面向调控信息新鲜度保障的电力至简物联网资源优化

doi:10.11959/j.issn.1000-436x.2022124

通信学报 ›› 2022, Vol. 43 ›› Issue (7): 203-214.doi: 10.11959/j.issn.1000-436x.2022124

面向调控信息新鲜度保障的电力至简物联网资源优化

廖海君¹, 贾泽晗¹, 周振宇¹, 刘念¹, 王飞¹, 甘忠², 姚贤炯²

¹ 华北电力大学河北省电力物联网技术重点实验室，河北保定 071003
² 国网上海市电力公司电力调度控制中心，上海 200122

修回日期:2022-05-31 出版日期:2022-07-25 发布日期:2022-06-01
作者简介:廖海君（1997- ），女，广西贵港人，华北电力大学博士生，主要研究方向为电力物联网、智能电网中多模态通信技术等
贾泽晗（1998- ），男，河北保定人，华北电力大学硕士生，主要研究方向为电力物联网、智能电网中多模态通信技术等
周振宇（1983- ），男，河北张家口人，博士，华北电力大学教授、博士生导师，主要研究方向为无线通信网络与新技术、物联网与现代传感技术、能源互联网信息通信技术等
刘念（1981- ），男，安徽安庆人，博士，华北电力大学教授、博士生导师，主要研究方向为智能配用电、综合能源系统、信息物理系统等
王飞（1973- ），男，河北保定人，博士，华北电力大学教授、博士生导师，主要研究方向为新型电力系统、风光发电功率预测、虚拟电厂、电力市场与需求响应等
甘忠（1975- ），男，湖北鄂州人，国网上海市电力公司工程师，主要研究方向为电力系统通信、电力系统自动化与网络安全、继电保护等
姚贤炯（1972- ），男，浙江镇海人，国网上海市电力公司工程师，主要研究方向为电力系统通信、光传输新技术、电力系统控制业务5G技术应用等
基金资助:
国家电网有限公司科技基金资助项目(52094021N010)

Dispatching and control information freshness guaranteed resource optimization in simplified power Internet of things

Haijun LIAO¹, Zehan JIA¹, Zhenyu ZHOU¹, Nian LIU¹, Fei WANG¹, Zhong GAN², Xianjiong YAO²

¹ Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China
² Power Dispatching and Control Center of State Grid Shanghai Municipal Electric Power Company, Shanghai 200122, China

Revised:2022-05-31 Online:2022-07-25 Published:2022-06-01
Supported by:
Science and Technology Project of State Grid Corporation of China(52094021N010)

摘要/Abstract

摘要：

信息新鲜度对分布式能源调控模型训练精度具有重要影响。信息新鲜度较差会导致训练模型损失值增加，降低调控可靠性与经济性，影响能量实时供需平衡。电力至简物联网能够为分布式能源调控提供即插即用、多模态融合的通信支撑，但仍面临跨域资源优化与模型训练适配性差、调控信息新鲜度难以保障等挑战。针对上述问题，提出基于调控信息新鲜度感知的通信与计算资源协同优化算法，通过赤字虚拟队列演进感知调控信息新鲜度偏差。在此基础上，利用深度Q网络学习信道分配与批量规模联合优化策略，最小化模型损失函数，保障调控信息新鲜度长期约束。仿真结果表明，相较于基于联邦深度强化学习的低时延资源分配算法与自适应联邦学习批量规模优化算法，所提算法使全局损失函数降低57.19%和24.60%，信息新鲜度提高35.34%和49.05%。

关键词: 电力至简物联网, 分布式能源调控, 调控信息新鲜度, 多模态通信, 跨域资源协同

Abstract:

Information freshness conducts an important impact on the training accuracy of the distributed energy dispatching and control model.Poor dispatching and control information freshness will increase the loss function of the training model, reduce the reliability and economy of dispatching and control, and effect the real-time balance of energy supply and demand.Simplified power Internet of things can provide plug-and-play and multi-mode fusion communication support for distributed energy dispatching and control, but it still faces challenges of the inadaptability between cross-domain resource optimization and model training, and the difficulty in guaranteeing dispatching and control information freshness.To solve the above challenges, an information freshness aware-based communication-and-computation collaborative optimization algorithm (IFAC³O) was proposed, and the information freshness deviation was regulated by the awareness of deficit virtual queue evolution.On this basis, IFAC³O leveraged deep Q network and dispatching and control information freshness awareness to learn the channel allocation and batch size joint optimization strategy, thereby minimizing model loss function while guaranteeing long-term dispatching and control information freshness constraints.Compared with the federated DRL based low-latency resource allocation algorithm and adaptive federated learning-based batch size optimization algorithm, IFAC³O can reduce global loss function by 63.29% and 38.88% as well as improve information freshness by 20.59% and 57.69%.

Key words: simplified power Internet of things, distributed energy dispatching and control, dispatching and control information freshness, multi-mode communication, cross-domain resource cooperation

中图分类号:

TN915

廖海君, 贾泽晗, 周振宇, 刘念, 王飞, 甘忠, 姚贤炯. 面向调控信息新鲜度保障的电力至简物联网资源优化[J]. 通信学报, 2022, 43(7): 203-214.

Haijun LIAO, Zehan JIA, Zhenyu ZHOU, Nian LIU, Fei WANG, Zhong GAN, Xianjiong YAO. Dispatching and control information freshness guaranteed resource optimization in simplified power Internet of things[J]. Journal on Communications, 2022, 43(7): 203-214.

图/表 12

图1

图2

图3

表1

仿真参数"

参数	含义	取值
N	终端数量	12
J ₁,J₂,J₃	信道数量	5, 5, 5
T	迭代次数	200
\|D_n\|	终端本地数据集大小	50
γ	学习步长	0.1
P_PLC,P_WLAN,P_5G	终端传输功率/W	0.1, 0.1, 0.4
B_{n ,j}	信道带宽/kHz	200
$N_{0}^{U}$	噪声功率/(W·Hz^-1)	10^-12
V _H ,V_G	调控信息新鲜度权重，终端能耗赤字权重	80, 10
α_n	电磁干扰特征因子	1.4
β_n	电磁干扰偏斜参数	-0.791
υ_n	电磁干扰尺度参数	10^-4
μ_n	电磁干扰位置参数	1.2~2.6

表1

图4

图5

图6

图7

图8

图9

图10

表2

参考文献 25

[1]	王琦, 关添升 . 分布式能源接入对电网调度影响研究[J]. 应用能源技术, 2015(12): 42-44.
	WANG Q , GUAN T S . Study on the effect of distributed energy access to power grid scheduling[J]. Applied Energy Technology, 2015(12): 42-44.
[2]	彭政, 崔雪, 王恒 ,等. 考虑储能和需求侧响应的微网光伏消纳能力研究[J]. 电力系统保护与控制, 2017,45(22): 63-69.
	PENG Z , CUI X , WANG H ,et al. Research on the accommodation of photovoltaic power considering storage system and demand response in microgrid[J]. Power System Protection and Control, 2017,45(22): 63-69.
[3]	吴季珂 . 考虑通信时延的多主体分布式能源调控一致性研究[D]. 北京:华北电力大学, 2021.
	WU J K . Research on consensus of multi-agent distributed energy resources dispatching control considering communication delay[D]. Beijing:North China Electric Power University, 2021.
[4]	曾鸣, 彭丽霖, 孙静惠 ,等. 兼容需求侧可调控资源的分布式能源系统经济优化运行及其求解算法[J]. 电网技术, 2016,40(6): 1650-1656.
	ZENG M , PENG L L , SUN J H ,et al. Economic optimization and corresponding algorithm for distributed energy system compatible with demand-side resources[J]. Power System Technology, 2016,40(6): 1650-1656.
[5]	LI X J , WANG L J , YAN N ,et al. Cooperative dispatch of distributed energy storage in distribution network with PV generation systems[J]. IEEE Transactions on Applied Superconductivity, 2021,31(8): 1-4.
[6]	熊轲, 胡慧敏, 艾渤 ,等. 6G时代信息新鲜度优先的无线网络设计[J]. 物联网学报, 2020,4(1): 80-91.
	XIONG K , HU H M , AI B ,et al. Information freshness orientated wireless network design for 6G[J]. Chinese Journal on Internet of Things, 2020,4(1): 80-91.
[7]	鲍楠, 左加阔, 胡晗 ,等. 基于SDN的网络资源选择多目标优化算法[J]. 通信学报, 2019,40(2): 51-59.
	BAO N , ZUO J K , HU H ,et al. SDN based network resource selection multi-objective optimization algorithm[J]. Journal on Communications, 2019,40(2): 51-59.
[8]	桂冠, 王禹, 黄浩 . 基于深度学习的物理层无线通信技术:机遇与挑战[J]. 通信学报, 2019,40(2): 19-23.
	GUI G , WANG Y , HUANG H . Deep learning based physical layer wireless communication techniques:opportunities and challenges[J]. Journal on Communications, 2019,40(2): 19-23.
[9]	中国通信标准化协会. TC5 研究新一代无线接入网络体系架构[R]. 2021.
	CCSA. Research on the architecture of next-generation radio access network by TC5[R]. 2021. 2021.
[10]	刘光益. 6G网络三层四面至简、柔性、安全内生[R]. 2020.
	LIU G Y . 6G network with three layers and four sides,simple,flexible,and secure endogenous[R]. 2020.
[11]	赵羽, 杨洁, 刘淼 ,等. 面向视频监控基于联邦学习的智能边缘计算技术[J]. 通信学报, 2020,41(10): 109-115.
	ZHAO Y , YANG J , LIU M ,et al. Federated learning based intelligent edge computing technique for video surveillance[J]. Journal on Communications, 2020,41(10): 109-115.
[12]	LU Y L , HUANG X H , ZHANG K ,et al. Low-latency federated learning and blockchain for edge association in digital twin empowered 6G networks[J]. IEEE Transactions on Industrial Informatics, 2021,17(7): 5098-5107.
[13]	ZHANG J , GUO S , QU Z H ,et al. Adaptive federated learning on non-IID data with resource constraint[J]. IEEE Transactions on Computers, 2021,PP(99): 1.
[14]	李保罡, 武文静, 段晓 ,等. 基于 NOMA-MEC 系统的信息年龄最小化研究[J]. 通信学报, 2021,42(10): 222-232.
	LI B G , WU W J , DUAN X ,et al. Research on the minimizing of information age based on NOMA-MEC system[J]. Journal on Communications, 2021,42(10): 222-232.
[15]	SINHA D , ROY R . Scheduling status update for optimizing age of information in the context of industrial cyber-physical system[J]. IEEE Access, 2019,7: 95677-95695.
[16]	ZHOU Z Y , JIA Z H , LIAO H J ,et al. Secure and latency-aware digital twin assisted resource scheduling for 5G edge computing-empowered distribution grids[J]. IEEE Transactions on Industrial Informatics, 2022,18(7): 4933-4943.
[17]	ZHOU Z Y , WANG Z , YU H J ,et al. Learning-based URLLC-aware task offloading for Internet of health things[J]. IEEE Journal on Selected Areas in Communications, 2021,39(2): 396-410.
[18]	SUN W , LEI S Y , WANG L ,et al. Adaptive federated learning and digital twin for industrial Internet of things[J]. IEEE Transactions on Industrial Informatics, 2021,17(8): 5605-5614.
[19]	ZHOU Z Y , YANG X , XU C . Performance evaluation of multi-antenna based M2M communications for substation monitoring[C]// Proceedings of 2016 International Conference on Information and Communication Technology Convergence (ICTC). Piscataway:IEEE Press, 2016: 97-102.
[20]	孙径舟, 王乐涵, 孙宇璇 ,等. 面向6G网络的信息时效性度量及研究进展[J]. 电信科学, 2021,37(6): 3-13.
	SUN J Z , WANG L H , SUN Y X ,et al. Information timeliness metrics and research progress for 6G network[J]. Telecommunications Science, 2021,37(6): 3-13.
[21]	SUN Y X , ZHOU S , NIU Z S ,et al. Dynamic scheduling for over-the-air federated edge learning with energy constraints[J]. IEEE Journal on Selected Areas in Communications, 2022,40(1): 227-242.
[22]	SUN J , WANG L , JIANG Z ,et al. Age-optimal scheduling for heterogeneous traffic with timely throughput constraints[J]. IEEE Journal on Selected Areas in Communications, 2021,39(5): 1485-1498.
[23]	NEELY M J . Stochastic network optimization with application to communication and queueing systems[M]. San Rafael: Morgan and Claypool Publishers, 2010.
[24]	NGUYEN V D , SHARMA S K , VU T X ,et al. Efficient federated learning algorithm for resource allocation in wireless IoT networks[J]. IEEE Internet of Things Journal, 2021,8(5): 3394-3409.
[25]	LIU B W , HUA C Q , GU P . Age of information aware channel allocation for wireless industrial networks[C]// Proceedings of 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP). Piscataway:IEEE Press, 2019: 1-6.

面向调控信息新鲜度保障的电力至简物联网资源优化

Dispatching and control information freshness guaranteed resource optimization in simplified power Internet of things

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 25

相关文章 15

Metrics

推荐阅读 0

终端数量/个	信道数量/个	计算耗时/s
5	15	6.902 1
10	15	11.184 2
15	15	18.035 7
20	15	27.755 5

[1]	张海波, 兰凯, 陈舟, 王汝言, 邹灿, 王明月. 车联网中基于环的匿名高效批量认证与组密钥协商协议[J]. 通信学报, 2023, 44(6): 103-116.
[2]	冯霞, 崔凯平, 谢晴晴, 王良民. VANET中基于区块链的分布式匿名认证方案[J]. 通信学报, 2022, 43(9): 134-147.
[3]	刘俊, 王健. 轨道角动量光信号处理研究进展[J]. 通信学报, 2021, 42(11): 217-232.
[4]	王鹏, 张修社, 索龙, 史可懿. 基于随机时变图的时间确定性网络路由算法[J]. 通信学报, 2021, 42(9): 21-30.
[5]	张海波, 黄宏武, 刘开健, 贺晓帆. 车联网中可证安全的匿名可追溯快速组认证协议[J]. 通信学报, 2021, 42(6): 213-225.
[6]	朱近康, 柴名扬, 周武旸. 面向B5G/6G的三三三网络体系架构和优化学习机制[J]. 通信学报, 2021, 42(4): 62-75.
[7]	周振宇, 贾泽晗, 廖海君, 赵雄文, 张磊. 基于上下文学习的电力物联网接入控制方法[J]. 通信学报, 2021, 42(3): 150-159.
[8]	王文鼐, 张延贺, 吴炜, 柏琛, 王斌. 分布式排队中退避树的深度优先遍历算法[J]. 通信学报, 2021, 42(2): 72-80.
[9]	林艳, 闫帅, 张一晋, 李春国, 束锋. 基于交通流量预测的车联网双边拍卖边缘计算迁移方案[J]. 通信学报, 2020, 41(12): 205-214.
[10]	郭少勇,齐芫苑,代美玲,邱雪松,亓峰,张平. 面向智能共享的内生可信网络体系架构[J]. 通信学报, 2020, 41(11): 86-98.
[11]	赵海涛,陈跃,张唐伟,朱奇星,朱洪波. 车载异构网络中基于前向时延的多径传输路径调度优化[J]. 通信学报, 2020, 41(11): 99-107.
[12]	李红艳,张焘,张靖乾,史可懿,曾鹏程. 基于时变图的天地一体化网络时间确定性路由算法与协议[J]. 通信学报, 2020, 41(10): 116-129.
[13]	朱晓荣,张佩佩. 基于GAN的异构无线网络故障检测与诊断算法[J]. 通信学报, 2020, 41(8): 110-119.
[14]	陈福才,何威振,程国振,霍树民,周大成. 基于DPDK的内网动态网关关键技术设计[J]. 通信学报, 2020, 41(6): 139-151.
[15]	刘文学,陈诗军,葛建,袁洪,龚翠玲. 基于GNSS邻域相似性的5G基站纳秒级时间同步技术研究[J]. 通信学报, 2020, 41(1): 180-190.