摘要
随着可再生能源和互联网技术的快速发展,以大数据为代表的新型互联网技术为大量能源节点与信息节点间能量流和信息流的双向流动提供了可能,推动了能源体系的又一次变革。由于多能互补系统中冷热电负荷具有强随机性,且与各自的输入呈现非线性关系,因此人工神经网络常被用于多能互补综合能源系统中的冷热电负荷的预测。为解决新型配电网中多设备互联问题,本文在采集到多源异构数据的基础上,建立了基于IEC61850标准的新型配电网多设备信息模型。考虑到多源异构数据结构复杂、种类繁多,从逻辑和物理层面分析不同来源、不同格式数据的时间、空间、量值等特性,并综合考虑配电网大数据中多能负荷的不确定性,研究了基于大数据的新型配电网冷热电负荷预测方法。最后,基于对泰州中国医药城冷热电负荷特征分析,对其中冷热电负荷进行了预测,验证了本文所研究的新型配电网大数据集成技术的有效性与可行性。
With the rapid development of renewable energy and Internet technology, the novel Internet technology represented by big data provides the possibility for the two-way flow of energy and information between a large number of energy nodes and information nodes, and promotes another reform of the energy system. Since cold, heat and electricity loads in multi-energy complementary systems are strongly random, and present non-linear relationships with their respective inputs, artificial neural networks are often used to predict cold, heat and electricity loads in multi-energy complementary integrated energy systems.In order to solve the problem of multi-device interconnection in the new distribution network, based on the multi-source heterogeneous data collected, a new multi-device information model of novel power distribution network based on IEC61850 standard is established in this paper.Time, space, value and other characteristics of different sources and formats are analyzed from the logical and physical level, with the characteristics of multi-source heterogeneous data considered, such as complex structure and diverse classification. Also, based on the uncertainty of multi-energy load in the big data of the distribution network, this paper has studied the prediction method of cold, heat and electricity load in the novel distribution network based on big data. Finally, based on the characteristic analysis of cold, heat and electricity load in Taizhou China Medical City, the cold, heat and electricity load prediction has been carried out to verify the effectiveness and feasibility of the big data integration technology applied in the novel distribution network.
作者
梁馨予
方锐
甘青山
施亮
何律
管婵波
LIANG Xinyu;FANG Rui;SHI Liang;GAN Qingshan;HE Lyu;GUAN Chanbo(State Grid Changzhou Power Grid Company,Changzhou 213000,Jiangsu,China)
出处
《电力大数据》
2022年第7期53-61,共9页
Power Systems and Big Data
