基于张量低秩补全算法的极端天气短期负荷预测

Short-Term Load Forecasting Based on Tensor Low-Rank Completion Algorithm in Extreme Weather

在线阅读下载PDF

导出

摘要高效准确的短期电力负荷预测对提升新型电力系统经济运行十分重要。针对极端天气场景下负荷预测数据量较少、随机性较强的特点,提出一种基于张量低秩补全算法的短期负荷预测模型,并选取极端高温场景展开研究。首先,给出极端天气定义,并基于改进型炎热指数和气温两项指标进行数据筛选;其次,提出一种基于张量的负荷数据补全模型,补全缺失数据;然后,通过Pearson相关性分析筛选输入特征量,构建基于长短时记忆(long short term memory, LSTM)网络和粗糙集理论(rough set theory, RST)的LSTM-RST短期负荷预测模型;最后,以苏州某地实际负荷数据设置算例进行验证,仿真结果表明,所提短期负荷预测方法具有较高的准确性。 Efficient and accurate short-term power load forecasting is very important to improve the economic operation of the new power system.In view of the characteristics of less load forecasting data and strong randomness in extreme weather scenarios,a short-term load forecasting model based on the tensor low-rank completion algorithm is proposed,and extreme high temperature scenarios are selected for the research.First,the definition of extreme weather is given and data screening is performed based on the improved heat index and temperature.Then,a tensor-based load data completion model is proposed to complete the missing data.The input features are selected by Pearson correlation analysis,and the short-term load forecasting model based on long and short time memory(LSTM)network and rough set theory(RST)is constructed.Finally,the actual load data in Suzhou is used for verification,and the simulation results show that the proposed short-term forecasting method has high accuracy.

作者冯家欢史雪晨张赟胡涛封钰洪晨威洪奕吴越涛 FENG Jiahuan;SHI Xuechen;ZHANG Yun;HU Tao;FENG Yu;HONG Chenwei;HONG Yi;WU Yuetao(Suzhou Power Supply Branch of State Grid Jiangsu Electric Power Co.,Ltd.,Suzhou 215004,Jiangsu Province,China)

机构地区国网江苏省电力有限公司苏州供电分公司

出处《分布式能源》 2024年第4期51-59,共9页 Distributed Energy

基金国家电网公司科技项目(5100-202235272A-2-0-XG)。

关键词极端天气高温场景炎热指数短期负荷预测张量低秩补全长短时记忆(LSTM)网络粗糙集理论(RST) extreme weather high temperature scenario heat index short-term load forecasting tensor lowrank completion long short term memory(LSTM)network rough set theory(RST)

分类号 TK01 [动力工程及工程热物理] TM71 [电气工程—电力系统及自动化]

作者简介冯家欢(1994),男,硕士,工程师,研究方向为主网调度与故障处理。史雪晨(1996),女,硕士,研究方向为电力计量与电力负荷管理;张赟(1996),女,硕士,研究方向为电力营销管理;胡涛(1981),男,硕士,高级工程师,研究方向为电力营销管理;封钰(1996),男,硕士,研究方向为主网调度与负荷管理,fengyuhm@163.com;洪晨威(1996),男,硕士,研究方向为配网调度与负荷管理;洪奕(1995),男,硕士,工程师,研究方向为主网调度与故障处理;吴越涛(1984),男,硕士,高级工程师,研究方向为电力设备运行与维护。