complexity was proposed.The simulation results show that the multi-modal prediction method based on tensor chain has higher prediction accuracy and lower computing time in comparison with the classical Markov prediction method.

关 键 词：大数据 张量链 主特征值 多模态预测 并行计算 马尔科夫模型 复杂度分析 预测准确度 

分 类 号：TM[电气工程]