1. 山东省智能电网技术创新中心,山东,济南,250003
2. 山东省能源工业互联网大数据技术重点实验室,山东,济南,250003
纸质出版:2025
移动端阅览
张昊,刘冬兰,王睿,张方哲.基于自适应门控Mixup网络的5G智能配电网稳定性预测方法[J].智慧电力,2025,53(6):28-34.
ZHANG Hao, LIU Dongla, WANG Rui, et al. Prediction Method for 5G-enabled Smart Distribution Network Stability Based on Adaptive Gated Mixup Network[J]. 2025, 53(6): 28-34.
张昊,刘冬兰,王睿,张方哲.基于自适应门控Mixup网络的5G智能配电网稳定性预测方法[J].智慧电力,2025,53(6):28-34. DOI: 10.20204/j.sp.2025.06004.
ZHANG Hao, LIU Dongla, WANG Rui, et al. Prediction Method for 5G-enabled Smart Distribution Network Stability Based on Adaptive Gated Mixup Network[J]. 2025, 53(6): 28-34. DOI: 10.20204/j.sp.2025.06004.
随着智能配电网与5G通信技术的深度融合,电力系统在获得发展与创新的同时也面临着诸多挑战。针对配电网在复杂环境下稳定性预测准确率不高的问题,提出一种基于自适应门控Mixup网络(AGMN)的5G智能配电网稳定性预测方法。通过构建基于样本预测概率的自适应门控策略,并引入加权训练损失以增强模型的状态判别能力,从而改进虚拟样本的质量,最终实现预测模型准确率与泛化性能的全面提升。仿真分析表明,所提AGMN方法在不同样本类别分布下均表现出优异的预测效果和较强的泛化能力,且在样本类别不平衡场景中依然可以保持较高的准确率。
With the deep integration of smart distribution networks and 5G communication technologies, power systems are encountering both developmental opportunities and numerous challenges. To address the issue of low accuracy in stability prediction for distribution networks under complex environments, this paper proposes a 5G-enabled smart distribution network stability prediction method based on an adaptive gated mixup network (AGMN). By constructing an adaptive gated strategy grounded in sample prediction probabilities and introducing weighted training loss to enhance the model’s state discrimination capability, the quality of virtual samples is improved, thereby achieving comprehensive enhancement in prediction accuracy and generalization performance. Simulation analysis demonstrates that the proposed AGMN method exhibits superior prediction effectiveness and robust generalization capability under varying sample class distributions, while maintaining high accuracy even in class-imbalanced scenarios.
赵洋,赵晓红,任天成,等.5G通信在电力系统中的应用[J].山东电力技术,2020,47(10):6-10.
曹辰,王增平. 极端天气对新型电力系统的影响及应对措施思考[J]. 南方能源建设,2025,12(1):43-57.
王竞才,李琰,徐天奇. 基于扩展卡尔曼滤波的智能电网虚假数据检测[J].智慧电力,2022,50(3):49-56.
刘冬兰,张昊,卢思翰,等.电力物联网设备安全检测系统设计与应用[J].山东电力技术,2022,49(9):29-35.
BREVIGLIERI P,TÜRKÜCAN E,SÜLEYMAN E. Predicting smart grid stability with optimized deep models[J]. SN Computer Science,2021,2(15):1-12.
ANWER M H,AISHA H A H,HEBA G M,et al. Water wave optimization with deep learning driven smart grid stability prediction[J]. Computers,Materials and Continua,2022,73(3): 6019-6035.
马世英,朱存浩,郑超,等. 扩展相轨迹特征解析及暂态稳定判别方法研究[J]. 中国电机工程学报,2020,40(20):6516-6527.
ÖNDER M,DOGAN M U,POLAT K. Classification of smart grid stability prediction using cascade machine learning methods and the internet of things in smart grid[J]. Neural Computing and Applications,2023,35(24):17851-17869.
RAGHAVENDRA S,NEELAKANDAN S,PRAKASH M,et al. Artificial humming bird with data science enabled stability prediction model for smart grid[J]. Sustainable Computing:Informatics and Systems,2022,36(5):1-10.
刘嘉诚,刘俊,李雨婷,等. 基于两阶段信息压缩的电网动态轨迹预测与稳定性评估[J]. 电力系统自动化,2023,47(20):13-22.
刘颂凯,党喜,崔梓琪,等. 针对样本类不平衡的深度残差网络电力系统暂态稳定评估方法[J]. 智慧电力,2024,52(1):116-123.
REEM I A,EL-SAYED M E,MARWA M E,et al. Optimizing IoT-driven smart grid stability prediction with dipper throated optimization algorithm for gradient boosting hyperparameters[J]. Energy Reports,2024,12(1):305-320.
林涛,林政阳,李晨,等. 基于TCN的跟网/构网混合型新能源场站并网系统小干扰稳定性快速评估[J]. 电力科学与技术学报,2024,39(4):169-177.
李欣,付豫韬,李新宇,等. 基于GAF-CNN的电力系统暂态稳定评估[J]. 智慧电力,2023,51(11):45-52.
ALSIRHANI A,ALSHAHRANI M M,ABUKWAIK A,et al. A novel approach to predicting the stability of the smart grid utilizing MLP-ELM technique[J]. Alexandria Engineering Journal,2023,74(1):495-508.
ADEL B,MOHEMMED S. Stability prediction in smart grid using PSO optimized XGBoost algorithm with dynamic inertia weight updation[J]. Computer Modeling in Engineering and Sciences,2024,142(1):909-931
吕超,朱雪阳,丁忠林,等. 基于5G与CNN的智能电网稳定性预测[J]. 计算机系统应用,2021,30(7):158-164.
MADIAH B,ROSDIAZLI I,RHEA M,et al. Smart grid stability prediction model using neural network to handle missing inputs[J]. Sensor,2022,22(12):1-29.
LI G,GAO X,LIU C,et al. Cosine mixup:a mixup strategy for point cloud contrastive representation learning[J]. IEEE Transactions on Circuits and Systems II:Express Briefs,2024,71(2):967-971.
刘雨微,陈松灿. 基于IMIU的在线类增量对比学习[J]. 软件学报,2024,35(12):5544-5557.
WANG Y S,ZHANG H. A feature transfer model with Mixup and contrastive loss in domain generalization[J]. Journal of University of Science and Technology of China,2024,54(4):1-9.
王岩,张晨阳,李照奎. 基于跨域Mixup和自监督学习的少样本高光谱图像分类[J]. 激光杂志,2024,45(12):99-105.
ALHANAF A S,BALIK H H,FARSADI M. Intelligent fault detection and classification schemes for smart grids based on deep neural networks[J]. Energies,2023,16(22):1-19.
叶飞.新能源并网对电网稳定性的影响及应对策略研究[J].张江科技评论,2024,(6):110-112.
杨熠鑫. 基于神经网络的智能电网稳定性预测模型研究[J]. 微型电脑应用,2024,40(1):180-183.
SCHAFER B,MATTHIAE M,TIMME M,et al. Decentral smart grid control[J]. New Journal of Physics,2015,17(1):1-17.
OTHMAN A,KADDOUM G,EVANGELISTA J V,et al. Digital twinning in smart grid networks:Interplay,resource allocation and use cases[J]. IEEE Communications Magazine,2023,61(11):120-126.
ZHOU Y S,TATYANA O S.Using global t-SNE to preserve intercluster data structure[J].Nueral Computation,2022,34(8): 1637-1651.
0
浏览量
39
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621