考虑三相负荷时空特性和配变动态安全负载域的配变周前分相重过载预警方法

doi:10.19595/j.cnki.1000-6753.tces.241943

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (5477 KB)
输出: BibTeX | EndNote (RIS)

摘要

新型源、荷规模化接入,配网三相不平衡工况高发,分相重过载问题极为突出。现有配变重过载预警方法无法充分揭示三相负荷时空特性,未满足轻载及重过载工况下精度需求,忽视三相不平衡工况对配变载荷能力的影响,易导致虚警、漏警。该文提出考虑三相负荷时空特性和配变动态安全负载域的配变周前分相重过载预警方法。首先,探索配变三相负荷时空特性,建立基于特征组合动态选取技术与空间表征技术的特征强化表达方法。其次,提出基于SwinLSTM-D建立配变周前分相负荷预测模型,充分挖掘配变三相负荷时空特性。并且,面向预警任务在轻载及重过载工况下的高精度预测需求,构造双重加权混合损失函数(Dual Weighted Hybrid Loss,DWH),优化模型注意力分配模式。然后,提出刻画考虑配变热点温升约束的配变动态安全负载域,准确评估配变极限载荷能力。最后,提出基于配变动态安全负载域的配变周前分相重过载预警策略。利用中国南部某供电局配变实测数据进行算例验证,表明该文预测方法具有显著精度优势,高效满足配变周前分相重过载预警的实际生产需求。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	何华锦
	任洲洋
	冯健冰
	张海峰

关键词 ：三相不平衡工况, 三相负荷时空特性, 分相负荷预测, 配变动态安全负载域, 重过载预警

Abstract：

With the large-scale integration of new energy sources and diverse load profiles, three-phase imbalance conditions in distribution networks have become increasingly frequent, leading to significant issues of phase-overloaded distribution transformers. Existing pre-warning methods for transformer overloads fail to adequately reveal the spatiotemporal characteristics of three-phase loads, do not meet the accuracy requirements under light load and heavy overload conditions, and overlook the impact of three-phase imbalance on transformer load capacity. This often results in false alarms and missed warnings. To address these challenges, this paper proposes a transformer phase-overload pre-warning method for the week ahead, considering the spatiotemporal characteristics of three-phase loads and the Dynamic Safety Loading Region of the transformer.
Firstly, the spatiotemporal characteristics of three-phase loads on transformers are explored, and a feature enhancement expression method based on dynamic feature combination selection and spatial representation techniques is established. Secondly, a load forecasting model for transformer phases one week ahead is developed using SwinLSTM-D, which fully exploits the spatiotemporal characteristics of three-phase loads. To meet the high-precision prediction requirements under light load and heavy overload conditions for the pre-warning task, a Dual Weighted Hybrid Loss (DWH) function is constructed to optimize the model’s attention distribution pattern. Subsequently, the Dynamic Safety Loading Region of the transformer, which accounts for hotspot temperature rise constraints, is defined to accurately assess the transformer's limit load capacity. Finally, a pre-warning strategy based on the Dynamic Safety Loading Region is proposed to effectively pre-warn against transformer overload issues.
Case studies using measured data from a distribution transformer operated by a power supply bureau in southern China validate the proposed method. The results indicate that: 1) The proposed forecasting method exhibits significant accuracy advantages, with annual RMSE errors being 81.25% and 80.95% of the baseline model, and MAPE errors being 80.14% and 72.58% of the baseline model, respectively. Additionally, under light load and heavy overload conditions, the method demonstrates optimal adaptability, with RMSE errors at 58.68% and 78.99%, and MAPE errors at 59.42% and 69.74% of the baseline model, respectively. 2) The proposed pre-warning method achieves precise overload warnings for transformers under three-phase imbalance conditions, outperforming traditional methods.
Simulation analysis leads to the following conclusions: 1) Effectively capturing the spatiotemporal characteristics of three-phase transformer loads significantly enhances prediction accuracy. 2) By increasing the model’s attention distribution on samples under light load and heavy overload conditions, the model’s accuracy performance in these scenarios is ensured. 3) By characterizing the Dynamic Safety Loading Region of the transformer, the limit load space that meets hotspot temperature rise constraints within the safe operating timeframe is accurately defined, enabling precise pre-warning of transformer overloads.

Key words： Three-phase imbalance conditions spatiotemporal characteristics of three-phase loads phase-separation load forecasting dynamic safety loading region of distribution transformers heavy and overload warning

收稿日期: 2024-10-29

PACS:

TM714

基金资助:

中央高校基本科研业务费资助项目（2023CDJYXTD-004）

通讯作者: 任洲洋男,1986年生,副教授,博士生导师,研究方向为电力系统人工智能、电力能源系统低碳运行及规划等。E-mail：rzhouyange1108@163.com

作者简介: 何华锦男,2000年生,硕士研究生,研究方向为基于深度学习的变压器重过载预警等。E-mail：orange_hhj@163.com

引用本文:

何华锦, 任洲洋, 冯健冰, 张海峰. 考虑三相负荷时空特性和配变动态安全负载域的配变周前分相重过载预警方法[J]. 电工技术学报, 0, (): 250430-. He Huajin, Ren Zhouyang, Feng Jianbing, Zhang Haifeng. Week-Ahead Phase-Separated Overload Warning Method for Distribution Transformers Considering the Spatiotemporal Characteristics of Three-Phase Loads and the Dynamic Safety Loading Region. Transactions of China Electrotechnical Society, 0, (): 250430-.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.241943 https://dgjsxb.ces-transaction.com/CN/Y0/V/I/250430

[1] 赵飞龙, 咸日常, 荣庆玉, 等. 三相不平衡工况下配电变压器温升特性及绝缘损失分析[J]. 高电压技术, 2023, 49(10): 4364-4372.
Zhao Feilong, Xian Richang, Rong Qingyu, et al.Analysis of temperature rise characteristics and insulation loss of distribution transformer under three-phase unbalanced condition[J]. High Voltage Engineering, 2023, 49(10): 4364-4372.
[2] 李元, 刘宁, 梁钰, 等. 基于温升特性的油浸式变压器负荷能力评估模型[J]. 中国电机工程学报, 2018, 38(22): 6737-6746.
Li Yuan, Liu Ning, Liang Yu, et al.A model of load capacity assessment for oil-immersed transformer by using temperature rise characteristics[J]. Proceedings of the CSEE, 2018, 38(22): 6737-6746.
[3] 张智刚, 康重庆. 碳中和目标下构建新型电力系统的挑战与展望[J]. 中国电机工程学报, 2022, 42(8): 2806-2819.
Zhang Zhigang, Kang Chongqing.Challenges and prospects for constructing the new-type power system towards a carbon neutrality future[J]. Proceedings of the CSEE, 2022, 42(8): 2806-2819.
[4] 贺建章, 王海波, 季知祥, 等. 面向智能电网的配电变压器重过载影响因素分析[J]. 电网技术, 2017, 41(1): 279-284.
He Jianzhang, Wang Haibo, Ji Zhixiang, et al.Analysis of factors affecting distribution transformer overload in smart grid[J]. Power System Technology, 2017, 41(1): 279-284.
[5] 贺建章, 王海波, 季知祥, 等. 基于随机森林理论的配电变压器重过载预测[J]. 电网技术, 2017, 41(8): 2593-2597.
He Jianzhang, Wang Haibo, Ji Zhixiang, et al.Heavy overload forecasting of distribution transformers based on random forest theory[J]. Power System Technology, 2017, 41(8): 2593-2597.
[6] 张海峰, 任洲洋, 冯健冰, 等. 基于内驱进化预测模型和载荷能力动态评估的变压器周前重过载预警方法[J]. 电网技术, 2024, 48(10): 4349-4357, I0124.
Zhang Haifeng, Ren Zhouyang, Feng Jianbing, et al.A week-ahead heavy and overload warning strategy based on an endogenous evolutionary forecasting model and a transformer rating dynamic evaluation method[J]. Power System Technology, 2024, 48(10): 4349-4357, I0124.
[7] 杨智宇, 刘俊勇, 刘友波, 等. 基于自适应深度信念网络的变电站负荷预测[J]. 中国电机工程学报, 2019, 39(14): 4049-4061.
Yang Zhiyu, Liu Junyong, Liu Youbo, et al.Transformer load forecasting based on adaptive deep belief network[J]. Proceedings of the CSEE, 2019, 39(14): 4049-4061.
[8] 赵洋, 王瀚墨, 康丽, 等. 基于时间卷积网络的短期电力负荷预测[J]. 电工技术学报, 2022, 37(5): 1242-1251.
Zhao Yang, Wang Hanmo, Kang Li, et al.Temporal convolution network-based short-term electrical load forecasting[J]. Transactions of China Electrotechnical Society, 2022, 37(5): 1242-1251.
[9] Zheng Kedi, Chen Qixin, Wang Yi, et al.A novel combined data-driven approach for electricity theft detection[J]. IEEE Transactions on Industrial Informatics, 2019, 15(3): 1809-1819.
[10] 潘超, 陈祥, 蔡国伟, 等. 基于电磁-机械耦合原理的变压器三相不平衡运行绕组振动模-态特征[J]. 中国电机工程学报, 2020, 40(14): 4695-4707, 4747.
Pan Chao, Chen Xiang, Cai Guowei, et al.Mode-state characteristics of three-phase unbalanced operation winding vibration of transformer based on electromagnetic mechanical coupling principle[J]. Proceedings of the CSEE, 2020, 40(14): 4695-4707, 4747.
[11] 韩富佳, 王晓辉, 乔骥, 等. 基于人工智能技术的新型电力系统负荷预测研究综述[J]. 中国电机工程学报, 2023, 43(22): 8569-8592.
Han Fujia, Wang Xiaohui, Qiao Ji, et al.Review on artificial intelligence based load forecasting research for the new-type power system[J]. Proceedings of the CSEE, 2023, 43(22): 8569-8592.
[12] 赵洪山, 吴雨晨, 温开云, 等. 基于时空注意力机制的台区多用户短期负荷预测[J]. 电工技术学报, 2024, 39(7): 2104-2115.
Zhao Hongshan, Wu Yuchen, Wen Kaiyun, et al.Short-term load forecasting for multiple customers in A station area based on spatial-temporal attention mechanism[J]. Transactions of China Electrotechnical Society, 2024, 39(7): 2104-2115.
[13] 李延珍, 王海鑫, 杨子豪, 等. 基于非侵入式负荷分解的家庭负荷两阶段超短期负荷预测模型[J]. 电工技术学报, 2024, 39(11): 3379-3391.
Li Yanzhen, Wang Haixin, Yang Zihao, et al.Two-stage ultra-short-term load forecasting model of household appliances based on non-intrusive load disaggregation[J]. Transactions of China Electrotechnical Society, 2024, 39(11): 3379-3391.
[14] 陈轩伟. 基于BP-QR模型的负荷区间预测[J]. 电气技术, 2022, 23(4): 14-17, 24.
Chen Xuanwei.Load interval forecasting based on BP-QR model[J]. Electrical Engineering, 2022, 23(4): 14-17, 24.
[15] 李丹, 孙光帆, 缪书唯, 等. 基于多维时序信息融合的短期电力负荷预测方法[J]. 中国电机工程学报, 2023, 43(增刊1): 94-106.
Li Dan, Sun Guangfan, Miao Shuwei, et al.Short-term power load forecasting method based on multidimensional time series information fusion[J]. Proceedings of the CSEE, 2023, 43(S1): 94-106.
[16] Liu Yanzhu, Dutta S, Kong A W K, et al. An image inpainting approach to short-term load forecasting[J]. IEEE Transactions on Power Systems, 2022, 38(1): 177-187.
[17] 李云松, 张智晟. 考虑综合需求响应的Transformer-图神经网络综合能源系统多元负荷短期预测[J]. 电工技术学报, 2024, 39(19): 6119-6128.
Li Yunsong, Zhang Zhisheng.Transformer based multi load short-term forecasting of integrated energy system considering integrated demand response[J]. Transactions of China Electrotechnical Society, 2024, 39(19): 6119-6128.
[18] 国家质量监督检验检疫总局, 中国国家标准化管理委员会. 电力变压器第7部分:油浸式电力变压器负载导则: GB/T 1094.7—2008[S]. 北京: 中国标准出版社, 2009.
[19] 董旭柱, 张琛, 阮江军, 等. 油浸式电力变压器动态载荷评估技术研究与应用[J]. 高电压技术, 2021, 47(6): 1959-1968.
Dong Xuzhu, Zhang Chen, Ruan Jiangjun, et al.Research and practices of dynamic thermal rating for oil-immersed power transformer[J]. High Voltage Engineering, 2021, 47(6): 1959-1968.
[20] 张琛, 董旭柱, 阮江军, 等. 面向典型负荷曲线的油浸式电力变压器动态载荷能力评估方法[J]. 电网技术, 2024, 48(8): 3515-3524.
Zhang Chen, Dong Xuzhu, Ruan Jiangjun, et al.Dynamic thermal rating assessment method of oil-immersed power transformers based on typical load profiles[J]. Power System Technology, 2024, 48(8): 3515-3524.
[21] Rubasinghe O, Zhang Xinan, Chau T K, et al.A novel sequence to sequence data modelling based CNN-LSTM algorithm for three years ahead monthly peak load forecasting[J]. IEEE Transactions on Power Systems, 2024, 39(1): 1932-1947.
[22] Mousavi A, Baraniuk R G.Uniform partitioning of data grid for association detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(2): 1098-1107.
[23] Tang Song, Li Chuang, Zhang Pu, et al.SwinLSTM: improving spatiotemporal prediction accuracy using swin transformer and LSTM[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, France, 2023: 13424-13433.
[24] Guo Yixiu, Li Yong, Qiao Xuebo, et al.BiLSTM multitask learning-based combined load forecasting considering the loads coupling relationship for multienergy system[J]. IEEE Transactions on Smart Grid, 2022, 13(5): 3481-3492.
[25] Dong Ming, Grumbach L.A hybrid distribution feeder long-term load forecasting method based on sequence prediction[J]. IEEE Transactions on Smart Grid, 2020, 11(1): 470-482.
[26] Zhuang Wei, Fan Jili, Xia Min, et al.A multi-scale spatial-temporal graph neural network-based method of multienergy load forecasting in integrated energy system[J]. IEEE Transactions on Smart Grid, 2024, 15(3): 2652-2666.