数字配电网边缘计算模拟实验平台

doi:10.11930/j.issn.1004-9649.202310041

摘要/Abstract

摘要：

围绕数字配电网边缘计算实验平台建设问题，构建了数字配电网边缘计算模拟平台的三层式架构，设计了模拟实验平台各物理环节功能以及通信环境。针对边缘计算软硬件平台核心技术问题，围绕配电网运行控制需求提出了具体可行的模拟实验解决方案。以边缘侧就地电压控制为例，基于实验平台各个环节构建运行场景，验证了平台的功能可行性和有效性。

关键词: 数字配电网, 数字化, 边缘计算, 实验平台

Abstract:

This paper focuses on the construction of an experimental platform for edge computing, and first builds the three-layer experimental platform architecture. Then, the functions of each physical part of the experimental platform and the communication environment are designed. Subsequently, targeting the core technical problems of software and hardware of edge computing, a specific and feasible simulation solution is proposed around the operation and control needs of distribution networks. Finally, taking edge-side local voltage control as an example, the operation scenarios are constructed based on various aspects of the experimental platform to illustrate the functional feasibility and reliability of the platform.

Key words: digital distribution network, digitalization, edge computing, experimental platform

魏明江, 李鹏, 于浩, 冀浩然, 宋关羽, 习伟. 数字配电网边缘计算模拟实验平台[J]. 中国电力, 2024, 57(3): 12-19.

Mingjiang WEI, Peng LI, Hao YU, Haoran JI, Guanyu SONG, Wei XI. Experiment Platform of Edge Computing for Digital Distribution Networks[J]. Electric Power, 2024, 57(3): 12-19.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202310041

https://www.electricpower.com.cn/CN/Y2024/V57/I3/12

图/表 10

图 1 数字配电网及边缘计算模拟实验平台架构

Fig.1 Architecture of digital distribution networks and EPEC

图 2 仿真层功能构成

Fig.2 Architecture of simulation layer

图 3 一种典型数字配电网边缘计算装置

Fig.3 A typical edge computing device for digital distribution networks

图 4 边缘计算模拟实验平台网络架构

Fig.4 Network architecture of EPEC

图 5 边缘计算模拟实验平台软件运行环境

Fig.5 Applications' runtime environment of EPEC

表 1 人工智能任务测试参数

Table 1 Parameters of artificial intelligence tasks

网络	参数	数值
策略网络	输入参数数量	159
	输出参数数量	5
	模型参数数量	612 613
评价网络	输入参数数量	164
	输出参数数量	1
	模型参数数量	620 929

表 2 人工智能任务测试结果

Table 2 Test results of artificial intelligence tasks

子场景	参数	用时/ms
边缘推理过程	单次推理平均时长	0.981
云端训练过程	单次训练平均时长	106.327

表 3 边缘侧优化任务测试结果

Table 3 Test results of optimization tasks at edge side

参数		数值
变量数量/个		331.00
线性约束数量/个		162.00
二阶锥约束数量/个		52.00
求解失败次数/次		0
单次求解平均时长/s		0.49

图 6 融合系统多项服务的演示场景示意

Fig.6 Demonstration scenario schematic involved multiple services of EPEC

图 7 电压极值监控数据

Fig.7 Monitoring data of maximum and minimum voltages

参考文献 25

1	马喜平, 李亚昕, 梁琛, 等. 考虑高比例多元调节资源互动的配电网无功优化降损方法[J]. 中国电力, 2024, 57 (1): 123- 132.
	MA Xiping, LI Yaxin, LIANG Chen, et al. Reactive power optimization for loss reduction of distribution network considering interactions of high penetration level of multiple regulating energy resources[J]. Electric Power, 2024, 57 (1): 123- 132.
2	李鹏, 习伟, 蔡田田, 等. 数字电网的理念、架构与关键技术[J]. 中国电机工程学报, 2022, 42 (14): 5002- 5017.
	LI Peng, XI Wei, CAI Tiantian, et al. Concept, architecture and key technologies of digital power grids[J]. Proceedings of the CSEE, 2022, 42 (14): 5002- 5017.
3	刘曌, 孙庆凯, 许泽凯, 等. 能源互联网中的数字孪生技术体系、应用与挑战[J]. 中国电力, 2024, 57 (1): 230- 243.
	LIU Zhao, SUN Qingkai, XU Zekai, et al. System, applications and challenges of digital twin technology in energy Internet[J]. Electric Power, 2024, 57 (1): 230- 243.
4	习伟, 李鹏, 李鹏, 等. 面向配电网边缘计算装置的两阶段PMU数据压缩方法[J]. 电网技术, 2023, 47 (8): 3184- 3193.
	XI Wei, LI Peng, LI Peng, et al. Two-stage PMU data compression for edge computing devices of distribution networks[J]. Power System Technology, 2023, 47 (8): 3184- 3193.
5	张大波, 李雪婷, 陶维青. 基于边缘计算和深度学习的有限信息配电网单相接地故障区段定位[J]. 电力系统保护与控制, 2023, 51 (24): 22- 32.
	ZHANG Dabo, LI Xueting, TAO Weiqing. Single-phase ground fault section location in distribution networks with limited information based on edge computing and deep learning[J]. Power System Protection and Control, 2023, 51 (24): 22- 32.
6	王鹤, 王钲淇, 韩皓, 等. 使用蒙特卡罗逐时估算模型的住宅配电网光伏准入容量研究[J]. 东北电力大学学报, 2023, 43 (1): 9- 19.
	WANG He, WANG Zhengqi, HAN Hao, et al. Research on photovoltaic hosting capacity of residential distribution network based on Monte Carlo hourly estimation framework[J]. Journal of Northeast Electric Power University, 2023, 43 (1): 9- 19.
7	程杉, 傅桐, 李沣洋, 等. 含高渗透可再生能源的配电网灵活性供需协同规划[J]. 电力系统保护与控制, 2023, 51 (22): 1- 12.
	CHENG Shan, FU Tong, LI Fengyang, et al. Flexible supply demand collaborative planning for distribution networks with high penetration of renewable energy[J]. Power System Protection and Control, 2023, 51 (22): 1- 12.
8	李翠萍, 朱文超, 李军徽, 等. 分布式电源接入中压配电网的运行方案研究[J]. 东北电力大学学报, 2023, 43 (4): 57- 64.
	LI Cuiping, ZHU Wenchao, LI Junhui, et al. Research on the operation scheme of distributed generation access to medium voltage distribution network[J]. Journal of Northeast Electric Power University, 2023, 43 (4): 57- 64.
9	李帅, 徐迪, 文祥宇, 等. 面向配电网多业务资源智能调度的边缘容器迁移优化方法[J]. 中国电力, 2023, 56 (9): 120- 126.
	LI Shuai, XU Di, WEN Xiangyu, et al. An edge container migration optimization method for multi-service intelligent resource scheduling of distribution networks[J]. Electric Power, 2023, 56 (9): 120- 126.
10	黄南天, 郭玉, 赵暄远. 计及辐照区间划分的含光伏电源配电网源-荷联合场景生成[J]. 东北电力大学学报, 2023, 43 (5): 78- 84.
	HUANG Nantian, GUO Yu, ZHAO Xuanyuan. Combined source-load scenario generation for PV-containing distribution networks with calculation and irradiation interval classification[J]. Journal of Northeast Electric Power University, 2023, 43 (5): 78- 84.
11	丁琦欣, 覃洪培, 万灿, 等. 基于机会约束规划的配电网分布式光伏承载能力评估[J]. 东北电力大学学报, 2022, 42 (6): 28- 38.
	DING Qixin, QIN Hongpei, WAN Can, et al. Chance-constrained optimization-based distributed photovoltaic hosting capacity assessment of distribution networks[J]. Journal of Northeast Electric Power University, 2022, 42 (6): 28- 38.
12	习伟, 李鹏, 李鹏, 等. 基于深度强化学习的分布式电源就地自适应电压控制方法[J]. 电力系统自动化, 2022, 46 (22): 25- 31.
	XI Wei, LI Peng, LI Peng, et al. Adaptive local voltage control method for distributed generator based on deep reinforcement learning[J]. Automation of Electric Power Systems, 2022, 46 (22): 25- 31.
13	崔炳荣, 李德建, 刘亮, 等. 面向分布式光伏状态实时感知的边缘缓存与计算策略[J]. 智慧电力, 2023, 51 (8): 67- 74.
	CUI Bingrong, LI Dejian, LIU Liang, et al. Edge caching and computing strategy for distributed photovoltaic real-time sensing[J]. Smart Power, 2023, 51 (8): 67- 74.
14	杜觉晓, 赵留学, 莽修伟, 等. 基于边缘端目标识别与跟踪算法的输电线路航拍视频流诊断技术研究[J]. 智慧电力, 2023, 51 (6): 106- 113.
	DU Juexiao, ZHAO Liuxue, MANG Xiuwei, et al. Aerial video stream diagnosis technology for transmission lines based on edge target recognition and tracking algorithm[J]. Smart Power, 2023, 51 (6): 106- 113.
15	毋炳鑫, 黄利军, 王坤, 等. 边缘物联终端在智能化开关柜中的应用[J]. 南方电网技术, 2022, 16 (12): 38- 45.
	WU Bingxin, HUANG Lijun, WANG Kun, et al. Application of edge IoT terminal in intelligent switchgear[J]. Southern Power System Technology, 2022, 16 (12): 38- 45.
16	肖白, 朱珈汛, 刘鑫, 等. 基于CRITIC法和非合作博弈的电动汽车充电站双层规划[J]. 东北电力大学学报, 2022, 42 (4): 35- 49.
	XIAO Bai, ZHU Jiaxun, LIU Xin, et al. Bi-level planning of electric vehicle charging stations based on CRITIC method and non-cooperative game[J]. Journal of Northeast Electric Power University, 2022, 42 (4): 35- 49.
17	黄四亮, 孟湛博, 邢晓敏, 等. 考虑灾前预防和灾时响应状态下的弹性配电网提升策略研究[J]. 东北电力大学学报, 2023, 43 (4): 82- 89.
	HUANG Siliang, MENG Zhanbo, XING Xiaomin, et al. Consider the research on the improvement strategy of resilient distribution network under pre-disaster prevention and disaster response[J]. Journal of Northeast Electric Power University, 2023, 43 (4): 82- 89.
18	刘金, 李更丰, 孙思源, 等. 暴雨灾害下配电网预警与风险评估技术研究综述[J]. 东北电力大学学报, 2022, 42 (6): 1- 7.
	LIU Jin, LI Gengfeng, SUN Siyuan, et al. A review of early warning and risk assessment technologies for distribution networks under rainstorm disasters[J]. Journal of Northeast Electric Power University, 2022, 42 (6): 1- 7.
19	张颖, 寇凌峰, 季宇, 等. 计及储能与分布式电源协同的配电网分层分区优化控制[J]. 中国电力, 2021, 54 (2): 104- 112.
	ZHANG Ying, KOU Lingfeng, JI Yu, et al. Hierarchical and partitioned optimal control of distribution networks considering the coordination between energy storage and distributed generation systems[J]. Electric Power, 2021, 54 (2): 104- 112.
20	陆旭, 陈影, 许中平, 等. 面向5G边缘计算网络的联合需求响应与任务卸载策略[J]. 中国电力, 2022, 55 (10): 209- 218.
	LU Xu, CHEN Ying, XU Zhongping, et al. Joint demand response and task offloading strategy for 5G edge computing network[J]. Electric Power, 2022, 55 (10): 209- 218.
21	黄国威, 彭元泉, 范心明, 等. 含多端柔性多状态开关的有源配电网多阶段供电恢复方法[J]. 广东电力, 2020, 33 (12): 73- 80.
	HUANG Guowei, PENG Yuanquan, FAN Xinming, et al. Multi-step power restoration of active distribution networks with multi-terminal soft open point integration[J]. Guangdong Electric Power, 2020, 33 (12): 73- 80.
22	GAI K K, WU Y L, ZHU L H, et al. Permissioned blockchain and edge computing empowered privacy-preserving smart grid networks[J]. IEEE Internet of Things Journal, 2019, 6 (5): 7992- 8004. DOI
23	张宇航, 倪明, 孙永辉, 等. 针对网络攻击的配电网信息物理系统风险量化评估[J]. 电力系统自动化, 2019, 43 (21): 12- 22.
	ZHANG Yuhang, NI Ming, SUN Yonghui, et al. Quantitative risk assessment of cyber-physical system for cyber-attacks in distribution network[J]. Automation of Electric Power Systems, 2019, 43 (21): 12- 22.
24	GAO S, PENG Z, TAN F, et al. SymmeProof: compact zero-knowledge argument for blockchain confidential transactions[J]. IEEE Transactions on Dependable and Secure Computing, 2023, 20 (3): 2289- 2301.
25	LI P, JI J, JI H R, et al. MPC-based local voltage control strategy of DGs in active distribution networks[J]. IEEE Transactions on Sustainable Energy, 2020, 11 (4): 2911- 2921. DOI

[1]	夏向阳, 谭欣欣, 单周平, 李辉, 徐志强, 吴晋波, 岳家辉, 陈贵全. 储能电站锂离子电池本体安全关键技术及新技术应用情况[J]. 中国电力, 2024, 57(11): 1-17.
[2]	贺馨仪, 董明, 孙歆, 颜拥, 姚影. 标准数字化应用框架设计及其设备侧领域实践[J]. 中国电力, 2024, 57(11): 78-87.
[3]	吴钢, 周金辉, 李慧. 面向边缘增强分布式电力无线传感网的资源分配[J]. 中国电力, 2023, 56(8): 77-85,98.
[4]	李天楚, 容斌, 伍智鹏, 黄珏, 黄开来, 杨刚, 易杨. 基于边缘计算的风电群非故意发射超高次谐波抑制策略[J]. 中国电力, 2023, 56(8): 200-206,215.
[5]	马超. 面向机器可读标准的电力标准数字化述评与展望[J]. 中国电力, 2023, 56(8): 216-229.
[6]	杨晋祥, 彭勇刚, 蔡田田, 习伟, 邓清唐. 面向边缘计算的电力终端轻量级认证协议[J]. 中国电力, 2023, 56(4): 88-94.
[7]	严亚兵, 褚旭, 肖豪龙, 梁文武, 李辉, 夏振兴. 基于改进支持向量机的数字化变电站安全措施生成技术[J]. 中国电力, 2023, 56(10): 194-201.
[8]	孙毅, 常少南, 陈恺, 崔强, 沈维捷. 面向电工智慧物联的服务缓存和计算卸载策略[J]. 中国电力, 2022, 55(4): 23-32,43.
[9]	林日晖, 陈友立. 基于深度Q学习的含用户侧储能微电网频率-电压数字化智能控制策略[J]. 中国电力, 2022, 55(12): 43-50.
[10]	陆旭, 陈影, 许中平, 张海全, 慕春芳, 陈恺, 孙毅. 面向5G边缘计算网络的联合需求响应与任务卸载策略[J]. 中国电力, 2022, 55(10): 209-218.
[11]	黄冬梅, 王玥琦, 胡安铎, 孙锦中, 时帅, 孙园, 房岭锋. 融合多维度特征的绝缘子状态边缘识别方法[J]. 中国电力, 2022, 55(1): 133-141.
[12]	戴璐平, 瞿青, 黄露, 潘晔. 基于配网新形态下电费风险模型构建与应用[J]. 中国电力, 2021, 54(8): 98-102.
[13]	刘世栋, 卜宪德, 刘川, 田峰. 基于计算卸载的电力物联网能效优化研究[J]. 中国电力, 2021, 54(5): 28-34,45.
[14]	靳开元, 杨建华, 陈正, 王维洲, 侯斌, 薛文景. 基于区块链的分布式光伏就地消纳交易模式研究[J]. 中国电力, 2021, 54(5): 8-16.
[15]	路艳巧, 孙翠英, 曹红卫, 闫红伟. 基于边缘计算与深度学习的输电设备异物检测方法[J]. 中国电力, 2020, 53(6): 27-33.