Home > View > Focus

Modeling and application of marketing and distribution data based on graph computing

2022-09-16

中国电科院肖凯等：基于图计算的电力营配数据建模及应用

原创英文期刊编辑部全球能源互联网期刊 2022-09-16 08:00

摘要

电网配电、营销业务融合是实现设备深度协同和多能高效消纳的重点方向。随着分布式新能源不断接入配电网，营配业务信息结构越来越复杂，在统一数据模型和营配协同应用方面仍然存在不足。本文通过分析营配领域业务及数据现状，利用图数据理论，构建“营配一张图”数据模型和营配图数据计算框架，并针对营配贯通中重点关注的户变关系识别问题，基于营配用户电量数据，提出基于热重启随机梯度下降算法和余弦退火算法的户变拓扑辨识与补全模型，通过滑动时间窗口算法多次提取用户电量数据求解该模型，经统计分析确定户变关系。最后，在上述研究基础上，建立分布式光伏发电及配电负荷预测、营配设备运维知识图谱推理应用，实现分布式光伏发电与配电负荷协同预测消纳，提升营配设备智能运维能力。

Modeling and application of marketing and distribution data based on graph computing

基于图计算的营配数据建模及应用

Kai Xiao¹, Daoxing Li¹, Xiaohui Wang¹, Pengtian Guo¹

(1. China Electric Power Research Institute Co. Ltd., Beijing 100192, P. R. China)

收听作者1分钟语音介绍

Modeling and Application of Marketing and Distribution Data

Abstract

Integrating marketing and distribution businesses is crucial for improving the coordination of equipment and the efficient management of multi-energy systems. New energy sources are continuously being connected to distribution grids; this, however, increases the complexity of the information structure of marketing and distribution businesses. The existing unified data model and the coordinated application of marketing and distribution suffer from various drawbacks. As a solution, this paper presents a data model of "one graph of marketing and distribution" and a framework for graph computing, by analyzing the current trends of business and data in the marketing and distribution fields and using graph data theory. Specifically, this work aims to determine the correlation between distribution transformers and marketing users, which is crucial for elucidating the connection between marketing and distribution. In this manner, a novel identification algorithm is proposed based on the collected data for marketing and distribution. Lastly, a forecasting application is developed based on the proposed algorithm to realize the coordinated prediction and consumption of distributed photovoltaic power generation and distribution loads. Furthermore, an operation and maintenance (O&M) knowledge graph reasoning application is developed to improve the intelligent O&M ability of marketing and distribution equipment.

Keywords

Marketing and distribution connection, Graph data, Graph computing, Knowledge graph, Data model.

Fig.1 Marketing and distribution graph data model architecture topology

Fig.2 Graph data model construction and fusion process

Fig.3 Marketing and distribution graph data connection

Fig.4 Flowchart for topology identification and completion algorithm

Fig.5 Marketing and distribution graph computing framework

Fig.6 Graph computing task executor based on “micro-operation”

Fig.7 Distribution load and distributed photovoltaic generation prediction and consumption model

Fig.8 O&M knowledge graph reasoning application for marketing and distribution equipment

本文引文信息

Xiao K, Li DX, Wang XH, et al. (2022) Subsynchronous oscillation monitoring and alarm method based on phasor measurements. Global Energy Interconnection, 5(4): 343-352

肖凯，李道兴，王晓辉，等 (2022) 基于图计算的营配数据建模及应用. 全球能源互联网（英文）, 5(4): 343-352

Biographies

Kai Xiao

Kai Xiao received master degree at North China Electric Power University, Baoding, in 2013. He is working in China Electric Power Research Institute Co., Ltd. His research interests include power big data technology, graph computing and marketing business.

Daoxing Li

Daoxing Li received master degree at North China Electric Power University, Beijing, in 2021. He is working in China Electric Power Research Institute Co., Ltd. His research interests include artificial intelligence and graph computing.

Xiaohui Wang

Xiaohui Wang received the Doctor’s degree from North China Electric Power University, Beijing, 2012. He is currently working at the China Electric Power Research Institute Co., Ltd. Beijing. His research interests include power big data technology, artificial intelligence, active distributed network, energy internet.

Pengtian Guo

Pengtian Guo received master degree at North China Electric Power University, Beijing, in 2020. He is working in China Electric Power Research Institute Co., Ltd. His research interests include power Internet of things and artificial intelligence.

编辑：王彦博

审核：王伟

郑重声明

根据国家版权局相关规定，纸媒、网站、微博、微信公众号转载、摘编本网站作品，需包含本网站名称、二维码等关键信息，并在文首注明《全球能源互联网》原创。个人请按本网站原文转发、分享。

Modeling and application of marketing and distribution data based on graph computing

中国电科院 肖凯等：基于图计算的电力营配数据建模及应用

郑重声明

中国电科院肖凯等：基于图计算的电力营配数据建模及应用